Human action recognition has become one of the most active research topics in human-computer interaction and artificial intelligence, and has attracted much attention. Here, we employ a low-cost optical sensor Kinect ...Human action recognition has become one of the most active research topics in human-computer interaction and artificial intelligence, and has attracted much attention. Here, we employ a low-cost optical sensor Kinect to capture the action information of the human skeleton. We then propose a two-level hierarchical human action recognition model with self-selection classifiers via skeleton data. Especially different optimal classifiers are selected by probability voting mechanism and 10 times 10-fold cross validation at different coarse grained levels. Extensive simulations on a well-known open dataset and results demonstrate that our proposed method is efficient in human action recognition, achieving 94.19%the average recognition rate and 95.61% the best rate.展开更多
Background:In the field of genetic diagnostics,DNA sequencing is an important tool because the depth and complexity of this field have major implications in light of the genetic architectures of diseases and the ident...Background:In the field of genetic diagnostics,DNA sequencing is an important tool because the depth and complexity of this field have major implications in light of the genetic architectures of diseases and the identification of risk factors associated with genetic disorders.Methods:Our study introduces a novel two-tiered analytical framework to raise the precision and reliability of genetic data interpretation.It is initiated by extracting and analyzing salient features from DNA sequences through a CNN-based feature analysis,taking advantage of the power inherent in Convolutional neural networks(CNNs)to attain complex patterns and minute mutations in genetic data.This study embraces an elite collection of machine learning classifiers interweaved through a stern voting mechanism,which synergistically joins the predictions made from multiple classifiers to generate comprehensive and well-balanced interpretations of the genetic data.Results:This state-of-the-art method was further tested by carrying out an empirical analysis on a variants'dataset of DNA sequences taken from patients affected by breast cancer,juxtaposed with a control group composed of healthy people.Thus,the integration of CNNs with a voting-based ensemble of classifiers returned outstanding outcomes,with performance metrics accuracy,precision,recall,and F1-scorereaching the outstanding rate of 0.88,outperforming previous models.Conclusions:This dual accomplishment underlines the transformative potential that integrating deep learning techniques with ensemble machine learning might provide in real added value for further genetic diagnostics and prognostics.These results from this study set a new benchmark in the accuracy of disease diagnosis through DNA sequencing and promise future studies on improved personalized medicine and healthcare approaches with precise genetic information.展开更多
Cross entropy is a measure in machine learning and deep learning that assesses the difference between predicted and actual probability distributions. In this study, we propose cross entropy as a performance evaluation...Cross entropy is a measure in machine learning and deep learning that assesses the difference between predicted and actual probability distributions. In this study, we propose cross entropy as a performance evaluation metric for image classifier models and apply it to the CT image classification of lung cancer. A convolutional neural network is employed as the deep neural network (DNN) image classifier, with the residual network (ResNet) 50 chosen as the DNN archi-tecture. The image data used comprise a lung CT image set. Two classification models are built from datasets with varying amounts of data, and lung cancer is categorized into four classes using 10-fold cross-validation. Furthermore, we employ t-distributed stochastic neighbor embedding to visually explain the data distribution after classification. Experimental results demonstrate that cross en-tropy is a highly useful metric for evaluating the reliability of image classifier models. It is noted that for a more comprehensive evaluation of model perfor-mance, combining with other evaluation metrics is considered essential. .展开更多
This article employs a combined approach of biology and economics to reveal that biological evolution has an economic nature, evolving towards improved energy efficiency. The orthodox Darwinian theory of evolution des...This article employs a combined approach of biology and economics to reveal that biological evolution has an economic nature, evolving towards improved energy efficiency. The orthodox Darwinian theory of evolution describes evolution as the random variation of organisms and their survival through natural selection. In fact, the natural environment itself is a constantly changing context, and the strategy to adapt to this change is to enhance behavioral capabilities, thereby expanding the range and dimensions of behavior. Therefore, the improvement of behavioral capabilities is an important aspect of evolution. The enhancement of behavioral capabilities expands the range of adaptation to the natural environment and increases the space for behavioral choices. Within this space of behavioral choices, some options are more effective and superior to others;thus, the ability to select is necessary to make the improved behavioral capabilities more beneficial to the organism itself. The birth and development of the brain serve the purpose of selection. By using the brain to make selections, at least the “better” behavior will be chosen between two alternatives. Once the better behavior yields better results, and the organism can associate these results with the corresponding behavior, it will persist in this behavior. The persistent repetition of a behavior over generations will form a habit. Habits passed down through generations constitute a new environment, causing the organism’s genes to activate or deactivate certain functions, ultimately leading to genetic changes that are beneficial to that habit. Since the brain’s selection represents the organism’s self-selection, it differs from random variation;it is also a rational selection, choosing behaviors that either obtain more energy or reduce energy consumption. Thus, this evolution possesses an economic nature.展开更多
Malware attacks on Windows machines pose significant cybersecurity threats,necessitating effective detection and prevention mechanisms.Supervised machine learning classifiers have emerged as promising tools for malwar...Malware attacks on Windows machines pose significant cybersecurity threats,necessitating effective detection and prevention mechanisms.Supervised machine learning classifiers have emerged as promising tools for malware detection.However,there remains a need for comprehensive studies that compare the performance of different classifiers specifically for Windows malware detection.Addressing this gap can provide valuable insights for enhancing cybersecurity strategies.While numerous studies have explored malware detection using machine learning techniques,there is a lack of systematic comparison of supervised classifiers for Windows malware detection.Understanding the relative effectiveness of these classifiers can inform the selection of optimal detection methods and improve overall security measures.This study aims to bridge the research gap by conducting a comparative analysis of supervised machine learning classifiers for detecting malware on Windows systems.The objectives