Search

The academic community has witnessed a notable increase in paper publications, whereby the rapid pace at which modern society seeks information underscores the critical need for literature mapping. This study introduces an innovative automatic model for categorizing articles by subject matter using Machine Learning (ML) algorithms for classification and category labeling, alongside a proposed ranking method called SSS (Scientific Significance Score) and using Z-score to select the finest papers. This paper's use case concerns industry productivity. The key findings include the following: (1) The Decision Tree model demonstrated superior performance with an accuracy rate of 75% in classifying articles within the productivity and industry theme. (2) Through a ranking methodology based on citation count and publication date, it identified the finest papers. (3) Recent publications with higher citation counts achieved better scores. (4) The model's sensitivity to outliers underscores the importance of addressing database imbalances, necessitating caution during training by excluding biased categories. These findings not only advance the utilization of ML models for paper classification but also lay a foundation for further research into productivity within the industry, exploring themes such as artificial intelligence, efficiency, industry 4.0, innovation, and sustainability. [ABSTRACT FROM AUTHOR]

In recent years, with the advent of digital imaging technology, e.g., color printers and color scanners, it has become easier for counterfeiters to produce fake banknotes. The spread of counterfeit money causes loss to everyone involved in financial transactions. Therefore, an effective and reliable verification technique is necessary for successful and reliable financial transactions. This paper presents a cognitive computationbased technique for paper currency verification. In this regard, Scanning Electron Microscopy (SEM) and X-Ray Diffraction (XRD) analyses of counterfeit and genuine banknotes were performed. This experimentation confirmed that the materials used in preparation of genuine and counterfeit banknotes were totally different from each other. Based on these findings, a set of discriminative and robust features was proposed to re ect these differences in currency images. The proposed features represented characteristics of the materials of the banknote, such as printing ink, chemical composition, and surface coarseness. With these robust features, Support Vector Machines (SVMs) were employed for classification. In order to evaluate the performance of the proposed technique, experimentations were performed on a self-constructed dataset of Pakistani banknotes, comprised of 195 currency images, including 35 counterfeit banknotes. The results showed that the proposed system achieved 100% verification ability for properly captured images. [ABSTRACT FROM AUTHOR]

The paper reports the results of a comparative assessment concerned with the effectiveness of identifying the basic forms of partial discharges (PD) measured by the acoustic emission technique (AE), carried out by application of selected machine learning methods. As part of the re-search, the identification involved AE signals registered in laboratory conditions for eight basic classes of PDs that occur in paper-oil insulation systems of high-voltage power equipment. On the basis of acoustic signals emitted by PDs and by application of the frequency descriptor that took the form of a signal power density spectrum (PSD), the assessment involved the possibility of identifying individual types of PD by the analyzed classification algorithms. As part of the research, the results obtained with the use of five independent classification mechanisms were analyzed, namely: k-Nearest Neighbors method (kNN), Naive Bayes Classification, Support Vector Machine (SVM), Random Forests and Probabilistic Neural Network (PNN). The best results were achieved using the SVM classification tuned with polynomial core, which obtained 100% accuracy. Similar results were achieved with the kNN classifier. Random Forests and Naïve Bayes obtained high accuracy over 97%. Throughout the study, identification algorithms with the highest effectiveness in identifying specific forms of PD were established. [ABSTRACT FROM AUTHOR]

Microfluidic paper-based analytical devices (μPADs) have been widely used in point-of-care testing owing to their simple operation, low volume of the sample required, and the lack of the need for an external force. To obtain accurate semi-quantitative or quantitative results, μPADs need to respond to the challenges posed by differences in reaction conditions. In this paper, multi-layer μPADs are fabricated by the imprinting method for the colorimetric detection of C-reactive protein (CRP). Different lighting conditions and shooting angles of scenes are simulated in image acquisition, and the detection-related performance of μPADs is improved by using a machine learning algorithm. The You Only Look Once (YOLO) model is used to identify the areas of reaction in μPADs. This model can observe an image only once to predict the objects present in it and their locations. The YOLO model trained in this study was able to identify all the reaction areas quickly without incurring any error. These reaction areas were categorized by classification algorithms to determine the risk level of CRP concentration. Multi-layer perceptron, convolutional neural network, and residual network algorithms were used for the classification tasks, where the latter yielded the highest accuracy of 96%. It has a promising application prospect in fast recognition and analysis of μPADs. [ABSTRACT FROM AUTHOR]

Copyright of Informatica (03505596) is the property of Slovene Society Informatika and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The traditional method for transformer moisture diagnosis is to establish empirical equations between feature parameters extracted from frequency domain spectroscopy (FDS) and the transformer’s moisture content. However, the established empirical equation may not be applicable to a novel testing environment, resulting in an unreliable evaluation result. In this regard, it is acknowledged that FDS combined with machine learning is more suitable for estimating moisture content in a variety of test environments. Nonetheless, the accuracy of the estimation results obtained using the existing method is limited by the algorithm’s inability to generalize. To address this issue, we propose an AdaBoost algorithm-enhanced back-propagation neural network (BP_AdaBoost). This study creates a database by extracting feature parameters from the FDS that characterize the insulation states of the prepared samples. Then, using the BP_AdaBoost algorithm and the newly constructed database, the moisture estimation models are trained. Finally, the results of the estimation are discussed in terms of laboratory and field transformers. By comparing the proposed BP_AdaBoost algorithm to other intelligence algorithms, it is demonstrated that it not only performs better in generalization, but also maintains a high level of accuracy. [ABSTRACT FROM AUTHOR]

Construction Engineering and Management (CEM) is a broad domain with publications covering interrelated subdisciplines and considered a key source of knowledge sharing. Previous studies used scientometric methods to assess the current impact of CEM publications; however, there is a need to predict future citations of CEM publications to identify the expected high-impact trends in the future and guide new research efforts. To tackle this gap in the literature, the authors conducted a study using Machine Learning (ML) algorithms and Social Network Analysis (SNA) to predict CEM-related citation metrics. Using a dataset of 93,868 publications, the authors trained and tested two machine learning classification algorithms: Random Forest and XGBoost. Validation of the RF and XGBoost resulted in a balanced accuracy of 79.1% and 79.5%, respectively. Accordingly, XGBoost was selected. Testing of the XGBoost model revealed a balanced accuracy of 80.71%. Using SNA, it was found that while the top CEM subdisciplines in terms of the number of predicted impactful papers are "Project planning and design", "Organizational issues", and "Information technologies, robotics, and automation"; the lowest was "Legal and contractual issues". This paper contributes to the body of knowledge by studying the citation level, strength, and interconnectivity between CEM subdisciplines as well as identifying areas more likely to result in highly cited publications. [ABSTRACT FROM AUTHOR]

