Cooling fans are one of the critical components of air-forced (AF) dry-type transformers for regulating internal temperatures. Therefore, effective malfunction detection is crucial to maintain the transformer temperature within an acceptable range and prevent overheating. Regular maintenance occurs periodically and issues with cooling fans may arise between maintenance periods, leading to prolonged operation under malfunctioning conditions and potential failures. In addition, utilities typically have online information about whether a fan works or not without providing information about cooling fan malfunctioning circumstances. To address these challenges, this study proposes learning-based online monitoring techniques to detect malfunctions in AF transformer cooling fans. Random forests (RFs) and convolutional neural networks (CNNs) are developed to classify the audio signals from cooling fans into normal and malfunctioning classes. Unlike RFs, which require separate feature extraction, CNNs are trained based on spectrogram images derived from audio signals. Thus, various time-frequency techniques are utilized for feature extraction in RFs. Besides, multiple data augmentation techniques are employed to enhance the dataset size and diversity. Algorithmic performance is optimized through hyperparameter tuning and classifier threshold adjustment. Simulations reveal that CNNs outperform RFs, whereas the latter provides superior interpretability of acoustic features compared to the former.

The fossil record is notorious for being incomplete and distorted, frequently conditioning the type of knowledge that can be extracted from it. In many cases, this often leads to issues when performing complex statistical analyses, such as classification tasks, predictive modelling, and variance analyses, such as those used in Geometric Morphometrics. Here different Generative Adversarial Network architectures are experimented with, testing the effects of sample size and domain dimensionality on model performance. For model evaluation, robust statistical methods were used. Each of the algorithms were observed to produce realistic data. Generative Adversarial Networks using different loss functions produced multidimensional synthetic data significantly equivalent to the original training data. Conditional Generative Adversarial Networks were not as successful. The methods proposed are likely to reduce the impact of sample size and bias on a number of statistical learning applications. While Generative Adversarial Networks are not the solution to all sample-size related issues, combined with other pre-processing steps these limitations may be overcome. This presents a valuable means of augmenting geometric morphometric datasets for greater predictive visualization.

In response to the growing challenges in drone security and airspace management, this study introduces an advanced drone classifier, capable of detecting and categorizing Unmanned Aerial Vehicles (UAVs) based on acoustic signatures. Utilizing a comprehensive database of drone sounds across EU-defined classes (C0 to C3), this research leverages machine learning (ML) techniques for effective UAV identification. The study primarily focuses on the impact of data augmentation methods—pitch shifting, time delays, harmonic distortion, and ambient noise integration—on classifier performance. These techniques aim to mimic real-world acoustic variations, thus enhancing the classifier's robustness and practical applicability. Results indicate that moderate levels of augmentation significantly improve classification accuracy. However, excessive application of these methods can negatively affect performance. The study concludes that sophisticated acoustic data augmentation can substantially enhance ML-driven drone detection, providing a versatile and efficient tool for managing drone-related security risks. This research contributes to UAV detection technology, presenting a model that not only identifies but also categorizes drones, underscoring its potential for diverse operational environments.

A key component for the proper functioning, availability, and reliability of power grids is the power trans- former. Although these are very reliable assets, the early detection of incipient degradation mechanisms are very important to prevent failures that may shorten their lifetime. In this work a review and comparative analysis, of classical Machine Learning algorithms (such as single and ensemble classification algorithms) and two automatic machine learning classifiers, are presented for the fault diagnosis of power transformers. The goal is to determine whether fully automated ML approaches are worse or better than traditional ML frameworks that require a human in the loop (such as a data scientist) to identify transformer faults from oil-dissolved gases data. The methodology uses a DB compiled from published and proprietary transformer fault samples. Faults data is obtained from the literature, the Duval pentagon method, and user-expert knowledge. The parameters from, either single or ensemble classifiers, were optimized through standard machine learning procedures. The results showed that the best performing algorithm is a robust automatic machine learning classifiers model followed by classical algorithms such as neural networks and stacking ensembles. These results highlight the ability of a robust automatic machine learning model for, handling imbalanced power transformers faults datasets with high accuracy, using the minimum tuning effort by the electrical experts. By providing the most probable transformer fault condition will reduce the time required to find and solve the fault.

In power systems there are complex transformer structures, whose accurate analysis is not possible using the techniques available today. This paper presents a systematic data driven analysis method for coupled inductors of arbitrary complexity. The method first establishes a winding matrix N mapping the windings to the limbs of the transformer. A permeance matrix P is created from the reluctance network of the magnetic core. A generalized inductance matrix L mapping currents in the transformer windings to the induced voltages is generated based on the winding (N) and permeance (P) matrices. The inductance matrix representation of a coupled inductor is then transformed to an admittance matrix, which can be integrated to the nodal analysis of the electrical circuit surrounding the coupled inductor. The method presented is validated by simulations with real transformer structures using electromagnetic transient program (EMTP/ATP).

The author demonstrates a stable Lagrangian solid modeling method, tracking the interactions of solid mass particles rather than using a meshed grid. This numerical method avoids the problem of tensile instability often seen with smooth particle applied mechanics by having the solid particles apply stresses expected with Hooke's law, as opposed to using a smoothing function for neighboring solid particles. This method has been tested successfully with a bar in tension, compression, and shear, as well as a disk compressed into a flat plate, and the numerical model consistently matched the analytical Hooke's law as well as Hertz contact theory for all examples. The solid modeling numerical method was then built into a 2-D model of a pressure vessel, which was tested with liquid water particles under pressure and simulated with smoothed particle hydrodynamics. This simulation was stable, and demonstrated the feasibility of Lagrangian specification modeling for fluid–solid interactions.

Epilepsy is a prevalent neurological disorder with considerable risks, including physical impairment and irreversible brain damage from seizures. Given these challenges, the urgency for prompt and accurate seizure detection cannot be overstated. Traditionally, experts have relied on manual EEG signal analyses for seizure detection, which is labor-intensive and prone to hu-man error. Recognizing this limitation, the rise of deep learning methods has been heralded as a promising avenue, offering more refined diagnostic precision. On the other hand, the prevailing challenge in many models is their constrained emphasis on specific domains, potentially diminishing their robustness and precision in complex real-world environments. This paper presents a novel model that seamlessly integrates the salient features from the time-frequency domain alongside pivotal statistical attributes derived from EEG signals. This fusion process involves the integration of essential statistics, including the mean, median, and variance, combined with the rich data from compressed time-frequency (CWT) images processed using auto-encoders. This multidimensional feature set provides a robust foundation for subsequent analytic steps. A long short-term memory (LSTM) network, meticulously optimized for the renowned Bonn Epilepsy dataset, was used to enhance the capability of the proposed model. Preliminary evaluations underscore the prowess of the proposed model: remarkable 100% accuracy in most of the binary classifications, impressive performance exceeding 95% for three-class and four-class challenges, and a commendable rate exceeding 93.5% for the five-class classification.

Time recordings of impulse-type oscillation responses are short and highly transient. These characteristics may complicate the usage of classical spectral signal processing techniques for a) describing the dynamics and b) deriving discriminative features from the data. However, common model identification and validation techniques mostly rely on steady-state recordings, characteristic spectral properties and non-transient behavior. In this work, a recent method, which allows reconstructing differential equations from time series data, is extended for higher degrees of automation. With special focus on short and strongly damped oscillations, an optimization procedure is proposed that fine-tunes the reconstructed dynamical models with respect to model simplicity and error reduction. This framework is analyzed with particular focus on the amount of information available to the reconstruction, noise contamination and non-linearities contained in the time series input. Using the example of a mechanical oscillator, we illustrate how the optimized reconstruction method can be used to identify a suitable model and to extract features from uni-variate and multivariate time series recordings in an engineering-compliant environment. Moreover, the determined minimal models allow for identifying the qualitative nature of the underlying dynamical systems as well as testing for the degree and strength of non-linearity. The reconstructed differential equations would then be potentially available for classical numerical studies, such as bifurcation analysis. These results represent a physically interpretable enhancement of data-driven modeling approaches in structural dynamics.

Due to the non-contact measurement characteristics of trackside acoustic technology, it is now utilized for train bearing fault diagnosis. However, the relative motion between the train and the trackside acoustic detection device introduces Doppler aberration in the collected acoustic signal, which affects bearing fault diagnosis. Moreover, when a fault occurs in the train bearing, its acoustic signal exhibits cyclic smoothness characteristics that can be effectively analyzed using the cyclic smoothness method for more accurate judgment. In order to minimize diagnostic errors and enhance accuracy in bearing fault diagnosis, this study integrates bearing fault characteristics with Doppler aberration correction methods and cyclic smoothness techniques for current-stage bearings diagnostics. The overall time-domain graph becomes more compact with an approximately 50% increase in amplitude after correction compared to pre-correction values; other parameters experience enhancements ranging from 20-60%. These results validate the feasibility of our proposed approach and establish a framework for conducting bearing fault diagnosis based on cyclically smoothed Doppler aberration correction.

Large power transformers are generally associated with a maximum capacity rating of 100 MVA or higher. These large liquid dielectric power transformers are a custom-built piece of equipment, thus very expensive, and a backbone element of the power grid. In extreme cases as, for example, severe geomagnetic disturbances, permanently monitoring their condition will enhance their electrical reliability and resilience to guarantee efficient management of its life cycle. However, some traditional monitoring/diagnosis techniques have singular features when applied to large power transformers and their interlinked subsystems. In this context, and since that information is hardly put in evidence and compiled in the literature, this paper reviews the particularities of monitoring and diagnosing those assets.

Air conditioners are indispensable necessities in daily life and industrial production. However, the heat generation of their internal core power components can limit their performance release. In this work, we explore the application of thermoelectric coolers (TECs) in the field of power device heat dissipation through finite element simulation. First, we geometrically modeled the structure and typical operating conditions of core power devices in air conditioners. We compared the temperature fields in air cooling and TEC active cooling modes for high power consumption power devices in a 319 K operating environment. The simulation results show that in the single air cooling mode, the maximum temperature of the 173.8 W power device reaches 394.4 K and the average temperature reaches 373.9 K, which exceeds its rated operating temperature of 368.1 K. However, after adding TEC, the maximum temperature of the power device drops to 331.8 K at an operating current of 7.5 A and the average temperature of the device is 326.5 K. It indicates that TEC active cooling has a significant effect on the temperature control of the power device. At the same time, we also studied the effect of TEC working current on the temperature control effect of power devices. For TEC, there is a minimum working current of 5 A; when it is less than 5 A, TEC has no cooling effect; the cooling effect of TEC increases with an increase in working current. When the TEC working current is 10 A, the average temperature of the power device can be reduced to 292.9 K. This study has made a meaningful exploration of the application of TEC in chip temperature control and heat dissipation, providing a new solution for chip thermal management and accurate temperature control.

Heart sounds and murmurprovidecrucial diagnosis information for valvular heart diseases (VHD). Phonocardiogram (PCG) combined with modern digital processing techniques, provides a complementary tool for clinicians. This article proposes a benchmark different time-frequency representations, which are spectogram, mel-spectogram and cochleagram for obtaining images, in addition to the use of two interpolation techniques to improve the quality of the images, which are Bicubic and Lanczos. Deep features are extracted from a pre-trained model called VGG16 and for feature reduction the Boruta algorithm is applied. To evaluate the models and obtain more precise results, nested cross-validation is used. The best results achieved in this study were for coclegram with 99.2% accuracy and mel-spectogram representation with the bicubic interpolation technique which reached 99.4% accuracy, both having support vector machine (SVM) as classifier 10 algorithm. Overall, this study highlights the potential of time-frequency representations of PCG 11 signals combined with modern digital processing techniques and machine learning algorithms for 12 accurate diagnosis of VHD.

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.

