检索结果-内蒙古大学图书馆

High-Confidence Sample Generation Technology and Application for Global Land-Cover classification

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2023年 16卷 3248-3263页

作者： Xi, Xinyuan Liu, Zhimin Sun, Lin Xie, Shuai Wang, Zhihui Shandong Univ Sci & Technol Coll Geodesy & Geomat Qingdao 266590 Peoples R China

Deep learning technology has become one of the most important technologies in remote sensing land classification applications. Its powerful sample-learning and information-mining abilities promote the continuous improvement of classification accuracy. A large volume of high-quality and representative sample data is the premise for the successful application of deep learning technology. Conventional methods of obtaining samples through manual delineation or surface surveys require a great deal of manpower and material resources. Therefore, the inability to obtain sufficient and widely representative high-quality samples is one of the key factors limiting the application of deep learning technology. In this study, the method of generating sample data obtains high-confidence classification results from a variety of existing high-quality classification products as deep learning samples, which are then used to support the application of deep learning technology for land-cover classification. When the three global land-cover classification products, FROM-GLC-2015, GLC_FCS30-2015, and GlobeLand30, have the same type of discrimination, the sample is considered a high-confidence sample. Based on this, a large volume of sample data widely distributed around the world was obtained. Using the extracted samples, a random forest classifier was trained using multiple types of information from the Landsat data, and land-cover classification was achieved. Application experiments were conducted in several typical regions, and the classification results were verified. The results showed that the classification accuracy of random forests under the support of samples generated using the sample extraction method proposed in this article was considerably higher than that of the three land-cover classification products.

关键词： Training Remote sensing Earth Deep learning classification algorithms Data models Artificial satellites classification land-cover classification Landsat random forest sample generation

来源：评论

学校读者我要写书评

暂无评论

Boosting With Prior for Accurate classification

引用

IEEE ACCESS 2023年 11卷 128125-128134页

作者： Baig, Mubasher Ejaz, Tahir Fahad, Khawaja M. Gilani, Syed Asif Mehmood Awais, Mian M. Saeed, Sana Natl Univ Comp & Emerging Sci NUCES Dept Comp Sci Lahore 54770 Pakistan Lahore Univ Management Sci LUMS Dept Comp Sci Lahore 54792 Pakistan

Adaptive Boosting (AdaBoost) based meta learning algorithms generate an accurate classifier ensemble using a learning algorithm with only moderate accuracy guarantees. These algorithms have been designed to work in typical supervised learning settings and hence use only labeled training data along with a base learning algorithm to form an ensemble. However, significant knowledge about the solution space might be available along with training data. The accuracy and convergence rate of AdaBoost might be improved using such knowledge. An effective way to incorporate such knowledge into boosting based ensemble learning algorithms is presented in this paper. Using several synthetic and real datasets, empirical evidence is reported to show the effectiveness of proposed *** improvements have been obtained by applying the proposed method for detecting roads in aerial images.

关键词： classification algorithms Boosting Training Training data Ensemble learning Mathematical models Convergence AdaBoost ensemble learning prior/domain knowledge

来源：评论

学校读者我要写书评

暂无评论

Open-Set classification for Signal Diagnosis of Machinery Sensor in Industrial Environment

引用

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 2023年第3期19卷 2574-2584页

作者： Chen, Jianming Wang, Guangjin Lv, Jiancheng He, Zhenan Yang, Taibo Tang, Chenwei Sichuan Univ Coll Comp Sci Chengdu 610065 Peoples R China Sichuan Univ Nucl Power Inst China Reactor Engn Res Subinst Chengdu 610065 Peoples R China