include Investigating the performance of various classifiers,such as Gaussian Naïve Bayes,K Nearest Neighbors(KNN),Stochastic Gradient Descent Classifier(SGDC),and Decision Tree,in detecting Windows malware.Evaluating the accuracy,efficiency,and suitability of each classifier for real-world malware detection scenarios.Identifying the strengths and limitations of different classifiers to provide insights for cybersecurity practitioners and researchers.Offering recommendations for selecting the most effective classifier for Windows malware detection based on empirical evidence.The study employs a structured methodology consisting of several phases:exploratory data analysis,data preprocessing,model training,and evaluation.Exploratory data analysis involves understanding the dataset’s characteristics and identifying preprocessing requirements.Data preprocessing includes cleaning,feature encoding,dimensionality reduction,and optimization to prepare the data for training.Model training utilizes various supervised classifiers,and their performance is evaluated using metrics such as accuracy,precision,recall,and F1 score.The study’s outcomes comprise a comparative analysis of supervised machine learning classifiers for Windows malware detection.Results reveal the effectiveness and efficiency of each classifier in detecting different types of malware.Additionally,insights into their strengths and limitations provide practical guidance for enhancing cybersecurity defenses.Overall,this research contributes to advancing malware detection techniques and bolstering the security posture of Windows systems against evolving cyber threats.展开更多
Driven by both the“new engineering”initiative and the energy revolution,the traditional engineering education model can hardly meet the demand of the energy and electric power industry for diversified and interdisci...Driven by both the“new engineering”initiative and the energy revolution,the traditional engineering education model can hardly meet the demand of the energy and electric power industry for diversified and interdisciplinary outstanding engineers.Based on the“industry-university-research-application”four-in-one collaborative education concept,this paper constructs a new training system centered on classified cultivation and classified evaluation.The system aims to solve core problems such as homogeneous training,disconnection between industry and academia,single evaluation method,and insufficient faculty.Through measures including modular courses,the dual-tutor system,and diversified practical platforms,it realizes differentiated and precise talent training,so as to deliver outstanding engineers with the ability to“define problems,break through technologies,and create value”for the energy and electric power industry.展开更多
Human Activity Recognition(HAR)in drone-captured videos has become popular because of the interest in various fields such as video surveillance,sports analysis,and human-robot interaction.However,recognizing actions f...Human Activity Recognition(HAR)in drone-captured videos has become popular because of the interest in various fields such as video surveillance,sports analysis,and human-robot interaction.However,recognizing actions from such videos poses the following challenges:variations of human motion,the complexity of backdrops,motion blurs,occlusions,and restricted camera angles.This research presents a human activity recognition system to address these challenges by working with drones’red-green-blue(RGB)videos.The first step in the proposed system involves partitioning videos into frames and then using bilateral filtering to improve the quality of object foregrounds while reducing background interference before converting from RGB to grayscale images.The YOLO(You Only Look Once)algorithm detects and extracts humans from each frame,obtaining their skeletons for further processing.The joint angles,displacement and velocity,histogram of oriented gradients(HOG),3D points,and geodesic Distance are included.These features are optimized using Quadratic Discriminant Analysis(QDA)and utilized in a Neuro-Fuzzy Classifier(NFC)for activity classification.Real-world evaluations on the Drone-Action,Unmanned Aerial Vehicle(UAV)-Gesture,and Okutama-Action datasets substantiate the proposed system’s superiority in accuracy rates over existing methods.In particular,the system obtains recognition rates of 93%for drone action,97%for UAV gestures,and 81%for Okutama-action,demonstrating the system’s reliability and ability to learn human activity from drone videos.展开更多
The categorization of brain tumors is a significant issue for healthcare applications.Perfect and timely identification of brain tumors is important for employing an effective treatment of this disease.Brain tumors po...The categorization of brain tumors is a significant issue for healthcare applications.Perfect and timely identification of brain tumors is important for employing an effective treatment of this disease.Brain tumors possess high changes in terms of size,shape,and amount,and hence the classification process acts as a more difficult research problem.This paper suggests a deep learning model using the magnetic resonance imaging technique that overcomes the limitations associated with the existing classification methods.The effectiveness of the suggested method depends on the coyote optimization algorithm,also known as the LOBO algorithm,which optimizes the weights of the deep-convolutional neural network classifier.The accuracy,sensitivity,and specificity indices,which are obtained to be 92.40%,94.15%,and 91.92%,respectively,are used to validate the effectiveness of the suggested method.The result suggests that the suggested strategy is superior for effectively classifying brain tumors.展开更多
The increasing risk of ground pressure disasters resulting from deep well mining highlights the urgent need for advanced monitoring and early warning systems.Ground pressure monitoring,supported by microseismic techno...The increasing risk of ground pressure disasters resulting from deep well mining highlights the urgent need for advanced monitoring and early warning systems.Ground pressure monitoring,supported by microseismic technology,plays a pivotal role in ensuring mine safety by enabling real-time identifi cation and accurate classification of vibration signals such as microseismic signals,blasting signals,and noise.These classifications are critical for improving the efficacy of ground pressure monitoring systems,conducting stability analyses of deep rock masses,and implementing timely and precise roadway support measures.Such eff orts are essential for mitigating ground pressure disasters and ensuring safe mining operations.This study proposes an artificial intelligence-based automatic classification network model for mine vibration signals.Based on conventional convolutional neural networks,the proposed model further incorporates long short-term memory(LSTM)networks and attention mechanisms.The LSTM component eff ectively captures temporal correlations in time-series mining vibration data,while the attention mechanism enhances the models’ability to focus on critical features within the data.To validate the eff ectiveness of our proposed model,a dataset comprising 480,526 waveform records collected in 2022 by the microseismic monitoring system at Guangxi Shanhu Tungsten Mine was used for training,validation,and testing purposes.Results demonstrate that the proposed artifi cial intelligence-based classifi cation method achieves a higher recognition accuracy of 92.21%,significantly outperforming traditional manual classification methods.The proposed model represents a signifi cant advancement in ground pressure monitoring and disaster mitigation.展开更多