To increase crop productivity, recognition of a plant disease is a very pivotal task. The prior identification of plant diseases helps farmers to prevent losses occurred by various types of plant diseases. Manual observation and identification of plant diseases is a very tedious task as it requires a lot of time, money, efforts etc. therefore an automated system is required that efficiently identifies plant disease in a minimum span of time without requiring much efforts. Plant disease have been identified using various techniques such as image segmentation, clustering, convolution neural network, decision trees and many more by determining the patterns of plant images based on their colour, spots, light intensity over a certain period of time by various researchers. This paper aims to portray the techniques formulate in this area. This work infers the major challenges that thus far not explored. [ABSTRACT FROM AUTHOR]

The Ultra-Wideband (UWB) Location-Based Service is receiving more and more attention due to its high ranging accuracy and good time resolution. However, the None-Line-of-Sight (NLOS) propagation may reduce the ranging accuracy for UWB localization system in indoor environment. So it is important to identify LOS and NLOS propagations before taking proper measures to improve the UWB localization accuracy. In this paper, a deep learning-based UWB NLOS/LOS classification algorithm called FCN-Attention is proposed. The proposed FCN-Attention algorithm utilizes a Fully Convolution Network (FCN) for improving feature extraction ability and a self-attention mechanism for enhancing feature description from the data to improve the classification accuracy. The proposed algorithm is evaluated using an open-source dataset, a local collected dataset and a mixed dataset created from these two datasets. The experiment result shows that the proposed FCN-Attention algorithm achieves classification accuracy of 88.24% on the open-source dataset, 100% on the local collected dataset and 92.01% on the mixed dataset, which is better than the results from other evaluated NLOS/LOS classification algorithms in most scenarios in this paper. [ABSTRACT FROM AUTHOR]

Ageing power systems infrastructure and concerns about climate change have increased interest in the next generation of grid infrastructure, known as the smart grid (SG). This study studies a particularly critical SG application: intelligent monitoring of power transformers for the early detection of insulation failure. Specifically, the focus is on the use of machine learning algorithms to distinguish between different types of partial discharges, which are closely correlated with insulation failure. Measurements made using acoustic emission sensors are used to train and test different classification algorithms. In an earlier study, high classification accuracies were achieved using training and test datasets collected under similar measurement conditions. However, under different conditions, classification accuracy was greatly reduced. Experiments using the latest classification techniques were performed, producing significant improvements in classification accuracy. A possible reason for these results could be a form of overfitting, and further experiments were conducted to test this hypothesis. [ABSTRACT FROM AUTHOR]

With the development of air transport and improved ecological environment, bird strikes on aircraft have become a significant threat to flight safety. Accurate and efficient identification of airport birds can enhance the efficiency of airport staff in bird strike prevention. Public datasets for bird classification are typically limited in size and not specifically tailored for airport birds. Therefore, this paper introduces a self‐built airport bird dataset, ADB‐20, and proposes an image recognition method based on an improved ResNet model. First, this paper replaces traditional convolution in the residual structure with the Pyramidal Convolution method, ensuring the extraction of multiscale features. Second, it introduces the Parallel Convolutional Block Attention Moduleto the backbone network, considering features in both channel and spatial dimensions. Last, the Atrous Spatial Pyramid Pooling module is incorporated to capture contextual information at various scales. Experimental results show that the PPA‐ResNet model achieves an accuracy of 95.2%, with a recall of 93.7%, a precision of 96.8%, and an F1 score of 95.2% on the ADB‐20 dataset. The proposed algorithm significantly enhances classification performance compared to other mainstream image classification algorithms. These indicators confirm that the results of this study can precisely identify airport birds, aid airport personnel in making informed decisions, and guarantee the safety of aviation transport. [ABSTRACT FROM AUTHOR]

Scientific literature is published at a rate that makes manual data extraction a highly time-consuming task. The Comprehensive Antibiotic Resistance Database (CARD) utilizes literature to curate information on antimicrobial resistance genes and to enable time-efficient triage of publications we have developed a classification algorithm for identifying publications describing first reports of new resistance genes. Trained on publications contained in the CARD, CARD*Shark downloads, processes and identifies publications recently added to PubMed that should be reviewed by biocurators. With CARD*Shark, we can minimize the monthly scope of articles a biocurator reviews from hundreds of articles to a few dozen, drastically improving the speed of curation while ensuring no relevant publications are overlooked. Database URLhttp://card.mcmaster.ca [ABSTRACT FROM AUTHOR]

Personal credit assessment plays a crucial role in the financial system, which not only relates to the financial activities of individuals but also affects the overall credit system and economic health of society. However, the current problem of data imbalance affecting classification results in the field of personal credit assessment has not been fully solved. In order to solve this problem better, we propose a data-enhanced classification algorithm based on a Pixel Convolutional Neural Network (PixelCNN) and a Generative Adversarial Network (Wasserstein GAN, WGAN). Firstly, the historical data containing borrowers' borrowing information are transformed into grayscale maps; then, data enhancement of default images is performed using the improved PixelCNN-WGAN model; and finally, the expanded image dataset is inputted into the CNN, AlexNet, SqueezeNet, and MobileNetV2 for classification. The results on the real dataset LendingClub show that the data enhancement algorithm designed in this paper improves the accuracy of the four algorithms by 1.548–3.568% compared with the original dataset, which can effectively improve the classification effect of the credit data, and to a certain extent, it provides a new idea for the classification task in the field of personal credit assessment. [ABSTRACT FROM AUTHOR]

Cloud model similarity algorithm is an important part of cloud modelling theory. Most of the existing cloud model similarity algorithms suffer from poor discriminability, poor classification, unstable results, and low time efficiency. In this paper, a new similarity algorithm is proposed that considers the triangular cloud model distance and shape. First, according to the D T distance formula, a new exponential closeness measure is defined, with which the distance similarity of cloud models is characterized. Then, the shape similarity is calculated according to the variance of the cloud model cloud drops. Finally, the two similarities are synthesized to define a similarity algorithm for determining the distance from the D T distance formula and shape based on the triangular cloud model (DDTSTCM). In this paper, discriminability, stability, efficiency and theoretical interpretability are taken as the evaluation indices. Equipment security system capability evaluation experiment, cloud model differentiation simulation experiment and time series classification accuracy experiment are set up to verify the effectiveness of the algorithm in terms of the four above aspects. The experimental results show that DDTSTCM has good differentiation and excellent classification effects. In the classification experiment for the time series, the average classification accuracy of DDTSTCM reaches 91.78%, which is at least 2.78% higher than those of the other seven commonly used algorithms. The CPU running efficiency of DDTSTCM is also extremely high, and the average CPU running time of group training is always on the order of milliseconds, which effectively reduces the time cost. Finally, a case study is conducted to analyse a risk assessment problem for China's island microgrid industry, and the evaluation results based on DDTSTCM are in line with human cognition and have good value for engineering applications. [ABSTRACT FROM AUTHOR]