In recent years, the signal diagnosis on devices operating under industrial environment has attracted increasing attention. Most data-driven signal diagnosis methods are based on a closed-set assumption that class sets of training and test data are the same. However, in industrial scenarios, during the running process of the device, the operating environment and condition may change over time, continuing generating data belonging to unknown classes with new characteristics and distribution. The unknown classes usually reflect new modes or faults of the device needed to be captured. They are unavailable in training phase, contradicting the closed-set assumption. Existing methods are inappropriate to this type of open-set classification, requiring to classify known classes and recognize unknown classes. To address this challenging problem, this article proposes a generic open-set signal classification method. First, we apply Fourier transform to convert the sensor signals from time domain to frequency domain, then data in the time and frequency domains are fused. Next, a variational encoder-classifier network is proposed to classify known classes and learn the distribution of feature space to extract robust latent features. Finally, based on extreme value theory and entropy, a pair of discriminators determine whether samples belong to unknown or not. The experimental results on two vibration-signal datasets from bearings and nuclear reactor demonstrate the effectiveness and superiority of our proposed open-set signal classification method, especially in practical applications.

关键词： Training Feature extraction Anomaly detection classification algorithms Time-domain analysis Testing Clustering algorithms Deep learning (DL) fault diagnosis machine health monitoring open-set classification vibration signal

来源：评论

学校读者我要写书评

暂无评论

Improving Non-Negative Positive-Unlabeled Learning for News Headline classification

引用

IEEE ACCESS 2023年 11卷 40192-40203页

作者： Ji, Zhanlin Du, Chengyuan Jiang, Jiawen Zhao, Li Zhang, Haiyang Ganchev, Ivan North China Univ Sci & Technol Coll Artificial Intelligence Tangshan 063210 Peoples R China Tsinghua Univ Inst Precis Med Beijing Natl Res Ctr Informat Sci & Technol Beijing 100084 Peoples R China Xian Jiaotong Liverpool Univ Dept Comp Suzhou 215000 Peoples R China Univ Limerick Telecommun Res Ctr TRC Limerick V94 T9PX Ireland Univ Plovdiv Paisii Hilendarski Dept Comp Syst Plovdiv 4000 Bulgaria Bulgarian Acad Sci Inst Math & Informat Sofia 1040 Bulgaria

With the development of Internet technology, network platforms have gradually become a tool for people to obtain hot news. How to filter out the current hot news from a large number of news collections and push them to users has important application value. In supervised learning scenarios, each piece of news needs to be labeled manually, which takes a lot of time and effort. From the perspective of semi-supervised learning, on the basis of the non-negative Positive-Unlabeled (nnPU) learning, this paper proposes a novel algorithm, called 'Enhanced nnPU with Focal Loss' (FLPU), for news headline classification, which uses the Focal Loss to replace the way the classical nnPU calculates the empirical risk of positive and negative samples. Then, by introducing the Virtual Adversarial Training (VAT) of the Adversarial training for large neural LangUage Models (ALUM) into FLPU, another (and better) algorithm, called 'FLPU+ALUM', is proposed for the same purpose, aiming to label only a small number of positive samples. The superiority of both algorithms to the state-of-the-art PU algorithms considered is demonstrated by means of experiments, conducted on two datasets for performance comparison. Moreover, through another set of experiments, it is shown that, if enriched by the proposed algorithms, the RoBERTa-wwm-ext model can achieve better classification performance than the state-of-the-art binary classification models included in the comparison. In addition, a 'Ratio Batch' method is elaborated and proposed as more stable for use in scenarios involving only a small number of labeled positive samples, which is also experimentally demonstrated.

关键词： Labeling classification algorithms Text categorization Artificial neural networks Support vector machines Feature extraction Task analysis Adversarial machine learning Text classification non-negative positive-unlabeled (nnPU) learning focal loss virtual adversarial training (VAT) adversarial training for large neural language models (ALUM)

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous Feature Based Time Series classification With Attention Mechanism

引用

IEEE ACCESS 2023年 11卷 19373-19384页

作者： Zhang, Hanbo Wang, Peng Liang, Shen Zhou, Tongming Wang, Wei Fudan Univ Sch Comp Sci Shanghai 200438 Peoples R China Univ Paris Cite Data Intelligence Inst Paris diiP F-75013 Paris France