Due to the advantages of low latency, low power consumption and high flexibility of FPGA-based acceleration technology, it has been more and more widely studied and applied in the field of computer vision in recent years. An FPGA-based feature extraction and tracking accelerator for real-time visual odometry (VO) and visual simultaneous localization and mapping (V-SLAM) is proposed, which can realize the complete acceleration processing capability of the image front-end and directly output the feature point ID and coordinates to the backend. The accelerator consists of image preprocessing, pyramid processing, optical flow processing, and feature extraction and tracking modules. For the first time, it implements a hardware solution that combines features from accelerated segment test (FAST) corners with Gunnar Farneback (GF) dense optical flow, to achieve better feature tracking performance and provide more flexible technical route selection. In order to solve the scale invariance and rotation invariance lacking problem of FAST features, an efficient pyramid module with a five-layer thumbnail structure is designed and implemented. The accelerator is implemented on a modern Xilinx Zynq FPGA. The evaluation result shows that the accelerator can achieve stable tracking of features of violently shaking images, and is consistent with the results of MATLAB code running on PC. When operating at 100MHz, the accelerator can process 108 frames per second for 720P images and 48 frames per second for 1080P images. Compared to PC CPUs that consume seconds of time, the processing latency is greatly reduced to the order of milliseconds, making GF dense optical flow an efficient and practical technical solution on the edge side.

Genomics involving tens of thousands of genes is a complex system determining phenotype. An interesting and vital issue is that how to integrate highly sparse genetic genomics data with a mass of minor effects into prediction model for improving prediction power. We find that deep learning method can work well to extract features by transforming highly sparse dichotomous data to lower dimensional continuous data in a non-linear way. This idea may provide benefits in risk prediction based on genome-wide data associated e.g. integrating most of the information in the genotype data. Hence, we developed a multi-stage strategy to extract information from highly sparse binary genotype data and applied it for risk prediction. Specifically, we first reduced the number of biomarkers via a univariable regression model to a moderate size. Then a trainable auto-encoder was used to extract compact representations from the reduced data. Next, we performed a LASSO problem process over a grid of tuning parameter values to select the optimal combination of extracted features. Finally, we applied such feature combination to two prognostic models, and evaluated predictive effect of the models. The results of simulation studies and real data applying indicated that these highly compressed transformation features could better improve predictive performance and did not easily lead to over-fitting.

We propose a deep-learning approach for the joint MIMO detection and channel decoding problem. Conventional MIMO receivers adopt a model-based approach for MIMO detection and channel decoding in linear or iterative manners. However, due to the complex MIMO signal model, the optimal solution to the joint MIMO detection and channel decoding problem (i.e., the maximum likelihood decoding of the transmitted codewords from the received MIMO signals) is computationally infeasible. As a practical measure, the current model-based MIMO receivers all use suboptimal MIMO decoding methods with affordable computational complexities. This work applies the latest advances in deep learning for the design of MIMO receivers. In particular, we leverage deep neural networks (DNN) with supervised training to solve the joint MIMO detection and channel decoding problem. We show that DNN can be trained to give much better decoding performance than conventional MIMO receivers do. Our simulations show that a DNN implementation consisting of seven hidden layers can outperform conventional model-based linear or iterative receivers. This performance improvement points to a new direction for future MIMO receiver design.

Keywords: Electrical power systems, Support vector machines, Random Forest, Machine learning, Wavelet transform, Transmission lines fault, Electrical power quality, Short circuit, Classification of faults, Localization of faults, Decision trees, Ensemble learning, K-nearest neighbors.

Moving object detection plays a crucial role in various applications, particularly in traffic surveillance and collision warning systems. However, the high cost of training and slow detection pose significant challenges to the practicality and real-time performance of existing methods. These challenges hinder the practicality and real-time performance of existing methods. The need for a reliable and efficient moving object detection system prompts the search for cost-effective strategies. Enhancing detection speed without sacrificing accuracy is crucial for real-time applications. Overcoming these challenges is essential to advance the field of moving object detection and improve its applicability in various domains. This paper presents a comprehensive review of the literature on moving object detection, proposes novel strategies to overcome the challenges of high training costs and slow detection. The study emphasizes the importance of reliable speed monitoring systems and advancements in control systems to enhance driver assistance on urban highways. Each frame in the dataset undergoes YOLOv6 processing to detect and classify objects, generating bounding box predictions and class probabilities. Optical flow, specifically the Lucas-Kanade method, is then utilized to compute motion vectors between consecutive frames. These motion vectors facilitate object tracking across frames, enabling refined bounding box positions and improving overall object tracking accuracy. The results demonstrate the effectiveness of the proposed technique in reducing training costs, improving detection speed, and maintaining a high level of accuracy when compared to existing methods. The paper concludes by summarizing the findings and highlighting the potential of the proposed strategy for precise and reliable moving object recognition in real-world traffic scenarios

In recent years, governments applied intelligent transportation system (ITS) technique to provide several convenience services (e.g., garbage truck app) for residents. This study proposes a garbage truck fleet management system (GTFMS) and data feature selection and data clustering methods for travel time prediction. A GTFMS includes mobile devices (MD), on-board units, fleet management server, and data analysis server (DAS). When user uses MD to request the arrival time of garbage truck, DAS can perform the procedure of data feature selection and data clustering methods to analyses travel time of garbage truck. The proposed methods can cluster the records of travel time and reduce variation for the improvement of travel time prediction. After predicting travel time and arrival time, the predicted information can be sent to user’s MD. In experimental environment, the results showed that the accuracies of previous method and proposed method are 16.73% and 85.97%, respectively. Therefore, the proposed data feature selection and data clustering methods can be used to predict stop-to-stop travel time of garbage truck.

Sensitivity to weather conditions, and specially to clouds, is a severe limiting factor to the use of optical remote sensing for Earth monitoring applications. A possible alternative, is to resort to weather-insensitive synthetic aperture radar (SAR) images. However, in many real-world applications, critical decisions are made based on some informative spectral features, such as water, vegetation or soil indices, which cannot be extracted from SAR images. In the absence of optical sources, these data must be estimated. The current practice is to perform linear interpolation between data available at temporally close time instants. In this work, we propose to estimate missing spectral features through data fusion and deep-learning. Several sources of information are taken into account - optical sequences, SAR sequences, DEM - so as to exploit both temporal and cross-sensor dependencies. Based on these data, and a tiny cloud-free fraction of the target image, a compact convolutional neural network (CNN) is trained to perform the desired estimation. To validate the proposed approach, we focus on the estimation of the normalized difference vegetation index (NDVI), using coupled Sentinel-1 and Sentinel-2 time-series acquired over an agricultural region of Burkina Faso from May to November 2016. Several fusion schemes are considered, causal and non-causal, single-sensor or joint-sensor, corresponding to different operating conditions. Experimental results are very promising, showing a significant gain over baselines methods according to all performance indicators.

Machine learning approaches are currently used to understand or model complex physical systems. In general, a substantial number of samples must be collected to create a model with reliable results. However, collecting numerous data is often relatively time-consuming or expensive. Moreover, the problems of industrial interest tend to be more and more complex and depending on a high number of parameters. High dimensional problems intrinsically involve the need of large data amount through the curse of dimensionality. That is why, new approaches based on smart sampling techniques are investigated to minimize the number of samples to be given to train the model, such as Active Learning methods. Here, we propose a technique based on a combination of Fisher information matrix and of Sparse Proper Generalized Decomposition that enables the definition of a new Active Learning informativeness criterion in high dimensions. We provide examples proving the performances of this technique on a theoretical 5D polynomial function and on an industrial crash simulation application. The results prove that the proposed strategy over-perform the usual ones.

Automated Electrocardiogram (ECG) processing is an important technique which helps in identifying abnormalities in the heart before any formal diagnosis. This research presents a real-time and lightweight R-assisted feature extraction algorithm and a heartbeat classification scheme which achieves highly accurate abnormality detection. In the proposed algorithm, we extract fifteen features from each heartbeat taken from raw Lead-II ECG signals. The features carry medically valuable information such as locations, amplitude and energy of ECG waves (P, Q, R, S, T waves) which are then used for detection of any abnormality that might be present in the heartbeat using various classification algorithms. We have used four popular databases from Physionet and extracted ten thousand ECG signals from each for training the models and benchmarking results. Four classification models i.e. Naïve Bays, k-Nearest Neighbor, Neural Network, Decision Tree were used for abnormality detection validating the efficiency of the system.

This paper proposes a forecast-centric adaptive learning model that engages with the past studies on the order book and high-frequency data, with applications to hypothesis testing. In line with the past literature, we produce brackets of summaries of statistics from the high-frequency bid and ask data in the CSI 300 Index Futures market and aim to forecast the one-step-ahead prices. Traditional time series issues, e.g. ARIMA order selection, stationarity, together with potential financial applications are covered in the exploratory data analysis, which pave paths to the adaptive learning model. By designing and running the learning model, we found it to perform well compared to the top fixed models, and some could improve the forecasting accuracy by being more stable and resilient to non-stationarity. Applications to hypothesis testing are shown with a rolling window, and further potential applications to finance and statistics are outlined.

Generative AI has gained enormous interest nowadays due to new applications like chatGPT, DALL E, Stable Difussion and Deep Fake. Particularly DALL E, Stable Difussion and others (Adobe Firefly, ImagineArt...) are able to create images from a text prompt and are also able to recreate real photographs. Due to this fact, intense research has arisen to create new image forensics applications able to distinguish between real captured images and videos and artificial ones. Detecting forgeries made with Deep Fake is one of the most researched issues. This paper is about another kind of forgery detection. The purpose of this research aims to detect photo realistic AI created images versus real photos coming from a physical camera. For this purpose, techniques that perform a pixel level feature extraction are used. First one is Photo Response Non-Uniformity (PRNU). PRNU is a special noise due to imperfections on the camera sensor that is used for source camera identification. The underlying idea is that AI images will have a different PRNU pattern. Second one is Error level analysis (ELA). This is other type of feature extraction traditionally used for detecting image editions. In fact, ELA is being used nowadays by photographers to detect manually AI created images. Both kinds of features are used to train Convolutional Neural Networks to differentiate between AI images and real photographs. Good results are obtained achieving accuracy rates over 95%. Both extraction methods are carefully assessed by computing precision/recall and F1-score measurements.

Vertical Indoor Farming (VIF) with hydroponics offers a promising perspective for sustainable food production. Intelligent control of VIF system components plays a key role in reducing operating costs and increasing crop yields. Modern machine vision (MV) systems use Deep Learning (DL) in combination with camera systems for various tasks in agriculture, such as disease and nutrient deficiency detection, and flower and fruit identification and classification for pollination and harvesting. This study presents the applicability of MV technology with DL modelling to detect the growth stages of chilli plants using YOLOv8 networks. The influence of different bird’s eye and side view datasets and different YOLOv8 architectures was analysed. To generate the image data for training and testing the YOLO models, chilli plants were grown in a hydroponic environment and imaged throughout their life cycle using four camera systems. The growth stages were divided into growing, flowering and fruiting classes. All trained YOLOv8 models showed reliable identification of growth stages with high accuracy. The results indicate that models trained with data from both views show better generalisation. YOLO’s middle architecture achieved the best performance.

Semi-continuous data are very common in the social science and economics. In this paper, a Bayesian variable selection procedure is developed to assess the influence of exogenous factors including observed and unobserved on the semi-continuous data. Our formulation is based on the two-part latent variable model with polytomous response. We consider two schemes for the penalties of regression coefficients and factor loadings: the Bayesian spike and slab bimodal prior and the Bayesian lasso prior. Within the Bayesian framework, we implement Markov Chains Monte Carlo sampling method to conduct posterior inference. To facilitate posterior sampling, we recast the logistic model in part one as the norm-like mixture model. Gibbs sampler is designed to draw observations from the posterior. Our empirical results show that with suitable hyper-parameters, the spike and slab bimodal method slightly outperforms the Bayesian lasso in the current analysis. Finally, a real example related to the China household finance survey is analyzed to illustrate the application of the methodology.. .

