Object classification is a crucial task in deep learning, which involves the identification and categorization of objects in images or videos. Although humans can easily recognize common objects, such as cars, animals, or plants, performing this task on a large scale can be time-consuming and error-prone. Therefore, automating this process using neural networks can save time and effort while achieving higher accuracy. Our study focuses on the classification step of human chromosome karyotyping, an important medical procedure that helps diagnose genetic disorders. Traditionally, this task is performed manually by expert cytologists, which is a time-consuming process that requires specialized medical skills. Therefore, automating it through deep learning can be immensely useful. To accomplish this, we implemented and adapted existing preprocessing and data augmentation techniques to prepare the chromosome images for classification. We used ResNet-50 convolutional neural networks and an ensemble approach to classify the chromosomes, obtaining state-of-the-art performance in the tested dataset.

There are thousands of rare genetic diseases that could be treated with classical gene therapy strategies such as the addition of the defective gene via viral or non-viral delivery or by direct gene editing. However, several genetic defects are too complex for these approaches. These “genomic mutations” include aneuploidies, intra and inter chromosomal rearrangements, large deletions, or inversion and copy number variations. Chromosome Transplantation (CT) refers to the precise substitution of an endogenous chromosome with an exogenous one. By the addition of an exogenous chromosome and the concomitant elimination of the endogenous one, every genetic defect, irrespective of its nature, could be resolved. In the current review, we analyze the state of the art of this technique and discuss its possible application to human pathology. CT might not be limited to the treatment of human diseases. By working on sex chromosomes, we showed that female cells can be obtained from male cells, since chromosome-transplanted cells can lose either sex chromosome, giving rise to 46,XY or 46,XX diploid cells, a modification that could be exploited to obtain female gametes from male cells. Moreover, CT could be used in veterinary biology, since entire chromosomes containing an advantageous locus could be transferred to animals of zootechnical interest without altering their specific genetic background and the need for long and complex interbreeding. CT could also be useful to rescue extinct species if only male cells were available. Finally, the generation of “synthetic” cells could be achieved by repeated CT into a recipient cell. CT is an additional tool for genetic modification of mammalian cells.

Multimodal remote sensing data classification can enhance the model’s ability to distinguish land features through multimodal data fusion. In this context, how to help models understand the relationship between multimodal data and target tasks is the focus of researchers. Inspired by human feedback learning mechanisms, causal reasoning mechanisms, and knowledge induction mechanisms, this paper integrates causal learning, reinforcement learning, and meta learning into a unified remote sensing data classification framework and proposed the causal meta-reinforcement learning (CMRL). First, based on feedback learning mechanisms, we have overcome the limitations of traditional implicit optimization of fusion features and customized a reinforcement learning environment for multimodal remote sensing data classification tasks. Through feedback interactive learning between agents and the environment, we help them understand the complex relationships between multimodal data and labels, thereby achieving full mining of multimodal complementary information. Second, based on the causal inference mechanism we designed causal distribution prediction action, classification reward, and causal intervention reward, capturing pure causal factors in multimodal data and cutting off false statistical associations between non-causal factors and class labels. Finally, based on the knowledge induction mechanism, we designed a bi-layer optimization mechanism based on meta-learning. By constructing a meta training task and meta validation task simulation model in the generalization scenario of unseen data, we helped the model induce cross-task shared knowledge, thereby improving its generalization ability for unseen multimodal data. The experimental results on multiple sets of multimodal datasets show that the proposed method achieved state-of-the-art performance in multimodal remote sensing data classification tasks.

Two X chromosomes of female mammals randomly inactivate one of paternal or maternal X chromosome in early embryonic development and all the daughter cells produced from these cells retain the same feature of X chromosome inactivation, which is called X chromosome inactivation (XCI). Studying the mechanisms of XCI is important for understanding epigenetic that plays an important role in age-associated diseases. The previous studies have demonstrated that binding of RNAs and DNAs may play a role in activating gene expression. In this paper, our study aims to explore whether the mechanisms of XCI involve the RNA binding strength to X chromosome DNAs. The bioinformatics analyses based on big data were used to analyze the simulated binding strength of RNAs (RNA binding strength) to 23 chromosomes (including X chromosome and 22 human autosomes) and the characteristics of repetitive sequences in the X-inactivation centre. The results revealed that RNA binding strength of the long arm of the X chromosome that is almost entirely inactivated in XCI was significantly lower than that of all autosomes and the short arm of X chromosome, meanwhile the RNA binding strengths of inactivation regions in X chromosome were significantly lower than that of regions escaping from XCI. Different repetitive sequence clusters within the center of XCI presented a cross distribution characteristic. To further prove whether the repetitive sequences in human X chromosome involve in XCI, we cloned long interspersed element (LINE-1, L1) and short interspersed element (Alu) from human Xq13, the center of XCI, and constructed expression vectors carrying sense-antisense combination repetitive sequences (L1s or Alus). Effects of combined L1 or combined Alu sequences on expression of EGFP reporter gene were examined in stably transfected HeLa cells, which simulates the effects of repetitive sequences located on chromosomes. The results of experiments revealed transcribed L1 repetitive sequences activated EGFP reporter gene expression, so did the Alus. The experiment results suggested repetitive sequences activated genes by interaction of transcribed RNAs and DNAs. Since the binding of RNAs and DNAs can activate gene, so the low RNA binding strength of human X chromosome may be one of reasons of XCI. The cross distribution characteristics of different repetitive sequence clusters leading to a cascade of gene activation or gene inactivation may be the reason of transcriptional silencing one of the X chromosomes in female mammals.

Motion related human activity recognition using wearable sensors can potentially enable various useful daily applications. So far, most studies view it as a stand-alone mathematical classification problem without considering the physical nature of human motions. Consequently, they suffer from data dependencies and encounter the dimension disaster problem and the over-fitting issue, and their models are never human-readable. In this study, we start from a deep analysis on natural physical properties of human motions, and then propose a useful feature selection method to quantify each feature's classification contribution capability. On one hand, the "dimension disaster" problem can be avoid to some extent, due to the affined dimension of key features; On the other hand, over-fitting issue can be depressed since the knowledge implied in human motions are nearly invariant, which compensates the possible data inadequacy. The experiment results indicate that the proposed method performs superior to those adopted in related works, such as decision tree, k-NN, SVM, neural networks.

Cloud-induced atmospheric extinction and occlusion have a major effect on the effectiveness and quality of telescope observations. Real-time cloud cover distribution and long-term statistical data are essential for astronomical siting and telescope operations. At ground-based astronomical telescope sites, cloud cover distribution is currently analyzed using manual observation methods. However, the main disadvantages of manual observation methods are human subjective, heavy workloads and poor real-time performance. Therefore, a real-time automatic cloud images classification method is desperately needed. This paper presents a new cloud identification method, which is named PSO+XGBoost model by combining eXtreme Gradient Boosting (XGBoost) and Particle Swarm Optimization (PSO). The entire cloud image is divided into 37 sub-regions in order to more precisely identify the distribution of the clouds. 19 features are then extracted, including the sky background, star density, lighting conditions, and subregion grayscale values. The experimental results have shown that the overall classification accuracy of 96.91% and our model is able to outperform several state-of-the-art baseline methods. Our approach achieves high accuracy in comparison with the manual observation methods. Moreover, this method meets telescope real-time scheduling requirements.

Separase is a key cysteine protease to separate sister chromatids through digestion of cohesion ring that inhibits chromosome segregation as trigger of metaphase–anaphase transition in eukaryotes and highly regulated its activity by binding with securin and cyclinB-CDK1 complex. Those bindings prevent proteolytic activity of separase until the onset of anaphase. Chromosome missegregation and aneuploidy are frequently observed in malignancies. However, there are some difficulties for biochemical examinations due to instability of separase in vitro and a few spatiotemporal resolution approaches monitoring live separase activity throughout mitotic processes. Here we have developed FRET-based molecular sensors including GFP variants with separase cleavable sequences as donor and covalently attached fluorescent dye as acceptor molecules applicable to conventional live cell imaging and flow cytometric analysis because of efficient live cell uptake. We investigated performance of equivalent molecular sensors localized or not localized inside nucleus under cell cycle control using flow cytometry. Synchronized cell cycle progression rendered significant separase activity detections in both molecular sensors. We obtained consistent outcomes with localized molecular sensor introduction and cell cycle control by fluorescent microscopic observations. We thus established live cell separase activity monitoring systems specifically or statistically that could lead to elucidate separase properties in detail.

Many types of banana (Musa spp.)—one of the most economically important horticultural crops—exist, and their ploidy (diploid, triploid, and tetraploid, usually) and genome types (containing A or/and B genome in most cases) differ. At present, observation and genome type detection are commonly used to identify banana germplasm resources. However, the former is tedious, while the latter cannot distinguish categories below genome types. It is therefore urgent that a simple and effective method for identifying banana germplasm resources is established. We sequenced and analyzed the ribosomal DNA internal transcribed spacer (ITS) sequences of 62 banana germplasm and found that the sequencing peaks, especially the 20 bp region near the 420 bp position (referred to as the “420 bp region”), exhibited relatively recognizable and repeatable polymorphism characteristics. Using the “420 bp region” as a marker, we were able to quickly distinguish bananas belonging to different genome type groups (comprising the AA, AB, AAA, ABB, AAB, ABBB, AAAB, and AAAA groups) or different subgroups in the same genome type group (for example, the Cavendish, Gros Michel, Red, Lakatan, and Ibota Bota subgroups in the AAA group; and the Pisang Raja, Plantain, Pome and Silk subgroups in the AAB group). Moreover, it appeared that Sanger sequencing of ITS could be used for identifying banana hybrid offspring. These results demonstrated that the banana ITS region contains rich genetic information that is useful for genotyping. In general, ITS sequencing simplifies the classification of banana germplasm resources and has potential application in several areas of Musa improvement.

The hybrid zone between chromosome races of the common shrew (Sorex araneus) provides an exceptional model to study the potential role of chromosome rearrangements in the initial steps of speciation. The Novosibirsk and Tomsk races differ by a series of Robertsonian fusions with monobrachial homology. They form a narrow hybrid zone and generate hybrids with both simple (chain of three chromosomes) and complex (chain of eight or nine) synaptic configurations. Using immunolocalisation of the meiotic proteins, we examined chromosome pairing and recombination in males from the hybrid zone. Homozygotes and simple heterozygotes for Robertsonian fusions showed a low frequency of synaptic aberrations (< 10%). The carriers of complex synaptic configurations showed multiple pairing abnormalities, which might lead to reduced fertility. Recombination frequency in the proximal regions of most chromosomes of all karyotypes was much lower than in the other regions. The strong suppression of recombination in the pericentromeric regions and co-segregation of race specific chromosomes involved in the long chains would be expected to lead to linkage disequilibrium between genes located there. Genic differentiation, together with the high frequency of pairing aberrations in male carriers of the long chains, might contribute to maintenance of the narrow hybrid zone.

Background Tropical and subtropical crops such as coffee, cacao, and papaya are valuable commodities and its consumption is a seemingly indispensable part of the daily lives of billions of people across the world. Conventional breeding in these crops is lengthy and yields are threatened by runaway global warming. In this review we propose the application of chromosome engineering and synthetic biology principles in order to enhance synthesis of key metabolites, and transmission of wild traits for resistance to stress and disease. Conclusions It is hoped that the adoption of such technological approaches may enhance the resilience of agricultural communities, lead to economic growth and secure the availability of key resources for generations to come.

In this paper, we propose an imagined speech-based brain wave pattern recognition using deep learning. Multiple features were extracted concurrently from eight-channel Electroencephalography (EEG) signals. To obtain classifiable EEG data with fewer number of sensors, we placed the EEG sensors on carefully selected spots on the scalp. To decrease the dimensions and complexity of the EEG dataset and to avoid overfitting during the deep learning algorithm, we utilized the wavelet scattering transformation. A low-cost 8-channel EEG headset was used with MATLAB 2023a to acquire the EEG data. The Long-Short Term Memory Recurrent Neural Network (LSTM-RNN) was used to decode the identified EEG signals into four audio commands: Up, Down, Left, and Right. Wavelet scattering transformation was applied to extract the most stable features by passing the EEG dataset through a series of filtration processes. Filtration has been implemented for each individual command in the EEG datasets. The proposed imagined speech-based brain wave pattern recognition approach achieved a 92.50% overall classification accuracy. This accuracy is promising for designing a trustworthy imagined speech-based Brain-Computer Interface (BCI) future real-time systems. For better evaluation of the classification performance, other metrics were considered, and we obtained 92.74%, 92.50% and 92.62% for precision, recall, and F1-score, respectively.

