Laser-targeted weeding methods further enhance the sustainable development of green agriculture, with one key technology being the improvement of weed localization accuracy. Here, we propose an improved YOLOv8 instance segmentation based on bidirectional feature fusion and deformable convolution (BFFDC-YOLOv8-seg) to address the challenges of insufficient weed localization accuracy in complex environments with resource-limited laser weeding devices. Initially, by training on extensive datasets of plant images, the most appropriate model scale and training weights are determined, facilitating the development of a lightweight network. Subsequently, the introduction of the Bidirectional Feature Pyramid Network (BiFPN) during feature fusion effectively prevents the omission of weeds. Lastly, the use of Dynamic Snake Convolution (DSConv) to replace some convolutional kernels enhances flexibility, benefiting the segmentation of weeds with elongated stems and irregular edges. Experimental results indicate that the BFFDC-YOLOv8-seg model achieves a 4.9% increase in precision, an 8.1% increase in recall rate, and a 2.8% increase in mAP50 value to 98.8% on a vegetable weed dataset compared to the original model. It also shows improved mAP50 over other typical segmentation models such as Mask R-CNN, YOLOv5-seg, and YOLOv7-seg by 10.8%, 13.4%, and 1.8%, respectively. Furthermore, the model achieves a detection speed of 24.8 FPS on the Jetson Orin nano standalone device, with a model size of 6.8MB that balances between size and accuracy. The model meets the requirements for real-time precise weed segmentation, suitable for complex vegetable field environments and resource-limited laser weeding devices.

Deep learning is widely used in image segmentation, effectively identifying crops and weeds and contributing to the reduction of herbicide use. Traditional methods of applying pesticides over large areas are inefficient in dealing with weeds as needed, leading to massive waste of pesticides, high-cost production, and serious environmental pollution. This affects crop yield and quality. Although weed recognition using conventional deep learning methods has evolved over time, there are still challenges in weed extraction, detection, and segmentation. Accurate recognition and detection of weeds are essential prerequisites for implementing variable spraying. This paper proposes a semantic segmentation method based on UNet++ for complex environments where accurate identification of plants and weeds is challenging, targeting weeds in sugar beets, peas, and rice. An attention module is integrated into the upsampling process of UNet++, and UNet++ is used as a backbone network to effectively integrate multi-scale information, efficiently suppressing external noise interference. The UNet++ model with an integrated attention mechanism module achieves higher IOU than the general UNet++ model used in medical image analysis. This method effectively detects crops and weeds in complex backgrounds, providing reference material for the accurate application of robotic herbicides.

This review provides a comprehensive and updated information on chalcones, presenting their sources, methods of identification and properties putting emphasis on applications in agricultural industry. Vast exploitation of synthetic pesticides led to the weed and pest resistance issue, causing economic loss but more importantly health risk due to pesticide overuse. Because one of the aim of the European Green Deal 2030 is the Farm to Fork strategy which targets on reducing by 50% the use of chemical pesticides by 2030, and push towards natural pesticides which are more environmentally friendly and restore natural resources, chalcones and their derivatives seem to fit perfectly. They have herbicidal, fungicidal, bactericidal and antiviral properties. Moreover, chalcones are naturally occurring substances, known for their favorable health effect for years, working on many areas. This review is complementary to the previous ones describing chalcones use in agriculture, updates them but additionally shows methods of detection.

The present study aims to identify tomato (Solanum lycopersicum L.) cultivars with weed-suppressive ability against target weed species in the tomato growing season. A greenhouse study was conducted with 17 tomato cultivars and target weeds Palmer amaranth (Amaranthus palmeri S. Wats), yellow nutsedge (Cyperus esculentus L.), and large crabgrass (Digitaria sanguinalis L.). Tomato plants and weed species were grown in the same pot. The height, chlorophyll, and dry weight biomass of the weeds were measured 28 days after sowing. The largest effect of tomato interference was on Palmer amaranth. Cultivar 15 reduced Palmer amaranth height, chlorophyll, and biomass by 58, 28, and 83%, respectively. Chlorophyll percentage of yellow nutsedge seedlings was suppressed by 15% by cultivar 64, whereas 13% of its height was reduced by cultivar 20. Cultivar 15 reduced biomass of yellow nutsedge by 40%. The percentage of chlorophyll of large crabgrass was reduced by 22% with cultivar 5, whereas the height and biomass were reduced by 35 and 44% with cultivars 38 and 63, respectively. Factoring all parameters evaluated, cultivars 38, 33, and 7 were most suppressive against the problematic weed species in tomato.

A field experiment was conducted at farmer field of Sundarbazar, Lamjung during rainy season of 2020 with an objective to determine the dynamics of weed with respect different planting methods and varieties. The experiment was laid out in split plot design with three replications where five Varieties (KabreKodo 1, KabreKodo 2, Dalle 1, Okhale 1 and local) were used as the main plot factor and three planting methods (Direct sowing;10*10cm, Conventional transplanting;10*10 cm with 15 days old seedlings and System of Crop Intensification;25*25 cm with 30 days old seedlings) as sub plot factor. Result showed that among 5 genotypes of weeds based on Importance value index, Cyperusrotundus was the most dominant during the initial stage but after the first weeding, Aegeratumhaustinianum dominated the field. Weed biomass and density was recorded highest in directly sown field than that in transplanted field. Among the transplanted crop, weed infestation was seen higher in SCI than in conventionally transplanted finger millet due to wider spacing. But after the first hand weeding, due to profuse root growth and tillering in SCI, weeds were suppressed and thus weed biomass was observed higher in CT. After one hand weeding, SCI showed higher weed control index, crop resistance index and planting method efficiency index in terms of yield. Weed infestation was observed higher in Dalle 1 among varieties.

Aiming at the problems of inaccurate segmentation of long object and information loss of small object in real-time semantic segmentation algorithm, this paper proposes a lightweight multi-branch real-time semantic segmentation network based on BiseNetV2. The new auxiliary branch makes full use of spatial details and context information to cover the long object in the field of view. Meanwhile, in order to ensure the inference speed of the model, the asymmetric convolution is used in each stage of the auxiliary branch to design a structure with low computational complexity. In the multi-branch fusion stage, the alignment and fusion module is designed to provide guidance information for deep and shallow feature mapping, so as to make up for the problem of feature misalignment in the fusion of information at different scales, and thus reduce the loss of small target information. In order to further improve the model’s awareness of key information, a global context module is designed to capture the most important features in the input data. The proposed network uses NVIDIA GeForce RTX 3080 Laptop GPU experiment, on the road street view data set Cityscapes and CamVid average occurring simultaneously ratio reached 77.1% and 78.4% respectively, with running speed of 127 frames/s respectively and 112 frames/s. The experimental results show that the proposed algorithm can achieve real-time segmentation and improve the accuracy significantly, showing good semantic segmentation performance

Open-vocabulary learning has recently gained prominence as a means to enable image segmentation for arbitrary categories based on textual descriptions. This advancement has extended the applicability of segmentation systems to a broader range of generally purpose scenarios. However, current methods often revolve around specialized architectures and parameters tailored to specific segmentation tasks, resulting in a fragmented landscape of segmentation models. In response to these challenges, we introduce OVAMTSeg, a versatile framework designed for Open-Vocabulary and Multitask Image Segmentation. OVAMTSeg harnesses adaptive prompt learning to empower the model to capture category-sensitive concepts, enhancing its robustness across diverse multi-task and scenario contexts. Text prompts are employed to effectively capture semantic and contextual features of the text, while cross-attention and cross-modal interactions enable the fusion of image and text features. Furthermore, a transformer-based decoder is incorporated for dense prediction. Extensive experimental results underscore the effectiveness of OVAMTSeg, showcasing its state-of-the-art performance and superior generalization capabilities across three segmentation tasks. Notable achievements include a 47.5 mIoU in referring expression segmentation, 51.6 mIoU on Pascal-VOC with four unseen classes, 46.6 mIoU on Pascal-Context in zero-shot segmentation, 65.9 mIoU on Pascal-5i, and 35.7 mIoU on COCO-20i datasets for one-shot segmentation.

This study aimed at testing the effectiveness of novel combinations of chemical and physical methods to control Prosopis juliflora, an invasive weed in the Moshi and Simanjiro districts of Nothern Tan-zania. Six different treatments including manual uprooting, glyphosate, bark chop with chemical application, two separate chemical mixtures and control were tested in a total of 32 plots, which represented two land use types (grazing land and farmland) found in the two districts. Each plot covered 20m×30m plot area. Two response variables (stem count and tree volume) were recorded to compare weed population density before and after treatment six months later. An analysis of the untreated control plots, showed that the inherent growth potential of P. juliflora was higher in Moshi than in Simanjiro district. The number of stems increased during the experiment for all six treatments showing that the P. juliflora population had not yet reached the local carrying capacity. For the manual control treatment, the increase was reduced compared to the untreated control. For all other treatments, the increase in stem count was on par with that in the untreated control or even higher. Thus, we conclude that only manual uprooting had a controlling effect but not to the extent that it eradicated P. juliflora. Thus, it is for P. juliflora as for weed control in general: weed control must be an ongoing effort.

Pulmonary Embolism (PE) is the obstruction of blood arteries in the lungs by a blood clot. The mortality risk for PE is approximately 30%. Detecting pulmonary embolism in the segmental arteries of the lung is more challenging than in the main arteries and is very prone to being missed. A computer-based approach was created in this work to automatically identify pulmonary embolism in the segmental arteries using computed tomography images. The system's infrastructure includes an enhanced Mask R-CNN deep neural network that has been trained with images containing PE. The network accurately identifies the location of the pulmonary embolism on the computed tomography picture and successfully extracts its borders. The investigation was conducted by generating a local dataset. The study's performance was evaluated using pulmonary embolisms identified manually by the expert radiologist. The sensitivity, specificity, accuracy, dice coefficient, and Jaccard index values for 2130 pictures were 96.4%, 93.5%, 96.1%, 0.96, and 0.90, respectively. The improved Mask R-CNN model has demonstrated superior performance when compared to the traditional Mask R-CNN and U-Net models. This high-performance technology is designed to identify pulmonary embolism and will aid professionals in assessing the size of the embolism.

Interaction between multiple phases especially liquid-gas is one of the most common phenomena in industrial systems. Computer Vision enables modern systems to derive an automated and robust image-processing technique to address this issue. However, diverse experimental conditions still make it a challenging task to overcome. In Deep Learning, instance segmentation has created a niche in various computer vision applications as it aims to provide different instance IDs to objects belonging to the same class. In this paper, we propose a novel approach employing the YOLO (You Look Only Once) an end-to-end deep learning architecture for the detection and segmentation of bubbles in fluid flows. YOLOv5 offers significant improvements in both speed and accuracy compared to its predecessors like YOLOv3. Therefore, we train the YOLOv5 network on a dataset consisting of annotated images representing instances of bubbles across varied fluid flow environments. This paper provides both qualitative and quantitative evaluation of three YOLOv5 networks (small, medium, and extra-large) in detecting and segmenting bubbles with high accuracy and efficiency. Based on the metrics all three YOLOv5 models achieved high precision above 0.98 for bounding box detection and 0.97 for segmentation mask, and high recall value greater than 0.97 for box and 0.96 for mask quality was achieved. The achieved results indicate that the models accurately localize bubbles within the image frame, and distinguish bubble pixels from the background. Also, mean average precision (mAP50-95) consistently exceeds 0.84 across all models for the bounding box and 0.73 for the segmentation mask. The ascertained results emphasize the potential of YOLOv5 architecture as a powerful tool for automated bubble analysis in real-world applications. Our research contributes to advancing the field of deep neural networks in fluid systems and provides a fresh approach for future developments in automated bubble analysis.

We propose a novel unsupervised semantic segmentation method for fast and accurate flood area detection utilizing color images acquired from Unmanned Aerial Vehicles (UAVs). To the best of our knowledge, this is the first fully unsupervised method for flood area segmentation in color images captured by UAVs, without the need of pre-disaster images. The proposed framework addresses the problem of flood segmentation based on parameter-free calculated masks and unsupervised image analysis techniques. First, a fully unsupervised algorithm gradually excludes areas classified as non-flood utilizing calculated masks over each component of the LAB colorspace, as well an RGB vegetation index and the detected edges of the original image. Unsupervised image analysis techniques, such as distance transform, are then applied, producing a probability map for the location of flooded areas. Finally, flood detection is obtained by applying the hysteresis thresholding segmentation. The proposed method is tested and compared with variations, and other supervised methods in two public datasets, consisting of 953 color images in total, yielding high-performance results, with 87.4% and 80.9% overall accuracy and F1-Score, respectively. The results and computational efficiency of the proposed method show that it is suitable for on board data execution and decision-making during UAVs flight.

