检索结果-内蒙古大学图书馆

algorithm using supervised subspace learning and non-local representation for pose variation recognition

IET COMPUTER VISION 2020年第7期14卷 528-537页

作者： Liao, Mengmeng Wang, Changzhi Gu, Xiaodong Fudan Univ Dept Elect Engn Shanghai 200433 Peoples R China

Pose variation has been one of the challenges of face recognition. To solve this challenge, the authors propose a classification algorithm using supervised subspace learning and non-local representation (SSLNR). In SSLNR, they first propose a supervised subspace learning algorithm (SSLA). SSLA includes three different terms. The first term is the difference term, which can reduce the intra-class differences. The second term is the block-diagonal regularisation term, which promotes the samples to be represented by intra-class samples. The last one is the noise robust term. Then, the original samples are mapped to the learned subspace by using SSLA. Thus, the intra-class differences of the samples mapped to the learned subspace are reduced. Finally, those mapped samples are classified by proposed non-local constraint-based extended sparse representation classifier. SSLNR is extensively evaluated using four databases, namely Georgia Tech, Label faces in the wild, FEI and CVL. Experimental results show that SSLNR achieves better performance than some state-of-the-art algorithms, such as DARG and RRNN.

关键词： sample mapping supervised subspace learning algorithm learned subspace pose variation recognition block-diagonal regularisation term image classification learning (artificial intelligence) feature extraction nonlocal constraint-based extended sparse representation classifier intra-class differences image representation classification algorithm nonlocal representation intra-class samples pose estimation SSLA SSLNR face recognition noise robust term

来源：评论

学校读者我要写书评

暂无评论

Ensemble Machine Learning Model to Predict the Waterborne Syndrome

引用

algorithmS 2022年第3期15卷 93页

作者： Gollapalli, Mohammed Imam Abdulrahman Bin Faisal Univ Coll Comp Sci & Informat Technol Dept Comp Informat Syst POB 1982 Dammam 31441 Saudi Arabia

The COVID-19 epidemic has highlighted the significance of sanitization and maintaining hygienic access to clean water to reduce mortality and morbidity cases worldwide. Diarrhea is one of the prevalent waterborne diseases caused due to contaminated water in many low-income countries with similar living conditions. According to the latest statistics from the World Health Organization (WHO), diarrhea is among the top five primary causes of death worldwide in low-income nations. The condition affects people in every age group due to a lack of proper water used for daily living. In this study, a stacking ensemble machine learning model was employed against traditional models to extract clinical knowledge for better understanding patients' characteristics;disease prevalence;hygienic conditions;quality of water used for cooking, bathing, and toiletries;chemicals used;therapist's medications;and symptoms that are reflected in the field study data. Results revealed that the ensemble model provides higher accuracy with 98.90% as part of training and testing phases when experimented against frequently used J48, Naive Bayes, SVM, NN, PART, Random Forest, and Logistic Regression models. Managing outcomes of this research in the early stages could assist people in low-income countries to have a better lifestyle, fewer infections, and minimize expensive hospital visits.

关键词： waterborne disease classification algorithm machine learning data mining retrospective analysis artificial intelligence public health prevalence and management

来源：评论

学校读者我要写书评

暂无评论

Wearable Pressure Sensor Suit for Real-Time Detection of Incorrect Exercise Techniques

Wearable Pressure Sensor Suit for Real-Time Detection of Inc...

引用

IEEE Sensors

作者： Ivin Kuriakose Shirley Chauhan Anis Fatema Aftab M. Hussain FeCS Lb Cener for VLSI nd Ebedded Syses Technoogy (CVEST) Inernion Insiue of Inforion Technoogy Hyderbd IndiFeCS Lb Cener for VLSI nd Ebedded Syses Technoogy (CVEST) Inernion Insiue of Inforion Technoogy Hyderbd IndiFeCS Lb Cener for VLSI nd Ebedded Syses Technoogy (CVEST) Inernion Insiue of Inforion Technoogy Hyderbd IndiFeCS Lb Cener for VLSI nd Ebedded Syses Technoogy (CVEST) Inernion Insiue of Inforion Technoogy Hyderbd Indi

ISBN: (数字)9781665484640

ISBN: (纸本)9781665484657

In recent years, the popularity of weight training has increased significantly. However, incorrect technique or physical form while performing an exercise can not only slow down progress but also cause serious injuries. Deadlift is a famous weight training exercise, which if done incorrectly, can lead to chronic back pain. In this paper, we present a wearable pressure sensor system that checks the posture of the user while performing deadlift. The suit employs a set of flexible pressure sensors, made using velostat (piezoresistive) material, to get the amount of bending for specific muscles. We have developed an algorithm to process the data in real-time so that feedback about incorrect posture can be provided to the user immediately. The algorithm has been configured using data from a single subject, however, it provides accurate classification for multiple subjects in the same weight class, thus eliminating the need for subject-wise configuration. The algorithm classifies a repetition (rep) of the exercise into a good rep or bad rep with an overall accuracy of 95.5%, across three subjects. With some enhancements, the system can also be configured to classify reps of other exercises.