Domain generalization has led to remarkable achievements in Hyperspectral Image (HSI) classification. Inspired by contrastive language-image pre-training (CLIP), the language-aware domain generalization method has been explored to learn cross-domain-invariant representation. However, existing methods face some challenges: 1) The weak capacity to extract long-range contextual information and inter-class correlation. 2) Due to the inadequacies of the large-scale pre-training for HSI data, the spatial-spectral features of HSI and linguistic features can not be straightforwardly alignment. To address the above problems, a novel network has been proposed with a CLIP framework, which consists of an image encoder, based on an encoder-only transformer to obtain the global contextual information and inter-class correlation, a frozen text encoder, and a cross-attention mechanism, named Linguistic-Interact-with-Visual Engager (LIVE), enhances the interaction between two modalities. Extensive experiments demonstrating superior performance over state-of-the-art methods in HSI Domain Generalization with a CLIP framework.

The ability to detect the presence as well as classify the activities of individuals behind visually obscuring structures is of significant benefit to police, security and emergency services in many situations. This paper presents the analysis from a series of experimental results generated using a through-the-wall (TTW) Frequency Modulated Continuous Wave (FMCW) C-Band radar system named Soprano. The objective of this analysis was to classify whether an individual was carrying an item in both hands or not using micro-Doppler information from a FMCW sensor. The radar was deployed at a standoff distance, of approximately 0.5 m, outside a residential building and used to detect multiple people walking within a room. Through the application of digital filtering, it was shown that significant suppression of the primary wall reflection is possible, significantly enhancing the target signal to clutter ratio. Singular Value Decomposition (SVD) signal processing techniques were then applied to the micro-Doppler signatures from different individuals. Features from the SVD information have been used to classify whether the person was carrying an item or walking free handed. Excellent performance of the classifier was achieved in this challenging scenario with accuracies up to 94%, suggesting that future through wall radar sensors may have the ability to reliably recognize many different types of activities in TTW scenarios using these techniques.

Early in development, placental and marsupial mammals harbouring at least two X chromosomes per nuclei are faced with a choice that affects the rest of their lives: which of those X chromosomes to transcriptionally inactivate. This choice underlies phenotypical diversity in the composition of tissues and organs and in their response to environment, and can determine whether an individual will be healthy or affected by an X-linked disease. Here, we review our current understanding of the process of choice during X-chromosome inactivation and its implications, focusing on the strategies evolved by different mammalian lineages and on the known and unknown molecular mechanisms and players involved. We also call for a revised manner in which to think about choice during random X-inactivation.

High-quality chromosome-scale haplotype sequences— of diploid genomes, polyploid genomes and metagenomes — provide important insights into genetic variation associated with disease and biodiversity. However, whole-genome short read sequencing does not yield haplotype information that spans whole chromosomes directly. Computational assembly of shorter haplotype fragments is required for haplotype reconstruction, which can be challenging owing to limited fragment lengths and high haplotype and repeat variability across genomes. Recent advancements in long-read and chromosome-scale sequencing technologies, alongside computational innovations, are improving the reconstruction of haplotypes at the level of whole chromosomes. Here, we review recent methodological progress in these areas and discuss perspectives that could enable routine high-quality haplotype reconstruction in clinical and evolutionary studies.

B chromosomes are supernumerary chromosomes which are found in addition to the normal standard chromosomes (A chromosomes). B chromosomes are well known to accumulate several types of repeats. Although the evolution of B chromosomes has been subject of numerous studies, the mechanisms of accumulation and evolution of repetitive sequences is not fully understood. Recently, new genomic approaches have shed light on the origin and accumulation of different classes of repetitive sequences in the process of B chromosome formation and evolution. Here we discuss the impact of repetitive sequences accumulation on the evolution of plant B chromosomes.

Sentiment analysis plays a crucial role in understanding customer feedback, guiding product development, and informing business decisions. This paper introduces term sentiment entropy (TSE), a novel weighting method that leverages the distribution of sentiment labels associated with words to enhance text classification accuracy. TSE complements traditional TF-IDF techniques by capturing the nuances of sentiment variation across different contexts. Experiments across diverse public datasets demonstrate TSE's potential to improve sentiment analysis performance, especially in capturing subtle sentiment shifts and adapting to specific domains. While computational cost and label quality pose challenges, TSE offers a promising avenue for refining sentiment analysis and opening new research frontiers.

In order to achieve the elimination of the negative impacts of transport on road safety, the European Union is taking various measures resulting from its commitment to improve road safety. One of the instruments for achieving the objectives set is social legislation for the work of drivers in road freight and passenger transport. In line with the objective of improving the quality of working conditions for road transport drivers and road safety, the European Union applies Regulation (EC) No 561/2006 on the harmonisation of certain social legislation relating to road transport, which lays down rules on driving times, breaks and rest periods for drivers operating in road freight and passenger transport. The main objective of the paper is to assess the impact of social legislation on road transport safety by means of real research and to identify the factors influencing the violation of the legislation depending on the type of transports carried out in domestic or international road freight transport.

Detection of subsurface archaeological remains using a range of remote sensing methods, poses several challenges until today. Recent studies regarding the detection of archaeological proxies like those of cropmarks highlight the complexity of the phenomenon. In this work we present three different methods, and associated indices, for identifying stressed reflectance signatures indicating buried archaeological remains, based on a dataset of measured ground spectroradiometric reflectance. Several spectral profiles between the visible and near infrared part of the spectrum, were taken over a controlled environment in Cyprus during the 2011-2012 and are re-used in this study. The first two (spectral) methods are based on a suitable analysis of the spectral signatures in (1) the visible part of the spectrum, and in particular in the neighborhood of 570 nm, and (2) the red edge-near infrared part of the spectrum, in the neighborhood of 730 nm. Machine learning (decision trees) allows for the deduction of suitable wavelengths to focus on, in order to formulate the proposed indices and the associated classification criteria (decision boundaries) that can enhance the detection probability of stressed vegetation. Noise in the signal is taken into account by simulating reflectance signatures perturbed by white noise. Applying decision tree classification on the ensemble of simulations and basic statistical analysis we refine the formulation of the indices and criteria for the noisy signatures. The success rate of the proposed methods is over 90%. The third method rests on the estimation of vegetation/canopy reflectance parameters through inversion of the physical-based PROSAIL reflectance model and the associated classification through machine learning methods. The obtained results provide further insights into the formation of stress vegetation that occurred due to the presence of shallow buried archaeological remains, which are well aligned with physical-based models and existing empirical knowledge. To the best of the authors' knowledge, this is the first study demonstrating the usefulness of radiative transfer models such as PROSAIL for understanding the formation of cropmarks. Similar studies can support future research directions towards the development of regional remote sensing methods and algorithms if systematic observations are adequately dispersed in space and time.

The application of artificial intelligence to point-of-care testing (POCT) disease detection has become a hot research field, in which breath detection which detects the patient's exhaled VOCs combined with sensor arrays of Convolutional Neural Network (CNN) algorithms as a new lung cancer detection is attracting more researchers' attention. However, due to low accuracy, high complexity computation and large number of parameters make the CNN algorithms difficult transplant to the embedded system of POCT devices. A lightweight neural network (LTNet) in this work is proposed to deal with this problem, and meanwhile, achieve high-precision classification of acetone and ethanol gases, which are respiratory markers for lung cancer patients. Compared to currently popular lightweight CNN models such as EfficientNet, LTNet has fewer parameters (32K) and its training weight size is only 0.155 MB. LTNet achieved an overall classification accuracy of 99.06% and 99.14% in the own mixed gas dataset and the University of California (UCI) dataset, which are both higher than that of the five existing models’, and it also offers the shortest training (844.38s and 584.67s) and inference time (23s and 14s) in the same validation set. Compared to the existing CNN models, LTNet is more suitable for resource-limited POCT devices.

Timely and accurate information on tree species is crucial for the sustainable management of natural resources, forest inventory, biodiversity detection, and carbon stock calculation. The advancement of remote sensing technology and artificial intelligence has facilitated the acquisition and analysis of remote sensing data, resulting in more precise and effective classification of tree species. Multimodal remote sensing data and deep learning seem to be the current tree species classification research mainstream, whether or not. The current review on the remote sensing data and deep learning tree species classification methods perspectives to analyze the unimodal and multimodal remote sensing data and classification methods in this realm is missing. To bridge the gap, we search for major trends in the remote sensing data and tree species classification methods, provide a detailed overview of classic deep learning-based methods for tree species classification, and discuss the limitations.

Surface water distribution extracted from remote sensing data has been used in water resource assessment, coastal management, and environmental change studies. Traditional manual methods for extracting water bodies cannot satisfy the requirements for mass processing of remote sensing data; therefore, accurate automated extraction of such water bodies has remained a challenge. The histogram bimodal method (HBM) is a frequently used objective tool for threshold selection in image segmentation. The threshold is determined by seeking twin peaks, and the valley values between them; however, automatically calculating the threshold is difficult because complex surfaces and image noise which lead to not perfect twin peaks (single or multiple peaks). We developed an operational automated water extraction method, the modified histogram bimodal method (MHBM). The MHBM defines the threshold range of water extraction through mass static data; therefore, it does not require the identification of twin histogram peaks. It then seeks the minimum values in the threshold range to achieve automated threshold. We calibrated the MHBM for many lakes in China using Landsat 8 Operational Land Imager (OLI) images, for which the relative error (RE) and squared correlation coefficient (R2) for threshold accuracy were found to be 2.1% and 0.96, respectively. The RE and root-mean-square error (RMSE) for the area accuracy of MHBM were 0.59% and 7.4 km2. The results show that the MHBM could easily be applied to mass time-series remote sensing data to calculate water thresholds within water index images and successfully extract the spatial distribution of large water bodies automatically.

This paper focuses on optimal sensor positioning for monitoring activities of daily living and investigates different combinations of features and models on different sensor positions, i.e., the side of the waist, front of the waist, chest, thigh, head, upper arm, wrist, and ankle. Sixteen features are extracted and the feature importance is measured by using the Relief-F feature selection algorithm. Eight classification algorithms are evaluated on a dataset collected from young subjects and that collected from elderly subjects, with two different experimental settings. To deal with different sampling rates, signals with a high data rate are down-sampled and a transformation matrix is used for aligning signals to the same coordinate system. The thigh, chest, side of the waist, and front of the waist are the best four sensor positions for the first dataset (young subjects), with average accuracy values being greater than 95%. The best model obtained from the first dataset for the side of the waist is validated on the second dataset (elderly subjects). The most appropriate number of features for each sensor position is reported. The results provide a reference for building activity recognition models for different sensor positions, as well as for data acquired from different hardware platforms and subject groups.

ACL instability poses a significant challenge in traumatology and orthopedic medicine, often requiring accurate diagnosis for appropriate treatment. While the pivot-shift test offers a crucial means of assessment, its reliance on subjective interpretation underscores the need for supplementary imaging studies. This study aims to address this limitation by developing a Bayesian classification algorithm tailored for integration into a mobile application. Using the built-in inertial sensors of smartphones, this new approach aims to dynamically evaluate rotational stability during knee examinations. Orthopedic specialists conducted knee evaluations on 52 subjects, with subsequent analysis revealing interesting insights. Intraobserver and interobserver analyses, as measured by ICC, demonstrated strong agreement both in terms of timing between maneuvers (ICC = 0.94) and signal amplitude (ICC = 0.71-0.66). Notably, the Bayesian algorithm successfully classified 95% of joint hypermobility cases, with an additional 7 cases of hyperlaxity identified by the Pivot-Shift Meter (PSM). These findings highlight the practicality and effectiveness of implementing a Bayesian classification algorithm within a mobile application for assessing and categorizing signals captured by smartphone inertial sensors during the pivot-shift test.