The segmentation of abnormal regions is vital in smart manufacturing. However, the existing segmentation system for detecting sauce-packet leakage on intelligent sensors encounters an issue of imaging blurring caused by uneven illumination. This issue adversely affects segmentation performance, thereby impeding the rapid production of industrial assembly lines. To alleviate this issue, we propose the two-stage Illumination-aware Sauce-packet Leakage Segmentation (ISLS) method for intelligent sensors. The ISLS comprises two main stages: Illumination-aware region enhancement and leakage region segmentation. In the first stage, YOLO-Fastestv2 is employed to capture the Region of Interest (ROI), which reduces redundancy computations. Additionally, we propose an image enhancement to relieve the impact of uneven illumination, enhancing the texture details of ROI. In the second stage, we propose a novel feature extraction network. Specifically, we propose the Multi-scale Feature Fusion Module (MFFM) and the Sequential Self-Attention Mechanism (SSAM) to capture discriminative representations of leakage. The multi-level features are fused by MFFM with a small number of parameters, which capture leakage semantics at different scales. The SSAM realizes the enhancement of valid features and the suppression of invalid features by adaptive weighting of spatial and channel dimensions. Furthermore, we generated a self-built dataset of sauce-packets, including 606 images with various leakage areas. Comprehensive experiments demonstrate that our ISLS method shows better results than several state-of-the-art methods, with additional performance analyses deployed on intelligent sensors to affirm the effectiveness of our proposed method. Our code is available at https://github.com/LSJ5106/SauceDetect.

The task of weakly supervised point cloud semantic segmentation has received widespread attention and also has been widely used in autonomous driving, robotics, and modern industries. Due to the high dimensionality and large volume of point cloud data, many technical difficulties appeal to weakly supervised semantic processing, especially segmentation. However, weakly-supervised schemes usually provide only partial labelling information of the underlying point cloud data and thus need to effectively extract local features, geometric information, and contextual relationships only using these limited labelled data for supervised learning. To improve weakly-supervised semantic segmentation, we propose a novel segmentation network through the boundary-based feature aggregation based on a K-NN algorithm with down-sampling operation, and also introduce the smoothness loss and Siamese loss for effective segmentation. The experiments on public datasets demonstrate that our presented segmentation method exceeds most of the existing fully supervised and weakly-supervised methods in terms of mIoU. Specifically, our network has high segmentation accuracy on the labels of objects with similar geometrical structures, such as ceiling, wall, floor, chair and table, reaching 91.2%, 98.8%, 83.3%, 75.3% and 80.2%, respectively. Extensive experiments also illustrate its robustness, effectiveness, and generalization of the proposed weakly supervised segmentation network.

Image segmentation and classification still represent an active area of research since no universal solution can be identified. Established segmentation algorithms like thresholding are problem specific, treat well the easy cases and mostly relied on single parameter i.e intensity. Machine learning approaches offer alternatives where predefined features are combined into different classifiers. On the other hand, the outcome of machine learning is only as good as the underlying feature space. Differential geometry can substantially improve the outcome of machine learning since it can enrich the underlying feature space with new geometrical objects, called invariants. In this way, the geometrical features form a high-dimensional feature space for each pixel, where original objects can be resolved. Alternatives based on the geometry of the image scale-invariant interest points have been exploited successfully in the field of computer vision. Here, we integrate geometrical feature extraction based on signal processing, machine learning, and input relying on domain knowledge. The approach is exemplified on the ISBI 2012 image segmentation challenge data set. As a second application, we demonstrate powerful image classification functionality based on the same principles, which was applied to the HeLa and HEp-2 data sets. Obtained results demonstrate that feature space enrichment properly balanced with feature selection functionality can achieve performance comparable to deep learning approaches.

Medical image segmentation is a critical step in various healthcare applications, aiding in diagnosis, treatment planning, and disease monitoring. In this study, we investigate the efficacy of a segmentation approach based on the 2D wavelet transform. Leveraging a dataset comprising 10 diverse medical images, we evaluate the performance of our segmentation method using three key metrics: accuracy, precision, and recall. Our findings demonstrate that the proposed approach enhances segmentation accuracy, offering promising results compared to existing methods. By harnessing the multi-resolution feature extraction capabilities of the 2D wavelet transform, our method achieves improved delineation of medical image structures, paving the way for more accurate and efficient healthcare interventions.

Depth-sensing technology has led to broad applications of inexpensive depth cameras that can capture human motion and scenes in 3D space. Background subtraction algorithms can be improved by fusing color and depth cues, thereby allowing many issues encountered in classical color segmentation to be solved. In this paper, we propose a new fusion method that combines depth and color information for foreground segmentation based on an advanced color-based algorithm. First, a background model and a depth model are developed. Then, based on these models, we propose a new updating strategy that can eliminate ghosting and black shadows almost completely. Extensive experiments have been performed to compare the proposed algorithm with other, conventional RGB-D algorithms. The experimental results suggest that our method extracts foregrounds with higher effectiveness and efficiency.

Glaucoma, a global leading cause of blindness, necessitates accurate segmentation of the optic disc (OD) and optic cup (OC) for effective screening. However, existing segmentation methods based on convolutional neural networks (CNNs) suffer from high computational complexity and long inference times. In this paper, we propose an end-to-end segmentation method for the OD and OC using a lightweight MobileNetv3 as the feature extraction network. Our approach incorporates boundary branches and an adversarial learning network to achieve multi-label segmentation of the OD and OC. We evaluate the proposed method on three publicly available datasets: Drishti-GS, RIM-ONE-r3, and REFUGE. The experimental results demonstrate segmentation accuracies of 0.974/0.900, 0.966/0.875, and 0.962/0.880 for the OD and OC on the respective datasets, while significantly reducing inference time.

Tsallis entropy has been widely used in image thresholding because of its non-extensive properties. The non-extensive parameter q contained in this entropy plays an important role in various adaptive algorithms and has been successfully applied in bi-level image thresholding. In this paper, the relationships between parameter q and pixels’ long-range correlations have been further studied within multi-threshold image segmentation. It is found that the pixels’ correlations are remarkable and stable for images generated by a known physical principle, such as infrared images and medical CT images. And the corresponding non-extensive parameter q can be evaluated by using self-adaptive Tsallis entropy algorithm. The results of this algorithm are compared with those of Shannon entropy algorithm and the original Tsallis entropy algorithm, in terms of quantitative image quality evaluation metrics PSNR (Peak Signal-to-Noise Ratio) and SSIM (Structural Similarity). Furthermore, we observed that for image series with the same background, the q values determined by the adaptive algorithm are consistently kept in a narrow range. Therefore, similar or identical scenes during imaging would produce similar strength of long-range correlations, which provides potential applications for unsupervised image processing.

Lindernia dubia (L.) Pennell is a species with invasive behavior outside of its native range of distribution (North America), linked mainly to aquatic habitats. This annual species has been acknowledged as a weed in rice paddies in Europe and Asia. Due to the impacts of this invasive plant, some authors have even listed this species as a global invader. The present work focused on spontaneous plant species occurring in cattail seedlings grown in central Spain for the establishment of constructed wetlands. Weed inventory revealed the presence of L. dubia as a dominant spontaneous species in this crop environment. A suite of mesocosm experiments were designed to study the distribution of L.dubia versus the distribution of the other dominant plant species, and to determine traits associated with its weedy potential. Results showed that L.dubia presents competitive attributes such as morphological variability, early flowering, long seeding time, short growth cycle, small and light seeds and high seed production and germination rate (25 ⁰C), meaning a high reproductive capacity in a cycle of about three months, in non-limiting conditions for plant growth. Data from this work provide a basis for understanding the weedy potential of L.dubia, and for management decisions of a potentially invasive species, little investigated in Europe

A single paragraph of about 200 words maximum. For research articles, abstracts should give a pertinent overview of the work. We strongly encourage authors to use the following style of structured abstracts, but without headings: (1) Background: Place the question addressed in a broad context and highlight the purpose of the study; (2) Methods: briefly describe the main methods or treatments applied; (3) Results: summarize the article’s main findings; (4) Conclusions: indicate the main conclusions or interpretations. The abstract should be an objective representation of the article and it must not contain results that are not presented and substantiated in the main text and should not exaggerate the main conclusions.

Large datasets play a crucial role in the progression of surgical robotics, facilitating advancements in the fields of surgical task recognition and automation. Moreover, public datasets enable the comparative analysis of various algorithms and methodologies, thereby assessing their effectiveness and performance. The ROSMA (Robotics Surgical Maneuvers) dataset provides 206 trials of common surgical training tasks performed with the da Vinci Research Kit (dVRK). In this work, we extend ROSMA dataset with two annotated subsets: ROSMAT24, which contains bounding box annotations for instrument detection, and ROSMAG40, which contains high and low level gesture annotations. We propose an annotation method that provides independent labels for the right-handed tool and the left-handed tool. For instrument identification, we validate our proposal with a YOLOv4 model in two experimental scenarios. We demonstrate the generalization capabilities of the network to detect instruments in unseen scenarios. For gesture segmentation, we propose two label categories: high-level annotations that describe gestures at a maneuvers level, and low-level annotations that describe gestures at a fine-grain level. To validate this proposal, we have designed a recurrent neural network based on a bidirectional long-short term memory layer. We present results for four cross-validation experimental setups, reaching up to a 77.35% mAP.

With the rapid developments that have been made in computer vision and computer technology, semantic segmentation of high-resolution images has emerged as a mainstream and challenging task. The, segmentation of water areas remains a complex task due to the similar features between water areas or between water areas and other land objects. Meanwhile, since coastlines and riverbanks are typically presented in irregular shapes, it is difficult to obtain the categories of pixels at boundaries. This paper proposed the use of a Water-Land Boundary Attention Network (WLBANet) to improve the accuracy of pixels at boundaries between water and land. This network also reinforced the performance of contextual information extraction into distinguishing between water areas and other land objects. To prove the validity of this proposed network, WLBANet was performed on the Water Land Dataset (WLD), which is also by this paper, and which contains water areas and other land objects categories. The results demonstrates that the proposed method has significant effectiveness.

Verticillium wilt is a soil borne disease caused by distinct vegetative compatibility groups (VCG) of the fungus Verticillium dahliae. Two V. dahliae isolates were recovered from symptomatic cot-ton plants in Australian cotton fields and were assigned to two distinct vegetative compatibility groups (VCGs). One corresponding to the defoliating (VCG 1A) and the other non-defoliating (VCG 2A) pathotypes of Verticillium, have been transformed with Red and Green Fluorescent protein genes, respectively. The transformants maintained their ability to infect cotton and both strains were observed to colonise the xylem vessels of cotton plants. Moreover, we observed that the cotton V. dahliae strains could also infect some sampled non-Gossypium species found in the Australian landscape. The fluorescently labelled strains of V. dahliae will allow us to gain a thorough understanding of the infection processes of this important pathogen.

The increasing prevalence of species that are detrimental to biodiversity is a major concern, particularly for managers of National Parks. To develop effective programs for controlling weeds, it is essential to have a thorough understanding of the extent and severity of infestations, as well as the contributing factors such as temperature, rainfall, and disturbance. Predicting these factors on a regional scale requires models that can incorporate a wide range of variables in a quantifiable manner, while also assisting with on-ground operations. In this study, we present two Bayesian Network models specifically designed for six significant weed species found along the southern coast of Australia. Our models are based on empirical data collected during a coastal weed survey conducted in 2015 and repeated in 2016. We applied these models to the coastal national parks in the isolated and pristine East Gippsland region. Importantly, the prediction models were developed at two different spatial scales that directly corresponded to the scale of the observations. Our findings indicate that coastal habitats, with their vulnerable environments and prevalence of open dune systems, are particularly susceptible to weed infestations. Moreover, adjacent regions also have the potential for colonization if these infestations are not effectively controlled. Climate-related factors play a role in moderating the potential for colonization, which is a significant concern for weed control efforts in the context of global climate change.

Weeds are among the major constraints to any crop production system, reducing productivity and profitability. Herbicides are among the most effective methods to control weeds, and reliance on herbicides for weed control has increased significantly with the advent of herbicide-resistant crops. Unfortunately, over-reliance on herbicides leads to environmental-health issues and herbicide-resistant weeds, causing human-health and ecological concerns. Crop diversification can help manage weeds sustainably in major crop production systems. It acts as an organizing principle under which technological innovations and ecological insights can be combined to manage weeds sustainably. Diversified cropping can be defined as the conscious inclusion of functional biodiversity at temporal and/or spatial levels to improve the productivity and stability of ecosystem services. Crop diversification helps to reduce weed density by negatively impacting weed seed germination and weed growth. Additionally, diversified farming systems are more resilient to climate change than monoculture systems and provide better crop yield. However, there are a few challenges to adopting a diversified cropping system, which ranges from technology innovations, government policies, farm-level decisions, climate change, and market conditions. In this review, we discuss how crop diversification supports sustainable weed management, the challenges associated with it, and the future of weed management with respect to the diversification concept.