Machine learning techniques and a dataset of five wells from the Rawat oilfield in Sudan containing 93,925 samples per feature(seven well logs and one facies log) were used to classify four facies. Data preprocessing ...Machine learning techniques and a dataset of five wells from the Rawat oilfield in Sudan containing 93,925 samples per feature(seven well logs and one facies log) were used to classify four facies. Data preprocessing and preparation involve two processes: data cleaning and feature scaling. Several machine learning algorithms, including Linear Regression(LR), Decision Tree(DT), Support Vector Machine(SVM),Random Forest(RF), and Gradient Boosting(GB) for classification, were tested using different iterations and various combinations of features and parameters. The support vector radial kernel training model achieved an accuracy of 72.49% without grid search and 64.02% with grid search, while the blind-well test scores were 71.01% and 69.67%, respectively. The Decision Tree(DT) Hyperparameter Optimization model showed an accuracy of 64.15% for training and 67.45% for testing. In comparison, the Decision Tree coupled with grid search yielded better results, with a training score of 69.91% and a testing score of67.89%. The model's validation was carried out using the blind well validation approach, which achieved an accuracy of 69.81%. Three algorithms were used to generate the gradient-boosting model. During training, the Gradient Boosting classifier achieved an accuracy score of 71.57%, and during testing, it achieved 69.89%. The Grid Search model achieved a higher accuracy score of 72.14% during testing. The Extreme Gradient Boosting model had the lowest accuracy score, with only 66.13% for training and66.12% for testing. For validation, the Gradient Boosting(GB) classifier model achieved an accuracy score of 75.41% on the blind well test, while the Gradient Boosting with Grid Search achieved an accuracy score of 71.36%. The Enhanced Random Forest and Random Forest with Bagging algorithms were the most effective, with validation accuracies of 78.30% and 79.18%, respectively. However, the Random Forest and Random Forest with Grid Search models displayed significant variance between their training and testing scores, indicating the potential for overfitting. Random Forest(RF) and Gradient Boosting(GB) are highly effective for facies classification because they handle complex relationships and provide high predictive accuracy. The choice between the two depends on specific project requirements, including interpretability, computational resources, and data nature.展开更多
To improve the performance of the multiple classifier system, a new method of feature-decision level fusion is proposed based on knowledge discovery. In the new method, the base classifiers operate on different featur...To improve the performance of the multiple classifier system, a new method of feature-decision level fusion is proposed based on knowledge discovery. In the new method, the base classifiers operate on different feature spaces and their types depend on different measures of between-class separability. The uncertainty measures corresponding to each output of each base classifier are induced from the established decision tables （DTs） in the form of mass function in the Dempster-Shafer theory （DST）. Furthermore, an effective fusion framework is built at the feature-decision level on the basis of a generalized rough set model and the DST. The experiment for the classification of hyperspectral remote sensing images shows that the performance of the classification can be improved by the proposed method compared with that of plurality voting （PV）.展开更多
The turbo air classifier is widely used powder classification equipment in a variety of fields. The flow field characteristics of the turbo air classifier are important basis for the improvement of the turbo air class...The turbo air classifier is widely used powder classification equipment in a variety of fields. The flow field characteristics of the turbo air classifier are important basis for the improvement of the turbo air classifier＇s structural design. The flow field characteristics of the rotor cage in turbo air classifiers were investigated trader different operating conditions by laser Doppler velocimeter（LDV）, and a measure diminishing the axial velocity is proposed. The investigation results show that the tangential velocity of the air flow inside the rotor cage is different from the rotary speed of the rotor cage on the same measurement point due to the influences of both the negative pressure at the exit and the rotation of the rotor cage. The tangential velocity of the air flow likewise decreases as the radius decreases in the case of the rotor cage＇s low rotary speed. In contrast, the tangential velocity of the air flow increases as the radius decreases in the case of the rotor cage＇s high rotary speed. Meanwhile, the vortex inside the rotor cage is found to occur near the pressure side of the blade when the rotor cage＇s rotary speed is less than the tangential velocity of air flow. On the contrary, the vortex is found to occur near the blade suction side once the rotor cage＇s rotary speed is higher than the tangential velocity of air flow. Inside the rotor cage, the axial velocity could not be disregarded and is largely determined by the distances between the measurement point and the exit.展开更多
Predicting stock price movements is a challenging task for academicians and practitioners. In particular, forecasting price movements in emerging markets seems to be more elusive because they are usually more volatile...Predicting stock price movements is a challenging task for academicians and practitioners. In particular, forecasting price movements in emerging markets seems to be more elusive because they are usually more volatile often accompa-nied by thin trading-volumes and they are susceptible to more manipulation compared to mature markets. Technical analysis of stocks and commodities has become a science on its own;quantitative methods and techniques have been applied by many practitioners to forecast price movements. Lagging and sometimes leading technical indicators pro-vide rich quantitative tools for traders and investors in their attempt to gain advantage when making investment or trading decisions. Artificial Neural Networks (ANN) have been used widely in predicting stock prices because of their capability in capturing the non-linearity that often exists in price movements. Recently, Polynomial Classifiers (PC) have been applied to various recognition and classification application and showed favorable results in terms of recog-nition rates and computational complexity as compared to ANN. In this paper, we present two prediction models for predicting securities’ prices. The first model was developed using back propagation feed forward neural networks. The second model was developed using polynomial classifiers (PC), as a first time application for PC to be used in stock prices prediction. The inputs to both models were identical, and both models were trained and tested on the same data. The study was conducted on Dubai Financial Market as an emerging market and applied to two of the market’s leading stocks. In general, both models achieved very good results in terms of mean absolute error percentage. Both models show an average error around 1.5% predicting the next day price, an average error of 2.5% when predicting second day price, and an average error of 4% when predicted the third day price.展开更多