Object detection is one of the most critical tasks in the field of Computer vision. This task comprises identifying and localizing an object in the image. Architectural floor plans represent the layout of buildings and apartments. The floor plans consist of walls, windows, stairs, and other furniture objects. While recognizing floor plan objects is straightforward for humans, automatically processing floor plans and recognizing objects is a challenging problem. In this work, we investigate the performance of the recently introduced Cascade Mask R-CNN network to solve object detection in floor plan images. Furthermore, we experimentally establish that deformable convolution works better than conventional convolutions in the proposed framework. Identifying objects in floor plan images is also challenging due to the variety of floor plans and different objects. We faced a problem in training our network because of the lack of publicly available datasets. Currently, available public datasets do not have enough images to train deep neural networks efficiently. We introduce SFPI, a novel synthetic floor plan dataset consisting of 10000 images to address this issue. Our proposed method conveniently surpasses the previous state-of-the-art results on the SESYD dataset and sets impressive baseline results on the proposed SFPI dataset. The dataset can be downloaded from SFPI Dataset Link. We believe that the novel dataset enables the researcher to enhance the research in this domain further.

Federated learning trains a neural network model using the client's data to maintain the benefits of centralized model training, while maintaining the privacy. However, if the client data are not independently and identically distributed (non-IID) because of different environments, the accuracy of the model may suffer from client drift during training owing to discrepancies in each client's data. This study proposes a personalized federated learning algorithm based on the concept of multitask learning to divide each client model into two layers: a feature extraction layer and a category prediction layer. The feature extraction layer maps the input data to a low-dimensional feature vector space. Furthermore, the parameters of the neural network are aggregated with those of other clients using an adaptive method. The category prediction layer maps low-dimensional feature vectors to the label sample space, with its parameters remaining unaffected by other clients to maintain client uniqueness. The proposed personalized federated learning method produces faster learning model convergence rates and higher accuracy rates for the non-IID datasets in our experiments.

The unreliable prediction of the low frequency components from inverted acoustic impedance causes uncertainty in quantitative seismic interpretation. To address this issue, we first calculate various seismic and geological attributes that contain low frequency information, such as relative geological age, interval velocity, and integrated instantaneous amplitude. Then, we develop a method to predict the low frequency content of seismic data using these attributes, their high frequency components, and recurrent neural networks. Next, we test how to predict the low frequency components using stacking velocity obtained from velocity analysis. Using all the attributes and seismic data, we propose a supervised deep learning method to predict the low frequency components of the inverted acoustic impedance. The results obtained in both synthetic and real data cases show that the proposed method can improve the prediction accuracy of the low frequency components of the inverted acoustic impedance, with the best improvement in a real data example of 57.7% compared with the impedance predicted using well log interpolation.

In this study, a basic study was performed to analyze the seasonal temperature status of a research room in the Global Environment Research Building where ceiling-embedded indoor units are installed to study the room temperature status of the building as well as to improve its thermal environment. In addition, a direction for improvement of the indoor thermal environment in the winter was proposed through a CFD (computational fluid dynamics) simulation and was proven by an additional experiment. Through the results of this study, it appeared that if the ceiling-embedded indoor unit was installed in the small indoor space without considering the thermal vulnerability of its perimeter boundary, the air temperature of the upper part was greatly different from that of the bottom part in the winter. Hence, in this study, as a means to improve it, convectors were installed to minimize the effect of the external thermal environment and angle-controllable air flowing fans were installed to mitigate the stratification distribution. With such result, it was intended to present the essential data for improvement of the thermal environment as well as conservation of heating energy in the winter for buildings by reviewing the use of the ceiling-embedded indoor unit in the future.

Two algorithms of data processing are proposed to shorten the unmeasurable dead-zone close to the zero-position of measurement, i.e., the minimum working distance of a dispersive interferometer using optical frequency comb, which is a critical issue in millimeter-order short-range absolute distance measurement. After demonstrating the limitation of the conventional data processing algorithm, the principles of the proposed algorithms, namely the spectral fringe algorithm, and the combined algorithm that combines the spectral fringe algorithm with the excess fraction method, are presented, together with simulation results for demonstrating the possibility of the proposed algorithms for shortening the dead-zone with a high accuracy. An experimental setup of dispersive interferometer is also constructed for implementing the proposed data processing algorithms over spectral interference signals. Experimental results demonstrate that the dead-zone by the proposed algorithms can be as small as half of that by the conventional algorithm while the measurement accuracy can be further improved with the combined algorithm.

Unmanned Aerial Vehicles (UAVs) severing as the relay is an effective technology method to extend the coverage. It can also alleviate the congestion and increase the throughput, especially applied in UAV networks. However, since the energy of UAVs is limited and the resources in UAV networks are scarce, how to optimize the network delay performance under these constraints should be well investigated. Besides, the relationship among different resources, e.g. power and bandwidth, is coupled which makes the optimization more complex. This article investigates the problem of joint power and bandwidth allocation in UAV backhaul networks, which considers both the delay performance and the resource utilization efficiency. Considering the heterogeneous locations characteristics of different UAVs, we formulate the optimization problem as a Stackelberg game. The relay UAV acts as the leader and extended UAVs act as followers. Their utility functions take both the delay durance and the resource consumption into account. To capture the competitive relationship among followers, the sub-game is proved to be an exact potential game and exists Nash equilibriums (NE). The Stackelberg Equilibrium (SE) is proved afterwards. We utilize a hierarchical learning algorithm (HLA) to find out the best resource allocation strategies, which also reduces the computational complexity. Simulation results demonstrate the effectiveness of the proposed method.

Recently, significant progress has been made in developing computer-aided diagnosis (CAD) systems for identifying glaucoma abnormalities using fundus images. Despite their drawbacks, methods for extracting features such as wavelets and their variations, along with classifier like support vector machines (SVM), are frequently employed in such systems. This paper introduces a practical and enhanced system for detecting glaucoma in fundus images. This system adresses the chanallages encountered by other existing models in recent litrature. Initially, we have employed contrast limited adaputive histogram equalization (CLAHE) to enhanced the visualization of input fundus inmages. Then, the discrete ripplet-II transform (DR2T) employing a degree of 2 for feature extraction. Subsequently, a golden jackal optimization algorithm (GJO) employed to select the optimal features to reduce the dimension of the extracted feature vector. During the classification stage the least square support vector machine (LS-SVM) with three kernels called as linear, polynomial and radial basis function(RBF), for classifying of fundus images as glaucoma or healthy. The proposed method is validated with the current state-of-the-art models on two standard datasets, namely, G1020 and ORIGA. The results obtained from our experimental result demonstrate that our best suggested approach DR2T+GJO+LS-SVM-RBF obtains better classification accuracy 93.38% and 97.31% for G1020 and ORIGA dataset with less number of features. It establishes a more concise network structure when contrasted with traditional classifiers.

Many corner detector techniques have already been used in extracting information from UAV images to perform various photogrammetric and mapping activities. Among these techniques is the Feature from Accelerated Segment Test (FAST) and the Harris corner detector. It is widely agreed that the evaluation of detectors is of great importance because it evaluates and enhances the accuracy of the detected features. This research evaluates the performance of FAST-9 and FAST-12 as well as the Harris detector in terms of the repeatability rate, completeness, and correctness under different threshold values. Each method is evaluated in terms of its ability for detection UAV objects (crowd and cars features). Then the common detected features between both FAST versions and the Harris detector are extracted. This is to determine which method performs best under different image conditions (e.g., illumination variations, camera position and orientation, and image noise). The results show that the size of the threshold plays a crucial role in determining the number of detected feature points. An increase in the threshold value leads to a decrease in the number of detected points and vice versa. Thus, the correctness decreases whereas the completeness increases as a function of the threshold values. Furthermore, the relationship between the FAST-9 and the Harris detector is slightly better than those between the FAST-12 and the Harris detector. This is because the number of common features between the FAST-9 and the Harris detector are relatively higher than those between the FAST-12 and the Harris detector.

This paper addresses the problem of low accuracy of conventional channel estimation and signal detection in complex fields like mines; and the problem of replacing the deep receiver at the receiver side with a deep neural network requires a large amount of data for training and slow training time. Combining the receiver side with traditional communication knowledge, a channel estimation and signal detection method based on the joint ReEsNet and SDRNet under the mine is proposed. The detailed step is to use ReEsNet network for interpolation of conventional channel estimation. Then, on the basis of ReEsNet, the output data is channel equalized and pilots removed, and the previously processed data is input to SDRNet to perform signal recovery. In the complex mine environment, the MSE values are 2e-2 for LS, 6e-3 for MMSE, and 8.44e-5 for ReEsNet at the 1500th sample data for interpolation compared to the conventional channel estimation. the MSE of ReEsNet is the smallest and is closer to the real channel estimation. Compared with the proposed joint channel estimation and signal detection methods, fewer trainable parameters reduce 97% of the parameters compared to CCRNet and 84% of the parameters compared to CNNNet; their detection results, however, are not very different.

MIMO (multiple-input multiple-output) radar provides much more flexibility than the traditional radar for its ability to realize far more observation channels than the actual number of T/R (transmit and receive) elements. Designing the array of MIMO imaging radar, the commonly used virtual array theory generally assumes that all elements are placed on the same line. However, due to the physical size of the antennas and coupling effect between T/R elements, a certain height difference between T/R arrays is essential, resulting in the defocusing of edge points of the scene. On the other hand, the virtual array theory implies far-field approximation, leading to inevitable high grating lobes in the imaging result of near-field edge points of the scene observed by common MIMO array. To tackle these problems, this paper derives the relationship between target’s PSF (point spread function) and pattern of T/R arrays, by which the design criterion of near-field imaging MIMO array is presented. Firstly, the proper height between T/R arrays is designed to focus the near-field edge points well. Secondly, the far-field array is modified to suppress the grating lobes in the near-field area. Finally, the validity of the proposed methods is verified by simulations and an experiment.

An autonomous concrete crack inspection system is necessary for preventing hazardous incidents arising from deteriorated concrete surfaces. In this paper, we represent a concrete crack detection framework to aid the process of automated inspection. The proposed approach employs a deep convolutional neural network architecture for crack segmentation from concrete image. The proposed network alleviates the effect of gradient vanishing problem present in deep neural network architectures. A feature silencing module is incorporated in the crack detection framework, for eliminating unnecessary feature maps from the network. The overall performance of the network significantly improves as a result. Experimental results support the benefit of incorporating feature silencing within a convolutional neural network architecture for improving the network’s robustness, sensitivity, and specificity. An added benefit of the proposed architecture is its ability to accommodate for the trade-off between specificity (positive class detection accuracy) and sensitivity (negative class detection accuracy) with respect to the target application. Furthermore, the proposed framework achieves a high precision rate and processing time than crack detection architectures present in literature.

To support pathologists in breast tumor diagnosis, deep learning plays a crucial role in the development of histological whole slide image (WSI) classification methods. However, automatic classification is challenging due to the high-resolution data and the scarcity of representative training data. To tackle these limitations, we propose a deep learning-based breast tumor gigapixel histological image multi-classifier integrated with a high-resolution data augmentation model to process the entire slide by exploring its local and global information and generating its different synthetic versions. The key idea is to perform classification and augmentation in feature latent space, reducing the computational cost while preserving the class label of the input. We adopt a deep learning-based multi-classification method and evaluate the contribution given by a Conditional Generative Adversarial Network-based data augmentation model on the classifier’s performance for three tumor classes in the BRIGHT Challenge dataset. The proposed method has allowed us to achieve an average F1 equal to 69.5, considering only the WSI dataset of the Challenge. The results are comparable to those obtained by the Challenge winning method (71.6), also trained on the annotated tumor region dataset of the Challenge.