Weed seedbank is an indication of future weed infestation potential of the species and is essential for making strategic planning for its sustainable management. Parthenium weed (Parthenium hysterophorus L.) is an invasive alien species threatening the biodiversity and the environment in Malaysia. A study was, therefore, conducted to estimate the soil seedbank of the weed at four soil depths of four villages of Kuala Muda, Kedah. The aim was to indicate the critical s of parthenium weed seedbank in Malaysia. Soil samples were collected from the sites using a soil core. The seeds were extracted from the soil samples with sieve shaker at the Universiti Malaysia Kelantan laboratory, Jeli Campus. The study indicates that the weed seedbank is in critical level at the area. The highest number of weed seeds (6915/m2) was found in Kg. Kongsi 6, followed by Kg. Sungai Tok Rawang (4481 seeds/m2). The top layer of soil, 0-5 cm, contained the maximum number of weed seeds (4878 seeds/m2) and a significant number of seeds (316 seeds/m2) were noticed at 10-15 cm soil depth. The study suggests the Malaysian government to take immediate action to control parthenium weed seedbank of the sites.

Plant phenotype plays an important role in crop breeding and planting. Leaf phenotype is an important part of plant phenotype. In order to analyze the leaf phenotype, the target leaf is required to be segmented from the complex background image. In this paper, an automatic soybean leaf segmentation method based on object detection and interactive segmentation models is proposed. Firstly, the Libra R-CNN object detection algorithm is used to detect all soybean leaves in the image. Then, based on the idea that the target soybean leaf is located in the center of the image and the area is large, the detection bounding box of the target leaf is selected. In order not to destroy the segmentation result, the bounding box is optimized to completely enclose the whole leaf. Finally, according to the optimized bounding box, the prior channels of foreground and background are constructed using Gaussian model. The two channels together with the original image are as the input of the interactive object segmentation with inside-outside guidance model to segment the target soybean leaf. A large number of qualitative and quantitative experimental results show that the method has high segmentation accuracy and strong generalization capacity.

This research introduces a pioneering solution to the challenges posed by gastrointestinal tract (GI) cancer in radiation therapy, focusing on the imperative task of precise organ segmentation for minimizing radiation-induced damage. GI imaging has historically used manual demarcation, which is laborious and uncomfortable for patients. We address this by introducing the ResECA-U-Net deep learning model, a novel combination of the UNet and ResNet34 architectures. Furthermore, we further augment its functionality by incorporating the Efficient Channel Attention (ECA-Net) methodology. By utilizing data from the UW-Madison Carbone Cancer Centre, we carefully investigate several image processing techniques designed to capture critical local characteristics. With its foundation in computer vision concepts, the ResECA-U-Net model is excellent at extracting fine details from GI images. Sophisticated metrics such as intersection over union (IoU) and the dice coefficient are used to evaluate performance. Our study's outcomes demonstrate the effectiveness of the suggested method, yielding an impressive 96.27% Dice coefficient and 91.48% IoU. These results highlight the significant contribution that our strategy has made to the advancement of cancer therapy. Beyond its scientific merits, this work has the potential to significantly enhance cancer patients' quality of life and provide better long-term outcomes. Our work is a significant step towards automating and optimizing the segmentation process, which can potentially change how GI cancer is treated completely.

This article presents a succinct overview of the progress, obstacles, and uses of semantic segmentation and instance segmentation within the forestry domain. The objective of this review is to conduct a critical analysis of the current literature pertaining to segmentation techniques and provide a methodical summary of their impact on forestry-related activities, including but not limited to tree species classification, forest inventory, and ecological monitoring such as retrieval of dominant tree species. Through the process of synthesizing pivotal discoveries from multiple studies, this comprehensive analysis provides valuable perspectives on the present status of research and highlights prospective areas for further exploration. The primary topics addressed encompass the approach employed for executing the examination, the fundamental discoveries associated with semantic segmentation and instance segmentation in the domain of forestry, and the ramifications of these discoveries for the discipline. The results indicate that the utilization of semantic segmentation methods has been efficacious in the field of forestry for the precise identification of tree species. Such methods also aid in tracking of deforested regions over the course of time by separating other land-use classes from forested regions. Additionally, the employment of instance segmentation techniques exhibits potential in the demarcation of individual trees. Instance segmentation offers promising results due to deep learning models based on forest point clouds. However, several challenges persist in the successful implementation of semantic segmentation methods such as the presence of occlusions, overlapping branches, and intricate structures hampers the accurate segmentation of trees. Additionally, instance segmentation approaches that utilize models are mostly trained by using laser scanning data based on forest types which are typically trained on specific laser scanning data and forest types that create limitations in generalization from high to low resolution point clouds. Due to this reason, the existing approaches often struggle with handling these complex structures, leading to the need for manual methods for extracting measurements from forest point clouds. The review culminates by underscoring the necessity for additional research to tackle current obstacles and augment the precision and relevance of segmentation methodologies in the field of forestry. In general, the present article provides a significant reference for scholars and professionals who are interested in utilizing segmentation techniques in the field of forestry.

A crop-weed simulation model is presented to compare and evaluate Integrated Weed Management (IWM) strategies. Specifically, the model was parameterized for soybean crops in competition with Euphorbia davidii Subils. We used both, weed and crop demographic data surveyed in agronomic fields of the central zone of the Buenos Aires province, Argentina, throughout two crop cycles (2011/2012 and 2013/2014). The proposed model underwent a calibration process and subsequent validation with 70/30 % data split respectively (N=37). Two annual-based and one multiannual-based case studies were simulated to demonstrate the performance of the model. Different IWM strategies were compared under both, operational and tactical planning horizons through the evaluation of different model outcomes (i.e. crop yield, interspecific competition, economic return, and environmental impact). Our case studies results suggest that the inclusion of cultural management practices could reduce weed interspecific competition by 46 to 97 % and weed seed production by 40 to 89%. An increment in both expected crop yield, by 6 to 20%, and annual gross margin, by 44 to 199 US$.ha-1, were obtained in silico for similar levels of environmental impact.

This study evaluated the using of machine vision in combination with deep learning to identify weeds in real-time for wheat production system. PMAS-Arid Agriculture university research farm were selected for collection of images (6000 total images) of weeds and wheat crops under different weather condition. During growing season, the database was constructed to identify the weeds. For this study two framework were used TensorFlow and PyTorch under CNNs and Deep learning. Deep learning perfromed better with in PyTourch value as compared to another model in Tensorflow. comparing with other networks such as YOLOv4, we concluded that our network reaches a better result between speed and accuracy. Specifically, the maximum precision of weed and wheat plants were 0.89 and 0.91 respectively with 9.43 ms and 12.38 ms inference time per image (640 × 640) NVIDIA RTX2070 GPU.

Semantic segmentation of high-resolution remote sensing images provides detailed and precise feature information, playing a pivotal role in decision-making and analysis in sectors such as water management, agriculture, military, and environmental protection. However, most methods merely combine features from various branches directly, without a mechanism for spatial location feature screening, and treat all extracted features as equally important. To overcome these limitations, we introduce a novel spatially adaptive interaction network (SAINet) for dynamic interaction across different features in remote sensing semantic segmentation task. Specifically, we propose a spatial refined module that leverages local context information to filter spatial locations and extract salient regions. Following this, we introduce an innovative spatial interaction module that uses a spatial adaptive modulation mechanism to dynamically select and allocate spatial position weights. This facilitates interaction between local salient areas and global information, allowing the network to focus more on relevant regions. This flexible approach enables the network to capture more informative features, thereby enhancing segmentation accuracy. Experiments conducted on the DeepGlobe, Vaihingen, and Potsdam public datasets confirm the effectiveness and capability of SAINet. Our code and models will be publicly available

Weeds are unwanted and invasive plants that proliferate and compete for resources such as space, water, nutrients, and sunlight, affecting the quality and productivity of the desired crops. Weed detection is crucial for the application of precision agriculture methods and for this purpose machine learning techniques can be used, specifically convolutional neural networks (CNN). This study focuses on the search for CNN architectures and technology used to detect and identify weeds in different crops; 61 articles applying CNN architectures and technology were analyzed in the last five years (2019-2023). The results show the used of different devices to acquire the image for training, such as digital cameras, smartphones, and drone cameras. Additionally, the YOLO family and algorithms are the most widely adopted architectures, followed by VGG, ResNet, Faster R-CNN, AlexNet, and MobileNet, respectively. This study provides an update on CNNs that will serve as a starting point for researchers wishing to implement these weed detection and identification techniques.

This study introduces a sophisticated neural network structure for segmenting breast tumors. It achieves this by combining a pretrained Vision Transformer (ViT) model with a U-Net framework. The U-Net architecture, commonly employed for biomedical image segmentation, is further enhanced with Depthwise Separable Convolutional Blocks to decrease computational complexity and parameter count, resulting in better efficiency and less overfitting. The Vision Transformer, renowned for its robust feature extraction capabilities utilizing self-attention processes, efficiently captures the overall context within images, surpassing the performance of conventional convolutional networks. By using a pretrained ViT as the encoder in our U-Net model, we take advantage of its extensive feature representations acquired from extensive datasets, resulting in a major enhancement in the model’s ability to generalize and train efficiently. The suggested model has exceptional performance in segmenting breast cancers from medical images, highlighting the advantages of integrating transformer-based encoders with efficient U-Net topologies. This hybrid methodology emphasizes the capabilities of transformers in the field of medical image processing and establishes a new standard for accuracy and efficiency in activities related to tumor segmentation.

Weeds can have both positive and negative effects on agricultural environments. However, despite the growing interest in the ecology of weed communities in agricultural areas, few studies have been carried out in the northern region of the Andes of Colombia, where urban and agricultural expansion have gen-erated highly disturbed scenarios. The aim of this study is to analyze the diversity of vegetation and weed seed banks in three agricultural production systems and a forest ecosystem in the northern Andes of Colombia. Hill numbers were used to compare diversity, Beta diversity to assess changes in composition, and range-abundance-dominance curves at different sites. Likewise, indicator species were analyzed to find species associations to each system. The results revealed differences in the composition of weeds between the forest ecosystem and the agricultural production systems, with higher equitability in the forest ecosystem and higher dominance in agricultural systems. A higher differentiation was observed in the dominant species of each agricultural system, highlighting those considered pests due to their life history traits, giving them greater success against various anthropogenic selection pressures. These findings highlight the impact of anthropogenic disturbances on the ecological dynamics of weed com-munities in different ecosystems, which should be considered when planning integrated weed manage-ment techniques.

Broomrape (Orobanche cumana), root parasitic weed, negatively affects sunflower, thereby causing severe yield losses and required controls on O. cumana infestation. Brassinosteroids (BRs) plays key roles in plant growth and provides resilience to weed infection. This designed study evaluated the mechanisms by which BRs ameliorates O. cumana infection in sunflower (Helianthus annuus). The pretreatment of sunflower seeds with various concentrations of BRs (1, 10, and 100 nM) were applied with and without O. cumana infestation. Under O. cumana infection, a significant reduction in plant height (38.61%), fresh/dry biomass, photosynthesis and regulation in plant defense (POX, GST), BRs signaling (BAK1, BSK1 to BSK4) and synthesis (BRI1, BR6OX2) associated genes. Moreover, O. cumana elevated the levels of MDA, OH‒, H2O2 and O2•‒ in leaves/roots by 77%/112%, 62%/104%, 57%/98% and 55%/89.4% and caused ultrastructural damages in leaves/roots, suggesting the severe oxidative or cellular damages in sunflower. In response, plants activate activities of SOD and POD enzymes as well as reduced or oxidized glutathione, but unable to stimulate APX and CAT activities. Addition of BRs, especially at 10 nM notably lowered the production of oxidative stress, activated the enzymatic and non-enzymatic antioxidants. The downregulation in the reported genes by BRs attributed to the increased resilience of sunflower (via susceptible reaction). In nutshell, the pretreatment of BRs enhanced the sunflower resistance to O. cumana infection by improving the planta growth and biomass, photosynthesis, activating the antioxidant defense system, lowering the oxidative stress, cellular damages and modulating the expression of BR synthesis and signaling genes.

Despite the productivity, achieving long-term sustainability and maintaining plant biodiversity become the pivotal goals in orchard floor management, especially along tree rows. Thus, the paradigm of eradicating weeds in the tree row using chemical herbicide or repeated soil tillage needs to be substituted with more sustainable alternatives. This study was conducted in two commercial apple and peach orchards in Marche region (Italy). Two integrated mechanical approaches, integrated mowing (mower + brush or disc) and integrated tillage (blade weeder + integrated mowing), were compared with standard herbicide system in a 2-years trial. Weed species abundance, soil coverage rate, and weed biomass productions, including gas exchange parameters, tree growth, fruit yield and quality were measured. Both integrated practices had significant effects on the number of weed species, total vegetation coverage, and dry weed biomass production. No significant differences were found in terms of tree gas exchange parameters, growth and fruit yield. However, a few fruit quality parameters such as fruit firmness, solid soluble content and dry matter content responded positively to the integrated practices. These results suggest that the integrated mechanical approaches of weed management increased orchard biodiversity, and they had no adverse effects on tree growth, fruit yield, and quality.