The classification performance of model coal mill classifiers with different bottom incoming flow inlets was experimentally and numerically studied.The flow field adjacent to two neighboring impeller blades was measur...The classification performance of model coal mill classifiers with different bottom incoming flow inlets was experimentally and numerically studied.The flow field adjacent to two neighboring impeller blades was measured using the particle image velocimetry technique.The results showed that the flow field adjacent to two neighboring blades with the swirling inlet was significantly different from that with the non-swirling inlet.With the swirling inlet,there was a vortex located between two neighboring blades,while with the nonswirling inlet,the vortex was attached to the blade tip.The vorticity of the vortex with the non-swirling inlet was much lower than that with the swirling inlet.The classifier with the non-swirling inlet demonstrated a larger cut size than that with the swirling inlet when the impeller was stationary(~0 r·min-1).As the impeller rotational speed increased,the cut size of the cases with non-swirling and swirling inlets both decreased,and the one with the non-swirling inlet decreased more dramatically.The values of the cut size of the two classifiers were close to each other at a high impeller rotational speed(≥120 r·min-1).The overall separation efficiency of the classifier with the non-swirling inlet was lower than that with the swirling inlet,and monotonically increased as the impeller rotational speed increased.With the swirling inlet,the overall separation efficiency first increased with the impeller rotational speed and then decreased when the rotational speed was above 120 r·min-1,and the variation trend of the separation efficiency was more moderate.As the initial particle concentration increased,the cut sizes of both swirling and non-swirling inlet cases decreased first and then barely changed.At a low initial particle concentration(b 0.04 kg·m-3),the classifier with the swirling inlet had a larger cut size than that with the non-swirling inlet.展开更多
This study investigated the efficiency of learning the Chinese numeral classifiers by L2 Chinese learners by means of an alignment-oriented task. Participants were a total of 96 intermediate learners of L2 Chinese, wh...This study investigated the efficiency of learning the Chinese numeral classifiers by L2 Chinese learners by means of an alignment-oriented task. Participants were a total of 96 intermediate learners of L2 Chinese, who were randomly assigned to two experimental groups and one control group, with each group consisting of 32 participants. The continuation task used in this study consisted of a picture-based Chinese text depicting a room with an array of objects, which necessitates the use of classifiers. The two experimental groups were both required to first read the text and then write to describe their own rooms in comparison with the one in the text. One group was instructed to use the classifiers from the text as much as possible in their writing, whereas the other was not required to do so. Participants in the control group were first given the picture to look at in the absence of the text and then asked to describe their own rooms. The results showed that the continuation task significantly enhanced participants’ retention of the Chinese numeral classifiers, suggesting that the alignment-based approach is an effective way to learn difficult linguistic categories such as the Chinese classifiers.展开更多
Fuel injectors are considered as an important component of combustion engines. Operational weakness can possibly lead to the complete machine malfunction, decreasing reliability and leading to loss of production. To o...Fuel injectors are considered as an important component of combustion engines. Operational weakness can possibly lead to the complete machine malfunction, decreasing reliability and leading to loss of production. To overcome these circumstances, various condition monitoring techniques can be applied. The application of acoustic signals is common in the field of fault diagnosis of rotating machinery. Advanced signal processing is utilized for the construction of features that are specialized in detecting fuel injector faults. A performance comparison between novelty detection algorithms in the form of one-class classifiers is presented. The one-class classifiers that were tested included One-Class Support Vector Machine (OCSVM) and One-Class Self Organizing Map (OCSOM). The acoustic signals of fuel injectors in different operational conditions were processed for feature extraction. Features from all the signals were used as input to the one-class classifiers. The one-class classifiers were trained only with healthy fuel injector conditions and compared with new experimental data which belonged to different operational conditions that were not included in the training set so as to contribute to generalization. The results present the effectiveness of one-class classifiers for detecting faults in fuel injectors.展开更多
The methods for combining multiple classifiers based on belief functions require to work with a common and complete(closed)Frame of Discernment(Fo D)on which the belief functions are defined before making their combin...The methods for combining multiple classifiers based on belief functions require to work with a common and complete(closed)Frame of Discernment(Fo D)on which the belief functions are defined before making their combination.This theoretical requirement is however difficult to satisfy in practice because some abnormal(or unknown)objects that do not belong to any predefined class of the Fo D can appear in real classification applications.The classifiers learnt using different attributes information can provide complementary knowledge which is very useful for making the classification but they are usually based on different Fo Ds.In order to clearly identify the specific class of the abnormal objects,we propose a new method for combination of classifiers working with incomplete frames of discernment,named CCIF for short.This is a progressive detection method that select and add the detected abnormal objects to the training data set.Because one pattern can be considered as an abnormal object by one classifier and be committed to a specific class by another one,a weighted evidence combination method is proposed to fuse the classification results of multiple classifiers.This new method offers the advantage to make a refined classification of abnormal objects,and to improve the classification accuracy thanks to the complementarity of the classifiers.Some experimental results are given to validate the effectiveness of the proposed method using real data sets.展开更多
The rapid growth of multimedia content necessitates powerful technologies to filter, classify, index and retrieve video documents more efficiently. However, the essential bottleneck of image and video analysis is the ...The rapid growth of multimedia content necessitates powerful technologies to filter, classify, index and retrieve video documents more efficiently. However, the essential bottleneck of image and video analysis is the problem of semantic gap that low level features extracted by computers always fail to coincide with high-level concepts interpreted by humans. In this paper, we present a generic scheme for the detection video semantic concepts based on multiple visual features machine learning. Various global and local low-level visual features are systelrtically investigated, and kernelbased learning method equips the concept detection system to explore the potential of these features. Then we combine the different features and sub-systen on both classifier-level and kernel-level fusion that contribute to a more robust system Our proposed system is tested on the TRECVID dataset. The resulted Mean Average Precision （MAP） score is rmch better than the benchmark perforrmnce, which proves that our concepts detection engine develops a generic model and perforrrs well on both object and scene type concepts.展开更多