One of the most rapidly advancing areas of deep learning research aims at creating models that learn to disentangle the latent factors of variation from a data distribution. However, modeling joint probability mass functions is usually prohibitive, which motivates the use of conditional models assuming that some information is given as input. In the domain of numerical cognition, deep learning architectures have successfully demonstrated that approximate numerosity representations can emerge in multi-layer networks that build latent representations of a set of images with a varying number of items. However, existing models have focused on tasks requiring to conditionally estimate numerosity information from a given image. Here we focus on a set of much more challenging tasks, which require to conditionally generate synthetic images containing a given number of items. We show that attention-based architectures operating at the pixel level can learn to produce well-formed images approximately containing a specific number of items, even when the target numerosity was not present in the training distribution.

The anomaly detection task is very important in computer science. And there are a lot of anomaly detection methods. Different from some thresholding methods, some unsupervised methods could make us get more accurate and faster result, which is the object of the project. In this paper, I tried to use EWMA and some other methods in two datasets: Webank time consuming indicators dataset and AIOps Challenge dataset. The paper consists nine parts: background of the project, related work, description of algorithms, implementation details, experimental setup and data sets used, experimental results and discussion, future directions, reference and meeting notes.

Background. The Stanford Health Assessment Questionnaire-Disability Index (HAQ) is widely used to measure functional ability in persons with Rheumatoid Arthritis (RA). The instrument was developed with limited involvement from persons with RA, and their perception of the instrument has not been studied in depth. The aim of this study was to explore how persons with RA experience the use of the HAQ in care. Methods. Forty persons with RA were purposefully recruited to participate in semi-structured interviews. The interviews were then analyzed qualitatively using thematic analysis. Results. The participants questioned the relevance of the HAQ but nevertheless experienced that the instrument had a profound effect on their understanding of health and how care is delivered. The analysis resulted in three themes: Problems with individual items, meaning of the summative score, and effects on care and health perceptions. Conclusions. To make the HAQ relevant to persons with RA, it needs to be revised or to include an option to select items most meaningful to the respondent. To ensure relevance, the HAQ update should preferably be co-created by researchers, clinicians and persons with RA.

Skin cancer is an exquisite disease globally nowadays. Because of the poor contrast and apparent resemblance between skin and lesions, automatic identification of skin cancer is complicated. The rate of human death can be massively reduced if melanoma skin cancer can be detected quickly using dermoscopy images. In this research, an anisotropic diffusion filtering method is used on dermoscopy images to remove multiplicative speckle noise and the fast-bounding box (FBB) method is applied to segment the skin cancer region. Furthermore, the paper consists of two feature extractor parts. One of the two features extractor parts is the hybrid feature extractor (HFE) part and another is the convolutional neural network VGG19 based CNN feature extractor part. The HFE portion combines three feature extraction approaches into a single fused feature vector: Histogram-Oriented Gradient (HOG), Local Binary Pattern (LBP), and Speed Up Robust Feature (SURF). The CNN method also is used to extract additional features from test and training datasets. This two-feature vector is fused to design the classification model. This classifier performs the classification of dermoscopy images whether it is melanoma or non-melanoma skin cancer. The proposed methodology is performed on two ordinary datasets and achieved the accuracy 99.85%, sensitivity 91.65%, and specificity 95.70%, which makes it more successful than previous machine learning algorithms.

It is crucial to select the right machine learning classifier for image classification and face recog-nition. This study examines the effectiveness of four different face recognition classifiers - Support Vector Machines (SVM), Random Forest, K-Nearest Neighbors (KNN), and Neural Networks. An analysis of the Large Faces in the Wild (LFW) dataset was carried out using Principal Component Analysis (PCA). Classifiers are rigorously trained and evaluated based on the extracted features. Comparison of classifier performance is an insightful way to figure out their strengths and weaknesses. Having a visual representation of the classifier's performance gives a complete understanding of its capabilities. Through the selection of the most appropriate classifier, study results contribute to advancements in image classification, recognition, and biometric identification. The comparison study demonstrated that the Neural Network classifier was exceptionally accurate and proficient in recognizing faces from the LFW dataset when used in conjunction with PCA for feature extraction. According to the comparative analysis, the Neural Network classifier proved exceptionally accurate and proficient at identifying faces from the LFW dataset when combined with PCA for feature extraction.

Ransomware attacks have risen alarmingly, with encryption techniques becoming more complex. This paper introduces a novel detection model tailored for ransomware's distinctive characteristics. The Intel PIN tool extracts Windows API invocation sequences related to file operations. These sequences are used to construct n-grams, forming feature vectors enhanced by a new Class Feature Weighting (CFW) metric to improve malware detection. Preliminary results demonstrate elevated accuracy and precision versus existing methods. The major contributions are: (1) Introducing an innovative deep learning model for few-shot ransomware classification using entropy features and transfer learning. (2) Achieving high weighted F1-score in classifying ransomware variants into families with limited training data. (3) Demonstrating the potential of entropy-based features to capture intricacies lost in image-based approaches, improving detection of new strains.

Based on the dynamic strength variation mechanism of concrete under complex loading conditions, two approaches were devised: numerical testing and CT scanning, guided by the principle of minimizing energy dissipation. A methodology for calculating concrete's failure area and measuring its strength was developed. The analysis delves into the mechanisms behind failure patterns and variations in concrete specimen strength, focusing on crack initiation, development, and the resultant failure surface formed by crack propagation, along with the stress distribution in concrete specimens subjected to diverse loading conditions. Through evaluating the strength and computed failure area of concrete specimens, it is evident that the loading method influences both the strength and failure area of concrete specimens. In general, a larger failure area correlates with a higher measured strength.

Machinery degradation assessment can offer meaningful prognosis and health management in-formation. Although numerous machine prediction models based on artificial intelligence have emerged in recent years, they still face a series of challenges: (1) Many models continue to rely on manual feature extraction. (2) Deep learning models still struggle with long sequence prediction tasks. (3) Health indicators are inefficient for remaining useful life (RUL) prediction with cross-operational environments when dealing with high-dimensional datasets as inputs. This research proposes a health indicator construction methodology based on a transformer self-attention transfer network (TSTN). This methodology can directly deal with the high-dimensional raw dataset and keep all the information without missing when the signals are taken as the input of the diagnosis and prognosis model. First, we design an encoder with a long-term and short-term self-attention mechanism to capture crucial time-varying information from a high-dimensional dataset. Second, we propose an estimator that can map the embedding from the encoder output to the estimated degradation trends. Then, we present a domain dis-criminator to extract invariant features from different machine operating conditions. The case studies with the FEMTO-ST bearing dataset and the Monte Carlo method for RUL prediction during the degradation process are conducted. The experiment results fully exhibited the signif-icant advantages of the proposed method compared to other state-of-the-art techniques.

In this paper, a complete tool for real-time detection of atypical energy behaviors of airplanes is presented. The methodology extends in real time an existing offline process using Dubins trajectories as a predictor of the remaining distance to the runway threshold. Two major contributions are presented in this paper. First, a real-time measure of the aircraft energy behaviour is defined, indicating whether the aircraft is in good condition to intercept the extended runway centreline from its current position. Secondly, a 2D trajectory suggestion is given, allowing safe management of the approach path according to atypical criteria of historical data. Finally, this document proposes a comprehensive tool for air traffic controllers, which is a major step forward in understanding, becoming aware of and resolving critical situations that could lead to accidents.

To conduct high-precision and high-resolution numerical simulation of complex flow structures in turbomachinery, a high-order finite volume weighted essentially non-oscillatory (WENO) scheme for the large eddy simulation (LES) is improved and embedded into the three-dimensional viscous unsteady CFD solver NUAA-Turbo. Firstly, the spectral characteristics and unsteady convergence of the improved WENO scheme are studied. Compared with the classical WENO scheme, the improved WENO scheme has better dissipation and dispersion characteristics and faster convergence speed. Then, the coefficient CW of the Wall-Adapting Local Eddy-viscosity (WALE) model is calibrated by decaying homogeneous isotropic turbulence (DHIT) test case. Finally, the scheme is applied to conduct high-precision LES calculations of turbulent boundary layer flow, supersonic compression corner flow, and low-pressure turbine cascade separation flow. The numerical simulation results show that this WENO scheme has excellent shock wave capture ability and turbulence resolution and can capture more flow field details with less mesh size, greatly reducing the computational cost and laying a foundation for large-scale engineering application of LES.

Coal gasification with carbon dioxide is a process for generating clean gaseous fuels and relieving greenhouse effect. Zhundong coal has high alkali and alkali earth metals (AAEMs) content, medium volatile and low ash in nature. Isothermal CO₂ gasification of char derived from Zhundong coal (R-char) and char from acid washing R-char (AR-char) are performed in thermo-gravimetric analyzer (TGA). The effect of AAEMs is investigated on the gasification behavior in the range of temperatures 1073 K to 1273 K. The carbon conversion increases rapidly with increasing reaction temperature and CO₂ concentration. R-char has high gasification rate and carbon conversion compared with AR-char. The accuracy of the free-model approach for calculating activation energy at different conversions is validated by compared with different kinetic models (volume reaction model, distributed activation energy model). Moreover, R-char gasification with CO₂ shows a compensation effect as the Arrhenius parameters (EA and k0) increase or decrease simultaneously.

As the adoption of renewable energy sources grows, ensuring a stable power balance across various time frames has become a central challenge for modern power systems. In line with the "dual carbon" objectives and the seamless integration of renewable energy sources, harnessing the advantages of various energy storage resources and coordinating the operation of long-term and short-term storage have become pivotal directions for future energy storage deployment. To address the complexities arising from the coupling of different time scales in optimizing energy storage capacity, this paper proposes a method for energy storage planning that accounts for power imbalance risks across multiple time scales. Initially, the Seasonal and Trend decomposition using the Loess (STL) decomposition method is utilized to temporally decouple actual operational data. Subsequently, power balance computations are performed based on the obtained data at various time scales to optimize the allocation of different types of energy storage capacities and assess the associated imbalance risks. Finally, the effectiveness of the proposed approach is validated through hourly applications using real-world data from a province in China over recent years.

The correct classification of defects originating from partial discharges (PD) in medium-voltage (MV) switchgears with air insulation (AIS) remains a challenging research topic for scientists worldwide. In this article, the authors simulated four possible defects occurring in the power industry, including one that is a simultaneous combination of two commonly ones. In addition, the correctness of the algorithm was checked by adding a classification class without any fault. The measurement signals were recorded with TEV sensors. The effectiveness of various hy-brid-connected neural networks was tested and discussed: GoogleNet and SqueezeNet based on spectrograms, SAE with FNN, 2D-CNN with LSTM, and hybrid AE combined with CNN and LSTM. The highest effectiveness – approximately 97% – was demonstrated by the GoogleNet and SqueezeNet networks. The research results are expected to form the basis for the development of a universal and wireless capacitive sensor for monitoring the level of PD in switchgears.

This paper presents a novel sensor for the detection and characterization of regions of air turbulence that would be of use to improve UAV stability in bad weather. It consists of a combined Schlieren imager and a Radar Acoustic Sounding System (RASS) to produce dual modality “images” of air movement within the measurement volume. The ultrasound modulated Schlieren imager consists of a strobed point light source, parabolic mirror, light-block and camera which are controlled by two laptops. It provides a fine scale projection of the acoustic pulse modulated air turbulence through the measurement volume. The narrow beam 40 kHz/ 17 GHz RASS produces spectra based on Bragg enhanced Doppler radar reflections from the acoustic pulse as it travels. Tests using artificially generated air vortices showed some disruption of the Schlieren image and of the RASS spectrogram. This should allow the higher resolution Schlieren images to identify the turbulence mechanisms that are disrupting the RASS spectra.