Twin Support Vector Machine (TSVM) is a powerful machine learning method that is usually used to solve binary classification problems. But although the classification speed and performance of TSVM is better than that of primitive support vector machine, TSVM still faces the problem of difficult parameter selection; therefore, to overcome the problem of parameter selection of TSVM, this paper proposes a Chaotic Mapping Dung Beetle Optimization Algorithm-based Twin Support Vector Machine (CMDBO-TSVM) for automatic parameter selection. Due to the uncertainty of the random initialization population of the original Dung Beetle Optimization Algorithm, this paper additionally adds chaotic mapping initialization to improve the Dung Beetle Optimization Algorithm. Experiments on the dataset through this paper show that the classification accuracy of the CMDBO-TSVM has a better performance. [ABSTRACT FROM AUTHOR]

Heart disease remains a prevalent and critical health concern globally. This paper addresses the critical task of heart disease prediction through the utilization of advanced machine learning techniques. Our approach focuses on the enhancement of feature engineering by incorporating a novel integration of association and correlation analyses. A heart disease dataset from Kaggle was used for the experiments. Association analysis was applied to the categorical and binary features in the dataset. Correlation analysis was applied to the numerical features in the dataset. Based on the insights from association analysis and correlation analysis, a new dataset was created with combinations of features. Later, newly created features are integrated with the original dataset, and classification algorithms are applied. Five machine learning (ML) classifiers, namely decision tree, k-nearest neighbors (KNN), random forest, XG-Boost, and support vector machine (SVM), were applied to the final dataset and achieved a good accuracy rate for heart disease detection. By systematically exploring associations and relationships with categorical, binary, and numerical features, this paper unveils innovative insights that contribute to a more comprehensive understanding of the heart disease dataset. [ABSTRACT FROM AUTHOR]

Researchers and scientists need rapid access to text documents such as research papers, source code and dissertations. Many research documents are available on the Internet and need more time to retrieve exact documents based on keywords. An efficient classification algorithm for retrieving documents based on keyword words is required. The traditional algorithm performs less because it never considers words’ polysemy and the relationship between bag-of-words in keywords. To solve the above problem, Semantic Featured Convolution Neural Networks (SF-CNN) is proposed to obtain the key relationships among the searching keywords and build a structure for matching the words for retrieving correct text documents. The proposed SF-CNN is based on deep semantic-based bag-of-word representation for document retrieval. Traditional deep learning methods such as Convolutional Neural Network and Recurrent Neural Network never use semantic representation for bag-of-words. The experiment is performed with different document datasets for evaluating the performance of the proposed SF-CNN method. SF-CNN classifies the documents with an accuracy of 94% than the traditional algorithms. [ABSTRACT FROM AUTHOR]

This article summarizes a research paper that examines different modeling approaches for predicting various aspects of websites. The study covers tasks such as categorization, navigation prediction, and detecting malicious, fake news, and phishing websites. The researchers collected data from different sources and used a range of modeling techniques, including traditional machine learning algorithms and deep neural networks. The paper highlights the importance of adaptability in data acquisition and modeling due to the dynamic nature of the web. The researchers conclude that ongoing research is needed to keep up with the evolving nature of websites. [Extracted from the article]

Visual Cryptography (VC) is a process employed for the maintenance of secret information by hiding the secret messages that are embedded within the images. Typically, an image is partitioned into a number of shares that are stacked over one another in order to reconstruct back the original image accurately. The major limitation that existed in the traditional VC techniques is pixel expansion, in which pixel expansion is replaced with a number of sub-pixels in individual share, which causes a considerable impact on the contrast and resolution of the image that further gradually decreases the quality of the image. VC is named for its essential characteristics, such as transmitting the images with two or more shares with an equal number of black pixels and color pixel distribution. The secret message can be decrypted using Human Visual System (HVS). In this paper, 50 research papers are reviewed based on various classification algorithms, which are effectively used for the VC technique. The classification algorithms are categorized into three types, namely, meta-heuristic, heuristic, and evolutionary, and the research issues and challenges confronted by the existing techniques are reported in this survey. Moreover, the analysis is done based on the existing research works by considering the classification algorithms, tools, and evaluation metrics. [ABSTRACT FROM AUTHOR]

This study combines the present stage of the node classification problem with the fact that there is frequent noise in the graph structure of the graph convolution calculation, which can lead to the omission of some of the actual edge relations between nodes and the appearance of numerous isolated nodes. In this paper, we propose the graph neural network model ENode-GAT for improving the accuracy of small sample node classification using the method of external referencing of similar word nodes, combined with Graph Convolutional Neural Network (GCN), Graph Attention Network (GAT), and the early stop algorithm. In order to demonstrate the applicability of the model, this paper employs two distinct types of node datasets for its investigations. The first is the Cora dataset, which is widely used in node classification at this time, and the second is a small-sample Stock dataset created by Eastern Fortune's stock prospectus of the Science and Technology Board (STB). The experimental results demonstrate that the ENode-GAT model proposed in this paper obtains 85.1% classification accuracy on the Cora dataset and 85.3% classification accuracy on the Stock dataset, with certain classification advantages. It also verifies the future applicability of the model to the fields of stock classification, tender document classification, news classification, and government announcement classification, among others. [ABSTRACT FROM AUTHOR]

Presently, multi-label classification algorithms are mainly based on positive and negative logical labels, which have achieved good results. However, logical labeling inevitably leads to the label misclassification problem. In addition, missing labels are common in multi-label datasets. Recovering missing labels and constructing soft labels that reflect the mapping relationship between instances and labels is a difficult task. Most existing algorithms can only solve one of these problems. Based on this, this paper proposes a soft-label recover based label-specific features learning (SLR-LSF) to solve the above problems simultaneously. Firstly, the information entropy is used to calculate the confidence matrix between labels, and the membership degree of soft labels is obtained by combining the label density information. Secondly, the membership degree and confidence matrix are combined to construct soft labels, and this process not only solves the problem of missing labels but also obtains soft labels with richer semantic information. Finally, in the process of learning specific label features for soft labels. The local smoothness of the labels learned through stream regularization is complemented by the global label correlation, thus improving the classification performance of the algorithm. To demonstrate the effectiveness of the proposed algorithm, we conduct comprehensive experiments on several datasets. [ABSTRACT FROM AUTHOR]

Monitoring the driver's physical and mental state based on wearable EEG acquisition equipment, especially the detection and early warning of fatigue, is a key issue in the research of the brain–computer interface in human–machine intelligent fusion driving. Comparing and analyzing the waking (alert) state and fatigue state by simulating EEG data during simulated driving, this paper proposes a brain functional network construction method based on a phase locking value (PLV) and phase lag index (PLI), studies the relationship between brain regions, and quantitatively analyzes the network structure. The characteristic parameters of the brain functional network that have significant differences in fatigue status are screened out and constitute feature vectors, which are then combined with machine learning algorithms to complete classification and identification. The experimental results show that this method can effectively distinguish between alertness and fatigue states. The recognition accuracy rates of 52 subjects are all above 70%, with the highest recognition accuracy reaching 89.5%. Brain network topology analysis showed that the connectivity between brain regions was weakened under a fatigue state, especially under the PLV method, and the phase synchronization relationship between delta and theta frequency bands was significantly weakened. The research results provide a reference for understanding the interdependence of brain regions under fatigue conditions and the development of fatigue driving detection systems. [ABSTRACT FROM AUTHOR]