Radio Frequency Identification (RFID) is wireless technology that has been designed to automatically identify tagged objects using a reader. Several applications of this technology have been introduced in past literat...Radio Frequency Identification (RFID) is wireless technology that has been designed to automatically identify tagged objects using a reader. Several applications of this technology have been introduced in past literature such as pet identification and luggage tracking which have increased the efficiency and effectiveness of each environment into which it was integrated. However, due to the ambiguous nature of the captured information with the existence of missing, wrong and duplicate readings, the wide-scale adoption of the architecture is limited to commercial sectors where the integrity of the observations can tolerate ambiguity. In this work, we propose an application of RFID to take the reporting of class attendance and to integrate a predictive classifier to extract high level meaningful information that can be used in diverse areas such as scheduling and low student retention. We conclude by providing an analysis of the core strengths and opportunities that exist for this concept and how we might extend it in future research.展开更多
基金Supported by the National Nature Science Foundation of China under Grant Nos.11475003,61603003,and 11471093the Key Project of Cultivation of Leading Talents in Universities of Anhui Province under Grant No.gxfxZD2016174+2 种基金Funds of Integration of Cloud Computing and Big DataInnovation of Science and Technology of Ministry of Education of China under Grant No.2017A09116Anhui Provincial Department of Education Outstanding Top-Notch Talent-Funded Project under Grant No.gxbjZD26
文摘Human action recognition has become one of the most active research topics in human-computer interaction and artificial intelligence, and has attracted much attention. Here, we employ a low-cost optical sensor Kinect to capture the action information of the human skeleton. We then propose a two-level hierarchical human action recognition model with self-selection classifiers via skeleton data. Especially different optimal classifiers are selected by probability voting mechanism and 10 times 10-fold cross validation at different coarse grained levels. Extensive simulations on a well-known open dataset and results demonstrate that our proposed method is efficient in human action recognition, achieving 94.19%the average recognition rate and 95.61% the best rate.
文摘Background:In the field of genetic diagnostics,DNA sequencing is an important tool because the depth and complexity of this field have major implications in light of the genetic architectures of diseases and the identification of risk factors associated with genetic disorders.Methods:Our study introduces a novel two-tiered analytical framework to raise the precision and reliability of genetic data interpretation.It is initiated by extracting and analyzing salient features from DNA sequences through a CNN-based feature analysis,taking advantage of the power inherent in Convolutional neural networks(CNNs)to attain complex patterns and minute mutations in genetic data.This study embraces an elite collection of machine learning classifiers interweaved through a stern voting mechanism,which synergistically joins the predictions made from multiple classifiers to generate comprehensive and well-balanced interpretations of the genetic data.Results:This state-of-the-art method was further tested by carrying out an empirical analysis on a variants'dataset of DNA sequences taken from patients affected by breast cancer,juxtaposed with a control group composed of healthy people.Thus,the integration of CNNs with a voting-based ensemble of classifiers returned outstanding outcomes,with performance metrics accuracy,precision,recall,and F1-scorereaching the outstanding rate of 0.88,outperforming previous models.Conclusions:This dual accomplishment underlines the transformative potential that integrating deep learning techniques with ensemble machine learning might provide in real added value for further genetic diagnostics and prognostics.These results from this study set a new benchmark in the accuracy of disease diagnosis through DNA sequencing and promise future studies on improved personalized medicine and healthcare approaches with precise genetic information.
文摘Cross entropy is a measure in machine learning and deep learning that assesses the difference between predicted and actual probability distributions. In this study, we propose cross entropy as a performance evaluation metric for image classifier models and apply it to the CT image classification of lung cancer. A convolutional neural network is employed as the deep neural network (DNN) image classifier, with the residual network (ResNet) 50 chosen as the DNN archi-tecture. The image data used comprise a lung CT image set. Two classification models are built from datasets with varying amounts of data, and lung cancer is categorized into four classes using 10-fold cross-validation. Furthermore, we employ t-distributed stochastic neighbor embedding to visually explain the data distribution after classification. Experimental results demonstrate that cross en-tropy is a highly useful metric for evaluating the reliability of image classifier models. It is noted that for a more comprehensive evaluation of model perfor-mance, combining with other evaluation metrics is considered essential. .
文摘This article employs a combined approach of biology and economics to reveal that biological evolution has an economic nature, evolving towards improved energy efficiency. The orthodox Darwinian theory of evolution describes evolution as the random variation of organisms and their survival through natural selection. In fact, the natural environment itself is a constantly changing context, and the strategy to adapt to this change is to enhance behavioral capabilities, thereby expanding the range and dimensions of behavior. Therefore, the improvement of behavioral capabilities is an important aspect of evolution. The enhancement of behavioral capabilities expands the range of adaptation to the natural environment and increases the space for behavioral choices. Within this space of behavioral choices, some options are more effective and superior to others;thus, the ability to select is necessary to make the improved behavioral capabilities more beneficial to the organism itself. The birth and development of the brain serve the purpose of selection. By using the brain to make selections, at least the “better” behavior will be chosen between two alternatives. Once the better behavior yields better results, and the organism can associate these results with the corresponding behavior, it will persist in this behavior. The persistent repetition of a behavior over generations will form a habit. Habits passed down through generations constitute a new environment, causing the organism’s genes to activate or deactivate certain functions, ultimately leading to genetic changes that are beneficial to that habit. Since the brain’s selection represents the organism’s self-selection, it differs from random variation;it is also a rational selection, choosing behaviors that either obtain more energy or reduce energy consumption. Thus, this evolution possesses an economic nature.