The ubiquitous connectivity for the space-air-ground integrated network (SAGIN) of the beyond fifth generation of communication and sixth generation of communication (B5G/6G) is envisaged to meet the needs for the demanded quality of service (QoS), green communication, and "dual carbon" target. However, the offloading and computation of massive latency-sensitive tasks dramatically increases the energy consumption of the network. Furthermore, the traditional power supply technology of the network base stations (BSs) enhances the carbon emission. To address these issues, we first propose a SAGIN architecture with energy harvesting devices, where the BS is powered by both renewable energy (RE) and the conventional grid. The BS explores wireless power transfer (WPT) technology to power the unmanned aerial vehicle (UAV) for stable network operation. RE sharing between neighbouring BSs is designed to fully utilize RE for reduce carbon emission. Secondly, on the basis of task offloading decision, UAV trajectory, and RE sharing ratio, we construct cost functions with joint latency-oriented, energy consumption, and carbon emission. Then, we develop a twin delayed deep deterministic policy gradient (TD3PG) algorithm based on deep reinforcement learning to minimize the cost function. Finally, simulation results demonstrate that the proposed algorithm outperforms the benchmark algorithm in terms of reducing latency, energy saving, and lower carbon emission.

The aim of this study has been to develop a novel two-level multi-objective genetic algorithm (GA) to optimize time series forecasting data for fans used in road tunnels by the Swedish Transport Administration (Trafikverket). Level 1 is for the process of forecasting time series cost data, while level 2 evaluates the forecasting. Level 1 implements either a multi-objective GA based on the ARIMA model or a multi-objective GA based on the dynamic regression model. Level 2 utilises a multi-objective GA based on different forecasting error rates to identify a proper forecasting. Our method is compared with using the ARIMA model only. The results show the drawbacks of time series forecasting using only the ARIMA model. In addition, the results of the two-level model show the drawbacks of forecasting using a multi-objective GA based on the dynamic regression model. A multi-objective GA based on the ARIMA model produces better forecasting results. In level 2, five forecasting accuracy functions help in selecting the best forecasting. Selecting a proper methodology for forecasting is based on the averages of the forecasted data, the historical data, the actual data and the polynomial trends. The forecasted data can be used for life cycle cost (LCC) analysis.

Vibration monitoring is a critical aspect of assessing the health and performance of machinery and industrial processes. This study explores the application of machine learning techniques, specifically the Random Forest (RF) classification model, to predict and classify chatter—a detrimental self-excited vibration phenomenon—during machining operations. While sophisticated methods have been employed to address chatter, this research investigates the efficacy of a simplified RF model. The study leverages simulated vibration data, bypassing resource-intensive real-world data collection, to develop a versatile chatter detection model applicable across diverse machining configurations. The feature extraction process combines time-series features and Fast Fourier Transform (FFT) data features, streamlining the model while addressing challenges posed by feature selection. By focusing on the RF model’s simplicity and efficiency, this research advances chatter detection techniques, offering a practical tool with improved generalizability, computational efficiency, and ease of interpretation. The study demonstrates that innovation can reside in simplicity, opening avenues for wider applicability and accelerated progress in the machining industry.

The timely diagnosis of defects at their incipient stage of formation is crucial to extend the life-cycle of technical appliances. This is the case of mechanical-related stress, either due to long aging degradation processes (e.g., corrosion) or in-operation forces (e.g., impact events), which might provoke detrimental damages, such as cracks, disbonding or delaminations, most commonly followed by the release of acoustic energy. The localization of these sources can be successfully fulfilled via adoption of Acoustic Emission (AE)-based inspection techniques through the computation of the Time of Arrival (ToA), namely the time at which the induced mechanical wave released at the occurrence of the acoustic event arrives to the acquisition unit. However, the accurate estimation of the ToA may be hampered by poor Signal-to-Noise ratios (SNRs). In these conditions, standard statistical methods typically fail. In this work, two alternative Deep Learning methods are proposed for ToA retrieval, namely a Dilated Convolutional Neural Network (DilCNN) and a Capsule Neural Network for ToA (CapsToA). These methods have the additional benefit of being portable on resource-constrained microprocessors. Their performance has been extensively studied on both synthetic and experimental data, focusing on the problem of ToA identification for the case of a metallic plate. Results show that the two novel methods can achieve localization errors which are up to 70% more precise than those yielded by conventional strategies, even when the SNR is severely compromised (i.e., down to 2 dB). Moreover, DilCNN and CapsNet have been implemented in a tiny machine learning environment and then deployed on microcontroller units, showing a negligible loss of performance with respect to offline realizations.

Heart failure is a prevalent cardiovascular condition with significant health implications, necessitating effective diagnostic strategies for timely intervention. This study explores the potential of continuous monitoring of non-invasive signals, specifically integrating Photoplethysmogram (PPG) and Electrocardiogram (ECG), for enhancing early detection and diagnosis of heart failure. Leveraging a dataset from the MIMIC-III database, encompassing 682 heart failure patients and 954 controls. Feature selection techniques were used to systematically select key features which were identified for their clinical relevance and significance in capturing cardiovascular dynamics and to reduce computational complexity and to decrease the chance of overfitting the ML algorithms. These features are then utilized to train and evaluate machine learning algorithms, resulting in a model with an impressive accuracy of 98%, sensitivity of 97.60%, specificity of 96.90%, and precision of 97.20%. The integrated approach outperforms single-signal strategies, showcas-ng its potential for early, precise, and non-invasive heart failure diagnosis. Furthermore, the study underscores the significance of continuous monitoring through wearables, emphasizing the benefits of integrating multiple signals for a comprehensive evaluation of cardiovascular health. The proposed approach holds promise for implementation in hardware systems to enable continuous monitoring, aiding in early detection and prevention of critical health conditions.

Machine learning plays a key role in present day crime detection, analysis and prediction. The goal of this work is to propose methods for predicting crimes classified into different categories of severity. We implemented visualization and analysis of crime data statistics in recent years in the city of Boston. We then carried out a comparative study between two supervised learning algorithms, which are decision tree and random forest based on the accuracy and processing time of the models to make predictions using geographical and temporal information provided by splitting the data into training and test sets. The result shows that random forest as expected gives a better result by 1.54% more accuracy in comparison to decision tree, although this comes at a cost of at least 4.37 times the time consumed in processing. The study opens doors to application of similar supervised methods in crime data analytics and other fields of data science

Recent SDN advances address traditional network management challenges through centralized control and plane separation. SDN prevents breaches using a centralized controller but introduces risks. The controller can be a single point of failure. Thus, an OpenFlow Controller's flow-based anomaly detection enhances SDN security. Our research explored two OpenFlow intrusion detection methods. The first employed machine learning, NSL-KDD dataset, and feature selection, yielding 82% accuracy with random forest. The second combined deep neural networks with GRU-LSTM, achieving 88% accuracy using ANOVA F-Test and feature elimination. Experiments highlighted deep learning as superior for OpenFlow intrusion detection.

Side-scan sonar (SSS) detection is a key method in applications such as underwater environmental security and subsea resource development. The use of acoustic images for seabed target detection has gradually become a mainstream underwater detection method. However, many existing detection approaches primarily concentrate on tracking the evolution path of optical image object detection tasks, resulting in complex structures and limited versatility. To tackle this issue, we introduce a pioneering Dual-Domain Multi-Frequency Network (D2MFNet) meticulously crafted to harness the distinct characteristics of SSS image detection. In D2MFNet, aiming at the underwater detection requirements of small scenes, we introduce a novel method for optimize and improve the detection sensitivity of different frequency ranges and propose a Multi-Frequency Combined Attention Mechanism (MFCAM). This mechanism amplifies the relevance of dual-domain features across different channels and space. Moreover, recognizing that SSS images can provide richer insights after frequency domain conversion, we introduce a Dual-Domain Feature Pyramid Network (D2FPN). By incorporating frequency domain information representation, D2FPN significantly augments the depth and breadth of feature information in underwater small datasets. Our methods are seamlessly designed for integration into existing networks, offering plug-and-play functionality with substantial performance enhancements. We have conducted extensive experiments to validate the efficacy of our proposed techniques, and the results showcase their state-of-the-art performance. MFCAM improves the mAP by 16.9% in the KLSG dataset and 15.5% in the SCTD dataset. The mAP of D2FPN was improved by 8.4% in the KLSG dataset and by 9.8% in the SCTD dataset. We will make our code and models publicly available at https://dagshub.com/estrellaww00/D2MFNet.

In order to solve the problem of feature extraction of underwater acoustic signals in complex ocean environment, a new method for feature extraction from ship radiated noise is presented based on empirical mode decomposition theory and permutation entropy. It analyzes the separability for permutation entropies of the intrinsic mode functions of three types of ship radiated noise signals, and discusses the permutation entropy of the intrinsic mode function with the highest energy. In this study, ship radiated noise signals measured from three types of ships are decomposed into a set of intrinsic mode functions with empirical mode decomposition method. Then, the permutation entropies of all intrinsic mode functions are calculated with appropriate parameters. The permutation entropies are obviously different in the intrinsic mode functions with the highest energy, thus, the permutation entropy of the intrinsic mode function with the highest energy is regarded as a new characteristic parameter to extract the feature of ship radiated noise. After that, the characteristic parameters, namely, the energy difference between high and low frequency, permutation entropy, and multi-scale permutation entropy, are compared with the permutation entropy of the intrinsic mode function with the highest energy. It is discovered that the four characteristic parameters are at the same level for similar ships, however, there are differences in the parameters for different types of ships. The results demonstrate that the permutation entropy of the intrinsic mode function with the highest energy is better in separability as the characteristic parameter than the other three parameters by comparing their fluctuation ranges and the average values of the four characteristic parameters. Hence, the feature of ship radiated noise can be extracted efficiently with the method.

A continuous Deep Belief Network (cDBN) with two hidden layers is proposed in this paper, focusing on the problem of weak feature learning ability when dealing with continuous data. In cDBN, the input data is trained in an unsupervised way by using continuous version of transfer functions, the contrastive divergence is designed in hidden layer training process to raise convergence speed, an improved dropout strategy is then implemented in unsupervised training to realize features learning by de-cooperating between the units, and then the network is fine-tuned using back propagation algorithm. Besides, hyper-parameters are analysed through stability analysis to assure the network can find the optimal. Finally, the experiments on Lorenz chaos series, CATS benchmark and other real world like CO2 and waste water parameters forecasting show that cDBN has the advantage of higher accuracy, simpler structure and faster convergence speed than other methods.

The present grievous situation of the tuberculosis disease can be improved by efficient case management and timely follow-up evaluations. With the advent of digital technology this can be achieved by quick summarization of the patient-centric data. The aim of our study was to assess the effectiveness of the ODK Scan paper-to-digital system during testing period of three months. A sequential, explanatory mixed-method research approach was employed to elucidate technology use. Training, smartphones, application and 3G enabled SIMs were provided to the four field workers. At the beginning, baseline measures of the data management aspects were recorded and compared with endline measures to see the impact of ODK Scan. Additionally, at the end, users’ feedback was collected regarding app usability, user interface design and workflow changes. 122 patients’ records were retrieved from the server and analysed for quality. It was found that ODK Scan recognized 99.2% of multiple choice bubble responses and 79.4% of numerical digit responses correctly. However, the overall quality of the digital data was decreased in comparison to manually entered data. Using ODK Scan, a significant time reduction is observed in data aggregation and data transfer activities, however, data verification and form filling activities took more time. Interviews revealed that field workers saw value in using ODK Scan, however, they were more concerned about the time consuming aspects of the use of ODK Scan. Therefore, it is concluded that minimal disturbance in the existing workflow, continuous feedback and value additions are the important considerations for the implementing organization to ensure technology adoption and workflow improvements.