Fuzzy sets possess remarkable abilities in expressing and handling information uncertainty, which has resulted in their widespread application in various fields. Nevertheless, distance measurement between IFSs for quantitating their differences and levels of differentiation has remained an open problem that deserves attention. Despite the development of various metrics, they either lack intuitive insight or do not satisfy the axioms of distance measurement, leading to counterintuitive results. To address these issues, this paper proposed a distance measurement method based on Clark divergence, which satisfies the distance measurement axioms and exhibits nonlinearity. Numerical examples demonstrate that our method effectively distinguishes different indicators, yielding more reasonable results. Moreover, when comparing relative differences of the results, our method demonstrated superior adaptability to complex environmental decision-making, providing decision-makers with more accurate and confidential judgments. In our numerical and pattern classification application tests, we achieve an accuracy of 98%, a 40% increase in computing time efficiency and a relative diversity improvement of 35%. The pattern classification algorithm designed in this paper will offer a promising solution to inference problems. [ABSTRACT FROM AUTHOR]

This paper explores whether it is feasible to use the RGB color information in images of wheat canopies that were exposed to low temperatures during the growth season to achieve fast, non-destructive, and accurate determination of the severity of any freeze injury it may have incurred. For the study presented in this paper, we compared the accuracy of a number of algorithmic classification models using either meteorological data reported by weather services or the color gradation skewness-distribution from high-definition digital canopy images acquired in situ as inputs against a reference obtained by manually assessing the severity of the freeze injury inflicted upon wheat populations at three experimental stations in Shandong, China. The algorithms we used to construct the models included in our study were based on either K-means clustering, systematic clustering, or naïve Bayesian classification. When analyzing the reliability of our models, we found that, at more than 85%, the accuracy of the Bayesian model, which used the color information as inputs and involved the use of prior data in the form of the reference data we had obtained through manual classification, was significantly higher than that of the models based on systematic or the K-means clustering, which did not involve the use of prior data. It was interesting to note that the determination accuracy of algorithms using meteorological factors as inputs was significantly lower than that of those using color information. We also noted that the determination accuracy of the Bayesian model had some potential for optimization, which prompted us to subject the inputs of the model to a factor analysis in order to identify the key independent leaf color distribution parameters characterizing wheat freeze injury severity. This optimization allowed us to improve the determination accuracy of the model to over 90%, even in environments comprising several different ecological zones, as was the case at one of our experimental sites. In conclusion, our naïve Bayesian classification algorithm, which uses six key color gradation skewness-distribution parameters as inputs and involves the use of prior data in the form of manual assessments, qualifies as a contender for the development of commercial-grade wheat freeze injury severity monitoring systems supporting post-freeze management measures aimed at ensuring food security. [ABSTRACT FROM AUTHOR]

Medical image classification, a pivotal task for diagnostic accuracy, poses unique challenges due to the intricate and variable nature of medical images compared to their natural counterparts. While Convolutional Neural Networks (CNNs) and Transformers are prevalent in this domain, each architecture has its drawbacks. CNNs, despite their strength in local feature extraction, fall short in capturing global context, whereas Transformers excel at global information but can overlook fine-grained details. The integration of CNNs and Transformers in a hybrid model aims to bridge this gap by enabling simultaneous local and global feature extraction. However, this approach remains constrained in its capacity to model long-range dependencies, thereby hindering the efficient extraction of distant features. To address these issues, we introduce the MambaConvT model, which employs a state-space approach. It begins by locally processing input features through multi-core convolution, enhancing the extraction of deep, discriminative local details. Next, depth-separable convolution with a 2D selective scanning module (SS2D) is employed to maintain a global receptive field and establish long-distance connections, capturing the fine-grained features. The model then combines hybrid features for comprehensive feature extraction, followed by global feature modeling to emphasize on global detail information and optimize feature representation. This paper conducts thorough performance experiments on different algorithms across four publicly available datasets and two private datasets. The results demonstrate that MambaConvT outperforms the latest classification algorithms in terms of accuracy, precision, recall, F1 score, and AUC value ratings, achieving superior performance in the precise classification of medical images. [ABSTRACT FROM AUTHOR]

Vehicle classification technology is one of the foundations in the field of automatic driving. With the development of deep learning technology, visual transformer structures based on attention mechanisms can represent global information quickly and effectively. However, due to direct image segmentation, local feature details and information will be lost. To solve this problem, we propose an improved vision transformer vehicle classification network (IND-ViT). Specifically, we first design a CNN-In D branch module to extract local features before image segmentation to make up for the loss of detail information in the vision transformer. Then, in order to solve the problem of misdetection caused by the large similarity of some vehicles, we propose a sparse attention module, which can screen out the discernible regions in the image and further improve the detailed feature representation ability of the model. Finally, this paper uses the contrast loss function to further increase the intra-class consistency and inter-class difference of classification features and improve the accuracy of vehicle classification recognition. Experimental results show that the accuracy of the proposed model on the datasets of vehicle classification BIT-Vehicles, CIFAR-10, Oxford Flower-102, and Caltech-101 is higher than that of the original vision transformer model. Respectively, it increased by 1.3%, 1.21%, 7.54%, and 3.60%; at the same time, it also met a certain real-time requirement to achieve a balance of accuracy and real time. [ABSTRACT FROM AUTHOR]

Heart failure is a cardiovascular disease with significant morbidity and mortality, affecting a growing number of people worldwide [1]. The aim of this paper is to predict the probability of survival of patients by looking at their various characteristics, diseases, and lifestyles in the most successful way by using various machine learning methods. The 299 patients in the data set we use, had left ventricular systolic dysfunction in 2015 and are classified as New York Heart Association (NYHA) class III and IV. The probability of survival of patients is estimated by applying various machine learning methods on the data set. In this study, there are two versions. In the first version of the study, Principal Component Analysis (PCA) is used to reduce the size of the data set. The performance of the machine learning algorithms is then evaluated using a variety of metrics. In the second version, the data set is only subjected to machine learning techniques, and performance is then assessed. Accuracy, Matthews correlation coefficient (MCC), sensitivity, specifity, F1 score, receiver operating characteristic-area under the curve (ROC-AUC), and precision-recall area under the curve (PR-AUC) values are calculated to measure success. Comparing the two versions reveals that all machine learning algorithms in general have performed better in the second version without PCA. In the second version, the CatBoost algorithm gave the most successful result. Patients with heart failure can have their mortality status predicted using machine learning techniques. The goal of this paper is to look at a variety of characteristics in order to assess the patient's mortality status. The condition of the patient can be improved by selecting the proper treatment based on the mortality situation. [ABSTRACT FROM AUTHOR]