基金This researchwork is supported by Princess Nourah bint Abdulrahman University Researchers Supporting Project Number(PNURSP2024R411),Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Malware attacks on Windows machines pose significant cybersecurity threats,necessitating effective detection and prevention mechanisms.Supervised machine learning classifiers have emerged as promising tools for malware detection.However,there remains a need for comprehensive studies that compare the performance of different classifiers specifically for Windows malware detection.Addressing this gap can provide valuable insights for enhancing cybersecurity strategies.While numerous studies have explored malware detection using machine learning techniques,there is a lack of systematic comparison of supervised classifiers for Windows malware detection.Understanding the relative effectiveness of these classifiers can inform the selection of optimal detection methods and improve overall security measures.This study aims to bridge the research gap by conducting a comparative analysis of supervised machine learning classifiers for detecting malware on Windows systems.The objectives include Investigating the performance of various classifiers,such as Gaussian Naïve Bayes,K Nearest Neighbors(KNN),Stochastic Gradient Descent Classifier(SGDC),and Decision Tree,in detecting Windows malware.Evaluating the accuracy,efficiency,and suitability of each classifier for real-world malware detection scenarios.Identifying the strengths and limitations of different classifiers to provide insights for cybersecurity practitioners and researchers.Offering recommendations for selecting the most effective classifier for Windows malware detection based on empirical evidence.The study employs a structured methodology consisting of several phases:exploratory data analysis,data preprocessing,model training,and evaluation.Exploratory data analysis involves understanding the dataset’s characteristics and identifying preprocessing requirements.Data preprocessing includes cleaning,feature encoding,dimensionality reduction,and optimization to prepare the data for training.Model training utilizes various supervised classifiers,and their performance is evaluated using metrics such as accuracy,precision,recall,and F1 score.The study’s outcomes comprise a comparative analysis of supervised machine learning classifiers for Windows malware detection.Results reveal the effectiveness and efficiency of each classifier in detecting different types of malware.Additionally,insights into their strengths and limitations provide practical guidance for enhancing cybersecurity defenses.Overall,this research contributes to advancing malware detection techniques and bolstering the security posture of Windows systems against evolving cyber threats.
文摘Driven by both the“new engineering”initiative and the energy revolution,the traditional engineering education model can hardly meet the demand of the energy and electric power industry for diversified and interdisciplinary outstanding engineers.Based on the“industry-university-research-application”four-in-one collaborative education concept,this paper constructs a new training system centered on classified cultivation and classified evaluation.The system aims to solve core problems such as homogeneous training,disconnection between industry and academia,single evaluation method,and insufficient faculty.Through measures including modular courses,the dual-tutor system,and diversified practical platforms,it realizes differentiated and precise talent training,so as to deliver outstanding engineers with the ability to“define problems,break through technologies,and create value”for the energy and electric power industry.
基金funded by the Open Access Initiative of the University of Bremen and the DFG via SuUB Bremen.Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2024R348),Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Human Activity Recognition(HAR)in drone-captured videos has become popular because of the interest in various fields such as video surveillance,sports analysis,and human-robot interaction.However,recognizing actions from such videos poses the following challenges:variations of human motion,the complexity of backdrops,motion blurs,occlusions,and restricted camera angles.This research presents a human activity recognition system to address these challenges by working with drones’red-green-blue(RGB)videos.The first step in the proposed system involves partitioning videos into frames and then using bilateral filtering to improve the quality of object foregrounds while reducing background interference before converting from RGB to grayscale images.The YOLO(You Only Look Once)algorithm detects and extracts humans from each frame,obtaining their skeletons for further processing.The joint angles,displacement and velocity,histogram of oriented gradients(HOG),3D points,and geodesic Distance are included.These features are optimized using Quadratic Discriminant Analysis(QDA)and utilized in a Neuro-Fuzzy Classifier(NFC)for activity classification.Real-world evaluations on the Drone-Action,Unmanned Aerial Vehicle(UAV)-Gesture,and Okutama-Action datasets substantiate the proposed system’s superiority in accuracy rates over existing methods.In particular,the system obtains recognition rates of 93%for drone action,97%for UAV gestures,and 81%for Okutama-action,demonstrating the system’s reliability and ability to learn human activity from drone videos.
文摘The categorization of brain tumors is a significant issue for healthcare applications.Perfect and timely identification of brain tumors is important for employing an effective treatment of this disease.Brain tumors possess high changes in terms of size,shape,and amount,and hence the classification process acts as a more difficult research problem.This paper suggests a deep learning model using the magnetic resonance imaging technique that overcomes the limitations associated with the existing classification methods.The effectiveness of the suggested method depends on the coyote optimization algorithm,also known as the LOBO algorithm,which optimizes the weights of the deep-convolutional neural network classifier.The accuracy,sensitivity,and specificity indices,which are obtained to be 92.40%,94.15%,and 91.92%,respectively,are used to validate the effectiveness of the suggested method.The result suggests that the suggested strategy is superior for effectively classifying brain tumors.
基金supported in part by the National Science Fund for Distinguished Young Scholars under Grant (42025403)the National Key Research and Development Plan of China (2021YFA0716800)the National Key Research and Development Plan of China (2022YFC2903804)。
文摘The increasing risk of ground pressure disasters resulting from deep well mining highlights the urgent need for advanced monitoring and early warning systems.Ground pressure monitoring,supported by microseismic technology,plays a pivotal role in ensuring mine safety by enabling real-time identifi cation and accurate classification of vibration signals such as microseismic signals,blasting signals,and noise.These classifications are critical for improving the efficacy of ground pressure monitoring systems,conducting stability analyses of deep rock masses,and implementing timely and precise roadway support measures.Such eff orts are essential for mitigating ground pressure disasters and ensuring safe mining operations.This study proposes an artificial intelligence-based automatic classification network model for mine vibration signals.Based on conventional convolutional neural networks,the proposed model further incorporates long short-term memory(LSTM)networks and attention mechanisms.The LSTM component eff ectively captures temporal correlations in time-series mining vibration data,while the attention mechanism enhances the models’ability to focus on critical features within the data.To validate the eff ectiveness of our proposed model,a dataset comprising 480,526 waveform records collected in 2022 by the microseismic monitoring system at Guangxi Shanhu Tungsten Mine was used for training,validation,and testing purposes.Results demonstrate that the proposed artifi cial intelligence-based classifi cation method achieves a higher recognition accuracy of 92.21%,significantly outperforming traditional manual classification methods.The proposed model represents a signifi cant advancement in ground pressure monitoring and disaster mitigation.