The key links of face recognition are digital image preprocessing, facial feature extraction and pattern recognition, this article aimed at the current problem of slow speed and low recognition accuracy of face recognition , from the above three key links, on the basic of analyzing the therories of Fractional Differential Masks Operator (FDMO), Principal Component Analysis (PCA) and Support Vector Machine (SVM), design a kind of FDMO+PVA+SVM coupling algorithm that applies to face recognition to improve the speed and accuracy of it. To realize FDMO+PCA+SVM coupling algorithm, first, we should apply FDMO to face image processing binary marginalization, the purpose is getting face contour; Then, we apply PCA to get the feature of face image which is disposed by binary marainalization. At last, we can apply One-Against All of the SVM classifier and LibSVM software package to realize face recognition. Beside, the article with nine different coupling algorithm design four groups of experimental reaults on the ORL face database verified by comparative analysic FDMO+PCA+SVM coupling algorithm in the superiority of face recognition accuracy and speed.

Three kinds of inorganic alkali are introduced into tetraethylenepentamine (TPEA) and polyethyleneimine (PEI) modified MCM-41 as the CO2 adsorbents. FT-IR and TGA are used to characterize the surface groups and the thermal stability of adsorbents. Chemical titration method is used to measure the alkali amounts of adsorbents. Thermo-gravimetric analysis with 10%CO2/N2 as the simulated flue gas is used to test the CO2 adsorption performance of adsorbents. The results show that all three kinds of inorganic alkali containing adsorbents exhibit promoted CO2 adsorption capability than traditional TPEA and PEI modified samples. Ca(OH)2 and PEI modified samples exhibit the highest adsorption capacity and stable regeneration property. The introduction of inorganic alkali changes the chemical adsorption mechanism between CO2 and increases the effective alkali amounts due to its hydroxyl groups. The CO2 adsorption capacities have a linear dependence relation with the alkali amounts of adsorbents, indicating that alkali amount is a critical factor for novel adsorbents exploring.

Deep Learning (DL) and Machine Learning (ML) are widely used in many fields, but rarely used in Frequency Estimation (FE) and Slope Estimation (SE) of signals. Frequency and slope estimation for Frequency-Modulated (FM) and single-tone sinusoidal signals are essential in various applications, such as wireless communications, sonar, and radar measurements. In this work, artificial neural network (ANN) and convolutional neural network (CNN) are used in frequency and slope estimation for FM signals under Additive White Gaussian Noise (AWGN) and Additive Symmetric alpha Stable Noise (SαSN). SαS distributions are impulsive noise disturbances found in many communication environments like marine systems; their distribution lacks a closed-form Probability Density Function (PDF), except for specific cases, and infinite second-order statistic, hence Geometric SNR (GSNR) is used in this work to determine the impulsiveness of noise in a mixture of Gaussian and SαS noise processes. ANN is a machine learning classifier, designed with few layers for reducing FE and SE complexity while getting higher accuracy as compared with classical techniques. CNN is a deep learning classifier, designed with many layers for FE and SE, and proved to be more accurate than ANN when dealing with big data and finding optimal features. Simulation results show that SαS noise can be much more harmful for FE and SE of FM signals than Gaussian noise. DL and ML can significantly reduce FE complexity, memory cost, and power consumption, which is important in many systems such as some Internet of Things (IoT) sensor applications. After training DCNN for frequency and slope estimation of LFM signals, the performance of DCNN (in terms of accuracy) can give acceptable results at very low signal-to-noise ratios where TFD fails, giving more than 20dB difference in the GSNR working range.

Predicting nurse turnover is a growing challenge within the healthcare sector, profoundly impacting healthcare quality and the nursing profession. This study employs the Synthetic Minority Over-sampling Technique (SMOTE) to address class imbalance issues in the 2018 National Sample Survey of Registered Nurses (NSSRN) dataset and predict nurse turnover using machine learning (ML) algorithms. Four ML algorithms, namely logistic regression (LR), random forests (RF), decision tree (DT), and extreme gradient boosting (XGBoost), are applied to the SMOTE-enhanced dataset. The data is randomly split into an 80% training set and a 20% validation set. Eighteen carefully selected variables from the NSSRN database serve as predictive features, and the machine learning model identifies feature importance concerning nurse turnover. The study includes a performance comparison based on metrics such as Accuracy, Precision, Recall (Sensitivity), F1-score, and AUC. In summary, the results demonstrate that SMOTE-enhanced random forests (SMOTE_RT) exhibit the most robust predictive power, both in the classical approach (with all 18 predictive variables) and an optimized approach (utilizing eight key predictive variables). XGBoost, decision tree, and logistic regression follow in performance. Notably, age emerges as the most influential factor in nurse turnover, with working hours, EHR/EMR usability, individual income, and region also playing significant roles. This research offers valuable insights for healthcare researchers and stakeholders, aiding in selecting suitable ML algorithms for nurse turnover prediction.

Data4HumanRights training materials have been developed as open-source and tailored to limited resource settings where community data collectors often live and work. An overview of how the training material was developed together with community data collectors in Nigeria and Kenya is provided. The paper gives insights into the fundamental principles (i.e., inclusiveness, adaptive, limited resources, gender- and incentive-sensitive) and the structure of the open-access training materials. This resulted in 28 modules designed to be delivered in a face-to-face format in less than one day by a local trainer. To maximize adaptivity, the training modules can be mixed and matched (e.g., as individual modules or a learning path of several modules around a specific training need). The individual modules cover a range of methods and tools that are useful to human rights work, for example, documenting evictions, performing rapid needs assessments after acute crises, community profiling, and monitoring community development indicators. The training materials contain instructions for the facilitator(s) of the training and all necessary training materials to conduct the training. To maximize inclusivity, the training covers basic to advanced topics. Most training modules address basic training topics that can be optimally followed with a mobile phone (to avoid using a computer and printing handouts). The training was developed and implemented with local community groups in Nigeria and Kenya. The material is free to use, adapt, and translate into different contexts and languages.

This article proposes a measurement solution designed to monitor instantaneous frequency in power systems. It uses a data acquisition module and a GPS receiver for time stamping. A program in Python takes care of receiving the data, calculating the frequency, and finally transferring the measurement results to a database. The frequency is calculated with two different methods, which are compared in the article. The stored data is visualized using the Grafana platform, thus demonstrating its potential for comparing scientific data. The system as a whole constitutes an efficient low cost solution as a data acquisition system.

Natural gas hydrate, also known as combustible ice and mainly composed of methane, it is identified as the potential clean energy in the 21th century. Due to its large reserves, gas hydrate can ease problems caused by energy resource shortage and has gained attention around the world. In this paper, we focus on the exploration and development of gas hydrate as well as discussing its status and future development trend in China and abroad, then we analyze its opportunities and challenges in China from four aspects: resource, technology, economy and police with five forces model and PEST method. The results show, China has abundance gas hydrate resource; however the backward technologies and inadequate investment has seriously hindered the future development of gas hydrate, so China should establish relevant cooperation framework and intuitional arrangement to attract more investment as well as breaking through technical difficulties to make gas hydrate commercialization as soon as possible.

Transformers are increasing replacing older generation of deep neural networks due to their success in a wide range of application. The dominant approach of using transformers is to pre-train them on a large training dataset and then fine-tune them on a downstream task. However, as transformers becoming larger, the fine-tuning approach is become an infeasible approach for transfer learning. In this short survey, we list a few recent methods that makes using transformers based on transfer learning more efficient.

The monitoring of lake waterbody area in the Qinghai Tibet Plateau (QTP) is of great significance to deal with global climate change. As the latest generation of Landsat series satellites, Landsat-9 data not only have higher radiometric resolution, but also cooperate with other Landsat satellites to greatly improve the temporal resolution. It has great application potential in lake waterbody area monitoring. In order to explore the performance of different algorithms for extracting waterbody and lake waterbody area in Landsat-9 data under large-scale QTP regions, this study relies on Google Earth Engine (GEE) platform and selects 10 waterbody extraction algorithms as the basis to realize the quantitative evaluation of QTP lake waterbody area extraction results. The results show that the Random Forest (RF) algorithm performs best in all models. The overall accuracy of waterbody extraction is 95.84%, and the average error of lake waterbody area extraction is 1.505%. Among the traditional threshold segmentation waterbody extraction algorithms, the overall accuracy of the NDWI waterbody extraction method is 89.89%, and the average error of lake waterbody area extraction is 3.501%, which is the highest performance model in this kind of algorithms. This study proves that Landsat-9 data can effectively classify QTP waterbodies. With the development of cloud computing technologies such as Gee, more complex models such as RF can be selected to improve the extraction accuracy of water body and Lake area in large-scale research.

The design complexity of the new generation of civil aero-engines results in higher demands on engines’ components, higher component temperature, higher heat generation, and, finally, critical thermal management issues. This paper will propose a methodological approach to create physics-based models for heat loads developed by sources as well as a systematic sensitivity analysis to identify the effects of design parameters on the thermal behaviour of civil aero-engines. The ranges and levels of heat loads generated by heat sources (e.g., accessory gearbox, bearing, pumps, etc.) and heat absorption capacity of heat sinks (e.g., engine fuel, oil, and air) are discussed systematically. The practical research challenges for thermal management system design and development for the new and next generation of turbofan engines will then be addressed through a sensitivity analysis of the heat load values as well as the heat sinks flow rates. The potential solutions for thermal performance enhancements of propulsion systems will be proposed and discussed accordingly.

The most common source of transformer failure is in the insulation, and the most prevalent warning signal for insulation weakness is partial discharge (PD). Locating positons of these partial discharges would help repair the transformer to prevent failures. This work investigates algorithms that could be deployed to locate the position of a PD event using data from ultra-high frequency (UHF) sensors inside the transformer. These algorithms typically proceed in two steps: first determine the signal arrival time and then locate the position based on time differences. This paper reviews available methods for each task and then propose new algorithms: a convolutional iterative filter with thresholding (CIFT) to determine the signal arrival time and a reference table of travel times to resolve the source location. The effectiveness of these algorithms are tested with a set of laboratory-triggered PD events and two sets of simulated PD events inside transfers in production use. Tests show the new approach provides more accurate locations than the best-known data analysis algorithms, and the difference is particularly large, 3.7X, when the signal sources are far from sensors.

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.

Combining modern thermodynamics theory branches, including finite time thermodynamics or entropy generation minimization, constructal theory and entransy theory, with metallurgical process engineering, this paper provides a new exploration on generalized thermodynamic optimization theory for iron and steel production processes. The theoretical core is to thermodynamically optimize performances of elemental packages, working procedure modules, functional subsystems, and whole process of iron and steel production processes with real finite-resource and/or finite-size constraints with various irreversibilities toward saving energy, decreasing consumption, reducing emission and increasing yield, and to achieve the comprehensive coordination among the material flow, energy flow and environment of the hierarchical process systems. A series of application cases of the theory are reviewed. It can provide a new angle of view for the iron and steel production processes from thermodynamics, and can also provide some guidelines for other process industries.