Although breast cancer, with easy recurrence and high mortality, has become one of the leading causes of cancer death in women, early and accurate diagnosis of breast cancer can effectively increase the likelihood of a cure. Therefore, it is particularly important to improve the accuracy of early diagnosis of breast cancer. However, conventional early diagnosis relies on human experience and has a low accuracy rate. Therefore, many researchers have proposed various machine learning methods to improve the accuracy and efficiency of prediction. Most of the existing studies around breast cancer classification adopt a single algorithm to fit breast cancer data but ignore the applicability of different breast cancer data features to the model. In this paper, we adopt machine algorithms to strip the features of machine learning methods from the rest of the features and attempt to enhance the model effect by designing deep learning model structures to find the hidden patterns in the rest of the features. In addition, due to strict medical data privacy requirements and high collection difficulty and cost, the model designed in this paper will be trained on a small number of samples. As a result, we attempt to find a minimization model for a breast cancer classification algorithm that features both low cost and high efficiency. At the same time, the deep learning model is further designed to complement the original model when it is possible to introduce complex data indicators. Experimental values show that the design model in this paper performs best not only under limited data and limited indicators but also under limited data complex indicators, demonstrating the effectiveness of the approach of mixed comparison and feature selection of multiple classification algorithms. In summary, the fusion model designed and implemented in this paper performs well in the experiments, and the accuracy of the model test reaches 98.3%. [ABSTRACT FROM AUTHOR]

Low-Level Virtual Machine (LLVM) compiler infrastructure is a useful tool for building just-in-time (JIT) compilers, besides its reliable front end represented by a clang compiler and its elaborated middle end containing different optimizations that improve the runtime performance. This paper specifically addresses the part of building a JIT compiler using an LLVM with the scope of obtaining the hardware architecture details of the underlying machine such as the number of cores and the number of logical cores per processing unit and providing them to the NUMA-BTLP static thread classification algorithm and to the NUMA-BTDM static thread mapping algorithm. Afterwards, the hardware-aware algorithms are run using the JIT compiler within an optimization pass. The JIT compiler in this paper is designed to run on a parallel C/C++ application (which creates threads using Pthreads), before the first time the application is executed on a machine. To achieve this, the JIT compiler takes the native code of the application, obtains the corresponding LLVM IR (Intermediate Representation) for the native code and executes the hardware-aware thread classification and the thread mapping algorithms on the IR. The NUMA-Balanced Task and Loop Parallelism (NUMA-BTLP) and NUMA-Balanced Thread and Data Mapping (NUMA-BTDM) are expected to optimize the energy consumption by up to 15% on the NUMA systems. [ABSTRACT FROM AUTHOR]

Background: For non-invasive brain-computer interface systems (BCIs) with multiple electroencephalogram (EEG) channels, the key factor limiting their convenient application in the real world is how to perform reasonable channel selection while ensuring task accuracy, which can be modeled as a multi-objective optimization problem. Therefore, this paper proposed a two-objective problem model for the channel selection problem and introduced a domain knowledge-assisted multi-objective optimization algorithm (DK-MOEA) to solve the aforementioned problem. Methods: The multi-objective optimization problem model was designed based on the channel connectivity matrix and comprises two objectives: one is the task accuracy and the other one can sensitively indicate the removal status of channels in BCIs. The proposed DK-MOEA adopted a two-space framework, consisting of the population space and the knowledge space. Furthermore, a knowledge-assisted update operator was introduced to enhance the search efficiency of the population space by leveraging the domain knowledge stored in the knowledge space. Results: The proposed two-objective problem model and DK-MOEA were tested on a fatigue detection task and four state-of-the-art multi-objective evolutionary algorithms were used for comparison. The experimental results indicated that the proposed algorithm achieved the best results among all the comparative algorithms for most cases by the Wilcoxon rank sum test at a significance level of 0.05. DK-MOEA was also compared with a version without the utilization of domain knowledge and the experimental results validated the effectiveness of the knowledge-assisted mutation operator. Moreover, the comparison between DK-MOEA and a traditional classification algorithm using all channels demonstrated that DK-MOEA can strike the balance between task accuracy and the number of selected channels. Conclusion: The formulated two-objective optimization model enabled the selection of a minimal number of channels without compromising classification accuracy. The utilization of domain knowledge improved the performance of DK-MOEA. By adopting the proposed two-objective problem model and DK-MOEA, a balance can be achieved between the number of the selected channels and the accuracy of the fatigue detection task. The methods proposed in this paper can reduce the complexity of subsequent data processing and enhance the convenience of practical applications. [ABSTRACT FROM AUTHOR]

With the continuous development of Internet technology, using multimedia for virtual application has become a new way. In this paper, by introducing the bayesian classification algorithm, multimedia graphics and video for carding, testing and implementation of edge image of fine processing, matching the corresponding text for quick positioning, at the same time use the filter for image and video background picture, further classification, distinguish between background and text, the extraction of superposition character. Simulation results show that the bayesian classification algorithm is effective and improves the efficiency and accuracy of image and video processing. [ABSTRACT FROM AUTHOR]

Education is essential and increasingly crucial for the development of almost all countries worldwide. As educational data has become increasingly available, scholars have shown a growing interest in exploring the correlation between students’ academic achievements and other factors that may impact their performance using machine learning algorithms. This research paper introduces a novel hybrid classifier that aims to predict the academic performance of students by using a combination of different single algorithms. The proposed hybrid classifier (PHC) is compared to six available classification algorithms (random forest (RF), C4.5, classification and regression trees (CART), support vector machines (SVM), naive Bayes (NB) and K-nearest neighbors (KNN)) using recall, precision, F1-score, and accuracy evaluation measures. Our experimental results reveal that the PHC classifier consistently outperforms the individual classifiers across multiple evaluation metrics. Specifically, the PHC classifier achieved an accuracy rate of 92.40%, surpassing the RF, C4.5, and CART classifiers, which were the next best performers. In terms of precision and F1 score, the PHC also demonstrated superior performance, indicating its robustness in correctly identifying positive instances and providing balanced accuracy. While the C4.5 classifier performed comparably to the PHC classifier concerning the recall metric, the hybrid model’s overall performance highlights its effectiveness in leveraging the complementary strengths of the included classifiers. The suggested hybrid model has the potential to enhance students’ academic performance and success more effectively and efficiently. It could benefit students, educators, and academic institutions. Additionally, it provides practical insights for educators and institutions striving to improve student achievement using predictive analysis. [ABSTRACT FROM AUTHOR]