文摘Machine learning techniques and a dataset of five wells from the Rawat oilfield in Sudan containing 93,925 samples per feature(seven well logs and one facies log) were used to classify four facies. Data preprocessing and preparation involve two processes: data cleaning and feature scaling. Several machine learning algorithms, including Linear Regression(LR), Decision Tree(DT), Support Vector Machine(SVM),Random Forest(RF), and Gradient Boosting(GB) for classification, were tested using different iterations and various combinations of features and parameters. The support vector radial kernel training model achieved an accuracy of 72.49% without grid search and 64.02% with grid search, while the blind-well test scores were 71.01% and 69.67%, respectively. The Decision Tree(DT) Hyperparameter Optimization model showed an accuracy of 64.15% for training and 67.45% for testing. In comparison, the Decision Tree coupled with grid search yielded better results, with a training score of 69.91% and a testing score of67.89%. The model's validation was carried out using the blind well validation approach, which achieved an accuracy of 69.81%. Three algorithms were used to generate the gradient-boosting model. During training, the Gradient Boosting classifier achieved an accuracy score of 71.57%, and during testing, it achieved 69.89%. The Grid Search model achieved a higher accuracy score of 72.14% during testing. The Extreme Gradient Boosting model had the lowest accuracy score, with only 66.13% for training and66.12% for testing. For validation, the Gradient Boosting(GB) classifier model achieved an accuracy score of 75.41% on the blind well test, while the Gradient Boosting with Grid Search achieved an accuracy score of 71.36%. The Enhanced Random Forest and Random Forest with Bagging algorithms were the most effective, with validation accuracies of 78.30% and 79.18%, respectively. However, the Random Forest and Random Forest with Grid Search models displayed significant variance between their training and testing scores, indicating the potential for overfitting. Random Forest(RF) and Gradient Boosting(GB) are highly effective for facies classification because they handle complex relationships and provide high predictive accuracy. The choice between the two depends on specific project requirements, including interpretability, computational resources, and data nature.
文摘To improve the performance of the multiple classifier system, a new method of feature-decision level fusion is proposed based on knowledge discovery. In the new method, the base classifiers operate on different feature spaces and their types depend on different measures of between-class separability. The uncertainty measures corresponding to each output of each base classifier are induced from the established decision tables （DTs） in the form of mass function in the Dempster-Shafer theory （DST）. Furthermore, an effective fusion framework is built at the feature-decision level on the basis of a generalized rough set model and the DST. The experiment for the classification of hyperspectral remote sensing images shows that the performance of the classification can be improved by the proposed method compared with that of plurality voting （PV）.
基金supported by National Natural Science Foundation of China (Grant No. 50474035)
文摘The turbo air classifier is widely used powder classification equipment in a variety of fields. The flow field characteristics of the turbo air classifier are important basis for the improvement of the turbo air classifier＇s structural design. The flow field characteristics of the rotor cage in turbo air classifiers were investigated trader different operating conditions by laser Doppler velocimeter（LDV）, and a measure diminishing the axial velocity is proposed. The investigation results show that the tangential velocity of the air flow inside the rotor cage is different from the rotary speed of the rotor cage on the same measurement point due to the influences of both the negative pressure at the exit and the rotation of the rotor cage. The tangential velocity of the air flow likewise decreases as the radius decreases in the case of the rotor cage＇s low rotary speed. In contrast, the tangential velocity of the air flow increases as the radius decreases in the case of the rotor cage＇s high rotary speed. Meanwhile, the vortex inside the rotor cage is found to occur near the pressure side of the blade when the rotor cage＇s rotary speed is less than the tangential velocity of air flow. On the contrary, the vortex is found to occur near the blade suction side once the rotor cage＇s rotary speed is higher than the tangential velocity of air flow. Inside the rotor cage, the axial velocity could not be disregarded and is largely determined by the distances between the measurement point and the exit.
文摘Predicting stock price movements is a challenging task for academicians and practitioners. In particular, forecasting price movements in emerging markets seems to be more elusive because they are usually more volatile often accompa-nied by thin trading-volumes and they are susceptible to more manipulation compared to mature markets. Technical analysis of stocks and commodities has become a science on its own;quantitative methods and techniques have been applied by many practitioners to forecast price movements. Lagging and sometimes leading technical indicators pro-vide rich quantitative tools for traders and investors in their attempt to gain advantage when making investment or trading decisions. Artificial Neural Networks (ANN) have been used widely in predicting stock prices because of their capability in capturing the non-linearity that often exists in price movements. Recently, Polynomial Classifiers (PC) have been applied to various recognition and classification application and showed favorable results in terms of recog-nition rates and computational complexity as compared to ANN. In this paper, we present two prediction models for predicting securities’ prices. The first model was developed using back propagation feed forward neural networks. The second model was developed using polynomial classifiers (PC), as a first time application for PC to be used in stock prices prediction. The inputs to both models were identical, and both models were trained and tested on the same data. The study was conducted on Dubai Financial Market as an emerging market and applied to two of the market’s leading stocks. In general, both models achieved very good results in terms of mean absolute error percentage. Both models show an average error around 1.5% predicting the next day price, an average error of 2.5% when predicting second day price, and an average error of 4% when predicted the third day price.