Freezing of Gait (FOG) is an impairment that affects the majority of patients in the advanced stages of Parkinson’s Disease (PD). FOG can lead to sudden falls and injuries, negatively impacting the quality of life for the patients and their families. Rhythmic Auditory Stimulation (RAS) can be used to help patients recover from FOG and resume normal gait. RAS might be ineffective due to the latency between the start of a FOG event, it’s detection and initialization of RAS. We propose a system capable of both FOG prediction and detection using signals from tri-axial accelerometer sensors that will be useful in initializing RAS with minimal latency. We compared the performance of several time frequency analysis techniques, including moving windows extracted from the signals, handcrafted features, Recurrence Plots (RP), Short Time Fourier Transform (STFT), Discreet Wavelet Transform (DWT) and Pseudo Wigner Ville Distribution (PWVD) with Deep Learning (DL) based Long Short Term Memory (LSTM) and Convolutional Neural Networks (CNN). We also propose three Ensemble Network Architectures that combine all the time frequency representations and DL architectures. Experimental results show that our ensemble architectures significantly improve the performance compared with existing techniques. We also present the results of applying our method trained on publicly available dataset to data collected from patients using wearable sensors in collaboration with A.T. Still University.

The research of object classification and part segmentation is a hot topic in computer vision. A considerable number of studies have been carried out about deep learning on 3D point clouds. However,it is challenging to achieve effective feature learning due to sparsity of point clouds. Recently, a variety of Transformers have been adopted to improve point cloud processing and display great potential. Nevertheless, large numbers of Transformer layers tend to incur huge computational and memory costs. PointNet++ is one of the most influential neural architectures for point cloud understanding. Although the accuracy of PointNet++ has been largely surpassed by recent networks, this does not mean that PointNet++ has no potential.Thus, this paper offer two major contributions that significantly improve PointNet++ performance. Firstly, we introduce a novel contextual feature extraction (CFE) block that significantly enhances the feature extraction capabilities of PointNet++ networks. Secondly, to further enhance feature fusion, we seamlessly integrate a mutual learning (ML) block into the network architecture. By embedding these two innovative blocks within each layer of the network, we not only enrich the network's functionality but also impart it with greater robustness and adaptability. The specific experiments were conducted on the S3DIS (6-fold cross-validation) and Modelnet40 datasets with 86.5% and 92.7% accuracy, respectively, which proved that our model is comparable or even better than most existing methods for classification and segmentation tasks.

Convolutional Neural Networks (CNNs) have gained prominence in the research literature on image classification over the last decade. One shortcoming of CNNs, however, is their lack of generalizability and tendency to overfit when presented with small training sets. Augmentation directly confronts this problem by generating new data points providing additional information. In this paper, we investigate the performance of more than ten different sets of data augmentation methods, with two novel approaches proposed here: one based on the Discrete Wavelet Transform and the other on the Constant-Q Gabor transform. Pretrained ResNet50 networks are finetuned on each augmentation method. Combinations of these networks are evaluated and compared across three benchmark data sets of images representing diverse problems and collected by instruments that capture information at different scales: a virus data set, a bark data set, and a LIGO glitches data set. Experiments demonstrate the superiority of this approach. The best ensemble proposed in this work achieves state-of-the-art performance across all three data sets. This result shows that varying data augmentation is a feasible way for building an ensemble of classifiers for image classification (code available at https://github.com/LorisNanni).

Reasonable allocation of production plans and saving the overall electricity cost are crucial for large manufacturing conglomerates, which is an effective way for conglomerates to realize open-source and cost-saving. This paper develops an optimization model of off-site industrial production scheduling for enterprises in response to the problems of high electricity costs due to the irrational allocation of production schedules on the demand side of China's electric power and the difficulty of promoting industrial and commercial distributed photovoltaic (PV) projects in China. The model makes full use of the conditions of different PV resources and different electricity prices in different places to optimize the scheduling of industrial production in different places. The model is embedded with two sub-models of the electricity price prediction model and distributed photovoltaic kWh cost model to complete the model parameters, in which the electricity price prediction model utilizes the LSTM neural network. The integrated model is then solved by the particle swarm algorithm. To verify the effectiveness of the model in solving the problem of off-site production scheduling on the demand side of electricity, the research team researched two off-site pharmaceutical factories belonging to the same large pharmaceutical company. Finally, the research data were substituted into the model for solving, and it was concluded that the optimization model could significantly reduce the cost of electricity consumption of the enterprise by about 7.9 %.

Retiring coal power plants can reduce air pollution and health damages. However, the spatial distribution of those impacts remains unclear due to complex power system adjustments and pollution chemistry and transport. Focusing on coal retirements in Pennsylvania (PA), we analyze six counterfactual scenarios for 2019 that differ in retirement targets (e.g., reducing 50% of coal-based installed capacity vs. generation) and priorities (e.g., closing plants with higher cost, closer to Environmental Justice Areas, or with higher CO₂ emissions). Using a power system model of the PJM Interconnection, we find that coal retirements in PA shift power generation across PA and the Rest of PJM region leading to scenario-varying changes in the plant-level release of several air pollutants. Due to air pollution chemistry and transport and socio-demographics, these changes in turn give rise to a reduction of 10 to 182 PM_2.5-attributable deaths in PJM across the six scenarios, with most reductions occurring in PA. Scenarios that reduce more coal power generation yield greater aggregate health benefits due to air quality improvements in PA and adjacent downwind regions. In addition, vulnerable populations—in both PA and Rest of PJM—benefit most in scenarios that prioritize plant closures in PA near Environmental Justice Areas. These results demonstrate the importance of considering cross-regional linkages and socio-demographics in designing equitable retirement strategies.

The rapid industrial growth in solar energy is gaining increasing interest in renewable power from smart grids and plants. Anomaly detection in photovoltaic (PV) systems is a demanding task. In this sense, it is vital to utilize recent advances in machine learning to accurately and timely detect different anomalies and condition monitoring. This paper addresses this issue by evaluating different machine learning techniques and schemes and showing how to apply these approaches to solve anomaly detection and detect faults on photovoltaic components. For this, we apply distinct state-of-the-art machine learning techniques (AutoEncoder Long Short-Term Memory (AE-LSTM), Facebook-Prophet, and Isolation Forest) to detect faults/anomalies and evaluate their performance. These models shall identify the PV system's healthy and abnormal actual behaviors. Our results provide clear insights to make an informed decision, especially with experimental trade-offs for such complex solution space.

In recent decades, with the ever-growing scale of video data, near-duplicate videos continue to emerge. Data quality issue caused by near-duplicate videos is becoming more and more prominent, which has affected the application of normal videos. Although current studies on near-duplicate video detection can be helpful to uncover data quality issues for videos, they still lack a process of automatic merging for the video data represented by high-dimensional features, which are difficult to automatically clean the near-duplicate videos to improve data quality for video datasets. At present, there are few studies on near-duplicate video data cleaning. The existing studies have the sensitive problems of video data orderliness and clustering initial center under a condition that prior distribution is unknown, which seriously affect the accuracy of near-duplicate video data cleaning. To address the above issues, an automatic near-duplicate video data cleaning method based on a consistent feature hash ring is proposed in this paper. First, a residual network with convolutional block attention modules, a long short-term memory deep network, and an attention model are integrated to construct an RCLA deep network with the multi-headed attention mechanism to extract spatiotemporal features of video data. Then, a consistent feature hash ring is constructed, which can effectively alleviate the sensitivity of video data orderliness while providing a condition of near-duplicate video merging. To reduce the sensitivity of the initial cluster centers to results of near-duplicate video cleansing, an optimized feature distance-means clustering algorithm is constructed by utilizing a mountain peak function on a consistent feature hash ring, which can implement automatic cleaning of near-duplicate video data. Finally, experiments are conducted based on a commonly used dataset named CC_WEB_VIDEO and a coal mining video dataset. Compared with some existing works, simulation results demonstrate that the performance of the proposed method.

The application of smartphone-based color evaluation of passive sampling devices for gases has only been sparsely reported. The present review aims to compile available publications with respect to the configuration of the passive samplers, conditions of smartphone photographing, analytical procedure for color detection and quantification (including calibration processes), and their application to different target gases. The performance of the methods - whenever available - is presented regarding the analytical specifications selectivity, sensitivity, and limit of detection in comparison with other color evaluation methods of passive samplers. Practical aspects like requirements of instrumentation and ease of use will be outlined in view of the potential employment in education and citizen science projects. In one section of the review the inconsistent terminology of passive and diffusive sampling is discussed in order to clarify the distinction of information obtained from the uptake of the passive samplers between gas-phase concentration and the accumulated deposition flux of gaseous analytes. Colorimetric gas sensors are included in the review when applied in passive sampling configurations and evaluation is performed with smartphone-based color evaluation. Differences in the analytical procedures employed after the passive sampling step and prior to the detection of the colored compounds are also presented.

Disease detection and prediction have been one of the most frequent uses of machine learning models in the last decade, and Parkinson's disease is no exception. It is common for people in their old age to have one form of disease or another depending on the circumstances in which they find themselves. This study analyzed and evaluated various supervised machine learning models to detect the presence of Parkinson's disease in elderly individuals. An extreme gradient boosting model, along with other models, such as naïve Bayes, random forest, K-nearest neighbor, and support vector machine (SVM), was implemented to determine the best outcome. The extreme gradient boosting (XGBoost) model is a powerful boosting machine learning technique, particularly in terms of speed and accuracy. The results showed that the XGBoost model, which is an optimized version of the other boosting models, is capable of projecting the presence of Parkinson's disease with very high accuracy compared to other algorithms. The implemented classification algorithm extreme gradient boosting method achieved approximately 98 % accuracy, 97.5 % precision, 100.0 % recall, and 98.7% f1-score which are high compared with the results found in the existing literature.

This study investigates the application of frequency augmentation techniques to improve condition-based maintenance (CBM+) systems for airborne weapon systems, focusing on the predictive accuracy of velocity and acceleration parameters. Utilizing MIL-STD-1553B MUX data from 138 sorties of fixed-wing aircraft, we explored six augmentation methods, including traditional interpolations (linear, quadratic, cubic spline) and advanced machine learning models (K-Nearest Neighbor, LSTM, and Bi-LSTM). Our findings indicate that while traditional methods like linear interpolation are more effective for velocity parameters, advanced ML techniques, particularly Bi-LSTM, provide better results for acceleration parameters, which exhibit more complex and rapid variability. The study underscores the necessity of tailoring augmentation approaches to specific parameter characteristics and highlights the potential of ML models in capturing intricate patterns within time-series data. These insights are critical for advancing CBM+ systems in military avionics, enhancing reliability and operational efficiency through improved data processing strategies. Future work should explore more performant augmentation techniques, such as by integrating multi-dimensional datasets, and explore ways to develop automated tools for a more powerful predictive maintenance framework.

Natural polluted insulator surfaces are always coated with various kinds of soluble constituents, and those constituents affect flashover performance differentially. Currently this fact is not considered either in laboratory experiments or field pollution degree measurements, causing the existing insulation selection method to be deficient. In this paper a systematical research on insulator flashover voltage gradient correction involving types of soluble pollution constituents was presented. Taking typical type glass insulator as the sample, its flashover tests polluted by typical soluble chemicals NaCl, NaNO₃, KNO₃, NH₄NO₃, MgSO₄, Ca(NO₃)₂ and CaSO₄ were carried out. Then the flashover gradient correction was made combining the flashover performance of each soluble constituent, the ESDD contribution of the seven constituents, as well as the saturation performance of CaSO₄. The correction was well verified with the flashover test results of insulator polluted by three types of soluble mixture. Research results indicate that the flashover gradient correction method proposed by this paper performs well in reducing the calculating error. It is recommended to carry out component measurements and flashover gradient correction to better select outdoor insulation configuration.