Abstract: Fanconi anemia (FA), a chromosomal instability syndrome, is caused by inherited pathogenic variants in any of 22 FANC genes, that cooperate in the FA/BRCA pathway. This pathway regulates the repair of DNA interstrand crosslinks (ICLs) through homologous recombination. In FA proper repair of ICLs is impaired, and accumulation of toxic DNA double strand breaks occurs. In order to repair this type of DNA damage, FA cells activate alternative error-prone DNA repair pathways, that may lead to the formation of gross structural chromosome aberrations of which radial figures are the hallmark of FA and their segregation during cell division are the origin of subsequent aberrations like translocations, dicentrics and acentric fragments. The deficiency in DNA repair has pleiotropic consequences in the phenotype of patients with FA, including developmental alterations, bone marrow failure and an extreme risk to develop cancer. The mechanisms leading to the physical abnormalities during embryonic development have not been clearly elucidated, however FA has features of premature aging with chronic inflammation mediated by pro-inflammatory cytokines, that results in tissue attrition, selection of malignant clones and cancer onset. Moreover, the effect of the FA/BRCA pathway in germinal cells, evidenced by infertility in patients with FA attests of chromosomal instability and cell death also occurring in the germinal compartment.

The humpback puffer, Tetraodon palembangensis, also known as Pao palembangensis, is a species of poisonous freshwater pufferfish mainly distributed in Southeast Asia (Thailand, Laos, Malaysia and Indonesia). Despite interesting biological features, such as its very inactive nature, tetrodotoxin production and body expansion mechanisms, molecular research on the humpback puffer is still rare because of the lack of a high-quality reference genome. Here, we reported a first chromosome-level genome assembly of an adult humpback puffer, of which the genome size is 362 Mb with ~1.78 Mb contig N50 and ~15.8 Mb scaffold N50s. Based on the genome, ~61.5Mb (18.11%) repeat sequences were also identified, and totally 19,925 genes were annotated, 99.20% of which could be predicted with function using protein-coding function databases. Finally, a phylogenetic tree was constructed with single-copy gene families from ten teleost fishes. The humpback puffer genome will be a valuable genomic resource to illustrate possible mechanisms of tetrodotoxin synthesis and tolerance, providing clues for future detailed studies of biological toxins.

Quantitative trait loci (QTL) are genomic regions associated with phenotype variation of quantitative traits in a population. To date, a total of 267 QTL for 29 quantitative traits have been reported in 13 studies on flax. Of these, 200 QTL from 12 studies were identified based on genetic maps, scaffold sequences, or pre-released chromosome-scale pseudomolecules. Molecular markers for QTL identification differed across studies but were mainly based on simple sequence repeat (SSR) or single nucleotide polymorphism (SNP) markers. This article provides methods with software tools and database files to uniquely map SSR and SNP markers from different references onto the recently released chromosome-scale pseudomolecules. Using these methods, 195 QTL were successfully sorted onto the 15 flax chromosomes and grouped into 133 co-located QTL clusters. Mapping of QTL from different studies to the same reference enables comparisons and facilitates genome-wide QTL analysis, candidate gene scanning, and breeding applications.

Aerial image classification has become popular and has attracted extensive research efforts in recent decades. The main challenge lies in its very high spatial resolution but relatively insufficient spectral information. To this end, spatial-spectral feature extraction is a popular strategy for classification. However, parameter determination for that feature extraction is usually time-consuming and depends excessively on experience. In this paper, an automatic spatial feature extraction approach based on image raster and segmental vector data cross-analysis is proposed for the classification of very high spatial resolution (VHSR) aerial imagery. First, multi-resolution segmentation is used to generate strongly homogeneous image objects and extract corresponding vectors. Then, to automatically explore the region of a ground target, two rules, which are derived from Tobler’s First Law of Geography (TFL) and a topological relationship of vector data, are integrated to constrain the extension of a region around a central object. Third, the shape and size of the extended region are described. A final classification map is achieved through a supervised classifier using shape, size, and spectral features. Experiments on three real aerial images of VHSR (0.1 to 0.32 m) are done to evaluate effectiveness and robustness of the proposed approach. Comparisons to state-of-the-art methods demonstrate the superiority of the proposed method in VHSR image classification.

Inherited mutations in BRCA1 and BRCA2 genes increase risks for breast, ovarian, and other cancers. Both genes encode proteins for accurately repairing chromosome breaks. If mutations inactivate this function, broken chromosomes may not be restored correctly, allowing breaks to persist or rearrange chromosomes. These abnormalities are potentially catastrophic events that can originate from viral infections. I used bioinformatic analyses of publicly available breast cancer patient data to show that the distribution of chromosome breaks in hereditary breast cancers differs markedly from sporadic breast cancers. Then I tested hereditary breast cancer sequence data around chromosome breaks for DNA similarity to all known viruses. Human DNA flanking breakpoints usually had decisive matches to Epstein-Barr virus (EBV / HHV4) tumor variants HKHD40 and HKNPC60. Many breakpoints were near EBV genome anchor sites, human EBV tumor-like sequences, EBV-associated epigenetic marks, and some fragile sites. On chromosomes 2 and 12, sequences near EBV genome anchor sites accounted for 90% and 88% of breakpoints (p<0.0001), respectively. On chromosome 4, 51/52 inter-chromosomal breakpoints were close to EBV-like sequences in 19 hereditary breast cancers. In contrast, 19 sporadic breast cancers only had 12 interchromosomal breakpoint regions on chromosome 4 near EBV-like sequences. On various other chromosomes, five EBV genome anchor sites were near hereditary breast cancer breakpoints at precisely defined, disparate gene or LINE locations. Independent evidence further implicating EBV in hereditary breast cancer breakpoints is that 25 breast cancer break positions are within 1.25% of breakpoints in model EBV cancers. In addition to BRCA1 or BRCA2 mutations, all the hereditary breast cancers had mutated genes essential for immune responses. This compromise facilitates reactivation of herpes viruses which produce nucleases capable of breaking chromosomes. EBV also causes other deleterious effects: anchored EBV episomes can interfere with normal replication and obstruct DNA break repairs; even very early infection causes massive transcription changes. The results, therefore, imply proactive treatment and prevention of herpes viral infections may prevent some chromosome breaks and benefit BRCA mutation carriers.

With the rise of long-read sequencers and long-range technologies, delivering high-quality plant genome assemblies is no longer reserved to large consortia. Indeed, sequencing techniques but also computer algorithms have reached a point where the reconstruction of assemblies at the chromosome-scale is now feasible at the laboratory scale. Current technologies, and especially long-range technologies, are numerous and selecting the most promising one for the genome of interest is crucial to obtain optimal results. In this study, we resequenced the genome of the yellow sarson, Brassica rapa cv. Z1, using the Oxford Nanopore PromethION sequencer and assembled the sequenced data using current assemblers. To reconstruct complete chromosomes, we used and compared three long-range techniques, optical mapping, Omni-C and Pore-C sequencing libraries commercialized by Bionano Genomics, Dovetail Genomics and Oxford Nanopore Technologies respectively, or a combination of the three, in order to evaluate the capability of each technology.

Inherited mutations in BRCA1 and BRCA2 genes increase risks for breast, ovarian, and other cancers. Both genes encode proteins for accurately repairing chromosome breaks. If mutations inactivate this function, chromosome fragments may not be restored correctly. Resulting chromosome rearrangements can become critical breast cancer drivers. Because I had data from thousands of cancer structural alterations that matched viral infections, I wondered whether infections contribute to chromosome breaks and rearrangements in hereditary breast cancers. There are currently no interventions to prevent chromosome breaks because they are thought to be unavoidable. However, if chromosome breaks come from infections, they can be treated or prevented. I used bioinformatic analyses to test publicly available breast cancer sequence data around chromosome breaks for DNA similarity to all known viruses. Human DNA flanking breakpoints usually had the strongest matches to Epstein-Barr virus (EBV) tumor variants HKHD40 and HKNPC60. Many breakpoints were near sites that anchor EBV genomes, human EBV tumor-like sequences, EBV-associated epigenetic marks, and fragile sites. On chromosome 2, sequences near EBV genome anchor sites accounted for 90% of breakpoints (p<0.0001). On chromosome 4, 51/52 inter-chromosomal breakpoints were close to EBV-like sequences. Five EBV genome anchor sites were near breast cancer breakpoints at precisely defined, disparate gene or LINE locations. Breakpoint flanking regions resembled known EBV-cancers. Twenty-five breakpoints in breast cancers were within 1.25% of EBV cancer breakpoints. In addition to BRCA1 or BRCA2 mutations, all the breast cancers had mutated genes essential for immune responses. Because of this immune compromise, herpes viruses can activate and produce nucleases that break chromosomes. Alternatively, anchored viral episomes can obstruct break repairs, whatever the cause. The results, therefore, imply proactive treatment and prevention of herpes viral infections may prevent some chromosome breaks and benefit BRCA mutation carriers.

The pine pitch canker pathogen, Fusarium circinatum, is globally regarded as one of the most important threads to commercial pine-based forestry. Although genome sequences of this fungus are available, these remain highly fragmented or structurally ill-defined. Our overall goal was to provide high-quality assemblies for two notable strains of F. circinatum, and to characterize these in terms of coding content, repetitiveness, and the position of telomeres and centromeres. For this purpose, we used Oxford Nanopore Technologies MinION long read sequences, as well as Illumina short sequence reads. By leveraging the genomic synteny inherent to F. circinatum and its close relatives, these sequence reads were assembled to chromosome-level, where contiguous sequences mostly spanned from telomere to telomere. Comparative analyses unveiled remarkable variability in the twelfth and smallest chromosome, which is known to be dispensable. It presented a striking length polymorphism, with one strain lacking substantial portions from the chromosome's distal and proximal regions. These regions, characterized by a lower gene density and G+C content and an increased prevalence of repetitive elements, contrast starkly with the syntenic segments of the chromosome, as well as with the core chromosomes. We propose that these unusual regions might have arisen or expanded due to the presence of transposable elements. Comparison of overall chromosome structure revealed that centromeric elements often underpin intrachromosomal differences between F. circinatum strains, especially at chromosomal breakpoints. This suggested a potential role for centromeres in shaping the chromosomal architecture of F. circinatum and its relatives. The publicly available genome data generated here, together with the detailed metadata provided, represent essential resources for future studies of this important plant pathogen.

B chromosomes (Bs) were discovered a century ago, and since then most studies have focused on describing their distribution and abundance using traditional cytogenetics. Only recently have attempts been made to understand their structure and evolution at the level of DNA sequence. Many questions regarding the origin, structure, function and evolution of B chromosomes remain unanswered. Here we identify B chromosome sequences from several species of cichlid fish from Lake Malawi by examining the ratios of DNA sequence coverage in individuals with and without B chromosomes. We examine the efficiency of this method, and compare results using both Illumina and PacBio sequence data. The B chromosome sequences detected in 13 individuals from 7 species were compared to assess the rates of sequence replacement. B-specific sequence common to at least 12 of the 13 datasets are identified as the “Core” B chromosome. The location of B sequence homologs throughout the genome provides further support for theories of B chromosome evolution. Finally, we identified candidate genes located on the B chromosome which may regulate the segregation and maintenance of the B chromosome.

The advent of deep learning (DL) has revolutionized medical imaging, offering unprecedented avenues for accurate disease classification and diagnosis. DL models have shown remarkable promise for classifying brain tumor from Magnetic Resonance Imaging (MRI) scans. However, despite their impressive performance, the opaque nature of DL models poses challenges in understanding their decision-making processes, particularly crucial in medical contexts where interpretability is essential. This paper explores the intersection of medical image analysis and DL interpretability, aiming to elucidate the decision-making rationale of DL models in brain tumor classification. Leveraging state-of-the-art DL frameworks with transfer learning, we conduct a comprehensive evaluation encompassing both classification accuracy and interpretability. Using state-of-the-art DL frameworks with transfer learning, we conduct a thorough evaluation covering both classification accuracy and interpretability. We employ adaptive path-based techniques to understand the underlying decision-making mechanisms of these models. Grad-CAM and Grad-CAM++ highlight critical image regions where the tumors are located.

In Indonesia, types of meat are still identified manually due to increasing prices for beef and buf-falo ahead of Idul Fitri. Traders mix beef with pork to thwart the beef scam. Haar wavelet and GLCM, GLCM with angles of 0°, 45°, 90°, and 135°, as well as matrices using contrast, correlation, energy, homogeneity, and entropy, are used in feature extraction. The following are the results of meat image classification testing using k-NN, Haar wavelet, and GLCM: The k-NN algorithm shows superiority in identifying fresh (99%), frozen (99%), and rotten (96%) meat texture images with the most fantastic accuracy results in every situation. Meanwhile, GLCM routinely provides good results, especially regarding the texture image of fresh meat (183.21) and rotten meat (115.79). However, despite delivering less throughput than k-NN and GLCM, Haar wavelets are still helpful, especially when dealing with fresh meat texture images (89,96).