Time series classification (TSC) problem has been a significantly attractive research problem for decades. A large number of models with various types of features have been proposed. However, with the rapid development of new applications, like IoT and intelligent manufacturing, the time series data from different industries and applications are constantly emerging. To classify these data accurately, data scientists face the challenges of 1) how to select the optimal features and classification models and 2) how to interpret the results. To tackle these two challenges, in this paper, we propose a heterogeneous feature ensemble network, named FEnet. Multiple features, including time-domain, frequency-domain, and so on, are combined to build the model so that it can deal with the diversity of the data characteristics. Furthermore, to improve the interpretability, we propose a two-level attention mechanism. Finally, we propose two model optimization strategies to enhance classification accuracy and efficiency. Extensive experiments are conducted on real datasets and the results verify the accuracy, operation efficiency, and interpretability of FEnet.

关键词： Time series analysis Feature extraction Time-domain analysis Task analysis Data models Deep learning classification algorithms Time series classification feature ensemble attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Lower Limb Motion classification Using Energy Density Features of Surface Electromyography Signals' Activation Region and Dynamic Ensemble Model

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2023年 72卷 1页

作者： Qin, Pengjie Shi, Xin Han, Kesong Fan, Zhirui Chongqing Univ Sch Automat Chongqing 400044 Peoples R China Chinese Acad Sci Shenzhen Inst Adv Technol Shenzhen 518000 Peoples R China

Accurate classification of lower limb movements based on surface electromyography (sEMG) signals is vital for wearable auxiliary devices in military and medical rehabilitation. It is difficult to accurately obtain the effective features of the active region and establish a reliable classification model of complex lower limb motion modes due to the strong dynamic time variability of the sEMG signals. Thus, an onset point detection algorithm, namely, the maximum interclass variance (MIV) algorithm, was proposed to determine an accurate activation signal region. Then, a variational modal correlation dimension (VMCD) algorithm was proposed for feature construction to obtain the energy density feature (EDF) of the activation region, which reflects the activation signal's amplitude energy distribution state. Finally, a random sampling multiclassifier dynamic ensemble (RSDE) algorithm was proposed to rapidly construct an ensemble model by adapting to the feature changes of the sEMG signals. A total of 25 subjects were recruited to participate in the experiment. Compared with the other methods, the proposed method could accurately classify five lower limb motions by collecting only the data from three lower limb muscles. The average accuracy and response time were better than those of many existing classification methods. This indicates that the proposed method can improve the man-machine cooperative response speed, which is beneficial to enhance the application effect of sEMG auxiliary equipment.

关键词： Feature extraction Windows classification algorithms Muscles Heuristic algorithms Sensors Adaptation models Correlation dimension (CD) ensemble model feature extraction motion classification onset point detection surface electromyography (sEMG)

来源：评论

学校读者我要写书评

暂无评论

classification of Epileptic and Psychogenic Non-Epileptic Seizures Using Electroencephalography and Electrocardiography

引用

IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING 2023年 31卷 2831-2838页

作者： Xiong, Wenjuan Nurse, Ewan S. Lambert, Elisabeth Cook, Mark J. Kameneva, Tatiana Swinburne Univ Technol Sch Sci Comp & Engn Technol Hawthorn Vic 3122 Australia Seer Med Melbourne Vic 3000 Australia Univ Melbourne St Vincents Hosp Dept Med Melbourne Vic 3010 Australia Swinburne Univ Technol Sch Hlth Sci Hawthorn Vic 3122 Australia Swinburne Univ Technol Iverson Hlth Innovat Res Inst Hawthorn Vic Australia Univ Melbourne Graeme Clark Inst Melbourne Vic 3010 Australia Swinburne Univ Technol Iverson Hlth Innovat Res Inst Sch Sci Comp & Engn Technol Hawthorn Vic 3122 Australia Univ Melbourne Dept Biomed Engn Melbourne Vic 3010 Australia