Satellite imagery has had limited application in the analysis of pre-colonial settlement archaeology in the Caribbean; visible evidence of wooden structures perishes quickly in tropical climates. Only slight topographic modifications remain, typically associated with middens. Nonetheless, surface scatters, as well as the soil characteristics they produce, can serve as quantifiable indicators of an archaeological site, which can be detected by analysis of remote sensing imagery. A variety of data sets were investigated, with the intention to combine multispectral bands to feed a direct detection algorithm, providing a semi-automatic process to cross-correlate the datasets. Sampling was done using locations of known sites, as well as areas with no archaeological evidence. The pre-processed very diverse remote sensing data sets have gone through a process of image registration. The algorithm was applied in the northwestern Dominican Republic on areas that included different types of environments, chosen for having sufficient imagery coverage, and a representative number of known locations of indigenous sites. The resulting maps present quantifiable statistical results of locations with similar pixel value combinations as the identified sites, indicating higher probability of archaeological evidence. The results show the variable potential of this method in diverse environments.

The need for Artificial Intelligence (AI) and Machine Learning (ML) technologies is increasingly being leveraged for optimizing Data centers’ (DCs’) operations as the volume of operations management data increase tremendously. These strategies can assist operators in better understanding their DC operations and making informed decisions up front to preserve service reliability and availability. Aiming at creating models that optimize energy efficiency, identify inefficient resource utilization and scheduling policies, and predict outages. Apart from model hyperparameter tuning, feature selection is a crucial step to identify relevant features with the objective of providing insight into the data, improving performance, and reducing computational expenses. Although several feature selection methods have been discussed in various domains, none have been discussed in the context of the data center. This paper introduces SHapley Additive exPlanation (SHAP), a class of additive feature attribution values-based feature selection that is rarely discussed in literature. We compared the effectiveness of SHAP method with several widely used methods. We used a real DC dataset obtained from the ENEA CRESCO6 cluster with 2,0832 cores to evaluate the methods. To demonstrate the comparison of the methods, we picked the top 10 most important features from each method, the predictions were retrained, and their performance was evaluated using MAE, RMSE, and MPAE. The results show that the SHAP-assisted feature selection performed best and align with human intuition.

Analysis of land use/land cover (LULC) in the catchment areas is the first action toward safeguarding the freshwater resources. The LULC information in the watershed has gained popularity in the natural science field as it helps water resource managers and environmental health specialists develop natural resource conservation strategies based on available quantitative information. Thus, remote sensing is the cornerstone in addressing environmental-related issues at the catchment level. In this study, the performance of four machine learning algorithms (MLAs), such as Random Forests (RF), Support Vector Machine (SVM), Artificial Neural Networks (ANN), and Naïve Bayes (NB) was investigated to classify the catchment into nine relevant classes of the undulating watershed landscape using Landsat 8 Operational Land Imager (L8-OLI) imagery. The assessment of the MLAs were based on the visual inspection of the analyst and the commonly used assessment metrics, such as user’s accuracy (UA), producers’ accuracy (PA), overall accuracy (OA), and kappa coefficient. The MLAs produced good results, where RF (OA= 97.02%, Kappa= 0.96), SVM (OA= 89.74 %, Kappa= 0.88), ANN (OA= 87%, Kappa= 0.86), and NB (OA= 68.64 Kappa= 0.58). The results show the outstanding performance of the RF model over SVM and ANN with a small margin. While NB yielded satisfactory results, which could be primarily influenced by its sensitivity to limited training samples. In contrast, the robust performance of RF could be due to an ability to classify high-dimensional data with limited training data.

Pipeline integrity is an important area of concern for the oil and gas, refining, chemical, hydrogen, carbon sequestration, and electric-power industries, due to the safety risks associated with pipeline failures. Regular monitoring, inspection, and maintenance of these facilities is therefore required for safe operation. Large standoff magnetometry (LSM) is a non-intrusive, passive magnetometer-based mea- surement technology that has shown promise in detecting defects (anomalies) in regions of elevated mechanical stresses. However, analyzing the noisy multi-sensor LSM data to clearly identify regions of anomalies is a significant challenge. This is mainly due to the high frequency of the data collection, mis-alignment between consecutive inspections and sensors, as well as the number of sensor measurements recorded. In this paper we present LSM defect identification approach based on ma- chine learning (ML). We show that this ML approach is able to successfully detect anomalous readings using a series of methods with increasing model complexity and capacity. The methods start from unsupervised learning with "point" methods and eventually increase complexity to supervised learning with sequence methods and multi-output predictions. We observe data leakage issues for some methods with randomized train/test splitting and resolve them by specific non-randomized splitting of training and validation data. We also achieve a 200x acceleration of support-vector classifier (SVC) method by porting computations from CPU to GPU leveraging the cuML RAPIDS AI library. For sequence methods, we develop a customized Convolutional Neural Network (CNN) architecture based on 1D convolutional filters to identify and characterize multiple properties of these defects. In the end, we report the scalability of the best-performing methods and compare them, for viability in field trials.

Scientists and astronomers have attached Scientists and astronomers have attached great importance to the task of discovering new exoplanets, even more so if they are in the habitable zone. To date, more than 4300 exoplanets have been confirmed by NASA, using various discovery techniques, including planetary transits, in addition to the use of various databases provided by space and ground-based telescopes. This article proposes the development of a deep learning system for detecting planetary transits in Kepler Telescope lightcurves. The approach is based on related work from the literature and enhanced to validation with real lightcurves. A CNN classification model is trained from a mixture of real and synthetic data, and validated only with real data and different from those used in the training stage. The best ratio of synthetic data is determined by the perform of an optimisation technique and a sensitivity analysis. The precision, accuracy and true positive rate of the best model obtained are determined and compared with other similar works. The results demonstrate that the use of synthetic data on the training stage can improve the transit detection performance on real light curves.

Accurate forecasting of icing thickness has a great significance for ensuring the security and stability of power grid. In order to improve the forecasting accuracy, this paper proposes an icing forecasting system based on fireworks algorithm and weighted least square support vector machine (W-LSSVM). The method of fireworks algorithm is employed to select the proper input features with the purpose of eliminating the redundant influence. In addition, the aim of W-LSSVM model is to train and test the historical data-set with the selected features. The capability of this proposed icing forecasting model and framework is tested through the simulation experiments using real-world icing data from monitoring center of key laboratory of anti-ice disaster, Hunan, South China. The results show that the proposed W-LSSVM-FA method has a higher prediction accuracy and it may be a promising alternative for icing thickness forecasting.

In this paper, we first discuss the research status and application progress of the finite element method and the smoothed particle method. By analyzing the advantages of the smoothed particle method and the finite element method, a new coupling algorithm, namely FEM-SPH algorithm, is proposed. By the method of comparison, it shows that finite element method and SPH method in the simulation of large deformation problems each have advantages and disadvantages, the finite element method smoothed particle coupling algorithm is effective to achieve the performance of high computational efficiency and can naturally simulate large deformation problems across. In the process of calculation, the large deformation unit can be freely into an algorithm to facilitate the calculation accuracy and efficiency of three methods of numerical simulation. Through the study found, FEM-SPH algorithm not only overcome the defect of smooth particle tensile instability, but also overcomes the problem of low efficiency of finite element computation. To further test the FEM-SPH algorithm has advantages in the practical engineering, we have carried out the actual test to the example of the super high speed collision, concluded that, since the target of most of the computational domain is always finite element, smoothed particle focused only in contact with the projectile and target of local area, particle number is not much, the whole calculation process just ten minutes, computational efficiency has been greatly improved, at the same time in the simulation of large deformation, the advantage is very obvious .This provides a criterion for the actual project, depending on the specific material deformation mode and choose a more appropriate conversion algorithm.

Electric Transformers make up some of the most critical components of a power system. Their reliable operation is critical for an efficient power grid as well as economic viability for the transformer operators and owners. Power transformers, like other High Voltage (HV) electrical equipment experience aging and insulation degradation due to chemical, mechanical and electrical forces during their operation. Partial Dischargers (PD) are localized electrical discharges that develop within insulation systems of HV electrical equipment such as transformers. In transformers, PD occurs in different forms and various locations and insulation both internal and external of the transformer. PD originates as small pulses but tends to increase in size and intensity which can result in complete insulation failure. Monitoring partial discharges has proven to provide valuable information on the state of the insulation systems of the power transformer, allowing transformer operators to make calculated decisions for the maintenance and life of plant plans. This systematic literature review aims to systematically examine the use of machine learning techniques in classifying PD in transformers to present a complete indicator to allow for future research in the field. The systematic review surveyed a total of 81 research literature published from 2010 to 2023 that fulfilled a specific methodology which was developed as part of this study. The results revealed that supervised learning has been the most widely used Artificial Intelligence (AI) algorithm utilized, primarily in the form of Support Vector Machine (SVM). Regarding PD, the survey revealed that most researchers tend to use numerous types of PD and compare them to one another. Furthermore, the use of artificial PD defect models to simulate the occurrence of PD is widely used versus the use of actual power transformers. Most of the literature tends to not specify the physical characteristics of PD, such as the magnitude of PD, PD inception voltage and PD extinction voltage.

Since large power transformers are custom-made, and their design process is a labor-intensive task, their design process is split into different parts. In tendering, the price calculation is based on the preliminary design of the transformer. Due to the complexity of this task, it belongs to the most general branch of discrete, non-linear mathematical optimization problems. Most of the published algorithms are using a copper filling factor based winding model to calculate the main dimensions of the transformer during this first, preliminary design step. Therefore, these cost optimization methods are not considering the detailed winding layout and the conductor dimensions. However, the knowledge of the exact conductor dimensions is essential to calculate the thermal behaviour of the windings and make a more accurate stray loss calculation. The paper presents a novel, evolutionary algorithm-based transformer optimization method which can determine the optimal conductor shape for the windings during this examined preliminary design stage. The accuracy of the presented FEM method was tested on an existing transformer design. Then the results of the proposed optimization method have been compared with a validated transformer design optimization algorithm.

Pipeline conflicts arising from data dependencies are a common issue encountered in the hardware implementation of layered QC-LDPC decoders. This paper proposes an efficient layered decoding architecture to reduce pipeline conflicts without introducing stall cycles, by reordering the processing order offline and using the patch method based on variable-to-check message. The experimental results on the LDPC code of the IEEE802.16 standard in the OFDM-PON system demonstrate that the proposed architecture has a sensitivity improvement of 0.125 dBm and 0.375 dBm, respectively, compared with our previous work and the method described in the other work.

: The effects of the main parameters on the air entrainment rate, Qa, were investigated experimentally in a confined plunging liquid jet reactor CPLJR. Various downcomer diameters (Dc), jet lengths (Lj), liquid volumetric flow rates (Qj), nozzle diameters (dn), and jet velocity (Vj) were used to measure air entrainment, Qa. The non-linear relationship between the air entrainment ratio and confined plunging jet reactor parameters suggests that applying unconventional regression algorithms to predict the air entrainment ratio is appropriate. This study applied machine learning algorithms to the confined plunging jet reactor parameters to predict Qa. The obtained results showed that K-Nearest Neighbour (KNN) gave the best prediction abilities, R2 = 0.900, RMSE = 0.069, and MAE = 0.052. The sensitivity analysis was applied to determine the most effective predictor. The liquid volumetric flow rate (Qj) and jet velocity (Vj) were the most influential among all the input variables. Our findings support using machine learning algorithms to accurately forecast the CPLJR system’s experimental results.

Single-phase-to-ground fault in non-effectively grounded systems poses serious public safety concern. Along with increasing deployment of low-voltage (LV) sensors, new opportunities and ways are created for solving this traditional problem in distribution systems. A new approach, identifying primary single-phase-to-ground line fault and locating it through measurement data from smart sensors deployed in the secondary side of distribution transformers, is proposed in this paper. When a fault occurs in primary distribution feeder, the transient aerial mode voltage (AMV) of each LV smart sensor is calculated. The fault line can be identified by an abrupt change value of AMV at LV side. Next, by finding the position of the maximum value of this AMV from LV sensors on the fault line, the fault location can be pinpointed to two neighboring distribution transformers. The proposed method has been proven to be efficient and reliable by simulation studies.

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.