Recent advancements in deep learning have spurred the development of numerous novel semantic segmentation models for land cover mapping, showcasing exceptional performance in delineating precise boundaries and producing highly accurate land cover maps. However, to date, no systematic literature review has comprehensively examined semantic segmentation models in the context of land cover mapping. This paper addresses this gap by synthesizing recent advancements in semantic segmentation models for land cover mapping from 2017 to 2023, drawing insights on trends, data sources, model structures, and performance metrics based on a review of 106 extracted articles. Our analysis identifies top journals in the field, including MDPI Remote Sensing, IEEE Journal of Selected Topics in Earth Science, and IEEE Transactions on Geoscience and Remote Sensing, IEEE Geoscience and Remote Sensing Letters, ISPRS Journal Of Photogrammetry And Remote Sensing as the leading journals. We find that research predominantly focuses on land cover, urban areas, precision agriculture, environment, coastal areas, and forests. Geographically, 35.29% of the study areas are located in China, followed by USA (11.76%), France (5.88 %), Spain (4%) and others. Sentinel-2, Sentinel-1, and Landsat satellites emerge as the most commonly used data sources. Benchmark datasets such as ISPRS Vaihingen & Potsdam, LandCover.ai, DeepGlobe, and GID datasets are frequently employed. Model architectures predominantly utilize encoder-decoder, and hybrid convolutional neural network-based structures because of their impressive performances, with limited adoption of transformer-based architectures due to its computational complexity issue, and slow convergence speed. Lastly, this paper highlights existing key research gaps in the field to guide future research directions.

Uncontrolled and fast cell proliferation is the cause of brain tumors. Early cancer detection is vitally important in order to save many lives. Brain tumors can be divided into several categories depending on the kind, place of origin, pace of development, and stage of progression; as a result, tumor classification is crucial for targeted therapy. The aim of brain tumor segmentation is to accurately delineate the areas of the brain. A specialist with a thorough understanding of brain illnesses must manually identify the proper type of brain tumor. Additionally, processing a lot of images takes time and is tiresome. Therefore, automatic segmentation and classification techniques are required to speed up and enhance the diagnosis of brain tumors. Tumors can be quickly and safely detected by brain scans using imaging modalities, including computed tomography (CT), magnetic resonance imaging (MRI), and others. Machine learning (ML) and artificial intelligence (AI) have shown promise in the development of algorithms that aid in automatic classification and segmentation utilizing various imaging modalities. This review discussed various types of brain tumors, publicly accessible datasets, enhancement methods, segmentation, feature extraction, classification, machine learning techniques, and deep learning, learning through transfer, for the study of brain tumors.

Soybean (Glycine max L.) is a vital leguminous crop known for its rich nutritional profile, includ-ing high protein and oil content, making it a valuable resource in global agriculture and human nutrition. In Pakistan due to regulatory issues non-GMO soybean is grown therefore, the universal herbicide control method is not applicable. Similarly, for other crops, specific herbicides are avail-able but for soybean no crop specific herbicide is present. A comprehensive study was conducted over two growing seasons, in 2022 and 2023, at Agronomic Research Farm University of Agri-culture Faisalabad. The research involved 16 different treatments, including both six pre-emergence and eight post-emergence herbicides as well as a control group and weedy check. Findings of this study showed that critical importance of weed management in soybean cultiva-tion, as unchecked weed infestation can lead to substantial yield losses. Among the pre-emergence herbicide S-Metolachlor + Pendimethalin performed best and showed higher plant height (54.33 cm & 53.67 cm), 100 grain weight (11.57 g & 12 g), seed yield plant-1 (13.07 g and 12.87 g), lower Susceptibility Index (10%), higher weed control percentage (91.21% & 95.65%) higher weed con-trol efficiency (92.02% & 93.43%), herbicide efficiency index (27.54% & 32.48%) and lower weed index (18.16% & 21.70%) during 2022 and 2023 respectively. However, in post emergence herbi-cide the Fluizefop-p-butyl is most effective herbicide due to less crop injury 10% Susceptibility In-dex, higher plant height (42.67 cm & 44 cm), whole plant weight (93.33 g & 95 g), 100-grain weight (11.40 g & 11.77 g), seed yield plant-1 (12.87 g & 13.13 g), higher weed control percentage (91.12% & 91.03%) higher weed control efficiency (89.73% & 92.36%, herbicide efficiency index (21.18% & 30.41%) and lower weed index (19.42% & 20.08%) in both 2022 and 2023 respectively. Notably, herbicides such as S-Metolachlor + Atrazine + Mesotrione, Topramezone, Mesosulfu-ron-methyl + Iodosulfuron-methyl sodium and Mesotrione + Atrazine led to complete plant mor-tality, resulting lethal to soybean. The findings of this study support the hypothesis that screened the best suitable herbicides with less plant injury, and higher efficiency index. So, it is recom-mended that the application of S-Metolachlor + Pendimethalin as PRE and Fluizefop-p-butyl as POST showed the least injury and best weed control results with higher grain yield.

Foraminifera are single-celled marine organisms that construct shells that remain as fossils in the marine sediments. Classifying and counting these fossils are important in e.g. paleo-oceanographic and -climatological research. However, the identification and counting process has been performed manually since the 1800s and is laborious and time-consuming. In this work, we present a deep learning-based instance segmentation model for classifying, detecting, and segmenting microscopic foraminifera. Our model is based on the Mask R-CNN architecture, using model weight parameters that have learned on the COCO detection dataset. We use a fine-tuning approach to adapt the parameters on a novel object detection dataset of more than 7000 microscopic foraminifera and sediment grains. The model achieves a (COCO-style) average precision of 0.78±0.00 on the classification and detection task, and 0.80±0.00 on the segmentation task. When the model is evaluated without challenging sediment grain images, the average precision for both tasks increases to 0.84±0.00 and 0.86±0.00, respectively. Prediction results are analyzed both quantitatively and qualitatively and discussed. Based on our findings we propose several directions for future work, and conclude that our proposed model is an important step towards automating the identification and counting of microscopic foraminifera.

With the rapid development of smart phones, tablets and their operative systems, many positioning enabled sensors have been built into these devices. Users can now accurately fix their location according to the function of GPS receivers. For indoor environments, as in the case we are studying, WiFi based positioning is preferred to GPS due to the attenuation or obstruction of signals. This paper deals with the automatic classification of customers in a Sports Shop Center on the basis of their movements around the shop's premises. To achieve this goal, we start by collecting (x,y) coordinates from customers while they visit the store. Consequently, any costumer's path through the shop is formed by a list of coordinates, obtained with a frequency of one measurement per minute. Then, a guess about the full trajectory is constructed and a number of parameters about these trajectories is calculated before performing an Unsupervised Learning Clustering Process. As a result, we can identify several types of customers, and the dynamics of their behavior inside the shop. This information is of great value to the company, to be used both in the long term and also in short periods of time, monitoring the current state of the shop at any moment, identifying different types of situation appearing during restricted periods, or predicting customer flow conditions

Agriculture is an important sector of European Union in societal , economic and environmental dimensions. Sustainability of the sector require improvements in its key operations. Weeding is one of the crucial operation having impact on farms’ productivity, safety for farmers, food security and environmental state. To achieve EU policy goals of sustainable agriculture there are needed new technical and organizational solutions. One of the advanced techniques are laser based weeding technique. It is important to understand well the impacts of introduction of these tech-niques to the markets and agricultural practice in sustainability context. For that reason Social Life Cycle Assessment was performed. The method was based on participatory approach. The as-sessment was carried in three perspectives: general society, farmers, and business perspective re-lated to agriculture. Expert interviews based on questionnaires and workshops were realized to get the opinions on the impacts of a new laser technique on particular aspects of its implementation. The results show generally positive impact in all perspectives, especially in the perspective of farmers.

Pepper leaf segmentation plays a crucial role in monitoring pepper leaf diseases in various backgrounds and ensuring the healthy growth of peppers. However, existing transformer-based segmentation methods suffer from computational inefficiency, excessive parameterization, and limited utilization of edge information. To tackle these challenges, we propose an adaptive multi-scale MLP framework, named AMS-MLP, which combines the multi-path aggregation module (MPAM) and the multi-scale context relation mask module (MCRD) to refine the object boundaries in pepper leaf segmentation. AMS-MLP consists of an encoder-based network, an adaptive multi-scale MLP (AM-MLP) module, and a decoder network. In the encoder network, the MPAM module effectively fuses five-scale features to generate a single-channel mask, improving the accuracy of pepper leaf boundary extraction. The AM-MLP module divides the input features into two branches: the global multi-scale MLP branch captures long-range dependencies between image information, while the local multi-scale MLP branch focuses on extracting local feature maps. Adaptive attention mechanism is designed to dynamically adjust the weights of global and local features. The decoder network incorporates the MCRD module into the convolutional layer, enhancing the extraction of boundary features. To verify the performance of the proposed method, we conducted extensive experiments on three pepper leaf datasets with different backgrounds. The results demonstrate mIoU scores of 97.39%, 96.91%, and 97.91%, as well as F1 scores of 98.29%, 97.86%, and 98.51%, respectively. Comparative analysis with U-Net and state-of-the-art models reveals that the proposed method dramatically improves the accuracy and efficiency of pepper leaf image segmentation.

Faba bean is an important legume crop wordwide, grown both for food and feed. As for many legume crops, postemergence weed control is difficult. The aim of this work was to assess potential of intercropping on weed management by assessing the effect of mixing faba bean with different crops (wheat, barley, and pea) on weeds in the South of Spain. Four field trials were conducted over four consecutive seasons, and results found that addition alternate intercropping of faba bean and barley achieved high levels of weed control, both for coverage and biomass (92.7% and 76.6%, respectively). Intercropping with wheat did not reduce weed coverage but did decrease weed biomass by 46.1% as compared to faba bean monocrop. Intercropping with pea did not provide significant reductions for weed coverage neither for weed biomass. The diversity of the weed community was not altered by the different crop combinations tested. Additional experiments under controlled conditions were carried out to determine a possible role of barley allelopathy in weed suppression. A strong allelopathic effect entailing a reduction in the number of plants and biomass was detected for four weeds: Sinapis arvensis, Polypogon monspeliensis, Matricaria camomilla, and Medicago trucatula. It can be concluded that intercropping faba bean with barley is an excellent strategy for weed control in the Southern Spain.

Over the last five decades, weed management systems have relied primarily on synthetic herbicides. Due to the concerns over the potential impact of chemicals on human health and the environment, efforts are being made to reduce the heavy reliance on synthetic herbicides. To reduce the use of synthetic herbicides, the use of natural products such as essential oils, plant extracts, allelochemicals, agricultural by-products, and some microbes are gaining attention because of their short environmental half-life and low toxicity. They are a good alternative to synthetic herbicides, especially in organic agriculture, since they focus on environmental protection, and ecological stability. Most of the commercially available natural herbicides are non-selective and require careful application in order to preserve the cash crops. Although many studies in this direction have been undertaken, the use of these natural products is still not common because of their cost the difficulties in their synthesis due to their complex structure, cost effectiveness, poor performance, and rapid degradation. When used singly, these natural herbicides do not perform as well as the chemical herbicides. An integrated approach may provide better results. Using a combination of natural herbicides may be more effective than using just one.

A single paragraph of about 200 words maximum. For research articles, abstracts should give a pertinent overview of the work. We strongly encourage authors to use the following style of structured abstracts, but without headings: (1) Background: place the question addressed in a broad context and highlight the purpose of the study; (2) Methods: describe briefly the main methods or treatments applied; (3) Results: summarize the article’s main findings; (4) Conclusions: indicate the main conclusions or interpretations. The abstract should be an objective representation of the article, it must not contain results which are not presented and substantiated in the main text and should not exaggerate the main conclusions.

Anomaly detection and segmentation aim at distinguishing abnormal images from normal images and further localizing the anomalous regions. Feature reconstruction based method has become one of the mainstream methods for this task. This kind of method has two assumptions: (1) The features extracted by neural network is a good representation of the image. (2) The autoencoder solely trained on the features of normal images cannot reconstruct the features of anomalous regions well. But these two assumptions are hard to meet. In this paper, we propose a new anomaly segmentation method based on feature reconstruction. Our approach mainly consists of two parts: (1) We use a pretrained vision transformer (ViT) to extract the features of the input image. (2) We design a self-attention autoencoder to reconstruct the features. We regard that the self-attention operation which has a global receptive field is beneficial to the methods based on feature reconstruction both in feature extraction and reconstruction. The experiments show that our method outperforms the state-of-the-art approaches for anomaly segmentation on the MVTec dataset. It is both effective and time-efficient.

The problem of event detection in general noisy signals arises in many applications; usually, either a functional form for the event is available, or a previous annotated sample with instances of the event that can be used to train a classification algorithm. There are situations, however, where neither functional forms nor annotated samples are available; then it is necessary to apply other strategies to separate and characterize events. In this work, we analyze 15 minute-long samples of an acoustic signal, and are interested in separating sections, or segments, of the signal which are likely to contain significative events. For that, we apply a sequential algorithm with the only assumption that an event alters the energy of the signal. The algorithm is entirely based on Bayesian methods.