Deep Learning (DL) oriented document processing is widely used in different fields for extraction, recognition, and classification processes from raw corpora of data. The article examines the application of deep learning approaches, based on different neural network methods, including Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM), and Convolutional Neural Networks (CNN). The compared models were combined with two different word embedding techniques, namely: Bidirectional Encoder Representations from Transformers BERT and Gensim Word2Vec. The models are designed to evaluate the performance of architectures based on neural network techniques for the classification of CVs of Moroccan engineering students at ENSAK(National School of Applied Sciences of Kenitra, Ibn Tofail University). The used dataset included resumes collected from engineering students at ENSAK in 2023 for a project on the employability of Moroccan engineers in which new approaches were applied, especially machine learning, deep learning, and big data. Accordingly, 867 resumes were collected from five specialties of study (Electrical Engineering, Networks and Systems Telecommunications, Computer Engineering, Automotive Mechatronics Engineering, Industrial Engineering). The results revealed good performance of the proposed models based on the BERT embedding approach compared to models based on the Gensim Word2Vec embedding approach. Accordingly, the CNN-GRU/Bert model achieved slightly better accuracy with 0.9251 compared to other hybrid models.

Chromosome segregation in female germ cells and early embryonic blastomeres is known to be highly prone to errors. The resulting aneuploidy is therefore the most frequent reason for termination of early development and embryo loss in mammals. And when compatible with embryonic and foetal development, aneuploidy leads into severe developmental disorders. The main surveillance mechanism, essential for protection of cells against aneuploidy, is the Spindle Assembly Checkpoint (SAC). And although all eukaryotic cells are perhaps able to mount SAC response, it is not clear, whether this pathway is active in all cell types, including blastomeres of early embryos. In this review, we will summarize and discuss the published literature with regards to mechanisms controlling chromosome segregation in early embryos. Our conclusion is that early embryos show limited capabilities to react to chromosome segregation defects, which might, at least partially, explain the widespread problem of aneuploidy during early development.

The ability to directly look into genome sequences has opened great opportunities in plant breeding. Yet, the assembly of full-length chromosomes remains one of the most difficult problems in modern genomics. Genetic maps are commonly used in de novo genome assembly and are constructed on the basis of a statistical analysis of the number of recombination rather than physical distance in base pairs. This may affect the accuracy of the ordering and orientation of scaffolds within the chromosome, especially in the region of recombination suppression. Here we report the use of Tyr-FISH for validation of genetic and pseudochromosome maps. For probe design we developed a pipeline that is based on selection of a unique sequence with minimal potential fluorescent background arising from non-specific in situ hybridization. In total of 24 unique genes were located on physical chromosomes 2 and 6. The order of markers has been corrected by integration genetic and cytogenetic maps. Tyr-FISH mapping showed that the order of 23.1% (chromosome 2) and 27.3% (chromosome 6) of the tested genes differed between physical chromosomes and pseudochromosomes. Also the position of the mlh1 gene, which was not on the genetic map, was defined on physical chromosome 2. The results suggest the possibility of Tyr-FISH mapping of any gene that may not be neither on the genetic map nor in the assembly. Hence, Tyr-FISH provides valuable information for the improvement of the genome assembly.

Nucleosome positioning plays an important role in crucial biological processes like replication, transcription, and gene regulation. It has been widely used to predict the genome’s function and chromatin organisation. So far, the studies of patterns in nucleosome positioning have been limited to transcription start sites, CTCFs binding sites, and some promoter and loci regions. The genome-wide organisational pattern remains unknown. We have developed a theoretical model to coarse-grain nucleosome positioning data in order to obtain patterns in their distribution. Using hierarchical clustering on the auto-correlation function of this coarse-grained nucleosome positioning data, a genome-wide clustering is obtained for Candida albicans. The clustering shows the existence beyond hetero- and eu-chromatin inside the chromosomes.

The genus Rhodotorula includes basidiomycetous oleaginous yeast species. R. babjevae can produce compounds of biotechnological interest such as lipids, carotenoids and biosurfactants from low value substrates such as lignocellulose hydrolysate. High-quality genome assemblies are needed to develop genetic tools and to understand fungal evolution and genetics. Here, we combined short- and long-read sequencing to resolve the genomes of two R. babjevae strains, CBS 7808 (type strain) and DBVPG 8058 at chromosomal level. Both genomes have a size of 21 Mbp and a GC content of 68.2%. Allele frequency analysis indicated tetraploidy in both strains. They harbor 21 putative chromosomes with sizes ranging from 0.4 to 2.4 Mb. In both assemblies, the mitochondrial genome was recovered in a single contig, which shared 97% pairwise identity. The pairwise identity between the majority of chromosomes ranges from 82% to 87%. We found indications for strain-specific extrachromosomal endogenous DNA. 7,591 protein-coding genes and 7,607 associated transcripts were annotated in CBS 7808 and 7,481 protein-coding genes and 7,516 associated transcripts in DBVPG 8058. CBS 7808 has accumulated a higher number of tandem duplications than DBVPG 8058. We identified large translocation events between putative chromosomes and a high genetic divergence between the two strains.

The Upper Hunter Valley is a major coal mining area in New South Wales (NSW), Australia. Due to the ongoing increase of mining activities, PM10 (air-borne particle with an aerodynamic diameter less than 10 micrometres) pollution has become a major air quality concern in local communities. The early part of this study identified two air quality subregions in the valley. This paper aims to provide a holistic summarisation of the relationships between elevated PM10 pollution in two subregions and the local- and synoptic-scale meteorological conditions for spring and summer, when PM10 pollution is relatively high. A catalogue of twelve synoptic types and a set of six local meteorological patterns have been quantitatively derived and linked to each other using the self-organising map (SOM) technique. The complex meteorology-air pollution relationships have been visualised/interpretated on the SOM planes for two representative locations. It was found that the influence of local meteorological patterns differed significantly for mean PM10 levels vs the occurrence of elevated pollution events and between air quality subregions. In contrast, synoptic types showed generally similar relationships with mean vs elevated PM10 pollution in the valley. Two local meteorological patterns, the hot-dry-northwesterly wind conditions and the hot-dry-calm conditions, were found most PM10 pollution conducive in the valley when combined with a set of synoptic counterparts. These synoptic types are featured with the influence of eastward migrating continental high pressure system and westerly troughs, or a ridge extending northwest towards coastal northern NSW or southern Queensland from the Tasman Sea. The method and results can be used in air quality research for other locations of NSW, or similar regions elsewhere.

Rett Syndrome (RTT) is a severe neurodevelopmental disorder predominately diagnosed in females and primarily caused by pathogenic variants in the X-linked gene Methyl-CpG Binding Protein 2 (MECP2). Most often, the disease causing MECP2 allele resides on the paternal X chromosome while a healthy copy is maintained on the maternal X chromosome with inactivation (XCI) resulting in mosaic expression of one allele in each cell. Preferential inactivation of the paternal X chromosome is theorized to result in reduced disease severity; however, establishing such a correlation is complicated by known MECP2 genotype effects and an age dependent increase in severity. To mitigate these confounding factors, we developed an age- and genotype-normalized measure of RTT severity by modeling longitudinal data collected in the US Rett Syndrome Natural History Study. This model accurately reflected individual increase in severity with age and preserved group-level genotype specific differences in severity allowing for the creation of a normalized clinical severity score. Applying this normalized score to a RTT XCI dataset revealed that XCI influence on disease severity depends on MECP2 genotype with a correlation between XCI and severity observed only in individuals with MECP2 variants associated with increased clinical severity. This normalized measure of RTT severity provides the opportunity for future discovery of additional factors contributing to disease severity that may be masked by age and genotype effects.

Prunus tenella is a rare and precious relict plant in China. It is an important genetic resource for almond improvement and an indispensable material in ecological protection and landscaping. However, the research of molecular breeding and genetic evolution has been severely restricted, due to the lack of genome information. In this investigation, we created a chromosome-level genomic pattern of P. tenella, 231Mb in length with a contig N50 of 18.1 Mb by Hi-C techniques and high-accuracy PacBio HiFi sequencing. The present assembly predicted 32088 protein-coding genes, and an examination of the genome assembly indicated that 94.7% among all assembled transcripts were alignable to the genome assembly; most (97.24%) were functionally annotated. By phylogenomic genome comparison, we found that P. tenella is an ancient group that diverged approximately 13.4 million years ago (Mya) from 13 additional closely related species and about 6.5 Mya from the cultivated almond. Collinearity analysis revealed that P. tenella is highly syntenic and has high sequence conservation with almond and peach. However, this species also exhibit many presence/absence variants. Moreover, a large inversion at the 7,588 kb position of chromosome 5 was observed, which may have a significant association with phenotypic traits. Lastly, population genetic structure analysis in eight different populations indicated a high genetic differentiation among the natural distribution of P. tenella. This high-quality genome assembly provides critical clues and comprehensive information for the systematic evolution, genetic characteristics, and functional gene research of P. tenella. Moreover, it provides a valuable genomic resource for in-depth study in protecting, developing, and utilizing P. tenella germplasm resources.

The dynamics of surface and sub-surface water events can lead to slope instability resulting in anomalies such as slough slides on earthen levees. Early detection of these anomalies by a remote sensing approach could save time versus direct assessment. We have implemented a supervised Mahalanobis distance classification algorithm for the detection of slough slides on levees using complex polarimetric Synthetic Aperture Radar (polSAR) data. The classifier output was followed by a spatial majority filter post-processing step which improved the accuracy. The effectiveness of the algorithm is demonstrated using fully quad-polarimetric L-band Synthetic Aperture Radar (SAR) imagery from the NASA Jet Propulsion Laboratory’s (JPL’s) Uninhabited Aerial Vehicle Synthetic Aperture Radar (UAVSAR). The study area is a section of the lower Mississippi River valley in the southern USA. Slide detection accuracy of up to 98 percent was achieved, although the number of available slides examples was small.

Upland cotton is sensitive to 2,4-dichlorophenoxyacetic acid (2,4-D), and the identification of potentially 2,4-D tolerant cotton chromosome substitution (CS) lines and understanding tolerance mechanisms provide a significant step into the development and genetic improvement of upland cotton to reduce yield loss caused by 2,4-D herbicide effects including the drifts. Experiments were conducted to understand the possible mechanism of herbicide tolerance in CS-T04-15, CS-T07, and CS-B15sh, 2,4-D herbicide-tolerant cotton CS lines compared with TM-1, the 2,4-D herbicide susceptible recurrent parent of the CS line as control, using [14C]2,4-D. Percent absorption rate and translocation patterns of the 14C-labeled herbicide application at 5.17 kBq at 6 to 48 hours after treatment (HAT) were determined. The tolerant cotton CS lines showed 15-19% [14C]2,4-D uptake while TM-1 exhibited a reduced uptake of only 1.4% [14C]2,4-D at 24 HAT. Distribution of the absorbed [14C]2,4-D showed that 2-5% was translocated outside the treated leaf. In TM-1, 77% of the herbicide was translocated above and below the treated leaf, contrasting with the reduced translocation of 14C-labeled herbicide observed in the tolerant CS lines. Interestingly, CS-T04-15 showed a restricted movement of 14C below the treated leaf at 6 to 48 HAT, suggesting a novel mechanism of herbicide tolerance. This finding is the first report on upland cotton demonstrating a complex differential uptake and translocation associated with herbicide tolerance for [14C]2,4-D in cotton CS lines.