关键词： classification algorithm Deadlift Flexible system Pressure sensor Wearable suit

来源：评论

学校读者我要写书评

暂无评论

Enhancing the Reliability of Wi-Fi Network Using Evil Twin AP Detection Method Based on Machine Learning

引用

JOURNAL OF INFORMATION PROCESSING SYSTEMS 2020年第3期16卷 541-556页

作者： Seo, Jeonghoon Cho, Chaeho Won, Yoojae Chungnam Natl Univ Dept Comp Sci Engn Daejeon South Korea

Wireless networks have become integral to society as they provide mobility and scalability advantages. However, their disadvantage is that they cannot control the media, which makes them vulnerable to various types of attacks. One example of such attacks is the evil twin access point (AP) attack, in which an authorized AP is impersonated by mimicking its service set identifier (SSID) and media access control (MAC) address. Evil twin APs are a major source of deception in wireless networks, facilitating message forgery and eavesdropping. Hence, it is necessary to detect them rapidly. To this end, numerous methods using clock skew have been proposed for evil twin AP detection. However, clock skew is difficult to calculate precisely because wireless networks are vulnerable to noise. This paper proposes an evil twin AP detection method that uses a multiple-feature-based machine learning classification algorithm. The features used in the proposed method are clock skew, channel, received signal strength, and duration. The results of experiments conducted indicate that the proposed method has an evil twin AP detection accuracy of 100% using the random forest algorithm.

关键词： Access Point classification algorithm Clock Skew Evil Twin AP Rogue AP Wireless Network

来源：评论

学校读者我要写书评

暂无评论

Research on Wireless Network Consumer Satisfaction Prediction Method 21

Research on Wireless Network Consumer Satisfaction Predictio...

引用

Proceedings of the 2021 4th International Conference on Artificial Intelligence and Pattern Recognition

作者： Jian Xu Xi Wang Wireless Network Optimization Center China Mobile Communications GroupFujian Co.Ltd. China

ISBN: (纸本)9781450384087

With 5G network globalization, consumers have higher requirements for telecom operators' services. It is necessary to predict consumer satisfaction for analyzing consumer requirements. Based on the understanding of telecommunications services, the wireless network consumer satisfaction prediction is divided into three sub-predictive models: network quality, promotional activities, and tariff packages. At the same time, a hybrid sampling algorithm based on support vector machine (HS-SVM) which is used to classify the consumer satisfaction imbalance dataset is proposed to predict the consumer satisfaction of these three sub-predictive models, and the consumer's overall satisfaction is obtained by merging the results of the three sub-predictive models. The validity of the model is verified by wireless network consumer satisfaction dataset compared with the popular five separate classification algorithms and SMOTE combined with the five classification algorithms. The experimental results show that the F-value and G-mean of the proposed algorithm are improved. The proposed method has better classification performance and stronger robustness in the prediction of wireless network consumer satisfaction.

关键词： classification algorithm Support vector machine (SVM) Synthetic minority over- sampling technique (SMOTE) Wireless network consumer satisfaction imbalanced data

来源：评论

学校读者我要写书评

暂无评论

EMR-Based Phenotyping of Ischemic Stroke Using Supervised Machine Learning and Text Mining Techniques

引用

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS 2020年第10期24卷 2922-2931页

作者： Sung, Sheng-Feng Lin, Chia-Yi Hu, Ya-Han Chiayi Christian Hosp Ditmanson Med Fdn Dept Internal Med Div Neurol Chiayi 600 Taiwan Natl Chung Cheng Univ Inst Healthcare Informat Management Dept Informat Management Chiayi 62102 Taiwan Min Hwei Jr Coll Hlth Care Management Dept Nursing Tainan 736 Taiwan Natl Cent Univ Dept Informat Management Taoyuan 320 Taiwan Natl Chung Cheng Univ Ctr Innovat Res Aging Soc CIRAS Chiayi 62102 Taiwan Natl Cheng Kung Univ MOST AI Biomed Res Ctr Tainan 701 Taiwan

Ischemic stroke is a major cause of death and disability in adulthood worldwide. Because it has highly heterogeneous phenotypes, phenotyping of ischemic stroke is an essential task for medical research and clinical prognostication. However, this task is not a trivial one when the study population is large. Phenotyping of ischemic stroke depends primarily on manual annotation of medical records in previous studies. This article evaluated various strategies for automated phenotyping of ischemic stroke into the four subtypes of the Oxfordshire Community Stroke Project classification based on structured and unstructured data from electronical medical records (EMRs). A total of 4640 adult patients who were hospitalized for acute ischemic stroke in a teaching hospital were included. In addition to the structured items in the National Institutes of Health Stroke Scale, unstructured clinical narratives were preprocessed using MetaMap to identify medical concepts, which were then encoded into feature vectors. Various supervised machine learning algorithms were used to build classifiers. The study results indicate that textual information from EMRs could facilitate phenotyping of ischemic stroke when this information was combined with structured information. Furthermore, decomposition of this multi-class problem into binary classification tasks followed by aggregation of classification results could improve the performance.