Land cover mapping, essential for understanding global land use patterns, relies on satellite imagery for monitoring changes, assessing ecosystem health, and supporting conservation ef- forts. However, significant challenges remain in managing large, complex satellite imagery datasets, acquiring specialized datasets due to high costs and labor intensity, and a lack of comparative studies for optimal deep learning model selection. Additionally, a scarcity of aerial datasets specifically tailored for agricultural areas exists. This study addresses these gaps by presenting a method for semantic segmentations of land covers in agricultural areas using satellite images and deep learning models with pre-trained backbones. We introduce an efficient methodology for preparing semantic segmentation datasets and contribute the "Land Cover Aerial Imagery" (LICAID) dataset for semantic segmentation. The study focuses on the Franciacorta area, Lombardy Region, leveraging the rich diversity of the dataset to effectively train and evaluate the models. We conduct a comparative study, employing cutting-edge deep learning-based segmentation models (U-Net, SegNet, DeepLabV3) with various pre-trained backbones (ResNet, Inception, DenseNet, EfficientNet) on our dataset acquired from Google Earth Pro. Through meticulous data acquisition, preprocessing, model selection, and evaluation, we demonstrate the effectiveness of these techniques in accurately delineating land cover classes. Integrating pre-trained feature extraction networks significantly improves performance across various metrics. Additionally, addressing challenges such as data availability, computational resources, and model interpret-ability is essential for advancing the field of remote sensing and supporting sustainable environmental stewardship worldwide.

White matter hyperintensity (WMH) has been considered the primary biomarker from small-vessel cerebrovascular disease to Alzheimer’s disease (AD) and has been reported for its correlation of brain structural changes. To perform WMH related analysis with brain structure, both T1-weighted (T1w) and (Fluid Attenuated Inversion Recovery(FLAIR) are required. However, in a clinical situation, it is limited to obtain 3D T1w and FLAIR images simultaneously. Also, the most of brain segmentation technique supports 3D T1w only. Therefore, we introduced the semi-supervised learning method that can perform brain segmentation using FLAIR image only. Our method achieved a dice overlap score of 0.86 for brain tissue segmentation on FLAIR, with the relative volume difference between T1w and FLAIR segmentation under 4.8%, which is just as reliable as the segmentation done by its paired T1w image. We believe our semi-supervised learning method has a great potential to be used to other MRI sequences and provide encouragement to people who seek brain tissue segmentation from a non-T1w image.

Purpose: Carotid intraplaque hemorrhage (IPH) increases risk of territorial cerebral ischemic events, but different sequences or criteria have been used to diagnose or quantify carotid IPH. The purpose of this study was to compare manual segmentation and semi-automatic segmentation for quantification of carotid IPH on magnetization-prepared rapid acquisition with gradient-echo (MPRAGE) sequences. Methods: Forty patients with 16–79% carotid stenosis and IPH on MPRAGE sequences were reviewed by two trained radiologists with more than five years of specialized experience in carotid plaque characterization with carotid plaque MRI. Initially, the radiologists manually viewed the IPH based on the MPRAGE sequence. IPH volume was then measured by three different semi-automatic methods, with high signal intensity 150%, 175%, and 200%, respectively, above that of adjacent muscle on the MPRAGE sequence. Agreement on measurements between manual segmentation and semi-automatic segmentation was assessed using the intraclass correlation coefficient (ICC). Results: There was near-perfect agreement between manual segmentation and the 150% and 175% criteria for semi-automatic segmentation in quantification of IPH volume. The ICC of each semi-automatic segmentation were as follows: 150% criteria: 0.861, 175% criteria: 0.809, 200% criteria: 0.491. The ICC value of manual vs. 150% criteria and manual vs. 175% criteria were significantly better than the manual vs. 200% criteria (p < 0.001). Conclusions: The ICC of 150% and 175% criteria for semi-automatic segmentation are more reliable for quantification of IPH volume. Semi-automatic classification tools may be beneficial in large-scale multicenter studies by reducing image analysis time and avoiding bias between human reviewers.

Canola (Brassica napus L) is a profitable grain crop for Australian growers. However, weeds remain a major constraint for its production. Chemical herbicides are used for weed control, but this tactic also leads to the evolution of herbicide resistance in different weed species. Suppression of weeds by crop competition and allelopathic mechanisms has been receiving significant attention. Here, the weed suppressive ability, and associated functional traits and stability of four selected canola genotypes (PAK85388-502, AV-OPAL, AV-GARNET and BAROSSA) were examined at different locations of NSW, Australia. Results showed that there were significant effects of canola genotypes and of genotypes by crop density interaction on weed growth. Among the tested genotypes, PAK85388-502 and AV-OPAL were the most weed suppressive and, at plant density of 10 plants/m2, they reduced weed biomass of wild radish, shepherd’s purse and annual ryegrass by more than 80%. No significant differences were found in the primary root lengths among canola varieties; however, plants of the allelopathic genotype PAK8538-502 exhibited a 35% increase in lateral root number relative to plants of non-allelopathic genotype BAROSSA. The analysis of variance revealed a significant influence of genotypes with PAK85388-502 and AV-OPAL performed the best across all the research sites. Results showed that canola genotypes PAK85388-502 and AV-OPAL were more weed suppressive than AV-GARNET and BAROSSA and may release specific bioactive compounds in their surroundings to suppress neighbouring weeds. This study provides valuable information that could be utilised in breeding programs to select weed suppressive varieties of canola in Australia. Thus, lateral root number could be a potential target trait for weed suppressive varieties. Additionally, other root architecture traits may contribute to the underground allelopathic interaction to provide a competitive advantage to the crop.

One of the most leading causes of death worldwide is Colorectal cancer(CRC). Polyp segmentation is the most important detected measure for preventing CRC. However, there is still a missing rate for diminutive polyps and multiple ones. In order to solve the phenomenon, we propose to introduce auxiliary attention module(AAM) that can enhance the learning of features related to multiple and diminutive polyps by focusing more on the located and detailed information. Meanwhile, we design to decrease missed rate of multiple and diminutive polyps by implementing an area adaptive loss(AAL) which adapts the weight according to the area and the number of polyps. Our proposed novel AAM and AAL concentrates on training with hard examples and localized information. To evaluate the effectiveness and generalization ability of our proposed model, We utilize three different datasets of variable sizes and a cross dataset. Our proposed method achieves the best results on the Kvasir-SEG dataset, the CVC-ClinicDB dataset and the cross dataset, particularly for the Kvasir-Sessile dataset consisting of small,flat and diminutive polyps. Extensive experimental results show that our proposed DoubleAANet surpass the performance of all existing state-of-the-art segmentation methods.

In the realm of computer vision, semantic segmentation is the task of recognizing objects in images at the pixel level. This is done by performing a classification of each pixel. The task is complex and requires sophisticated skills and knowledge about the context to identify objects’ boundaries. The importance of semantic segmentation in many domains is undisputed. In medical diagnostics, it simplifies the early detection of pathologies, thus mitigating the possible consequences. In this work, we provide a review of the literature on deep ensemble learning models for polyp segmentation and we develop new ensembles based on convolutional neural networks and transformers. The development of an effective ensemble entails ensuring diversity between its components. To this end, we combine different models (HarDNet-MSEG, Polyp-PVT, and HSNet) trained with different data augmentation techniques, optimization methods, and learning rates, which we experimentally demonstrate to be useful to form a better ensemble. Most importantly, we introduce a new method to obtain the segmentation mask which is more suitable for combining transformers in an ensemble. In our extensive experimental evaluation, the proposed ensembles exhibit state-of-the-art performance.

Current bridge inspection practices rely on paper-based data acquisition, digitization, and multiple conversions in between incompatible formats to facilitate data exchange. This practice is time-consuming, error-prone, cumbersome, and leads to information loss. One aim for future inspection procedures is to have a fully digitized workflow that achieves loss-free data exchange, which lowers costs and offers higher efficiency. On the one hand, existing studies proposed methods to automatize data acquisition and visualization for inspections. These studies lack an open standard to make the gathered data available for other processes. On the other hand, several studies discuss data structures for exchanging damage information through out different stakeholders. However, those studies do not cover the process of automatic data acquisition and transfer. This study focused on a framework that incorporates automatic damage data acquisition, transfer, and a damage information model for data exchange. This enables inspectors to use damage data for subsequent analyses and simulations. The proposed framework shows the potentials for a comprehensive damage information model and related (semi-)automatic data acquisition and processing.

The Eucalyptus genus is the most planted forest crop in the world, with Brazil being one of the countries with the greatest productive potential. However, the occurrence of weeds can cause losses in productivity. Chemical control is widely used, but the efficiency of herbicides depends on factors such as the presence of straw in the soil and the occurrence of rainfall. Due to the scarcity of results regarding the interaction between herbicide, straw, and water depth in the forest sector, the objective of this study is to evaluate the efficiency of S-metolachlor + glyphosate in the control of grasses in different densities of eucalyptus straw and with simulated rain after the application of the product. The experiment was conducted in DBC, factorial 3×3×2, with four replications. The first factor represented 0, 50 and 100% of the commercial dose of S-metolachlor + glyphosate, the second 0, 5, and 10 ton ha-2 of straw, and the third 25 and 50mm of water depth applied in soil with a mix of grasses previously sowed. The rainfall simulation was performed 24 hours after herbicide application on each straw volume. The fresh mass of the aerial part of the grasses was collected 43 days after sowing and dried in an oven to determine the dry mass. Visual analyzes of the percentage of control were performed with scales ranging from 0 to 100, where 0 represents no control and 100 efficient control. The fresh and dry mass and the grasses' dry mass/water ratio decreased with increasing herbicide dosage and straw density. The dosage of 2.12 + 1.59 kg i.a. ha-1 of S-metolachlor + glyphosate resulted in greater control of grasses, and the treatments without straw and with the application of the herbicide had the highest percentages of control. Applying different water depths (25 mm or 50 mm) did not influence the control. Despite the control of grasses, the efficiency of the herbicide mixture was affected by the presence of vegetation cover.

Identification and segmentation of rock particles is very important in geology, mining, engineering construction, and environmental monitoring. Traditional methods for recognizing the rock particle characteristics are time-consuming, labor-intensive, and limited by the geographical scope of the sampling sites, which makes it more difficult to represent the spatial distribution of the rock particles accurately. Recent advancements in deep learning techniques offer promising solutions to automate this process. This study aims at utilizing state-of-the-art (SOTA) Mask R-CNN deep learning algorithm from the Detectron2 framework, to capture global features of rocks that will enable the recognition of rock particles more efficiently, just from having the rock images. These images are subject to image processing techniques such as a Gaussian filter, to denoise and smoothen the image, and an Illumination Adaptive Transformer (IAT) framework, to adjust the lighting exposure; all of which add to improve the quality of the image dataset. Afterward, the Mask R-CNN and Detectron2 models are utilized in training the images using transfer learning. Experimental results from evaluating the performance of the proposed algorithms showcase the effectiveness of the approach, thereby highlighting its potential to revolutionize rock particle segmentation across various domains.

Nowadays, semantic segmentation is increasingly used in exploration by underwater robots, for example in autonomous navigation, so that the robot can recognise the nature and elements of its environment during the mission and act according to this classification to avoid collisions. Other applications can be found in the search for archaeological artefacts, in the inspection of underwater structures or in species monitoring. Therefore, it is necessary to try to improve the performance in these tasks as much as possible. To this end, we compare some methods for improving image quality and for data augmentation and test whether higher performance metrics can be achieved with both strategies. The experiments are performed with the SegNet implementations and the SUIM dataset with 8 common underwater classes to compare the obtained results with the already known ones. The results obtained with both strategies show that they are beneficial and lead to better performance results by achieving a mean IoU of 56% and an increased overall accuracy of 81.8%. The single result shows that there are 5 classes with an IoU value above 60% and only one class with an IoU value below 30%, which is a more reliable result and easier to use in real contexts.

Teeth segmentation plays a pivotal role in dental diagnosis, treatment, planning, and the development of computer-aided dental systems. It enables precise identification and analysis of dental structures, aiding in detecting dental abnormalities, measuring tooth dimensions, and assessing oral health conditions. Accurate teeth segmentation also facilitates the automation of dental workflows, leading to improved efficiency and reduced human error. Artificial Intelligence (AI) has witnessed rapid advancements, with various approaches developed or enhanced. While Convolutional Neural Networks (CNNs) have been widely used in medical image segmentation, the U-Net architecture has emerged as a standout performer due to its exceptional segmentation capabilities. This paper presents a proof of concept for the Attention U-Net architecture, as previously used in [1], applied to teeth segmentation. The study demonstrates the superior performance of this network in accurately segmenting teeth using a newly available benchmark dataset called Tufts Dental X-Ray Dataset. When trained and tested on 10-fold cross-validation, the model achieved an average dice coefficient of 95.01%, intersection over union of 90.6%, and pixel accuracy of 98.82%. These scores surpass those of all other networks implemented on the same dataset. By leveraging the Attention U-Net architecture, our research showcases the potential of advanced AI techniques in dental radiography. The findings contribute to the ongoing efforts to develop automated systems to assist dental professionals in their clinical practice.