Classifications of AAFD/PCFD have evolved with an increased understanding of the pathology involved. A review of classification systems helps identify deficiencies and respective contributions to the evolution in understanding the classification of AAFD. Using multiple electronic database searches (Medline, PubMed) and Google search, original papers classifying AAFD were identified. Nine original articles were identified that met the inclusion criteria. Johnson's original classification and multiple variants provided a significant leap in understanding and communicating the pathology but remained tibialis posterior tendon focussed. Drawbacks of these classifications include the implication of causality, linearity of progression through stages, an over-simplification of stage 2 deformity and a failure to understand multiple tendons react, not just tibialis posterior. Later classifications, such as the PCFD classification, are deformity-centric. Early instability in non-cavus feet and all stages of cavus feet can present pain and instability with minor/no deformity. These may not be captured in deformity-based classifications biased to planus feet.' The authors developed the 'Triple Classification' (TC) understanding that primary pathology is a progressive ligament failure/instability that presents as tendon reactivity, deformity, and painful impingement. There is a variable manifestation dependent on starting foot morphology. This review has identified deficiencies within classification systems used in AAFD/PCFD and, as a result, was used to help develop a more comprehensive 'Triple classification'. Advantages of the TC include representing foot types with no deformity, defining complex secondary instabilities, delinking of foot types, tendon reactivity/ligament instability and deformity to represent these independently in a more comprehensive classification system.

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.

Aborycin is a type I lasso peptide with a stable interlocked structure, offering a favorable framework for drug development. The aborycin biosynthetic gene cluster gul from marine sponge-associated Streptomyces sp. HNS054 was cloned and integrated into the chromosome of S. coelicolor hosts with different copies. The 3-copy gul-integration strains S. coelicolor M1346::3gul showed better production than one-copy or 2-copy gul-integration strains, and the total titer reached approximately 10.4 mg/L, i.e., 2.1 times that of the native strain. Then, five regulatory genes, phoU (SCO4228), wblA (SCO3579), SCO1712, orrA (SCO3008) and gntR (SCO1678), which were reported to have negative effects on secondary metabolism, were further knocked out from the M1346::3gul genome by CRISPR/Cas9 technology. While the ΔSCO1712 mutant showed a significant decrease (4.6 mg/L) and the ΔphoU mutant showed no significant improvement (12.1 mg/L) in aborycin production, the ΔwblA, ΔorrA and ΔgntR mutations significantly improved the aborycin titers to approximately 23.6 mg/L, 56.3 mg/L and 48.2 mg/L, respectively, which were among the highest heterologous yields for lasso peptides in both Escherichia coli systems and Streptomyces systems. Thus, this study provided important clues for future studies on enhancing antibiotic production in Streptomyces systems.

Aegilops columnaris Zhuk. is tetraploid grass species (2n=4x=28, UcUcXcXc) closely related to Ae. neglecta and growing in Western Asia and a western part of the Fertile Crescent. Genetic diversity of Ae. columnaris was assessed using C-banding, FISH, nuclear and chloroplast (cp)DNA analyses, and gliadin electrophoresis. Cytogenetically Ae. columnaris was subdivided into two groups, C-I and C-II, showing different karyotype structure, C-banding and FISH patterns. Group C-I was more similar to Ae. neglecta. All types of markers revealed significant heterogeneity of the C-II group, although group C-I was also polymorphic. Two chromosomal groups were consistent with plastogroups identified in a current study based on sequencing of three chloroplast intergenic spacer regions. The similarity of group C-I of Ae. columnaris with Ae. neglecta and their distinctness from C-II indicate that divergence of the C-I group was associated with minor genome modifications. Group C-II could emerge from C-I relatively recently, probably due to introgression from another Aegilops species followed by a reorganization of the parental genomes. Most C-II accessions were collected from the very narrow geographic region, and they might originate from a common ancestor. We suggest that the C-II group is at the initial stage of species divergence and undergoing an extensive speciation process.

Convolutional Neural Networks (CNNs) are often criticized for their lack of transparency, acting as 'black boxes' in decision-making, a challenge compounded by class imbalance in ECG datasets, which limits their clinical application. This study introduces a CNN-based ECG signal classification model that enhances interpretability and addresses class imbalance through the Synthetic Minority Over-sampling Technique (SMOTE). The model also integrates Uniform Manifold Approximation and Projection (UMAP) for dimensionality reduction and SHAP value analysis, facilitating the visualization of decision boundaries and the assessment of feature contributions. Our evaluation using the MIT-BIH Arrhythmia Database highlights the model's high performance, with accuracy and precision nearing 1.00 for Normal ECG (NOR), Left Bundle Branch Block (LBBB), Right Bundle Branch Block (RBBB), and Ventricular Premature Beat (PVC) in the six-class task. In the ten-class task, the model demonstrated robustness, particularly with an accuracy of 0.9846, precision of 0.9783, recall of 0.9736, and F1 score of 0.9760 in Pacemaker Fusion Beat (PFHB), supported by an AUC of 0.9999 and AP of 0.9885. These results underscore the model's efficacy in cardiac rhythm recognition and resilience to class imbalance. Future research will explore sophisticated model architectures and feature extraction methods to enhance the model's generalization and clinical applicability for early heart disease diagnosis and personalized treatment.

Scene classification plays an important role in the intelligent processing of high-resolution satellite (HRS) remotely sensed image. In HRS image classification, multiple features, e.g. shape, color, and texture features, are employed to represent scenes from different perspectives. Accordingly, effective integration of multiple features always results in better performance compared to methods based on a single feature in the interpretation of HRS image. In this paper, we introduce a multi-task joint sparse and low-rank representation model to combine the strength of multiple features for HRS image interpretation. Specifically, a multi-task learning formulation is applied to simultaneously consider sparse and low-rank structure across multiple tasks. The proposed model is optimized as a non-smooth convex optimization problem using an accelerated proximal gradient method. Experiments on two public scene classification datasets demonstrate that the proposed method achieves remarkable performance and improves upon the state-of-art methods in respective applications.

Anticancer regimens for Hodgkin lymphoma (HL) patients include highly genotoxic drugs that have been very successful in killing tumor cells and providing a 90% disease-free survival at five years. However, these treatments do not have a specific cell target, damaging both cancerous and normal cells. Thus, HL survivors have a high risk of developing new primary cancers, both hematologic and solid tumors, that have been related to treatment. Several studies have shown that after-treatment, HL patients and survivors present persistent chromosomal instability, including non-clonal chromosomal aberrations. The frequency and type of chromosomal abnormalities appear to depend on the type of therapy and the cell type examined. For example, MOPP chemotherapy affects hematopoietic and germ stem cells leading to long-term genotoxic effects and azoospermia, while ABVD chemotherapy affects transiently sperm cells, with most of the patients showing recovery of spermatogenesis. Both regimens have long-term effects in somatic cells, presenting non-clonal chromosomal aberrations and genomic chaos in a fraction of non-cancerous cells. This is a source of karyotypic heterogeneity that could eventually generate a more stable population acquiring clonal chromosomal aberrations and leading towards the development of a new cancer.

Most Neotropical Psittacidae have a diploid number of 2n=70, and a dichotomy in chromosome patterns. Long-tailed species have biarmed macrochromosomes, while short - tailed ones have telo/acrocentric macrochromosomes. However, the use of chromosome painting with chicken and white hawk probes has demonstrated that karyotype evolution in Psittacidae includes a high number of inter/intrachromosomal rearrangements. Hence, to determine the phylogeny of Long and Short-Tailed species, and to propose a putative ancestral karyotype for this group, we constructed homology maps of Pyrrhura frontalis (PFR) and Amazona aestiva (AAE) and compared them to other previously analyzed long-tailed species. Chromosomes were analyzed by conventional staining and fluorescent in situ hybridization (FISH) using whole chromosome paints of G. gallus (GGA) and L. albicollis (LAL). Conventional staining showed a karyotype with 2n=70 in both species, with biarmed macrochromosomes in Pyrrhura frontalis and telo/acrocentric chromosomes in Amazona aestiva. Comparison of the results with the putative avian ancestral karyotype (PAK) showed fusions in P. frontalis of PAK1p/PAK4q (PFR1) and PAK6/PAK7 (PFR6) with a paracentric inversion in PFR6. However, in A. aestiva there was only the fusion between PAK6/7 (AAE7) with a paracentric inversion. Hybridizations with LAL probes confirmed these results. The results indicate that PFR retained a more basal karyotype than Anodorhynchus hyacinthinus (AHY), Ara macao (AMA) and Ara chloropterus (ACH), because these three species show the fusion PAK8/PAK9 that is not seen in PFR. Hence, we suggest that the ancestral karyotype of species with biarmed chromosomes have the fusions PAK1p/PAK4 and PAK6/PAK7 and, additionally, a pericentric inversion of PAK6/PAK7, while the fusion PAK8/PAK9 would have appeared in the common ancestor of Anodorhynchus hyacinthinus, Ara macao and Ara chloropterus. However, the species A. aestiva shows a characteristic plesiomorphic trait, since PAK1p/PAK4q and PAK8/9 fusions are absent. Our results base on chromosome rearrangements suggest the classification following the criterium of tail length may no reflect the real phylogenetic history of Neotropical Psittacidae.

A machine learning method for classifying Lung UltraSound is here proposed to pro- vide a point of care tool for supporting a safe, fast and accurate diagnosis, that can also be useful during a pandemic like as SARS-CoV-2. Given the advantages (e.g. safety, rapidity, portability, cost-effectiveness) provided by the ultrasound technology over other methods (e.g. X-ray, computer tomography, magnetic resonance imaging), our method was validated on the largest LUS public dataset. Focusing on both accuracy and efficiency, our solution is based on an efficient adaptive ensembling of two EfficientNet-b0 models reaching 100% of accuracy, which, to our knowledge, outperforms the previous state-of-the-art. The complexity of this solution keeps the number of parameters in the same order as an EfficientNet-b0 by adopting specific design choices that are adaptive ensembling with a combination layer, ensembling performed on the deep features, minimal ensemble only two weak models. Moreover, a visual analysis of the saliency maps on sample images of all the classes of the dataset reveals where the focus is on an inaccurate weak model versus an accurate model.

Adversarial Classification (AC) is a major subfield within the increasingly important domain of adversarial machine learning (AML). Most approaches to AC so far have followed a classical game-theoretic framework. This requires unrealistic common knowledge conditions untenable in the security settings typical of the AML realm. After reviewing such approaches, we present alternative perspectives on AC based on Adversarial Risk Analysis.

The 22q11.2 deletion syndrome is a multisystemic disorder characterized by a marked variability of phenotypic features making the diagnosis challenging for clinicians. The wide spectrum of clinical manifestations includes congenital heart defects, most frequently conotruncal cardiac anomalies, thymic hypoplasia and predominating cellular immune deficiency, laryngeal developmental defects, midline anomalies with cleft palate and velar insufficiency, structural airway defects, facial dysmorphism, parathyroid and thyroid gland hormonal dysfunctions, speech delay, developmental delay, neurocognitive and psychiatric disorders. Significant progress has been made in understanding the complex molecular genetic etiology of the 22q11.2 deletion syndrome underpinning the heterogeneity of clinical manifestations. The deletion is caused by chromosomal rearrangements in meiosis and is mediated by non-allelic homologous recombination events between low copy repeats or segmental duplications in the 22q11.2 region. A range of genetic modifiers, environmental factors as well as the impact of hemizygosity on the remaining allele contribute to the intricate genotype-phenotype relationships. This comprehensive review has been aimed at highlighting the molecular genetic background of 22q11.2 deletion syndrome in correlation with a clinical multidisciplinary approach.

Marek’s Disease (MD) has a significant impact on both the global poultry economy and animal welfare. The disease pathology can include neurological damage and tumour formation. Sexual dimorphism in immunity and known higher susceptibility of females to MD makes the chicken Z chromosome (GGZ) a particularly attractive target to study the chicken MD response. Previously, we used a Hy-Line F6 population from a full-sib advanced intercross line to map MD QTL regions (QTLRs) on all chicken autosomes. Here we mapped MD QTLRs on GGZ in the previously utilized F6 population with individual genotypes and phenotypes, and in eight elite commercial egg production lines with daughter-tested sires and selective DNA pooling (SDP). Four MD QTLRs were found from each analysis. Some of these QTLRs overlap regions from previous reports. All QTLRs were tested by indiviuals from the same eight lines used in the SDP and genotyped with markers located within and around the QTLRs. All QTLRs were confirmed. The results exemplify the complexity of MD resistance in chickens and the complex distribution of P-values and LD pattern and their effect on localization of the causative elements. Considering the fragments and interdigitated LD blocks while using LD to aid localization of causative elements, one must look beyond the insignificant markers, for possible distant markers and blocks in high LD with the significant block. The QTLRs found here may explain at least part of the gender differences in MD tolerance, and provide targets for mitigating the effects of MD.