The application of machine learning algorithms across various fields is gaining momentum, and the results increasingly emphasize the need for further testing and implementation. This is driven by the potential to streamline and expedite numerous processes. In this paper, we have employed five algorithms: KNN, Decision Tree, Random Forest, Logistic Regression, and Naive Bayes, and these algorithms have been tested in three large datasets. On average, their performance ranges from a minimum of 80% to a maximum of 90%. Data preprocessing has been completed, and concurrently, we have implemented the SMOTE algorithm to address the challenge of unbalanced data in this research. Simultaneously, the Naïve Bayes algorithm yields the most favorable results of Accuracy, Precision, Recall, and F1 Score, for the "is_arrested" class. Furthermore, to assess the performance of each algorithm, we employed metrics including Accuracy, Precision, Recall, and F1 Score. These metrics allowed us to decide which algorithm achieved the most effective classification. [ABSTRACT FROM AUTHOR]

Coordinated cyber-physical attacks (CCPAs) are dangerously stealthy and have considerable destructive effects against power grids. The problem of stealthy CCPA (SCCPA) localization, specifically identifying disconnected lines in attack, is a nonlinear multi-classification problem. To the best of our knowledge, only one paper has studied the problem; nevertheless, the total number of classifications is not appropriate. In the paper, we propose several methods to solve the problem of SCCPA localization. Firstly, considering the practical constraints and abiding by one of our previous studies, we elaborately determine the total number of classifications and design an approach for generating training and testing datasets. Secondly, we develop two algorithms to solve multiple classifications via the support vector machine (SVM) and random forest (RF), respectively. Similarly, we also present a one-dimensional convolutional neural network (1D-CNN) architecture. Finally, extensive simulations are carried out for IEEE 14-bus, 30-bus, and 118-bus power system, respectively, and we verify the effectiveness of our approaches in solving the problem of SCCPA localization. [ABSTRACT FROM AUTHOR]

With the increasing demand for high-resolution images, handling high-dimensional image data has become a key aspect of intelligence algorithms. One effective approach is to preserve the high-dimensional manifold structure of the data and find the accurate mappings in a lower-dimensional space. However, various non-sparse, high-energy occlusions in real-world images can lead to erroneous calculations of sample relationships, invalidating the existing distance-based manifold dimensionality reduction techniques. Many types of noise are difficult to capture and filter in the original domain but can be effectively separated in the frequency domain. Inspired by this idea, a novel approach is proposed in this paper, which obtains the high-dimensional manifold structure according to the correlationships between data points in the frequency domain and accurately maps it to a lower-dimensional space, named Frequency domain-based Manifold Dimensionality Reduction (FMDR). In FMDR, samples are first transformed into frequency domains. Then, interference is filtered based on the distribution in the frequency domain, thereby emphasizing discriminative features. Subsequently, an innovative kernel function is proposed for measuring the similarities between samples according to the correlationships in the frequency domain. With the assistance of these correlationships, a graph structure can be constructed and utilized to find the mapping in a low-dimensional space. To further demonstrate the effectiveness of the proposed algorithm, FMDR is employed for the semi-supervised classification problems in this paper. Experiments using public image datasets indicate that, compared to baseline algorithms and state-of-the-art methods, our approach achieves superior recognition performance. Even with very few labeled data, the advantages of FMDR are still maintained. The effectiveness of FMDR in dimensionality reduction and feature extraction of images makes it widely applicable in fields such as image processing and image recognition. [ABSTRACT FROM AUTHOR]

Currently, complex scene classification strategies are limited to high-definition image scene sets, and low-quality scene sets are overlooked. Although a few studies have focused on artificially noisy images or specific image sets, none have involved actual low-resolution scene images. Therefore, designing classification models around practicality is of paramount importance. To solve the above problems, this paper proposes a two-stage classification optimization algorithm model based on MPSO, thus achieving high-precision classification of low-quality scene images. Firstly, to verify the rationality of the proposed model, three groups of internationally recognized scene datasets were used to conduct comparative experiments with the proposed model and 21 existing methods. It was found that the proposed model performs better, especially in the 15-scene dataset, with 1.54% higher accuracy than the best existing method ResNet-ELM. Secondly, to prove the necessity of the pre-reconstruction stage of the proposed model, the same classification architecture was used to conduct comparative experiments between the proposed reconstruction method and six existing preprocessing methods on the seven self-built low-quality news scene frames. The results show that the proposed model has a higher improvement rate for outdoor scenes. Finally, to test the application potential of the proposed model in outdoor environments, an adaptive test experiment was conducted on the two self-built scene sets affected by lighting and weather. The results indicate that the proposed model is suitable for weather-affected scene classification, with an average accuracy improvement of 1.42%. [ABSTRACT FROM AUTHOR]

In the competitive landscape of steel-strip production, ensuring the high quality of steel surfaces is paramount. Traditionally, human visual inspection has been the primary method for detecting defects, but it suffers from limitations such as reliability, cost, processing time, and accuracy. Visual inspection technologies, particularly automation techniques, have been introduced to address these shortcomings. This paper conducts a thorough survey examining vision-based methodologies related to detecting and classifying surface defects on steel products. These methodologies encompass statistical, spectral, texture segmentation based methods, and machine learning-driven approaches. Furthermore, various classification algorithms, categorized into supervised, semi-supervised, and unsupervised techniques, are discussed. Additionally, the paper outlines the future direction of research focus. [ABSTRACT FROM AUTHOR]

With the rapid development of artificial intelligence in recent years, intelligent evaluation of college students' growth by means of the monitoring data from training processes is becoming a promising technique in the field intelligent education. Current studies, however, tend to utilize course grades, which are objective, to predict students' grade-point averages (GPAs), but usually neglect subjective factors like psychological resilience. To solve this problem, this paper takes mechanical engineering as the research object, and proposes a new machine-learning-driven GPA prediction approach to evaluate the academic performance of engineering students by incorporating psychological evaluation data into basic course scores. Specifically, this paper adopts SCL-90 psychological assessment data collected in the freshman year, including key mental health indicators such as somatization, depression, hostility, and interpersonal sensitivity indicators, as well as professional basic course scores, including mechanical principles, mechanical design, advanced mathematics, and engineering drawing. Four representative machine learning algorithms, Support Vector Machine (SVM), CNN-CBAM, Extreme Gradient Boosting (XGBoost) and Classification and Regression Tree (CART) that include deep and shallow models, respectively, are then employed to build a classification model for GPA prediction. This paper designs a validation experiment by tracking 229 students from the 2020 class from the School of Mechanical and Electrical Engineering of Henan University of Science and Technology, China. The students' academic performance in senior grades is divided into five classes to use as the prediction labels. It is verified that psychological data and course data can be effectively integrated into GPA prediction for college students, with an accuracy rate of 83.64%. Meanwhile, this paper also reveals that anxiety indicators in the psychological assessment data have the greatest impact on college students' academic performance, followed by interpersonal sensitivity. The experimental results also show that, for predicting junior year GPAs, psychological factors play more important role than they do in predicting sophomore GPAs. Suggestions are therefore given: the current practice in existing undergraduate teaching, i.e., only conducting psychological assessments in the initial freshman year, should be updated by introducing follow-up psychological assessments in each academic year. [ABSTRACT FROM AUTHOR]