Background: Medicinal plants are of great importance to health of individual and communities. About 80% of the population in Uganda relies on traditional medicine because western-trained medical personnel are limited especially in villages. Most Ugandans use Hymenoxys odorato for medicinal purposes e.g. to treat colds, fever, coughs, anti-helminthes, locally used as tea, anti-allergy and also as an anti-venom to relieve snake bites. Method: A group of 25 male wistar rats of 150 g–210 g were kept for 14 days while being fed and treated with the extract. At 14^th day, anesthesia was given and blood samples collected by cardiac puncture for hematological and biochemical investigations. Serum was analyzed for Alkaline Phosphatase, Aspartate Transaminase and Alanine Transaminase while whole blood was used for complete blood count. The liver and kidney were removed and placed in 10% formalin to prepare for histology staining using haematoxylin and eosin technique. Results: The extract elevated hepatic biomarker enzymes i.e. ALP, ALT and AST. The increase was found to be significantly different (P > 0.05) at 400 and 500 mg/kg doses as compared to the control group. Histological sections of the liver showed distortion of liver cytoarchitecture, steatosis, necrosis of hepatocytes and congestion of the sinusoids at high doses 300, 400 and 500 mg/kg body weight. In the sections of the kidney, there was mild distortion of the integrity of the kidney with glomerular hypercellularity at high doses (400 and 500 mg/kg per body weight). Conclusion: Hymenoxys odorato aqueous extract has toxic effects on the liver and kidney of wistar rats. The effects were observed to be in a dose dependent manner.

Coffee is one of the most valuable agricultural products worldwide, and it is crucial to have efficient tools to obtain reliable information about production. This study aims to estimate coffee plantation production using segmentation and deep learning techniques in RGB images. Photographs of coffee plants were taken in Tabaconas, San Ignacio-Cajamarca, to create a dataset of crops during the harvest stage. The images were segmented to detect coffee fruits. A deep learning method was developed with YOLOv5 to detect the fruits and OpenCV to count them. The results showed that YOLOv5 achieved an accuracy of 97.25%, a recall of 95.77%, and an F1-Score of 96.37%, demonstrating high reliability in detecting coffee fruits. The average detection time per image was 17.9 seconds. The metrics were evaluated using a confusion matrix, highlighting the model's good performance. In conclusion, segmentation and deep learning techniques, along with counting algorithms developed with OpenCV, proved effective for estimating coffee production. This approach provides a valuable tool for farmers, improving crop management and facilitating decision-making in precision agriculture.

Iberian ham, a traditional Spanish meat product, is renowned for its unique nutritional and sensory attributes, garnering widespread appreciation both domestically and internationally [1]. It is one of the most outstanding Spanish gastronomic treasures, with very special nutritional and sensory properties that make it highly appreciated throughout the world [2]. Recent trends indicate a notable surge in its consumption, a pattern projected to persist [3]. For an enhanced online shopping experience, understanding the specific characteristics and requirements of various consumer segments is crucial. This study aims to scrutinize national Iberian ham consumption patterns and, through survey methodologies, discern the preferences and needs of online consumers purchasing whole Iberian hams. The subsequent cluster analysis will empower suppliers with insights to pinpoint business prospects and craft segment-specific online marketing strategies.

Lesion studies are crucial in establishing brain-behavior relationships, and accurately segmenting the lesion represents the first step in achieving this. Manual lesion segmentation is the gold standard for chronic strokes. However, it is labor-intensive, subject to bias, and limits sample size. Therefore, our objective is to develop an automatic segmentation algorithm for chronic stroke lesions on T1-weighted MR images. Methods: To train our model, we utilized an open-source dataset: ATLAS v2.0 (Anatomical Tracings of Lesions After Stroke). We partitioned the dataset of 655 T1 images with manual segmentation labels into five subsets and performed a 5-fold cross-validation to avoid overfitting of the model. We used a deep neural network (DNN) architecture for model training. Results: To evaluate the model performance, we used three metrics that pertain to diverse aspects of volumetric segmentation including shape, location, and size. The Dice similarity coefficient (DSC) compares the spatial overlap between manual and machine segmentation. The average DSC was 0.65 (0.61- 0.67; 95% bootstrapped CI). Average symmetric surface distance (ASSD) measures contour distances between the two segmentations. ASSD between manual and automatic segmentation was 12mm. Finally, we compared the total lesion volumes and the Pearson correlation coefficient (ρ) between the manual and automatically segmented lesion volumes, which was 0.97(p-value &lt; 0.001). Conclusions: We present the first automated segmentation model trained on a large multicentric dataset. This model will enable automated on-demand processing of MRI scans and quantitative chronic stroke lesion assessment.

Lung cancer is a deadly disease if not diagnosed in its early stages. However, early detection of lung cancer is a challenging task due to the shape and size of its nodules. Radiologists need support from automated tools for precise opinion. Automated detection of the affected lungs nodule is difficult because of the shape similarity among healthy tissues. Over the years, several expert systems have been developed that help radiologists to diagnose lung cancer. In this article, we propose a framework to precisely detect lungs cancer by classifying it between benign and malignant nodules. The framework is tested using the subset of the publicly available at the Lung Image Database Consortium image collection (LIDC-IDRI). Multiple techniques including filtering and noise removing are applied for pre-processing. Subsequently, the OTSU and the semantic segmentation are used to accurately detect the unhealthy lungs nodules. In total, 13 nodules features were extracted using Principal Components Analysis (PCA) algorithm. Four optimal features are selected based on the classification performance. In the classification phase, 9 different classifiers are used along with two types of validation schemes i.e. train test holdout validation with 70-30 data split and 10 fold cross-validation. Our experiments show that the proposed system provides 99.23\% accuracy using logic boost classifier.

This paper compares a series of traditional and deep learning methodologies for the segmentation of textures. Six well-known texture composites first published by Randen and Hus{\o}y were used to compare traditional segmentation techniques (co-occurrence, filtering, local binary patterns, watershed, multiresolution sub-band filtering) against a deep-learning approach based on the U-Net architecture. For the latter, the effects of depth of the network, number of epochs and different optimisation algorithms were investigated. Overall, the best results were provided by the deep-learning approach. However, the best results were distributed within the parameters, and many configurations provided results well below the traditional techniques.

New advances of nano-enabled weed management: using poly(epsilon-caprolactone)-based nanoherbicides. A review

Palmer amaranth (Amaranthus palmeri) is a problematic common weed species, especially in cotton (Gossypium hirsutum). With the wide use of chemical herbicide and herbicide-tolerant transgenic cotton lines, Palmer amaranth populations have developed tolerance to commonly used herbicides. It is imperative to develop alternative weed control methods to slow the evolution of herbicide-resistant weed populations and provide new sources for weed management. Eleven chromosome substitution (CS) cotton lines CS-B26lo, CS-T17, CS-B16-15, CS-B17-11, CS-B12, CS-T05sh, CS-T26lo, CS-T11sh, CS-M11sh, CS-B22sh, and CS-B22lo were screened for weed-suppressing abilities in this study. The cotton lines were tested using the established stair-step structure methodology, which provided scope to study the effect of individual CS lines on the growth and development of Palmer amaranth weed without any interference of other external factors in the greenhouse. Height (cm) and chlorophyll concentration (cci) were measured for each plant in the system. The data were analyzed as a randomized complete block design using LSD mean comparisons of the genotypes at the P≤ .05 level. The 14th day after establishment resulted in the most significant variation in Palmer amaranth height reduction among the CS lines. Results indicated that CS-B22sh had the highest effect in reducing Palmer amaranth height and chlorophyll concentration with the most heightened susceptibility for Palmer amaranth. The cluster analysis revealed that Enlist® cotton, CS-CS-B22sh, and CS-T26lo were clustered in one group suggesting similar genetic potential with reference to Palmer amaranth growth and development. CS-B22sh showed novel genetic potential to control the growth and development of Palmer amaranth, a major weed in cotton fields. In the future, it will be interesting to investigate if CS-B22sh exudates from its root contain allelochemicals able to impede the growth and development of Palmer amaranth.

Localizing faults in a software is a tedious process. The manual approach is becoming impractical because of the large size and complexity of contemporary computer systems as well as their logs, which are often the primary source of information about the fault. Log-based Fault Localization (LBFL) is a popular method applied for this purpose. However, in real-world scenarios, this method is vulnerable to a large number of previously unseen log lines. In this paper, we propose a novel method that can guide programmers to the location of a fault by creating a hierarchy of log lines with the highest rank, selected by the traditional LBFL method. We use the intuition that the symptoms of faults are in the context of normal behavior, whereas suspicious log lines grouped together are from new or additional functionalities turned on during faulty execution. To obtain this context, we used unsupervised log sequence segmentation, which has been previously used to segment log sequences into meaningful segments. Experiments on real-life examples show that our method reduces the effort to find the most crucial logs by up to 64% compared to the traditional timestamp approach. We demonstrated that context is highly useful in advancing fault localization, showing the possibility of further speeding up the process.

While there are several ways to identify customer behaviors, few extract this value from information already in a database, much less extract relevant characteristics. This paper presents the development of a prototype using the recency, frequency, and monetary attributes for customer segmentation of a retail database. For this purpose, the standard K-means, K-medoids, and MiniBatch K-means were evaluated. The standard K-means clustering algorithm was more appropriate for data clustering than other algorithms as it remained stable until solutions with 6 clusters. The evaluation of the clusters’ quality was obtained through the internal validation indexes: Silhouette, Calinski Harabasz, and Davies Bouldin. Once consensus was not obtained, three external validation indexes were applied: global stability, stability per cluster, and segment-level stability across solutions. Six customer segments were obtained, identified by their unique behavior: Lost customers, disinterested customers, recent customers, less recent customers, loyal customers, and best customers. Their behavior was evidenced and analyzed, indicating trends and preferences.

Bone Scan Index (BSI) is an image biomarker for quantification on bone metastasis of cancers. To compute BSI, not only the hotspots (metastasis) but also the bones have to be segmented. Most related researches focus on binary classification on bone scintigraphy: having metastasis or none. Rare studies focus on pixelwise segmentation. In this study we compare three advanced convolutional neural network (CNN) based models to explore the bone segmentation on dataset in house. The best model is Mask R-CNN, which reaches the precision, sensitivity and F1-score: 0.93, 0.87, 0.90 for prostate cancer patients and 0.92, 0.86, 0.88 for breast cancer patients, respectively. The results are the average of 10-fold cross-validation, which reveals the reliability for clinical use on bone segmentation.

Since the emergence of convolutional neural networks (CNNs), and later vision transformers (ViTs), the standard paradigm for model development has been using a set of identical block types with varying parameters/hyper-parameters. To leverage the benefits of different architectural designs (e.g., CNNs and ViTs), we propose alternating structurally different types of blocks to generate a new architecture, mimicking how Lego blocks can be assembled. Using two CNN-based and one SwinViT-based blocks, we investigate three variations to the so-called LegoNet that apply the new block alternation concept for the segmentation task in medical imaging. We also study a new clinical problem that has not been investigated before – the right internal mammary artery (RIMA) and perivascular space segmentation from computed tomography angiography (CTA). It was proven to demonstrate a prognostic value to primary cardiovascular outcomes. We compare the model performance against popular CNN and ViT architectures using two large datasets (achieving 0.749 dice similarity coefficient (DSC) on the larger dataset). We also evaluate the model’s performance on three external testing cohorts, where an expert clinician corrected model-segmented results (DSC>0.90 for the three cohorts). To assess our proposed model for suitability in clinical use, we perform intra- and inter-observer variability analysis. Finally, we investigate a joint self-supervised learning approach to determine its impact on model performance.

As we all know, many more dynamic objects appear almost continuously in real world, which are immensely able to impair the performance of the majority of vision-based SLAM systems that are based on the static-world assumption. In order to improve the robustness and accuracy of visual SLAM in the high dynamic environment, a real-time and robust stereo SLAM system for dynamic scenes was proposed. To weaken influences of dynamic content, the moving object detection method was put forward in our visual odometry, then the semantic segmentation network was combined into our stereo SLAM to extract pixel-level contours of dynamic objects. Then influences of dynamic objects were extremely weaken and the performance of our system was increased markedly in dynamic, complex and crowed city spaces. Experiment with both on KITTI Odometry dataset and in a real-life scene, the results show that our method can dramatically decrease the tracking error or drift, improve the robustness and stability of our stereo SLAM in high dynamic outdoor scenarios.

Object segmentation is still considered a challenging problem in autonomous driving, particularly in consideration of real world conditions. Following this line of research, this paper approaches the problem of object segmentation using LiDAR-camera fusion and semi-supervised learning implemented in a fully-convolutional neural network. Our method is tested on real-world data acquired using our custom vehicle iseAuto shuttle. The data include all-weather scenarios, featuring night and rainy weather. In this work, it is shown that LiDAR-camera fusion with only a few annotated scenarios and semi-supervised learning, it is possible to achieve robust performance on real-world data in a multi-class object segmentation problem. The performance of our algorithm is measured in terms of intersection over union, precision, recall and area-under-the-curve average precision. Our network achieves 82% IoU in vehicle detection in day fair scenarios and 64% IoU in vehicle segmentation in night rain scenarios.