Psoriasis is a chronic, multisystem, inflammatory disease. The typical clinical cutaneous manifestation of psoriasis is scaly erythema or plaque, limited or widely distributed. However, psoriasis is far beyond the skin involvement and provides many challenges, including associated comorbidities. In this review, we classify psoriasis as cutaneous and systemic psoriasis, according to the clinical diversity and associated comorbid diseases, and recommend classification criteria for psoriasis. The key objective of this novel classification is to raise awareness of the complexity of this multifaceted disease and help to better understand and manage this complex disease comprehensively.

Cardiopulmonary resuscitation (CPR) is a widely practiced lifesaving skill. Conventional CPR is based on manual chest compressions and delivering mouth-to-mouth breaths. There has been advancement in biomedical technology over the last few decades which has led to the introduction of new techniques and devices in CPR as well. In light of these advancements, we propose SMEAR (Standard, Mechanical, ECMO Assisted, Augmented virtual and Remote) classification system to provide structured overview from traditional to novel methods and devices. The standard or Manual CPR, widely practiced by the general public during out-of-hospital cardiac arrests, combines active chest compressions with or without mouth breathing. However, to enhance CPR’s efficacy, various mechanical devices have been developed, encompassing Active Chest Compression, Passive Decompression, and those integrated with Automated External Defibrillators. Feedback sensor-equipped devices, include the Metronome, Accelerometer, Barometer, and Triaxial Field Induction. Mechanical devices, classified by their compression mechanisms, can be isolated – like the Piston-driven, Load-distributing, and Active Compression-Decompression (ACD) – or combined, as in ACD-ITV (Impedance Threshold Device), ACD-IAC (Interposed Abdominal Compression), and ACD-ITV-EECP (Enhanced External Counter Pulsation). Beyond mechanics, Extracorporeal CPR offers veno-arterial Extracorporeal Membrane Oxygenation in refractory cardiac arrest and can improve outcomes. Augmented Virtual Reality usage in training and provision of CPR is at the early stages. It has the potential of expanded usage in training public to provide high-quality CPR. A provider can be remotely guided step by step via telephone or smartphone applications, ensuring continuous support until professional assistance arrives.

Because it can make exact double-strand breaks in DNA, CRISPR-Cas9 can help almost every species and type of cell. It is a powerful way to change the DNA code. CRISPR-Cas9 can be used for a lot more than just changing genes. We are close to being able to do high-throughput gene screening, epigenome editing, in-vivo cell tagging, and RNA change. With the help of CRISPR-Cas9, the function of genes can be studied better, and more realistic disease models can be made. The revolutionary new discipline of gene editing has the potential to profoundly impact healthcare and the life sciences. By simplifying the process of creating double-strand breaks in the DNA of almost any species or kind of cell, CRISPR-Cas9 has revolutionized gene editing. Numerous applications have been found for the CRISPR-Cas9 system. High-throughput gene screening, RNA modification, live-cell chromosome marking, and epigenome editing are all examples. CRISPR-Cas9 facilitates gene research, leading to the development of CRISPR-based disease models. CRISPR-Cas9-based methods of altering the genome will aid researchers in learning more about sickness and discovering better ways to cure it, despite the fact that there are still many questions and large difficulties to answer.

The classification and summarization of online reviews using machine learning and deep learningbased approaches are the subject of this systematic literature review. Consumers, companies, and researchers can now find vital information from online reviews. Automatically categorizing and summarizing these reviews can offer useful information and facilitate decision-making. The purpose of this study is to offer a thorough overview of the current methodology, approaches, and developments in this area. The review concentrates on machine learning-based methods for categorization and summarizing tasks, highlighting their advantages, drawbacks, and new developments. This systematic review provides insights into the most recent methodologies and indicates prospective directions for further investigation by synthesizing the data from a wide range of pertinent research publications

This paper provides orthogonal moments (OM) such as, Zernike Moments(ZM), Psuedo Zernike Moments(PZM) and Orthogonal Fourier Mellin Moments(OFMM) for the analysis of melanoma images. The moment invariants may vary with respect to geometric variations. For the analysis of orthogonal moments hundred random melanoma images and hundred non-melanoma images have been taken into consideration from the database of 570 melanoma images and 250 non-melanoma images respectively. Orthoganal moments have been computed by varying the phase angles from 10° to 40° with an equal interval of 10° degree for the orders 2, 4,8,16,32,64,128,256 respectively. For the optimal OMs Particle Swarm Optimization (PSO) technique have been used. These set of extracted optimal OMs have been further applied to classify melanoma images. Support Vector Machine (SVM) has been used for the classification of [1]sensitivity=88.78%.

The scope of a lucrative career promoted by Google through its video distribution platform YouTube 1 has attracted a large number of users to become content creators. An important aspect of this line of work is the feedback received in the form of comments which show how well the content is being received by the audience. However, volume of comments coupled with spam and limited tools for comment classification makes it virtually impossible for a creator to go through each and every comment and gather constructive feedback. Automatic classification of comments is a challenge even for established classification models, since comments are often of variable lengths riddled with slang, symbols and abbreviations. This is a greater challenge where comments are multilingual as the messages are often rife with the respective vernacular. In this work, we have evaluated top-performing classification models and four different vectorizers, for classifying comments which are a mix of different combinations of English and Malayalam (only English, only Malayalam and Mix of English and Malayalam). The statistical analysis of results indicates that Multinomial Naïve Bayes, K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Random Forest and Decision Trees offer similar level of accuracy in comment classification. Further, we have also evaluated 3 multilingual sub-types of the novel NLP language model, BERT and compared its’ performance to the conventional machine learning classification techniques. XLM was the top-performing BERT model with an accuracy of 67.31%. Random Forest with Term Frequency Vectorizer was the best the top-performing model out of all the traditional classification models with an accuracy of 63.59%.

Avian sex chromosomes evolved after the divergence birds and crocodilians from their common ancestor, so they are much younger than the better-studied chromosomes of mammals. It has long been recognized that there may have been several stages to the evolution of avian sex chromosomes. For example, the CHD1 undergoes recombination in paleognaths but not neognaths. Genome assemblies have suggested there may be variation in the timing of barriers to recombination among Neognathae, but there remains little understanding of the extent of this variability. Here, we look at partial sequences of ATP5F1A, which is on the avian Z and W chromosomes. It is known that recombination of this gene has independently ceased in Galliformes, Anseriformes, and at least five neoavian orders, but whether there are other independent cessations of recombination among Neoaves is not understood. We used a combination of data extracted from published chromosomal-level genomes with data collected using PCR and cloning to identify Z and W copies in 22 orders. Our results suggest there may be at least 19 independent cessations of recombination within Neognathae, and 3 clades that may still be undergoing recombination (or have only recently ceased recombination). Analyses of ATP5F1A protein sequences revealed an increased amino acid substitution rate for W chromosome gametologs, suggesting relaxed purifying selection on the W chromosome. Supporting this hypothesis, we found that the increased substitution rate was particularly pronounced for buried residues, which are expected to be more strongly constrained by purifying selection. This highlights the dynamic nature of avian sex chromosomes, and that this level of variation among clades means they should be a good system to understand sex chromosome evolution.

The spectrum, intensity and overlap of symptoms between FGIDs and other gastrointestinal disorders characterize patients with FIGDs, who are incredibly different in their backgrounds. An additional challenge with regard to the diagnosis and treatment's applicability is the ongoing expansion of the risk factors believed to be connected to these disorders. Many cytokines and inflammatory cells have been found causing the continuous existence of low-inflammation, which is thought to be a basic pathophysiological process. The idea of the gut-brain axis has been created to offer a basic framework for the complex interactions that occur between the nervous system and intestinal functions, including the involvement of the gut bacteria. In this review paper, we intend to promote a hypothesis that FGIDs, should be seen through the perspective of the network of the neuroendocrine, immunological, metabolic and microbiome pathways. Hypothesis arises from an increased understanding of chronic inflammation as a systemic disorder, being omnipresent in chronic health conditions. Better understanding of inflammation role in the pathogenesis of FGIDs can be achieved by clustering markers of inflammation with data indicating symptoms, comorbidities, and psycho-social factors. Finding subclasses among related entities of FGIDs, may reduce patient heterogeneity and help clarify pathophysiology for better treatment.

The nursing process in clinical practice can be assessed using standardized language systems. The purpose is to find evidence on the effectiveness of the nursing process with standardized terminology using NANDA International, Nursing Interventions Classification, and Nursing Outcome Classification improving diag-nostic accuracy, nursing interventions, health outcomes, and people’s satisfaction. A systematic review was carried out in Medline and PreMedline, Embase, The Cochrane Library, CINAHL, SCI-EXPANDED, SSCI and Scielo and LILACS including randomized clinical trials, quasi-experimental, cohort and case-control studies. Selection and critical appraisal were conducted by two independent reviewers. The certainty of the evidence was assessed with Grading of Recommendations Assessment, Development and Evaluation Methodology. 17 studies were included with variability in the level and certainty of evidence. According to outcomes, 6 evaluated improvements in diagnostic accuracy and 11 evaluated improvements in individual health outcomes. No studies evaluated improvements in intervention efficacy or population satisfaction. There is a need to increase studies with rigorous methodologies that address diagnostic accuracy and indi-viduals’ health outcomes using NANDA International, Nursing Interventions Classification, and Nursing Outcome Classification; as well as implementing studies that evaluate the use of these terminologies for improvements in the efficacy of nurses' interventions and population satisfaction with the nursing process.

Non-linear activation functions are one of the main parts of deep neural network architectures. The choice of the activation function can affect model speed, performance and convergence. Most popular activation functions don't have any trainable parameters and don't alter during the training. We propose different activation functions with and without trainable parameters. Said activation functions have a number of advantages and disadvantages. We'll be testing the performance of said activation functions and comparing the results with widely known activation function ReLU. We assume that the activation functions with trainable parameters can outperform functions without ones, because the trainable parameters allow the model to "select'' the type of each of the activation functions itself, however, this strongly depends on the architecture of the deep neural network and the activation function itself.

Hyperspectral imaging provides vital information about the objects and elements present inside the image. That’s why they are very useful in satellite imagery as well as image forensics. Hyperspectral document analysis (HSDI) can be used for document authentication using ink analysis which can provide sufficient information about the composition and type of ink. In this project, we have implemented HSDI based ink classification technique using Principle Component Analysis for dimensionality reduction and K-means clustering for ink classification. This is unsupervised learning approach and it is very simple and efficient in order to classify limited number of bands. We have used this technique to classify 33 different bands of ink.

Leukemia is a form of blood cancer that results in an increase in the number of white blood cells in the body. The correct identification of Leukemia at any stage is essential. The current traditional approaches rely mainly on field expertise' knowledge, which is time consuming. The poor understanding and a long period of examination might damage the human body. In this situation an automated Leukemia identification delivers more reliable and accurate diagnostic information. To effectively diagnose acute lymphoblastic Leukemia from blood smears pictures, a new strategy based on traditional image analysis techniques with machine learning techniques, and a composite learning approach was constructed in this experiment. To identify the type of acute Leukemia first, four well-known machine learning models were utilized. It was discovered that Support Vector Machine (SVM) Provides the highest accuracy in this scenario. To boost the performance, a deep learning model Resnet50 was hybridized with SVM model. Finally, it was revealed that this composite approach achieved 99.9% accuracy.

Breast cancer is a common malignant tumour and studies have shown that early and accurate detection is crucial for patients. With the maturity of medical imaging and deep learning development, significant progress has been made in breast cancer classification, which greatly improves the accuracy and efficiency of classification. This review focuses on deep learning, migration learning, GAN, and lifelong learning to elaborate and summarise the important roles arising from breast cancer detection. This review also examines the dataset and labeling issues required for breast cancer classification. In conclusion, at the end of the article, we look at future directions for breast cancer classification research, including cross-migration learning, multimodal data fusion, model interpretability, and lifelong learning, and also explore how to provide personalized treatment plans for patients.