Featured Application: The new algorithm proposed in this paper is mainly applied to radar data processing. By accurately distinguishing between targets and clutter, the clutter removal rate can be improved, and target trajectories can be quickly and accurately established. This algorithm can comprehensively utilize the advantages of classifiers and data characteristics, reducing the dependence on training samples. Therefore, it is also suitable for classification applications on small sample datasets. Accurately classifying targets and clutter plots is crucial in radar data processing. It is beneficial for filtering out a large amount of clutters and improving the track initiation speed and tracking accuracy of real targets. However, in practical applications, this problem becomes difficult due to complex electromagnetic environments such as cloud and rain clutter, sea clutter, and strong ground clutter. This has led to poor performance of some commonly used radar plot classification algorithms. In order to solve this problem and further improve classification accuracy, the radar plot classification algorithm based on evidence adaptive updating (RPC-EAU) is proposed in this paper. Firstly, the multi-dimensional recognition features of radar plots used for classification are established. Secondly, the construction and combination of mass functions based on feature sample distribution are designed. Then, a confidence network classifier containing an uncertain class was designed, and an iterative update strategy for it was provided. Finally, several experiments based on synthetic and real radar plots were presented. The results show that RPC-EAU can effectively improve the radar plot classification performance, achieving a classification accuracy of about 0.96 and a clutter removal rate of 0.95. Compared with some traditional radar pattern recognition algorithms, it can improve by 1 to 10 percentage points. The target loss rate of RPC-EAU is also the lowest, only about 0.02, which is about one third to one half of the comparison algorithms. In addition, RPC-EAU avoids clustering all radar points in each update, greatly saving the computational time. The proposed algorithm has the characteristics of high classification accuracy, low target loss rate, and less computational time. Therefore, it is suitable for radar data processing with high timeliness requirements and multiple radar plots. [ABSTRACT FROM AUTHOR]

At present, the commonly used Bag of Words (BOW) expression ignores the semantic information of text and the problems of high dimension and high sparsity of feature extraction. This paper presents a multi-class text representation and classification algorithm. This project is based on the vector expression of keywords and takes the multi-category classification problem as the research object. Then, a hybrid Deep Location network (HDBN) is constructed by combining DBN with Boltzmann (DBM). Then, this paper does a lot of tests on the algorithm and proves the effectiveness of the algorithm. In addition, the 2D visual experiment is carried out with HDBN, and then the high-level text expression based on HDBN is obtained. The expression has strong cohesion and weak coupling. [ABSTRACT FROM AUTHOR]

Nowadays researchers are investing in electrical machines fault diagnosis area. The users and manufacturers are strong for containing diagnostic features for reliability and scalability improvement. The regular monitoring enables machine faults early detection and hence helpful for automation by providing process control. The fault detection performance and machinelearning algorithms classification are highly dependent on features involved. The aim of this paper is to solve the network mechanical vibration problem and for that a research on mechanical vibration fault diagnosis is proposed. The first is to use the vibration signal receiving device to record the vibration signal of the target device. In the process of receiving the signal, the measurement point is related to the accuracy of the received signal, so it is necessary to prepare the measurement point. Secondly, the principle of fault detection based on vibration detection is introduced. The main purpose of this method is to identify the fault characteristics, simulate the fault with MATLAB, and obtain the error time-frequency diagram behavior. The feature vector dimension obtained by the idling confirmation example is the same as that of the rotor, which is 14, including 8 relative wavelet packet intensity entropy feature indexes and higher values, minimum value, peak-to-peak value, mean value, mean square error and variance. Finally, the deficiencies of the detected vibration faults are identified and similar improvements are proposed. Improvements only reduce signal vibration, disrupting feature isolation and identifying patterns. The observed percentage accuracy for classification of faults through proposed approach is 98.2%. [ABSTRACT FROM AUTHOR]

INTRODUCTION: Sports video is an essential information resource. Classifying sports videos with high accuracy can effectively improve users' browsing and query effect. This project intends to study a motion video classification algorithm based on deep-learning particle filters to solve the problems of solid subjectivity and low accuracy of existing motion video classification algorithms. A critical box extraction method based on similarity is proposed. The moving video classification algorithm is studied based on a deep learning coding model. Examples of various types of sports videos are analyzed. The overall performance of the motion video classification algorithm proposed in this paper is much better than other existing motion video classification algorithms. This algorithm can significantly improve the classification performance of motion video. [ABSTRACT FROM AUTHOR]

Quickly and accurately judging the quality grades of apples is the basis for choosing suitable harvesting date and setting a suitable storage strategy. At present, the research of multi-task classification algorithm models based on CNN is still in the exploration stage, and there are still some problems such as complex model structure, high computational complexity and long computing time. This paper presents a light-weight architecture based on multi-task convolutional neural networks for maturity (L-MTCNN) to eliminate immature and defective apples in the intelligent integration harvesting task. L-MTCNN architecture with diseases classification sub-network (D-Net) and maturity classification sub-network (M-Net), to realize multi-task discrimination of the apple appearance defect and maturity level. Under different light conditions, the image of fruit may have color damage, which makes it impossible to accurately judge the problem, an image preprocessing method based on brightness information was proposed to restore fruit appearance color under different illumination conditions in this paper. In addition, for the problems of inaccurate prediction results caused by tiny changes in apple appearance between different maturity levels, triplet loss is introduced as the loss function to improve the discriminating ability of maturity classification task. Based on the study and analysis of apple grade standards, three types of apples were taken as the research objects. By analyzing the changes in apple fruit appearance in each stage, the data set corresponding to the maturity level and fruit appearance was constructed. Experimental results show that D-Net and M-Net have significantly improved recall rate, precision rate and F1-Score in all classes compared with AlexNet, ResNet18, ResNet34 and VGG16. [ABSTRACT FROM AUTHOR]

This paper aims to improve the accuracy of sentiment analysis on Apache Spark for a real-time general twitter data. A lot of works exist on sentiment analysis on offline or stored twitter data that uses several classification algorithms on relevant features extracted using well-known feature extraction methodologies on pre-processed text data. However, not much works exist for sentiment analysis of real-time twitter data and especially for the generic data on big data processing platforms such as Apache Spark. This paper proposes a real-time sentiment analysis for generic twitter data through Apache Spark using six classification algorithms on N-gram and Term Frequency - Inverse Document Frequency (TF-IDF) feature extraction methodologies on the pre-processed data. An exhaustive comparison is done using Logistic Regression (LR), Multinomial Naive Bayes (MNB), Random Forest Classfier(RFC), Support Vector Machine (SVM), K-Nearest Neighbour (K-NN), and Decision Tree (DT) classification algorithms. It is observed that the trigram feature extraction method performs the best on LR and SVM and the RFC results are also comparable on the considered general tweets data. [ABSTRACT FROM AUTHOR]