Worldwide, hundreds of thousands of people are diagnosed with kidney cancer and this disease is more common in developed and industrialized countries. Previously, kidney cancer was known as an elderly disease and was seen in people over a certain age; nowadays it is also seen in younger individuals and it is easier to diagnose thanks to new radiological diagnostic methods. A kidney tumor is a type of cancer that is extremely aggressive and needs surgical treatment rapidly. Today, approximately 30% of patients diagnosed with kidney cancer are unfortunately noticed at the stage of metastatic disease (spread to distant organs). The biggest factor that pushes us to this study is that kidney tumors progress unlike other cancer types with little or no symptoms. Therefore, conducting such studies is extremely important for early diagnosis. In this study, we compare the Unet3D models in order to help people who are dealing with difficulties in the diagnosis of kidney cancer. Unet, Unet+ResNet and Unet++ models were compared for image segmentation.

Clinically, knowing the number of red blood cells (RBCs) and white blood cells (WBCs) helps doctors to make the better decision on accurate diagnosis of numerous diseases. The manual cell counting is a very time-consuming and expensive process, and it depends on the experience of specialists. Therefore, a completely automatic method supporting cell counting is a viable solution for clinical laboratories. This paper proposes a novel blood cell counting procedure to address this challenge. The proposed method adopts SegNet - a deep learning semantic segmentation to simultaneously segment RBCs and WBCs. The global accuracy of the segmentation of WBCs, RBCs, and the background of peripheral blood smear images obtains 89% when segment WBCs and RBCs from the background of blood smear images. Moreover, an effective solution to separate grouped or overlapping cells and cell count is presented using Euclidean distance transform, local maxima, and connected component labeling. The counting result of the proposed procedure achieves an accuracy of 93.3% for red blood cell count using dataset 1 and 97.38% for white blood cell count using dataset 2.

The advent of large models, also known as foundation models, has significantly transformed the AI research landscape, with models like Segment Anything (SAM) achieving notable success in diverse image segmentation scenarios. Despite its advancements, SAM encountered limitations in handling some complex low-level segmentation tasks like camouflaged object and medical imaging. In response, in 2023, we introduced SAM-Adapter, which demonstrated improved performance on these challenging tasks. Now, with the release of Segment Anything 2 (SAM2)—a successor with enhanced architecture and a larger training corpus—we reassess these challenges. This paper introduces SAM2-Adapter, the first adapter designed to overcome the persistent limitations observed in SAM2 and achieve new state-of-the-art (SOTA) results in specific downstream tasks including medical image segmentation, camouflaged (concealed) object detection, and shadow detection. SAM2-Adapter builds on the SAM-Adapter's strengths, offering enhanced generalizability and composability for diverse applications. We present extensive experimental results demonstrating SAM2-Adapter's effectiveness. We show the potential and encourage the research community to leverage the SAM2 model with our SAM2-Adapter for achieving superior segmentation outcomes. Code, pre-trained models, and data processing protocols are available at http://tianrun-chen.github.io/SAM-Adaptor/.

This study examines the impact of weeds on sweet corn, where weeds compete with the main agricultural crops for essential elements such as nutrients, water, sunlight, and space for growth. In general. the use of herbicides is meant to suppress weed growth. Organic matter is important for plant growth and affects herbicide persistence. The study was aimed to explore the interdependence between ametryn herbicide and organic matter content and its impacts on weed growth, herbicide persistence, and sweet corn yield. The experiment was initiated in 2022 at the Experimental Station of the Faculty of Agriculture, Padjadjaran University, Indonesia, using a Split Plot Design in a Randomized Complete Block Design (RCBD) with three replicates. The experiments consisted of three levels of organic matter, i.e. low, medium, and high and 6 levels of ametryn herbicide at 0.0 (control), 0.5, 1.0, 1.5, 2.0, 2.5 kg a.i./ha. The results indicated that the apparent interdependence between ametryn herbicide doses of 1.5, 2.0 and 2.5 kg a.i./ha and the three levels of the organic matter content totally suppressed the weed growth. However, the effects of interdependence between ametryn herbicide and organic matter content on the herbicide persistence and on the sweet corn yield were not obvious. The ametryn herbicide gave excellent effects on sweet corn yield. Bioassay analysis showed that the lowest persistence of ametryn herbicide was in line with the highest content of the organic matter.

Accurate segmentation of the Left Ventricle (LV) in Echocardiogram (Echo) images is essential for cardiovascular analysis. Conventional techniques are labor-intensive and exhibit inter-observer variability. Deep learning has emerged as a powerful tool for automated medical image segmentation, offering advantages in speed and potentially superior accuracy. This study explores the efficacy of employing the YOLO (You Only Look Once) segmentation model for automated LV segmentation in Echo images. YOLO, a cutting-edge object detection model, achieves exceptional speed-accuracy balance through its well-designed architecture. It utilizes efficient dilated convolutional layers and bottleneck blocks for feature extraction, while incorporating innovations like path aggregation and spatial attention mechanisms. These attributes make YOLO a compelling candidate for adaptation to LV segmentation in Echo images. We posit that by fine-tuning a pre-trained YOLO based model on a well-annotated Echo image dataset, we can leverage the model's strengths in real-time processing and precise object localization to achieve robust LV segmentation. The proposed approach entails fine-tuning a pre-trained YOLO model on a rigorously labeled Echo image dataset. Model performance has been evaluated using established metrics such as mean Average Precision (mAP) at an Intersection over Union (IoU) threshold of 50% (mAP50) with 98.31%and across a range of IoU thresholds from 50% to 95% (mAP50:95) with 75.27%. Successful implementation of YOLO for LV segmentation has the potential to significantly expedite and standardize Echo image analysis. This advancement could translate to improved clinical decision-making and enhanced patient care.

Sea ice extraction and segmentation of remote sensing images is the basis for sea ice monitoring. Machine learning-based image segmentation methods rely on manual sampling and require complex feature extraction. Deep-learning semantic segmentation methods have the advantages of high efficiency, intelligence, and automation. Sea ice segmentation using deep learning methods faces the following problems: in terms of datasets, the high cost of sea ice image label production leads to fewer datasets for sea ice segmentation; in terms of image quality, remote sensing image noise and Severe weather conditions affects image quality, which affects the ac-curacy of sea ice extraction. To address the quantity and quality of the dataset, this study used multiple data augmentation methods for data expansion. To improve the semantic segmentation accuracy, the SC-U2-Net network was constructed using multi-scale inflation convolution and a multi-layer Convolutional Block Attention Module (CBAM) attention mechanism for the U2-Net network. The experiments showed that (1) data augmentation solved the problem of an insuffi-cient number of training samples to a certain extent and improved the accuracy of image seg-mentation. (2) This study designed a multilevel Gaussian noise data augmentation scheme to improve the network's ability to resist noise interference and achieve a more accurate segmenta-tion of images with different degrees of noise pollution. (3) The inclusion of a multi-scale inflation perceptron and multi-layer CBAM attention mechanism improved the ability of U2-Net network feature extraction and enhanced the model accuracy and generalization ability.

It is very difficult to accurately divide farmland and woodland in Gaofen 2 (GF-2) remote sensing image, because their single plant coverage is very small, and their spectra are very similar. The ratio of spatial resolution and one plant’s coverage area must be fully taken into account when designing the Convolutional Neural Network structure for extracting them from GF-2 image. We establish a Convolutional Encode Neural Networks model (CENN), The first layer has two sets of convolution kernels to learn the characteristics of farmland and woodland respectively, while the second layer is the encoder to encode the characteristics by transfer function, which can map the results to the corresponding category number. In the training stage, samples of farmland, woodland, and other categories are categorically used to train CENN, as soon as training is accomplished, CENN would acquire enough ability to accurately extract farmland and woodland from remote sensing images. The final extraction result is obtained by implementing per-pixel segmentation of images used to train the CENN. CENN is compared and analyzed with others such as Deep Belief Network (DBN), Full Convolutional Network (FCN), Deeplab Model. The results of experiments show that CENN can more accurately mine the characteristics of farmland and woodland, and it achieves its goal of extracting farmland and woodland with high precision from GF-2 images.

In every agricultural setting, weed seeds can be found in every cubic centimeter of soil. Weed seeds, as a valuable trait underlying the fate of weed populations, exhibit differing levels of seed dormancy, ensuring their survival under uncertain conditions. Seed dormancy is considered as an innate mechanism that constrains germination under suitable conditions that would otherwise stimulate germination of non-dormant seeds. This work provides new insight into changes in germination patterns along the dormant to nondormancy continuum in seeds with physiological dormancy. Notable findings are: (1) germination synchrony can act as a new parameter that quantitatively describes dormancy patterns and subsequently weed population dynamics, (2) germination synchrony is dynamic, suggesting that the more dormancy decreases, the more synchrony is obtainable, (3) after-ripening and stratification can function as a synchronizing agent that regulates germination behavior. Brassica napus showed the most synchronous germination with the value of 3.14, while lower level of germination asynchrony was for Sinapis arvensis, with the asynchrony value of 2.25. After-ripening and stratification can act as a synchronizing factor through decreasing asynchrony level and increasing synchrony. Weed establish a firm relationship between dormancy cycling and germination synchrony patterns, ensuring their survival and reproductive strategies. By germinating in synchrony, which is accompanied by cycling mechanisms, weeds have more opportunities to persist. The synchrony model used in the present study predicts germination behavior and synchrony along the dormant to nondormancy continuum in weed seeds with physiological dormancy, suggesting a useful method for quantification of germination strategies and weed population dynamics.

Facial acne is a prevalent dermatological condition regularly observed in the general population. This study introduces a novel deep learning model for facial acne segmentation utilizing a semi-supervised learning method known as bidirectional copy-paste, which synthesizes images by interchanging foreground and background parts between labeled and unlabeled images during the training phase. To overcome the lower performance observed in the labeled image training part compared to the previous methods, a new framework was devised to directly compute the training loss based on labeled images. The effectiveness of the proposed method was evaluated against previous semi-supervised learning methods using images cropped from facial images at acne sites. The proposed method achieved a Dice score of 0.5205 in experiments utilizing only 3% of labels, marking an improvement of 0.0151 to 0.0473 Dice score over previous methods. The proposed semi-supervised learning approach for facial acne segmentation demonstrates improvement in performance, offering a novel direction for future acne analysis.

In this paper, we use a machine learning method, known as Nonnegative Matrix Factorization, to extract from a given image some new information obtained from a number of color space representations. Such kind of information, termed ``metacolor'', can be considered as a particular color space representation of the image, which can be used to obtain a binary segmentation of the investigated image by distinguishing foreground and background pixels. Some numerical experiments prove that the proposed method shows improved results when compared with common simpler thresholding algorithms.

Contemporary advanced models for aspect-targeted opinion word extraction (ATOWE), which predominantly utilize BERT-based encoders at a word level, have shown limited advancements when integrated with graph convolutional networks (GCNs) for syntactic tree assimilation. Recognizing the prowess of BERT subwords in encapsulating rare or context-poor words, this study pivots from syntactic trees to BERT subwords, omitting GCNs from the structural framework. Our approach, named Aspect-Enhanced Wordpiece Extraction Model (AEWEM), focuses on refining aspect representation during encoding. We propose an input format of paired sentence-aspect, diverging from traditional single-sentence inputs. AEWEM demonstrates superior performance on benchmark datasets, establishing a robust foundation for future explorations in this domain.

Bone metastasis detection and quantification on bone scintigraphy is challenging and clinical important for treatment and patient’s life quality. To develop a CNN based diagnostic system for automated segmentation on bone metastasis regions is non-trivial, especially for a small dataset. A dataset in house comprising 100 breast cancer patients and 100 prostate cancer patients is utilized for this research. The Double U-Net model is adapted through the integration of background removal, adding negative samples, and transfer learning methods for bone metastasis detection. The performance is investigated via 10-fold cross-validation and computed in pixel-wise scale. The best model we achieved has precision of 63.08%, sensitivity of 70.82%, and F1-score of 66.72%. The developed system has the potential to provide pre-diagnostic reports for physicians in final decisions and the calculation of the bone scan index (BSI) with the combination with bone skeleton segmentation.

Vehicle identification is an important task in traffic monitoring because it allows for efficient inference and provides a cause for action. Vehicle classification via deep learning and other approaches such as segmentation is a critical tool for re-identification. In this paper, instance segmentation is used to identify vehicle makes with license plate detection, allowing for better unique vehicle recognition for re-identification. A dataset is annotated and modified, for example, by segmenting it with polygonal bounding boxes that capture the vehicle's unique frontal features. In addition, license plate localization is performed. The results showed improved classification as well as a high mAP for the dataset when compared to previous approaches based on CNN and deformed CNN. Furthermore, a deep residual network and fully connected layer-based classification were utilized as the backbone for feature representation. Instance segmentation detects objects by segmenting and classifying regions of interest. The imbalance in the dataset is resolved using a mosaic-tiled approach, which produces greater precision than other approaches.