To live in the information society means to be surrounded by billions of electronic devices full of sensors that constantly acquire data. This enormous amount of data must be processed and classified. A solution commonly adopted is to send these data to server farms to be remotely elaborated. The drawback is a huge battery drain due to high amount of information that must be exchanged. To compensate this problem data must be processed locally, near the sensor itself. But this solution requires huge computational capabilities. While microprocessors, even mobile ones, nowadays have enough computational power, their performance are severely limited by the Memory Wall problem. Memories are too slow, so microprocessors cannot fetch enough data from them, greatly limiting their performance. A solution is the Processing-In-Memory (PIM) approach. New memories are designed that are able to elaborate data inside them eliminating the Memory Wall problem. In this work we present an example of such system, using as a case of study the Bitmap Indexing algorithm. Such algorithm is used to classify data coming from many sources in parallel. We propose an hardware accelerator designed around the Processing-In-Memory approach, that is capable of implementing this algorithm and that can also be reconfigured to do other tasks or to work as standard memory. The architecture has been synthesized using CMOS technology. The results that we have obtained highlights that, not only it is possible to process and classify huge amount of data locally, but also that it is possible to obtain this result with a very low power consumption.

In past few years, unmanned aerial vehicles (UAV) or drones has been a hot topic encompassing technology, security issues, rules and regulations globally due to its remarkable advancements and uses in remote sensing and photogrammetry applications. This review paper highlights the evolution and development of UAV, classification and comparison of UAVs along with Hardware and software design challenges with diverse capabilities in civil and military applications. Further, safety and security issues with drones, existing regulations and guidelines to fly the drone, limitations and possible solutions have also been discussed.

In the present work, a portable device system applied in the detection and classification of different metallic ions was proposed and developed, aiming at its application in the monitoring of hydrological systems like rivers, lakes and groundwater. Considering the system features, a portable colorimetric system was developed by using a multispectral optoelectronic sensor. All the technology of quantification and classification of metallic ions using Optoelectronic Multispectral sensors was fully integrated in the embedded hardware FPGA technology and software based on virtual Instrumentation (NI LabView ®). The system was used as a colorimeter by using the chromogen reagent of 1-(2-pyridylazo)-2-naphthol (PAN) as an indicator and the results obtained together with the signal processing and pattern analysis using the method of the linear discriminant analysis, allowed to obtain excellent results in detection and classification of Pb(II), Cd(II), Zn(II), Cu(II), Fe(III) and Ni(II) ions, with almost the same level of performance in relation to those obtained from the UV-VIS spectrometers of high spectral resolution.

Many dioecious plants have sex chromosomes that are cytologically heteromorphic, but about half of species lack cytological differences between males and females and are thus homomorphic. Very little is known about the size and content of the non-recombining sex-determining region (SDR) in these species. Here, we assess the size and content of the SDR of the diploid dioecious herb Mercurialis annua, which has homomorphic sex chromosomes and shows signatures of mild Y-chromosome degeneration. We used RNAseq to identify new Y-linked markers for M. annua. Twelve of 24 transcripts with male-specific and male-biased expression could only be PCR-amplified from males and are thus Y-linked. We found a further six Y-linked sequences that were present in males but not females using genome capture data from multiple populations. We used the Y-linked sequences to identify and sequence 17 sex-linked bacterial artificial chromosomes (BACs), which form 11 groups of non-overlapping sequence, covering a total sequence length of about 1.5 Mb. Content analysis of this region suggests it is enriched for repeats, has a low gene density and contains few candidate sex-determining genes. The BACs map to a subset of the sex-linked region of the genetic map, which is estimated to be at least 14.5 Mb. This is substantially larger than estimates for other dioecious plants with homomorphic sex chromosomes, especially given the small genome size of M. annua. Our data provide a rare, high-resolution view of the homomorphic Y chromosome of a dioecious plant.

There are four categories of medical waste that cannot be mixed as this will cause serious problems such as environmental pollution or infection. In the past, the classification of medical waste often involved a lot of human and material resources to process, with workers at risk of exposure to infectious substances. Therefore, an augmented reality (AR) and artificial intelligence (AI) medical waste classification system and method were developed. This innovative medical waste classification system and method combines AR and AI identification technology to reduce the risk of manual judgment errors by clinical staff when handling medical waste.

OSI model used to be common network model for years. In the case of ad hoc networks with dynamic topology and difficult radio communications conditions, gradual departure is happening from the classical kind of OSI network model with a clear delineation of layers (physical, channel, network, transport, application) to the cross-layer approach. The layers of the network model in ad hoc networks strongly influence each other. Thus, the cross-layer approach can improve the performance of an ad hoc network by jointly developing protocols using interaction and collaborative optimisation of multiple layers. The existing cross-layer methods classification is too complicated, because it’s based on the whole manifold of network model layers combinations, regardless their importance. In this work, we review ad hoc networks cross-layer methods, propose the new useful classification of cross-layer methods, and show future research directions in ad hoc networks cross-layer methods development. The proposed classification can help to simplify the goal-oriented cross-layer protocol development.

Keywords: Convolutional Neural Network, Deep Learning, Skin cancer, Generative Adversarial Network

Concentrator photovoltaic (CPV) technology offers an alternative to conventional photovoltaic systems, focusing on the concentration of solar radiation through the optics of the system onto smaller and more efficient solar cells. However, the surface on which the solar beam is incident must remain oriented towards the position of the sun, which requires the use of large and heavy external elements known as solar trackers. In addition to their size, these elements must be as accurate as possible to avoid misalignment. To avoid the need of these solar trackers, the concept of tracking-integrated concentrating systems has been developed. This technology has been researched to make CPV systems accessible in places where conventional systems are not viable, such as building roofs or agrivoltaic fields. This review presents a detailed classification of the existing designs in the literature and providing an overview of this type of system. By eliminating the need for external solar trackers, tracking-integrated CPV systems offer a promising solution to increase the adoption of this technology. Therefore, it is expected that these systems will be a viable and effective option for solar power generation.

A recent paradigm shift in diagnostics of medulloblastoma allows the distinction of four major groups defined by genetic data rather than histology. This new molecular classification correlates better with prognosis and will allow better clinical management for therapies targeting druggable mutations, but also offers a new combination of monitoring tumor development in real-time and treatment response by sequential liquid biopsy. This review highlights recent developments after a century of milestones in neurosurgery, radio- and chemotherapy, but also controversial theories on the cell of origin, animal models and the use of liquid biopsy.

In this paper, we present the idea of Self Supervised learning on the Shape Completion and Classification of point clouds. Most 3D shape completion pipelines utilize autoencoders to extract features from point clouds used in downstream tasks such as Classification, Segmentation, Detection, and other related applications. Our idea is to add Contrastive Learning into Auto-Encoders to learn both global and local feature representations of point clouds. We use a combination of Triplet Loss and Chamfer distance to learn global and local feature representations. To evaluate the performance of embeddings for Classification, we utilize the PointNet classifier. We also extend the number of classes to evaluate our model from 4 to 10 to show the generalization ability of learned features. Based on our results, embedding generated from the Contrastive autoencoder enhances Shape Completion and Classification performance from 84.2% to 84.9% of point clouds achieving the state-of-the-art results with 10 classes.

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.

The visualization of hyperspectral images in display devices, having RGB colour composition channels is quite difficult due to the high dimensionality of these images. Thus, principal component analysis has been used as a dimensionality reduction algorithm to reduce information loss, by creating uncorrelated features. To classify regions in the hyperspectral images, K-means clustering has been used to form clusters/regions. These two algorithms have been implemented on the three datasets imaged by AVIRIS and ROSIS sensors.

Satellite communication (Satcom) is an artificial geostationary satellite that facilitates a wide range of telecommunications. Considering its quality of service (QoS) and security is crucial in government/military applications. The most challenging situation for efficient Satcom is radio frequency interference (RFI) environment. Thus, it is necessary to ensure that transmissions are incorruptible or at least sense the quality of its spectrum. This paper presents a new method to recognize received signal characteristics using a hierarchical classification in a multi-layer perceptron neural network. We consider signal modulation and the type of RFI as the characteristics of a real-time video stream transmitted in the direct broadcast satellite. Four different modulation types are investigated in this study. Moreover, the combination of the communication signal with various kinds of interference and their effects on the classification method widely have been analyzed. Besides, two robust feature selection techniques have been developed to reduce the data-set dimensional, which leads to optimizing the classification process. The results show that the Genetic Algorithm (GA) slightly outperforms Principal Component Analysis (PCA) for feature selection. Furthermore, the robustness of the proposed techniques is assessed to detect unknown signals at different signal to noise ratios.

The field of program classification, a critical aspect of software engineering, facilitates understanding and categorization of code across various applications, including anomaly detection, and code quality assessment. The advancement of cross-language program classification opens up avenues for efficient code translation among different programming languages, significantly aiding developers in rapid coding and reducing development cycles. Existing research primarily focuses on semantic code analysis, with limited emphasis on cross-linguistic challenges. To address this, we introduce an innovative neural network model, CodeSemanticsNN, which leverages a refined Syntax Structure (SS) approach. This model consists of two integral mechanisms: first, it adopts a novel SS representation that combines sequential and graph-based SS structures, enhancing semantic feature capture. Second, it employs a 'unified vocabulary' strategy to bridge the gap between diverse programming languages, facilitating efficient cross-language classification. Additionally, we have compiled a comprehensive dataset of 20,000 files spanning five programming languages, serving as a benchmark for cross-language classification. Our experiments on this dataset demonstrate that CodeSemanticsNN surpasses existing models in four key metrics: Precision, Recall, F1-score, and Accuracy.

Deep neural networks with powerful auto-optimization tools have been widely applied in various research fields, e.g., NLP and computer vision. However, existing neural network architectures typically are constructed using different inductive biases, e.g., preconceptions, expecting to decrease parameter search space during training, reduce computational cost or introduce expert knowledge in the neural network design. As an alternative, Multilayer Perceptron (MLP) provides much better freedom for exploration, has a lower inductive bias than convolutional neural networks (CNNs), and offers good flexibility in learning complex patterns. Even though, such neural architectures are commonly built in a flat Euclidean space, which is not necessarily the optimal space for any data, and is especially not good for modeling hierarchical correlations. Hyperbolic neural networks (HNNs) have gained attention for their ability to capture hierarchical structures present in complex data types like graphs. Recently, there has been an increasing interest to extend HNNs to computer vision tasks, motivated by the observations that images possess rich hierarchical relations. However, this is generally applied by employing a Euclidean backbone for learning higher-level semantic representations and only incorporating a hyperbolic classifier for classification, which, we argue, does not make full use of the advantage of hyperbolic space. Considering the recovery of the attention-free Multilayer Perceptron(MLP), in this paper, we extend it to non-Euclidean space and propose a novel architecture, named Hyperbolic Res-MLP (HR-MLP), that leverages fully hyperbolic layers to learn feature embeddings and perform image classification in an end-to-end fashion. With the help of the proposed Lorentz cross-patch and cross-channel layers, we can directly perform operations in the hyperbolic domain with fewer parameters, making it faster to train and providing comparatively better performance than its Euclidean counterpart. Experiments on CIFAR10, CIFAR100, and MiniImageNet demonstrate a comparable and superior performance when compared to Euclidean baselines. Our code is available at (https://github.com/Ahmad-Omar-Ahsan/HR-MLP)

This work proposes a metaheuristic-based approach for hyperparameter selection in a multilayer perceptron to classify electromyographic signals. The main goal of the study is to improve the performance of the model by optimizing four important hyperparameters: the number of neurons, the learning rate, the epochs, and the training batches. The approach proposed in this work shows that hyperparameter optimization using particle swarm optimization and gray wolf optimizer significantly improves the performance of a multilayer perceptron for classifying EMG motion signals. The final model achieved an average classification rate of 93% for the validation phases. The results obtained are promising and suggest that the proposed approach may be helpful for the optimization of deep learning models in other signal processing applications.

Multilabel learning goes beyond standard supervised learning models by associating a sample with more than one class label. Among the many techniques developed in the last decade to handle multilabel learning best approaches are those harnessing the power of ensembles and deep learners. This work proposes merging both methods by combining a set of gated recurrent units, temporal convolutional neural networks, and long short-term memory networks trained with variants of the Adam optimization approach. We examine many Adam variants, each fundamentally based on the difference between present and past gradients, with step size adjusted for each parameter. We also combine Incorporating Multiple Clustering Centers and a bootstrap-aggregated decision trees ensemble, which is shown to further boost classification performance. In addition, we provide an ablation study for assessing the performance improvement that each module of our ensemble produces. Multiple experiments on a large set of datasets representing a wide variety of multilabel tasks demonstrate the robustness of our best ensemble, which is shown to outperform the state-of-the-art. The MATLAB code for generating the best ensembles in the experimental section will be made available at https://github.com/LorisNanni.