基金financial support from the National Key Technologies R&D Program of China(2018YFF0216002)。
文摘The classification performance of model coal mill classifiers with different bottom incoming flow inlets was experimentally and numerically studied.The flow field adjacent to two neighboring impeller blades was measured using the particle image velocimetry technique.The results showed that the flow field adjacent to two neighboring blades with the swirling inlet was significantly different from that with the non-swirling inlet.With the swirling inlet,there was a vortex located between two neighboring blades,while with the nonswirling inlet,the vortex was attached to the blade tip.The vorticity of the vortex with the non-swirling inlet was much lower than that with the swirling inlet.The classifier with the non-swirling inlet demonstrated a larger cut size than that with the swirling inlet when the impeller was stationary(~0 r·min-1).As the impeller rotational speed increased,the cut size of the cases with non-swirling and swirling inlets both decreased,and the one with the non-swirling inlet decreased more dramatically.The values of the cut size of the two classifiers were close to each other at a high impeller rotational speed(≥120 r·min-1).The overall separation efficiency of the classifier with the non-swirling inlet was lower than that with the swirling inlet,and monotonically increased as the impeller rotational speed increased.With the swirling inlet,the overall separation efficiency first increased with the impeller rotational speed and then decreased when the rotational speed was above 120 r·min-1,and the variation trend of the separation efficiency was more moderate.As the initial particle concentration increased,the cut sizes of both swirling and non-swirling inlet cases decreased first and then barely changed.At a low initial particle concentration(b 0.04 kg·m-3),the classifier with the swirling inlet had a larger cut size than that with the non-swirling inlet.
文摘This study investigated the efficiency of learning the Chinese numeral classifiers by L2 Chinese learners by means of an alignment-oriented task. Participants were a total of 96 intermediate learners of L2 Chinese, who were randomly assigned to two experimental groups and one control group, with each group consisting of 32 participants. The continuation task used in this study consisted of a picture-based Chinese text depicting a room with an array of objects, which necessitates the use of classifiers. The two experimental groups were both required to first read the text and then write to describe their own rooms in comparison with the one in the text. One group was instructed to use the classifiers from the text as much as possible in their writing, whereas the other was not required to do so. Participants in the control group were first given the picture to look at in the absence of the text and then asked to describe their own rooms. The results showed that the continuation task significantly enhanced participants’ retention of the Chinese numeral classifiers, suggesting that the alignment-based approach is an effective way to learn difficult linguistic categories such as the Chinese classifiers.
文摘Fuel injectors are considered as an important component of combustion engines. Operational weakness can possibly lead to the complete machine malfunction, decreasing reliability and leading to loss of production. To overcome these circumstances, various condition monitoring techniques can be applied. The application of acoustic signals is common in the field of fault diagnosis of rotating machinery. Advanced signal processing is utilized for the construction of features that are specialized in detecting fuel injector faults. A performance comparison between novelty detection algorithms in the form of one-class classifiers is presented. The one-class classifiers that were tested included One-Class Support Vector Machine (OCSVM) and One-Class Self Organizing Map (OCSOM). The acoustic signals of fuel injectors in different operational conditions were processed for feature extraction. Features from all the signals were used as input to the one-class classifiers. The one-class classifiers were trained only with healthy fuel injector conditions and compared with new experimental data which belonged to different operational conditions that were not included in the training set so as to contribute to generalization. The results present the effectiveness of one-class classifiers for detecting faults in fuel injectors.
基金partially supported by National Natural Science Foundation of China(Nos.U20B2067,61790552,61790554)Shaanxi Science Fund for Distinguished Young Scholars,China(No.2018JC-006)。
文摘The methods for combining multiple classifiers based on belief functions require to work with a common and complete(closed)Frame of Discernment(Fo D)on which the belief functions are defined before making their combination.This theoretical requirement is however difficult to satisfy in practice because some abnormal(or unknown)objects that do not belong to any predefined class of the Fo D can appear in real classification applications.The classifiers learnt using different attributes information can provide complementary knowledge which is very useful for making the classification but they are usually based on different Fo Ds.In order to clearly identify the specific class of the abnormal objects,we propose a new method for combination of classifiers working with incomplete frames of discernment,named CCIF for short.This is a progressive detection method that select and add the detected abnormal objects to the training data set.Because one pattern can be considered as an abnormal object by one classifier and be committed to a specific class by another one,a weighted evidence combination method is proposed to fuse the classification results of multiple classifiers.This new method offers the advantage to make a refined classification of abnormal objects,and to improve the classification accuracy thanks to the complementarity of the classifiers.Some experimental results are given to validate the effectiveness of the proposed method using real data sets.
基金Acknowledgements This paper was supported by the coUabomtive Research Project SEV under Cant No. 01100474 between Beijing University of Posts and Telecorrrcnications and France Telecom R＆D Beijing the National Natural Science Foundation of China under Cant No. 90920001 the Caduate Innovation Fund of SICE, BUPT, 2011.
文摘The rapid growth of multimedia content necessitates powerful technologies to filter, classify, index and retrieve video documents more efficiently. However, the essential bottleneck of image and video analysis is the problem of semantic gap that low level features extracted by computers always fail to coincide with high-level concepts interpreted by humans. In this paper, we present a generic scheme for the detection video semantic concepts based on multiple visual features machine learning. Various global and local low-level visual features are systelrtically investigated, and kernelbased learning method equips the concept detection system to explore the potential of these features. Then we combine the different features and sub-systen on both classifier-level and kernel-level fusion that contribute to a more robust system Our proposed system is tested on the TRECVID dataset. The resulted Mean Average Precision （MAP） score is rmch better than the benchmark perforrmnce, which proves that our concepts detection engine develops a generic model and perforrrs well on both object and scene type concepts.
文摘Radio Frequency Identification (RFID) is wireless technology that has been designed to automatically identify tagged objects using a reader. Several applications of this technology have been introduced in past literature such as pet identification and luggage tracking which have increased the efficiency and effectiveness of each environment into which it was integrated. However, due to the ambiguous nature of the captured information with the existence of missing, wrong and duplicate readings, the wide-scale adoption of the architecture is limited to commercial sectors where the integrity of the observations can tolerate ambiguity. In this work, we propose an application of RFID to take the reporting of class attendance and to integrate a predictive classifier to extract high level meaningful information that can be used in diverse areas such as scheduling and low student retention. We conclude by providing an analysis of the core strengths and opportunities that exist for this concept and how we might extend it in future research.