Semantic segmentation is a very popular topic in modern computer vision and it has applications to many fields. Researchers proposed a variety of architectures over time, but the most common ones exploit an encoder-decoder structure that aims to capture the semantics of the image and it low level features. The encoder uses convolutional layers, in general with a stride larger than one, to extract the features, while the decoder recreates the image by upsampling an using skip connections with the first layers. In this work, we use DeepLab as architecture to test the effectiveness of creating an ensemble of networks by randomly changing the activation functions inside the network multiple times. We also use different backbone networks in our DeepLab to validate our findings. We manage to reach a dice coefficient of 0.888, and a mean Intersection over Union (mIoU) of 0.825, in the competitive Kvasir-SEG dataset. Results in skin detection also confirm the performance of the proposed ensemble, which is ranked first with respect to other state-of-the-art approaches (including HardNet) in a large set of testing datasets. The developed code will be available at https://github.com/LorisNanni.

This article presents a method of segmenting images with gray levels that uses Onicescu's information energy calculated in the context of the neutrosophic theory. Starting from the information energy calculation for complete neutrosophic information, it is shown how to extend its calculation for incomplete and inconsistent neutrosophic information. The segmentation method is based on calculation of thresholds for separating the gray levels using the local maximum points of the Onicescu information energy.

Lung nodule segmentation in CT images and its subsequent volume analysis can help determinethe malignancy status of a lung nodule. While several efficient segmentation schemes have beenproposed, only a few studies evaluated the segmentation’s performance for large nodules. In thisresearch, we contribute a semi-automatic system which is capable of performing robust 3-D segmen-tations on both small and large nodules with good accuracy. The target CT volume is de-noisedwith an anisotropic diffusion filter and a region of interest is selected around the target nodule ona reference slice. The proposed model performs nodule segmentation by incorporating a mean in-tensity based threshold in Geodesic Active Contour model in level sets. We also devise an adaptivetechnique using image intensity histogram to estimate the desired mean intensity of the nodule.The proposed system is validated on both lung nodules and phantoms collected from publicly avail-able diverse databases. Quantitative and visual comparative analysis of the proposed work withthe Chan-Vese algorithm and statistic active contour model of 3D Slicer platform is also presented.The resulting mean spatial overlap between segmented nodules and reference nodules is 0.855, themean volume bias is 0.10±0.2 ml and the algorithm repeatability is 0.060 ml. The achieved resultssuggest that the proposed method can be used for volume estimations of small as well as large-sizednodules.

The driving force behind adopting the idea of ​​sustainable development are producers and retailers. Unfortunately, when preparing their product range for consumers, many of them still only pay attention to the size of the customers’ earnings, how often they shop and how much they buy when shopping. In consumer segmentation, sustainable values ​​that consumers apply when making their purchasing decisions are rarely taken into account. The aim of this article is to show that values ​​such as environmental protection, the ethical behaviour of producers, fair trade or maximising the utility function of consumption are so important in the purchasing process in the coffee market that they can be used as segmentation variables. The Polish coffee market was selected to carry out segmentation taking into account the consumers' sustainable values. The main source of the article is the results of a standardized online survey conducted on a nationwide sample of 800 coffee consumers in July 2018. Multi-dimensional analyses such as extrapolative factor analysis (EFA) and cluster analysis (CA) were used to describe the obtained results. As a result, six segments of coffee consumers were identified and described: “responsible, aspiring to be connoisseurs”, “loyal coffee enthusiasts”, “pragmatic users”, “coffee laypersons”, “sophisticated connoisseurs”, “consumerists, connoisseurs, but not at any price”. Among the identified segments, the sustainable consumption values ​​most often mentioned refer to "responsible, aspiring to be connoisseurs", and the least often - ”consumerists, connoisseurs, but not at any price”. The conclusions presented in the last part of the article may be used by manufacturing and trade enterprises, operating on the coffee market, in order to respond to the identified needs and expectations of consumers and by governmental and social organisations so as to determine the directions of pro-ecological education of consumers.

Weed competitive ability (WCA) is a desirable key trait for the improvement of grain yield under direct-seeded rice (DSR) and the aerobic rice ecosystem. The present study targeted screening of 167 introgression lines (ILs) of a Green Super Rice (GSR) IR2-6 population derived from a cross between Weed Tolerant Rice 1 (WTR1) as the recipient parent and Y134 as the donor parent developed at IRRI for weed competitiveness in screen house conditions (SHC). The ILs were phenotyped for WCA traits such as early seed germination (ESG) and early seedling vigor (ESV) in Petri dishes and pot experiment conditions. The results of phenotypic variance revealed ESG-related traits, especially first germination count (1st GC) that positively correlated with second germination count (2nd GC), germination percentage (GP), total dry weight (TDW), total fresh weight (TFW), and vigor index (VI-1), whereas, in ESV, all the traits were positively correlated with each other except for three traits: root dry weight (RDW), 1st GC, and GP-2. The ESG and ESV traits are vital for weed competitiveness. A 6K SNP array was used to study the genetic association for the WCA traits. Forty-four QTLs for WCA traits were mapped on all chromosomes (except on chromosomes 4 and 8) through single marker analysis (SMA). Out of 44 QTLs, 29 were associated with ESG traits and 15 with ESV traits, with LOD scores of 2.93 to 8.03 and 2.93 to 5.04 and explained phenotypic variance ranging from 7.85% to 19.9% and from 7.85% to 13.2%, respectively. However, 31 QTLs were contributed by a negative additive allele from Y134, whereas a positive additive allele was contributed by WTR1 in 13 QTLs. Among them, two QTL hotspot regions were mapped on chromosome 11 (24.7-27.9 Mb) and chromosome 12 (14.8-17.4 Mb). The majority of the QTLs related to WCA traits were grouped into two QTL hotspots: QTL hotspot-I (qAFW11.1, qFC11.1, qFC11.2, qSC11.1, qGP-111.1, qGP-111.2, qTFGS11.1, qVI-111.1, and qVI-111.2) and QTL hotspot-II (qFC12.1, qFC12.2, qSC12.1, qFC12.2, qGP-112.1, qGP-112.2, qTFGS12.1, qTFGS12.2, qVI-112.1, qIV12.2, qFC12.1, and qGC12.2), and a few of them were co-localized on chromosomes 11 and 12. Further, we fine-tuned in the genomic regions of QTL hotspots and identified a total of 13 putative candidate genes on chromosomes 11 and 12 collectively. The present study is the first report on the genetic basis of WCA-related traits and the co-localized QTLs, which could be highly valuable in future breeding programs aiming to improve WCA in rice.

Fire outbreaks continue to cause damage despite the improvements in fire-detection tools and algorithms. It is still challenging to implement a well performing and optimized approach, which is sufficiently accurate, and has tractable complexity and low false alarming rate. Small amount of fire and identification of fire from a long distance is also a challenge in previously proposed techniques. In this study, we propose a novel hybrid model based on Convolutional Neural Networks (CNN) to detect and analyze fire intensity. 21 convolutional layers, 24 Rectified Linear Unit (ReLU) layers, 6 pooling layers, 3 fully connected layers, 2 dropout layers, and a softmax layer are included in the proposed 57-layer CNN model. Our proposed model performs instance segmentation in order to distinguish between fire and non-fire events. To reduce the intricacy of the proposed model, we also propose a key-frame extraction algorithm. The proposed model uses Internet of Things (IoT) devices to alert the relevant person by calculating the severity of fire. Our proposed model is tested on a publicly available dataset having fire and normal videos. The achievement of 95.25 % classification accuracy, 0.09% False Positive Rate (FPR), 0.65 percent False Negative Rate (FNR), and a prediction time of 0.08 seconds validates the proposed system.

Objective:The Glioma brain tumor detection and segmentation methods are proposed in this paper using machine learning approaches. Methods:The boundary edge pixels are detected using Kirsch’s edge detectors and then contrast adaptive histogram equalization method is applied on the edge detected pixels. Then, Ridgelet transform is applied on this enhanced brain image in order to obtain the Ridgelet multi resolution coefficients. Further, features are derived from the Ridgelet transformed coefficients and the features are optimized using Principal Component Analysis (PCA) method and these optimized features are classified into Glioma or non-Glioma brain images using Co-Active Adaptive Neuro Fuzzy Expert System (CANFES) classifier.Results:The proposed method with PCA and CANFES classification approach obtains 97.6% of se, 98.56% of sp, 98.73% of Acc, 98.85% of Pr, 98.11% of FPR and 98.185 of FNR, then the proposed Glioma brain tumor detection method using CANFES classification approach only.

The segmentation and de-noising are basic operations, required in every signal processing and classification system. The classical segmentation and de-noising approaches are time-invariant. Consequently, it results in the post processing of an unnecessary information and causes an increase in the system processing activity and power consumption. In this context, an efficient event-driven segmentation and de-noising technique is proposed. It is founded on the principles of level crossing and activity selection. Therefore, it can adapt its sampling frequency, segmentation window length and position along with the filter order by analyzing the input signal local characteristics. As a result, the computational complexity and the power consumption of the proposed system is reduced compared to the counter ones. The suggested system performance is compared with the classical one. It is done for the case of a multi-channel Electroencephalogram (EEG) signals. Results show a noticeable compression gain with an effective adaptation of the de-noising filters order. It aptitudes a significant computational gain, transmission data rate reduction and power consumption reduction of the proposed technique, compared to the counter ones. It shows that the proposed solution is an attractive candidate to embed in the new generation EEG wearables.

Precision agriculture including camera-guided row detection and hydraulic steering are often used as an alternative because crop damage can be decreased and driving speed can be increased comparable to herbicide applications.The effects of different approaches as uncontrolled (UC), mechanical weed control (MWC), herbicide weed control (HWC) and mechanical + herbicide control (MWC+HWC) on weed density and yield of sugar beet were tested and evaluated in two trials (2021 and 2022) in South Transylvania at the tested intervals BBCH 19 and 31. Weed control efficacy (WCE) depends on the emergence of the weeds and a good timing of weed controls in all the trials and methods, though the highest yield of sugar beet roots was recorded in the treatment MWC+HWC, with an increase up to 12-15% (56.48 t ha-1) yield from HWC (50.22 t ha-1) and a yield increase of more than 35- 40% than MWC (42.34 t ha-1). Our trials show that is possible to increase yield and have less chemical applications with the introduction of the new precision technologies in agriculture included here the sensor-guided mechanical controls.

Woolly cupgrass (Eriochloa villosa /Thunb./ Kunth) is a common weed in East Asia and North America. This weed plant spreading quickly in Europa. There are several reasons for the successfulness, especially its germination properties. As other Panicoideae species contain benzoxazinoids it was supposed that woolly cupgrass also contains these chemicals. For this reason the benzoxazinoid content of plants at the stage of flowering was investigated. As it was supposed, woolly cupgrass contain benzoxazinoids, which is a novel occurrence of these chemicals in Poaceae family.

Our world is increasingly challenged by managing the impacts of natural disasters, particularly floods, which are frequent, dangerous, and costly. Traditional flood mapping methods, reliant on Optical satellites (MSI), struggle under cloud cover which is typical during such events. Synthetic Aperture Radar (SAR) offers a promising alternative with its cloud-penetrating capability, though its use has been limited due to complexity and data labeling challenges. This project aims to develop a SAR-based flood segmentation model that can rapidly and accurately map floods globally, with high adaptability to different flood types and regions. By utilizing deep learning and a novel transfer-learning technique that combines the strengths of Optical/MSI and SAR data, the model seeks to bypass the challenges of manual labeling and improve mapping accuracy. Initial results show the model's effective generalization across various flood events, with superior performance indicated by an Intersection over Union (IoU) of 0.72, outperforming existing methods and demonstrating promising capabilities in precise flood mapping.

The usage of classic segmentation methods has drastically decreased recently. Implementation of convolutional neural networks and their modifications leads to significantly improved results. With the help of U-net, you can perform automatic segmentation. However, this requires significantly more hardware and software resources. The use of cloud computing now provides a wide range of possibilities, which allows processing and sharing the obtained experience and results to improve the quality of diagnosis. This article presents an approach to implementing MLOPS for automatic image segmentation using U-net technology. The approach's key feature is the developed software block that allows the creation of a dataset based on given rules. The infrastructure also supports automatically deploying the necessary environment on the cloud, particularly on DigitalOcean.

In the realm of digital libraries, efficiently managing and accessing scientific publications necessitates automated bibliographic reference segmentation. This study addresses the challenge of accurately segmenting bibliographic references, a task complicated by the varied formats and styles of references. Focusing on the empirical evaluation of Conditional Random Fields (CRF), Bidirectional Long Short-Term Memory with CRF (BiLSTM+CRF), and Transformer Encoder with CRF (Transformer+CRF) architectures, this research employs Byte Pair Encoding and Character Embeddings for vector representation. The models underwent training on the extensive Giant corpus and subsequent evaluation on the Cora Corpus to ensure a balanced and rigorous comparison, maintaining uniformity across embedding layers, normalization techniques, and Dropout strategies. Results indicate that the BiLSTM+CRF architecture outperforms its counterparts by adeptly handling the syntactic structures prevalent in bibliographic data, achieving an F1-Score of 0.96. This outcome highlights the necessity of aligning model architecture with the specific syntactic demands of bibliographic reference segmentation tasks. Consequently, the study establishes the BiLSTM+CRF model as a superior approach within the current state-of-the-art, offering a robust solution for the challenges faced in digital library management and scholarly communication.