The strategy of any organization is based on the growth of its customer base, and one of 6 its principles is that selling a product to an existing customer is much more profitable than acquiring 7 a new customer. However, this approach has several opportunities for improvement, since it usu- 8 ally has a totally reactive approach, which does not give opportunity to the areas specialized in 9 customer experience and recovery, to give an effective response for that moment, since the customer 10 is gone at the time of the intervention. This happens because usually a diagnostic analysis of cus- 11 tomers who have stopped buying products or services in a defined period, commonly three (3) pe- 12 riods or months, is performed. This paper challenges the way to face this problem, and proposes 13 the development of a complete solution, which does not focus exclusively on the prediction of 14 churn, as is usually done in the state of the art research, but to intervene in different interactions 15 that can be carried out with customers. The above focused not only to prevent customer churn, but 16 to generate an added value of continuous improvement in sales processes, increase customer pene- 17 tration, leading to an improvement in customer experience and consequently, an increase in cus- 18 tomer loyalty.

The classifier system proposed in this work combines the dissimilarity spaces produced by a set of Siamese neural networks (SNNs) designed using 4 different backbones, with different clustering techniques for training SVMs for automated animal audio classification. The system is evaluated on two animal audio datasets: one for cat and another for bird vocalizations. Different clustering methods reduce the spectrograms in the dataset to a set of centroids that generate (in both a supervised and unsupervised fashion) the dissimilarity space through the Siamese networks. In addition to feeding the SNNs with spectrograms, additional experiments process the spectrograms using the Heterogeneous Auto-Similarities of Characteristics. Once the similarity spaces are computed, a vector space representation of each pattern is generated that is then trained on a Support Vector Machine (SVM) to classify a spectrogram by its dissimilarity vector. Results demonstrate that the proposed approach performs competitively (without ad-hoc optimization of the clustering methods) on both animal vocalization datasets. To further demonstrate the power of the proposed system, the best stand-alone approach is also evaluated on the challenging Dataset for Environmental Sound Classification (ESC50) dataset. The MATLAB code used in this study is available at https://github.com/LorisNanni.

By generalizing the notion of pointwise 1-type Gauss map, the generalized 1-type Gauss map has been recently introduced. Without any assumption, we classified all possible ruled surfaces with generalized 1-type Gauss map in a 3-dimensional Minkowski space. In particular, null scrolls do not have the proper generalized 1-type Gauss map. In fact, it is harmonic.

Superpixels are a representation of still images as pixel grids because of their more meaningful information compared with atomic pixels. However, their usefulness for video classification has been given little attention. In this paper, rather than using spatial RGB values as low-level features, we use optical flows mapped into hue-saturation-value (HSV) space to capture rich motion features over time. We introduce motion superpixels, which are superpixels generated from flow fields. After mapping flow fields into HSV space, independent superpixels are formed by iteration of seeded regions. Every grid of a motion superpixel is tracked over time using nearest neighbors in the histogram of flow (HOF) for consecutive flow fields. To define the temporal representation, the evolution of three features within the superpixel region, namely the HOF, HOG, and the center of superpixel mass are used as descriptors. The bag of features algorithm is used to quantify final features, and generalized histogram-kernel support vector machines are used as learning algorithms. We evaluate the proposed superpixel tracking on first-person videos and action sports videos.

For the particular selected type of fractals, i.e., the Kronecker product based fractals, the introductory common classification is proposed. It essentially relies on the size and content of the initial fractal matrix. In turn, it gives one of the possible explanation of the phenomenal ability to produce a few of the most popular fractals using many different algorithms, languages and tools. Also, it paves the way to discover on the regular basis thousands of the new fractals, and this gives researchers a wider range of fractal models to choose from.

Relapsed acute lymphoblastic leukemia (ALL) represents a continuous challenge for the clinician. Despite recent advances in treatment, the risk of relapse remains significant. The clinical, biological, cytogenetic, and molecular characteristics may be different at the time of relapse. Current comprehensive genome sequencing studies suggest that most relapsed patients, especially those with late relapses, acquire new genetic abnormalities, usually within a minor clone that emerges after ALL diagnosis. We report the case of a 23-year-old young woman diagnosed with Philadelphia chromosome negative B-cell acute lymphoblastic leukemia. The patient underwent allogeneic stem cell transplantation (allo-HSCT) after complete remission. Although having favorable prognostic factors at diagnosis, the disease relapsed early after allo-HSCT. The cytogenetic and molecular exam at relapse was positive for the Philadelphia chromosome, respectively for the bcr-abl transcript. What exactly led to the relapse of this disease in a more aggressive cytogenetic and molecular form, although there were no predictive elements in the diagnosis of this relapse?

Biologists seek to identify a small number of significant features that are important, non-redundant, and relevant from diverse omics data. For example, statistical methods like LIMMA and DEseq distinguish differentially expressed genes between a case and control group from the transcript profile. Researchers also apply various column subset selection algorithms on genomics datasets for a similar purpose. Unfortunately, genes selected by such statistical or machine learning methods are often highly co-regulated, making their performance inconsistent. Here, we introduce a novel feature selection algorithm that selects highly disease-related and non-redundant features from a diverse set of omics datasets. We successfully applied this algorithm to three different biological problems: a) disease to normal sample classification, b) multiclass classification of different disease samples, and c) disease subtypes detection. Considering classification ROC-AUC, False-positive, and False-negative rates, our algorithm outperformed other gene selection and differential expression (DE) methods for all six types of cancer datasets from TCGA considered here for binary and multiclass classification problems. Moreover, genes picked by our algorithm improved the disease subtyping accuracy for four different cancer types over the state-of-the-art methods. Hence, we posit that our proposed feature reduction method can support the community to solve various problems, including the selection of disease-specific biomarkers, precision medicine design, and disease sub-type detection.

This article presents an automated vision-based algorithm for the die-scale inspection of wafer images captured using scanning acoustic tomography (SAT). This algorithm can find defective and abnormal die-scale patterns, and produce a wafer map to visualize the distribution of defects and anomalies on the wafer. The main procedures include standard template extraction, die detection through template matching, pattern candidate prediction through clustering, and pattern classification through deep learning. To conduct the template matching, we first introduce a two-step method to obtain a standard template from the original SAT image. Subsequently, a majority of the die patterns are detected through template matching. Thereafter, the columns and rows arranged from the detected dies are predicted using a clustering method; thus, an initial wafer map is produced. This map is composed of detected die patterns and predicted pattern candidates. In the final phase of the proposed algorithm, we implement a deep learning-based model to determine defective and abnormal patterns in the wafer map. The experimental results verified the effectiveness and efficiency of our proposed algorithm. In conclusion, the proposed method performs well in identifying defective and abnormal die patterns, and produces a wafer map that presents important information for solving wafer fabrication issues.

Breast cancer is the most common cause of death for women worldwide. Thus, the ability of artificial intelligence systems to predict and classify breast cancer is very important. In this paper, a hybrid ensemble method classification mechanism is proposed based on a majority voting mechanism. First, the performance of different state-of-the-art machine learning classification algorithms for the Wisconsin Breast Cancer Dataset (WBCD) were evaluated. The three best classifiers were then selected based on their F3 score. F3 score is used to emphasize the importance of false negatives (recall) in breast cancer classification. Then, these three classifiers, simple logistic Regression learning, stochastic gradient descent learning and multilayer perceptron network, are used for ensemble classification using a voting mechanism. We also evaluated the performance of hard and soft voting mechanism. For hard voting, majority-based voting mechanism was used and for soft voting we used average of probabilities, product of probabilities, maximum of probabilities and minimum of probabilities-based voting methods. The hard voting (majority-based voting) mechanism shows better performance with 99.42% as compared to the state-of-the-art algorithm for WBCD.

Power quality (PQ) plays an important role in ensuring the smooth operation of power systems. PQ disturbances may cause significant consequences, impacting the reliability and efficiency of power networks. This paper presents a comprehensive review of PQ within smart grids and the integration of renewable energy sources. Methods of detecting, classifying, optimizing, and mitigating PQ events are reviewed with providing a brief theoretical explanation for each technique. Related work done in the past two decades, was conducted, presenting a clear view of the development of research in a chronological order serving as a guide for future investigations in this field of study.

Convolutional Neural Networks (CNNs) present drawbacks for modeling geometric transformations, such as scaling and rotation, caused by the convolution operation’s locality. Deformable convolution (DCON), a mechanism that substitutes standard convolution, increasing the receptive field to capture relevant features, is a promising approach to solve this drawback and improve the robustness of CNNs. However, the optimal way to replace the standard convolution with its deformable counterpart in a CNN model is unclear. In this study, we clarify this aseveration by conducting several experiments using deformable convolutions applied in the layers that conform a small four-layer CNN model. We also use deformable convolutions on the four-layers of several ResNet CNNs with depths 18, 34, 50, and 101. The models were tested in binary balanced classes with 2D data for image classification: Cats &amp; Dogs, EyesPACS, Spyders &amp; Chickens, and Shapes. After this testing, we evaluated DCON in 3D data for action recognition: UCF101 and Human2 (a dataset we compiled to control movement, clothing and background). The contribution of this research lies in a guideline to use DCON. It can be summarized as follows: if DCON is used on the first layers of the proposal of model (with simple features), the computational resources expressed as the quantity of Flops will tend to increase and produce bigger misclassification than the standard CNN. However, if the DCON is used at the end layers, the quantity of Flops used in the training and testing will decrease, and the classification accuracy will improve by up to 20% about the base model. Moreover, it gains robustness when using deformable convolutions because it can adapt to the region of interest. Also, the best kernel size of the DCON is three. It showed better results than size five. In the last case, the quantity of Flops increase quadratically, but their performance does not increase significantly. With these results, we propose a guideline to use the DCON and contribute to understanding the impact of DCON on the robustness of CNNs.

Machine learning and computer vision have proven to be valuable tools for farmers to streamline their resource utilization to lead to more sustainable and efficient agricultural production. These techniques have been applied to strawberry cultivation in the past with limited success. To build on this past work, in this study two separate sets of strawberry images, along with their associated diseases, were collected and subjected to, resizing, and augmentation. Subsequently, a combined dataset consisting of 9 classes was utilized to fine-tune three distinct pre-trained models: Vision Transformer (ViT), MobileNetV2, and ResNet18. To address the imbalanced class distribution in the dataset, each class was assigned weights to ensure nearly equal impact during the training process. To enhance the outcomes, new images were generated by removing backgrounds, reducing noise, and flipping them. The performances of ViT, MobileNetV2, and ResNet18 were compared after being selected. Customization specific to the task was applied to all three algorithms, and their performances were assessed. Throughout this experiment, none of the layers were frozen, ensuring all layers remained active during training. Attention heads were incorporated into the first 5 and last 5 layers of MobileNetV2 and ResNet18, while the architecture of ViT was modified. The results indicated accuracy factors of 98.4%, 98.1%, and 97.9% for ViT, MobileNetV2, and ResNet18, respectively. Despite the data being imbalanced, the precision, which indicates the proportion of correctly identified positive instances among all predicted positive instances, approached nearly 99% with the ViT. MobileNetV2 and ResNet18 demonstrated similar results. Overall, the analysis revealed that the Vision Transformer model exhibited superior performance in strawberry ripeness and disease classification. The inclusion of attention heads in the early layers of ResNet18 and MobileNet18, along with the inherent attention mechanism in ViT, improved the accuracy of image identification. These findings offer the potential for farmers to enhance strawberry cultivation through passive camera monitoring alone, promoting the health and well-being of the population.

it still undergoes corrosion when exposed to corrosive environments. This paper proposes an evaluation method for assessing the corrosion level of SPCC steel specimens using traditional eddy current testing (ECT), along with two different machine learning approaches. The objective is to classify the corroded state of the specimens into two states: a less corroded state (state-1) and a highly corroded state (state-2). Generative and discriminative models were implemented for classification. The generative classifier was based on the Gaussian mixture model (GMM), while the discriminative model was based on the logistic regression model. The models used features based on the absolute maximum of the perturbation magnetic field components at two different frequencies. The performance of the classifiers was evaluated using metrics such as absolute error, accuracy, precision, recall, and F1 score. The results indicate that high classification accuracy can be achieved based on both methods using traditional eddy current testing.