Patients with psychogenic non-epileptic seizures (PNES) may exhibit similar clinical features to patients with epileptic seizures (ES). Misdiagnosis of PNES and ES can lead to inappropriate treatment and significant morbidity. This study investigates the use of machine learning techniques for classification of PNES and ES based on electroencephalography (EEG) and electrocardiography (ECG) data. Video-EEG-ECG of 150 ES events from 16 patients and 96 PNES from 10 patients were analysed. Four preictal periods (time before event onset) in EEG and ECG data were selected for each PNES and ES event (60-45 min, 45-30 min, 30-15 min, 15-0 min). Time-domain features were extracted from each preictal data segment in 17 EEG channels and 1 ECG channel. The classification performance using k-nearest neighbour, decision tree, random forest, naive Bayes, and support vector machine classifiers were evaluated. The results showed the highest classification accuracy was 87.83% using the random forest on 15-0 min preictal period of EEG and ECG data. The performance was significantly higher using 15-0 min preictal period data than 30-15 min, 45-30 min, and 60-45 min preictal periods (p<0.001). The classification accuracy was improved from 86.37% to 87.83% by combining ECG data with EEG data (p<0.001). The study provided an automated classification algorithm for PNES and ES events using machine learning techniques on preictal EEG and ECG data.

关键词： Electroencephalography Electrocardiography Random forests Feature extraction Australia Support vector machines classification algorithms classification epileptic seizures (ES) electroencephalography (EEG) electrocardiography (ECG) machine learning psychogenic non-epileptic seizures (PNES)

来源：评论

学校读者我要写书评

暂无评论

Pre-Trained Model-Based NFR classification: Overcoming Limited Data Challenges

引用

IEEE ACCESS 2023年 11卷 81787-81802页

作者： Rahman, Kiramat Ghani, Anwar Alzahrani, Abdulrahman Tariq, Muhammad Usman Rahman, Arif Ur Int Islamic Univ Islamabad Dept Software Engn Islamabad 44000 Pakistan Int Islamic Univ Islamabad Dept Comp Sci Islamabad 44000 Pakistan Univ Jeddah Coll Comp Sci & Engn Jeddah 23218 Saudi Arabia Abu Dhabi Univ Abu Dhabi Sch Management Abu Dhabi U Arab Emirates Bahria Univ Dept Comp Sci Islamabad 44000 Pakistan

Machine learning techniques have shown promising results in classifying non-functional requirements (NFR). However, the lack of annotated training data in the domain of requirement engineering poses challenges to the accuracy, generalization, and reliability of ML-based methods, including overfitting, poor performance, biased models, and out-of-vocabulary issues. This study presents an approach for the classification of NFR in software requirements specification documents by extracting features from word embedding pre-trained models. The novel algorithms are specifically designed to extract relevant representative features from pre-trained word embedding models. In addition, each pre-trained model is paired with the four tailored neural network architectures for NFR classification including RPCNN, RPBiLSTM, RPLSTM, and RPANN. This combination results in the creation of twelve unique models, each with its unique configuration and characteristics. The results show that the integration of pre-trained GloVe models with RPBiLSTM demonstrates the highest performance, achieving an impressive average Area Under the Curve (AUC) score of 96%, a precision of 85%, and recall of 82%, highlighting its strong ability to accurately classify NFRs. Furthermore, among the integration of pre-trained Word2Vec models, RPLSTM achieved notable results, with an AUC score of 95%, precision of 86%, and recall of 80%. Similarly, integrated fastText-based pre-trained models the RPBiLSTM yield competitive performance, with an AUC score of 95%, precision of 85%, and recall of 80%. This comprehensive and integrated approach provides a practical solution for effectively analyzing and classifying NFR, thereby facilitating improved software development practices.

关键词： Feature extraction Data models classification algorithms Software algorithms Training Requirements engineering Task analysis Software engineering requirements engineering NFR classifications pre-trained model machine learning natural language processing

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving classification in Multiple Clouds eHealthcare

引用

IEEE TRANSACTIONS ON SERVICES COMPUTING 2023年第1期16卷 493-503页

作者： Wang, Shenqing Ge, Chunpeng Zhou, Lu Wang, Huaqun Liu, Zhe Wang, Jian Nanjing Univ Aeronaut & Astronaut Coll Comp Sci & Technol Nanjing 210016 Peoples R China Nanjing Univ Aeronaut Astronaut Shenzhen Res Inst State Key Lab Cryptol Beijing 100878 Peoples R China Nanjing Univ Posts & Telecommun Sch Comp Sci Nanjing 210003 Peoples R China