Due to the numerous objects with regular structures in indoor environments, identifying and modeling the regular objects in scenes aids indoor robots in sensing unknown environments. Typically, point cloud preprocessing can obtain highly complete object segmentation results in scenes which can be utilized as the objects for geometric analysis and modeling, thus ensuring modeling accuracy and speed. However, due to the lack of a complete object model, it is not possible to recognize and model segmented objects through matching methods. To achieve a greater understanding of scene point clouds, this paper proposes a direct geometric modeling algorithm based on segmentation results, which focuses on extracting regular geometries in the scene, rather than objects with geometric details or combinations of multiple primitives. This paper suggests using simpler geometric models to describe the corresponding point cloud data. By fully utilizing the surface structure information of segmented objects, the paper analyzes the types of faces and their relationships to classify regular geometric objects into two categories: planar and curved. Different types of geometric objects are fitted using random sampling consistency algorithms with type classification results as prior knowledge, and segmented results are modeled through a combination of size information associated with directed bounding boxes. For indoor scenes with occlusion and stacking, utilizing a higher-level semantic expression can effectively simplify the scene, complete scene abstraction and structural modeling, and aid indoor robots' understanding and further operation in unknown environments. [ABSTRACT FROM AUTHOR]

In order to reduce the influence of redundant features on the performance of the model in the process of accelerometer behavior recognition, and to improve the recognition accuracy of the model, this paper proposes an improved Whale Optimization algorithm with mixed strategy (IWOA) combined with the extreme gradient boosting algorithm (XGBoost) as a preferred method for chicken behavior identification features. A nine-axis inertial sensor was used to obtain the chicken behavior data. After noise reduction, the sliding window was used to extract 44 dimensional features in the time domain and frequency domain. To improve the search ability of the Whale Optimization algorithm for optimal solutions, the introduction of the good point set improves population diversity and expands the search range; the introduction of adaptive weight balances the search ability of the optimal solution in the early and late stages; the introduction of dimension-by-dimension lens imaging learning based on the adaptive weight factor perturbs the optimal solution and enhances the ability to jump out of the local optimal solution. This method's effectiveness was verified by recognizing cage breeders' feeding and drinking behaviors. The results show that the number of feature dimensions is reduced by 72.73%. At the same time, the behavior recognition accuracy is increased by 2.41% compared with the original behavior feature dataset, which is 95.58%. Compared with other dimensionality reduction methods, the IWOA–XGBoost model proposed in this paper has the highest recognition accuracy. The dimension reduction results have a certain degree of universality for different classification algorithms. This provides a method for behavior recognition based on acceleration sensor data. [ABSTRACT FROM AUTHOR]

Cloud thermodynamic phase (ice, liquid, undetermined) classification is an important first step for cloud retrievals from passive sensors such as MODIS (Moderate-Resolution Imaging Spectroradiometer). Because ice and liquid phase clouds have very different scattering and absorbing properties, an incorrect cloud phase decision can lead to substantial errors in the cloud optical and microphysical property products such as cloud optical thickness or effective particle radius. Furthermore, it is well established that ice and liquid clouds have different impacts on the Earth's energy budget and hydrological cycle, thus accurately monitoring the spatial and temporal distribution of these clouds is of continued importance. For MODIS Collection 6 (C6), the shortwave-derived cloud thermodynamic phase algorithm used by the optical and microphysical property retrievals has been completely rewritten to improve the phase discrimination skill for a variety of cloudy scenes (e.g., thin/thick clouds, over ocean/land/desert/snow/ice surface, etc). To evaluate the performance of the C6 cloud phase algorithm, extensive granule-level and global comparisons have been conducted against the heritage C5 algorithm and CALIOP. A wholesale improvement is seen for C6 compared to C5. [ABSTRACT FROM AUTHOR]

Dragon fruit is one of the most popular fruits in China and Southeast Asia. It, however, is mainly picked manually, imposing high labor intensity on farmers. The hard branches and complex postures of dragon fruit make it difficult to achieve automated picking. For picking dragon fruits with diverse postures, this paper proposes a new dragon fruit detection method, not only to identify and locate the dragon fruit, but also to detect the endpoints that are at the head and root of the dragon fruit, which can provide more visual information for the dragon fruit picking robot. First, YOLOv7 is used to locate and classify the dragon fruit. Then, we propose a PSP-Ellipse method to further detect the endpoints of the dragon fruit, including dragon fruit segmentation via PSPNet, endpoints positioning via an ellipse fitting algorithm and endpoints classification via ResNet. To test the proposed method, some experiments are conducted. In dragon fruit detection, the precision, recall and average precision of YOLOv7 are 0.844, 0.924 and 0.932, respectively. YOLOv7 also performs better compared with some other models. In dragon fruit segmentation, the segmentation performance of PSPNet on dragon fruit is better than some other commonly used semantic segmentation models, with the segmentation precision, recall and mean intersection over union being 0.959, 0.943 and 0.906, respectively. In endpoints detection, the distance error and angle error of endpoints positioning based on ellipse fitting are 39.8 pixels and 4.3°, and the classification accuracy of endpoints based on ResNet is 0.92. The proposed PSP-Ellipse method makes a great improvement compared with two kinds of keypoint regression method based on ResNet and UNet. Orchard picking experiments verified that the method proposed in this paper is effective. The detection method proposed in this paper not only promotes the progress of the automatic picking of dragon fruit, but it also provides a reference for other fruit detection. [ABSTRACT FROM AUTHOR]

Fine classification of urban nighttime lighting is a key prerequisite step for small-scale nighttime urban research. In order to fill the gap of high-resolution urban nighttime light image classification and recognition research, this paper is based on a small rotary-wing UAV platform, taking the nighttime static monocular tilted light images of communities near Meixi Lake in Changsha City as research data. Using an object-oriented classification method to fully extract the spectral, textural and geometric features of urban nighttime lights, we build four types of classification models based on random forest (RF), support vector machine (SVM), K-nearest neighbor (KNN) and decision tree (DT), respectively, to finely extract five types of nighttime lights: window light, neon light, road reflective light, building reflective light and background. The main conclusions are as follows: (i) The equal division of the image into three regions according to the visual direction can alleviate the variable scale problem of monocular tilted images, and the multiresolution segmentation results combined with Canny edge detection are more suitable for urban nighttime lighting images; (ii) RF has the highest classification accuracy among the four classification algorithms, with an overall classification accuracy of 95.36% and a kappa coefficient of 0.9381 in the far view region, followed by SVM, KNN and DT as the worst; (iii) Among the fine classification results of urban light types, window light and background have the highest classification accuracy, with both UA and PA above 93% in the RF classification model, while road reflective light has the lowest accuracy; (iv) Among the selected classification features, the spectral features have the highest contribution rates, which are above 59% in all three regions, followed by the textural features and the geometric features with the smallest contribution rates. This paper demonstrates the feasibility of nighttime UAV static monocular tilt image data for fine classification of urban light types based on an object-oriented classification approach, provides data and technical support for small-scale urban nighttime research such as community building identification and nighttime human activity perception. [ABSTRACT FROM AUTHOR]