关键词： Natural language processing Tools Hospitals Machine learning algorithms Task analysis Information management classification algorithm clinical diagnosis electronic medical records machine learning natural language processing text mining

来源：评论

学校读者我要写书评

暂无评论

Design and analysis of a general vector space model for data classification in Internet of Things

引用

EURASIP JOURNAL ON WIRELESS COMMUNICATIONS AND NETWORKING 2019年第1期2019卷 1页

作者： Sang, Jinguo Pang, Shanchen Zha, Yang Yang, Fan Shandong Univ Sci & Technol Coll Comp Sci & Engn Qingdao 266590 Shandong Peoples R China China Univ Petr Coll Comp & Commun Engn Qingdao 266580 Shandong Peoples R China Beijing Baidu Netcom Sci & Technol Co Ltd Beijing 100000 Peoples R China Zhongnan Univ Econ & Law Sch Informat & Secur Engn Wuhan 430073 Hubei Peoples R China

The amount of information increases explosively in Internet of Things, because more and more data are sensed by large amount of sensors. The explosive growth of information makes it difficult to access information efficiently, so it is an effective method to decrease the amount of information to be transferred on network by text classification. This paper proposes a new text classification algorithm based on vector space model. This algorithm improves the feature selection and weighting methods by introducing synonym replacement to traditional text classification algorithms. The experimental results show that the proposed classification algorithm has considerably improved the precision and recall of classification.

关键词： Internet of Things Edge computing Text classification Feature selection Feature weighting classification algorithm Vector space model

来源：评论

学校读者我要写书评

暂无评论

Multi-View classification via a Fast and Effective Multi-View Nearest-Subspace Classifier

引用

IEEE ACCESS 2019年 7卷 49669-49679页

作者： Shu, Ting Zhang, Bob Tang, Yuan Yan Univ Macau Dept Comp & Informat Sci Macau 999078 Peoples R China

Multi-view data represented in multiple views contains more complementary information than a single view, whereby multi-view learning explores and utilizes the multi-view data. In general, most existing multi-view learning methods consider the correlation between multiple views. However, the relationship between classes and views which is also important in multi-view learning has never been involved in the existing works. In this paper, we propose a fast and effective multi-view nearest-subspace classifier (MV-NSC) by taking advantage of both the two relationships simultaneously. MV-NSC consists of four main parts: 1) projection residual, 2) view-dependent class separability, 3) view similarity, and 4) final decision. The last part combines the first three parts in one final decision matrix, while the first three parts utilize the information of the multi-view data in various aspects. Our proposed method is evaluated on four benchmark datasets and compared with seven other classifiers including both multi-and single-view algorithms. According to the experimental results, it shows that our proposed method is effective, efficient, and robust in multi-view classification.

关键词： Adaption model classification algorithm multi-view data nearest-subspace classifier view-dependent class separability view similarity

来源：评论

学校读者我要写书评

暂无评论

Multimodal Sparse Representation-Based classification Scheme for RF Fingerprinting

引用

IEEE COMMUNICATIONS LETTERS 2019年第5期23卷 867-870页

作者： Yang, Kiwon Kang, Jusung Jang, Jehyuk Lee, Heung-No Gwangju Inst Sci & Technol Sch Elect Engn & Comp Sci Gwangju 61005 South Korea

In this letter, we propose a multimodal method for improving radio frequency (RF) fingerprinting performance that uses multiple features cultivated from RF signals. Combining multiple features, including a falling transient feature that has not previously been used in RF fingerprinting studies, we aim to demonstrate that the proposed method results in improved accuracy. We show that a sparse representation-based classification (SRC) scheme can be a good platform for combining multiple features. The experimental results on RF signals acquired from eight walkie-talkies show that the RF fingerprinting accuracy of the proposed method improves significantly as the number of features increases.

关键词： classification algorithm feature extraction multimodality RF fingerprinting radio frequency identification

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Rule Based classification algorithms for Credit Risk Assessment 31

A Comparative Study of Rule Based Classification Algorithms ...

引用

31st International-Business-Information-Management-Association Conference

作者： Smiti, Salima Soui, Makram Gasmi, Ines Univ Gabes Gabes Tunisia Cent Univ Grp Interdisciplinary Res Ctr Gabes Tunisia Univ Manouba Manouba Tunisia

ISBN: (纸本)9780999855102

Credit risk is the most important issue for financial institutions. Its assessment becomes an important task used to predict defaulter customers and classify customers as good or bad payers. To this objective, numerous techniques have been applied for credit risk assessment. However, to our knowledge several evaluations techniques are black-box models such as neural networks, SVM, etc. They generate applicants' classes without any explanation. In this paper, we propose to assess credit risk using rules classification method. Our output is a set of rules, which describe and explain the decision. To this end, we will compare seven classification algorithms (JRip, Decision Table, OneR, ZeroR, Fuzzy Rule, PART and Genetic programming (GP)) where the goal is to find the best rules satisfying many criteria: Accuracy, Sensitivity and Specificity. The obtained results confirm the efficiency of the GP algorithm for German and Australian datasets compared to other rule-based techniques to predict credit risk.

关键词： classification algorithm credit risk assessment data mining rule extraction

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

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

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：