Internet of Things (IoT) is increasingly being used in real life, especially in the eHealthcare field. Among eHealthcare, the application of predicting patients' health status based on their daily activity data which is collected by IoT equipment has attracted extensive attentions and researches. In this application, patients' data which are treated as time-series data are transmitted to healthcare center (HC), then HC makes predictions based on an established classification model. However, making predictions using classification models requires a lot of computing resources, while HC usually cannot afford such numerous calculations. The use of the cloud solves the problem of insufficient computing resources, but it causes another problem, namely the leakage of user privacy. In particular, not only patients' data leak patients' privacy information, the classification model also causes the privacy disclosure of patients and HC. Therefore, we propose a method to store patients' data and classification model in multiple clouds respectively. According to the method, we design a new system model and propose an algorithm which can protect patients' data and classification model from leakage and offload calculation to multiple clouds. Our algorithm can better protect privacy of patients and HC in more complex classification scene, and can effectively reduce the computational cost of the healthcare center.

关键词： Hidden Markov models Cloud computing Privacy classification algorithms Data models Computational modeling Monitoring HMM eHealthcare privacy-preserving

来源：评论

学校读者我要写书评

暂无评论

Accelerating Crop Yield: Multisensor Data Fusion and Machine Learning for Agriculture Text classification

引用

IEEE ACCESS 2023年 11卷 20795-20805页

作者： Reyana, A. Kautish, Sandeep Karthik, P. M. Sharan Al-Baltah, Ibrahim Ahmed Jasser, Muhammed Basheer Mohamed, Ali Wagdy Karunya Inst Technol & Sci Dept Comp Sci & Engn Coimbatore 641114 Tamil Nadu India Dept Comp Sci & Engn LBEF Campus Kathmandu 44600 Nepal SSM Inst Engn & Technol Dept Civil Engn Dindigul 624002 Tamil Nadu India Sanaa Univ Fac Comp Sci & Informat Technol Dept Informat Technol Sanaa Yemen Sunway Univ Sch Engn & Technol Dept Comp & Informat Syst Petaling Jaya 47500 Selangor Malaysia Cairo Univ Fac Grad Studies Stat Res Operat Res Dept Giza 12613 Egypt Amer Univ Cairo Sch Sci & Engn Dept Math & Actuarial Sci Cairo 11835 Egypt

Sensors are now used by farmers and agronomists to help them improve their operations. They use sensor data transmitted via IoT to remotely monitor their crops. Farmers today manage crops in a controlled environment to increase yields in the name of modern farming. Crop productivity, on the other hand, is influenced by the severity of the weather and disease variations. The primary objective of this paper is to present a novel Multisensor Machine-Learning Approach (MMLA) for classifying multisensor data. The fusion strategy supports high-quality data analysis in agricultural contexts for cultivation recommendations. Based on the proposed recommendation system, eight crops were classified: cotton, gram, groundnut, maize, moong, paddy, sugarcane, and wheat. Crop species were classified using three machine learning algorithms: J48 Decision Tree, Hoeffding Tree, and Random Forest. To evaluate the performance of the proposed multi-text classifier, only the top eight classes were investigated. The classifier's performance is measured in terms of precision, recall, F-measure, MCC, ROC Area, and PRC Area class, and the results are compared with the state-of-the-art classifiers. The Random forest algorithm has the lowest error measure of RMSE at 13%, RAE at 38.67%, and RRSE at 44.21%, demonstrating effectiveness in classifying the agriculture text. Thus, the use of a multisensor data fusion approach based on crop recommendation provides greater precision in prediction, resulting in a significant increase in crop yield while also creating awareness in the condition-based environmental monitoring system.

关键词： Crops Agriculture Sensors Monitoring Random forests classification algorithms Data integration Machine learning crop yield cultivation recommendation farmers multisensor machine learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：