检索结果-内蒙古大学图书馆

International Conference on Futuristic Technologies (INCOFT)

作者： Bhavani. R T Vijay Muni Ravi Kumar Tata Jonnadula Narasimharao K Murali Harpreet Kaur Dept.of Information Technology Kings Engineering College Chennai India Dept.of Electrical and Electronics Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram India Dept.of Computer Science and Engineering CMR Technical Campus Medchal Hyderabad India Dept.of Electronics and Communication Engineering VijayaInstitute of Technology for Women Enikepadu India Dept.of Computer Science and Engineering Lovely Professional University Phagwara India

The identification of feelings sent via one’s voice has evolved from a niche field into an essential part of humancomputer interaction (HCI). These systems seek to facilitate more natural interactions between humans and machines by favouring direct voice interaction over the use of conventional input devices in order to comprehend verbal information and to make it simpler for human listeners to respond. A few examples include the use of emotion patterns derived from speech in medical applications, dialogue systems for spoken languages such as those used in cell phone call centres, onboard driving systems in automobiles, and the usage of such patterns in other contexts. In the research that has been done on speech emotion recognition (SER), a variety of methods, many of which are considered to be industry standards in speech analysis and classification, have been applied to the process of extracting emotions from signals. The most crucial stages of the speech emotion recognition (SER) process are the phases that deal with the extraction of features and the categorization of features. For the purpose of speech processing, researchers have developed a variety of features, including prosodic features, vocal traction features, and other hybrid features. The second step involves the categorization of features through the application of deep learning methods. These methods have just lately been put up as a potential replacement for SER’s more conventional methods.

关键词： Deep learning Industries Emotion recognition Speech analysis Input devices Medical services Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Expression of Concern for: Deep Learning Techniques for Speech Emotion Recognition

Expression of Concern for: Deep Learning Techniques for Spee...

引用

International Conference on Futuristic Technologies (INCOFT)

ISBN: (数字)9781665450461

ISBN: (纸本)9781665450478

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Logic-based Energy Management for WSNs in Smart Grid Applications

Fuzzy Logic-based Energy Management for WSNs in Smart Grid A...

引用

Soft Computing for Security Applications (ICSCSA), International Conference on

作者： K. Vengatesan R. Vijayalakshmi Sayyad Samee Neha Chopade Shilpa Mahalle K. Bashkaran Department of AIDS Sanjivani University Kopargaon Department of Computer Science and Engineering Velammal College of Engineering and Technology Madurai Dept.of Computer Science Al Sadara School Al Ain Abu Dhabi UAE SIES College of Management Studies Kongunadu College of Engineering and Technology Thottiam

ISBN: (数字)9798331515720

ISBN: (纸本)9798331515737

Fuzzy Logic-Based Energy Management (FLBEM) is an innovative approach for optimizing energy consumption in Wireless Sensor Networks (WSNs) utilized in Smart Grid applications. This technique employs fuzzy logic principles to dynamically adjust network parameters, such as transmission power and data sampling rates, to enhance energy efficiency while maintaining reliable communication. By intelligently adapting to network conditions and environmental factors, FLBEM extends the operational lifetime of sensor nodes and ensures the stability of the WSN, thus facilitating real-time monitoring and control of Smart Grid systems. The proposed FLBEM approach encompasses a comprehensive framework that includes the design of fuzzy logic controllers, the development of energy-aware routing protocols, and the integration of renewable energy sources for powering sensor nodes. Simulation results demonstrate significant improvements in energy efficiency, network lifetime, and overall performance, validating the effectiveness of the FLBEM strategy in the context of Smart Grid applications. As energy management remains a critical concern for WSNs, the implementation of FLBEM offers a promising solution to address the challenges of energy conservation and sustainability in modern power systems.

关键词： Fuzzy logic Wireless sensor networks Renewable energy sources Power system stability Energy efficiency Stability analysis Smart grids Power system reliability Reliability Sustainable development

来源：评论

学校读者我要写书评

暂无评论

Human Activity Recognition using ShuffleNetV2 Model

Human Activity Recognition using ShuffleNetV2 Model

引用

Intelligent Computing and Control for engineering and Business Systems (ICCEBS)

作者： Shanufa Nazrin P S J.V. Bibal Benifa Anu K. P Aiswarya Vijayakumar dept. of Computer Science St.Joseph's college (university of calicut) Thrissur Kerala dept.of Computer Science and Engineering Indian Institute of Information Technology kottayam Kerala India

HAR is specified as the crucial task within the field of computer vision and artificial intelligence. Main aim of HAR is to observing and labelling different human activity images of distinct data sources by machines such as computer. HAR has applications in various fields. CNN model is an appropriate model for HAR task, due to their ability to automaticaly acquire relevant spatial features, capture hierarchical representations, and handle input of various sizes and types. So it is utilized for developing HAR model. This model can detect objects and also can classify images. The model contains wide ranging catogories. ShuffleNetV2 is a particular architecture within it, mainly for efficient and lightweight deep learning task. This paper develops an intelligent HAR using ShuffleNetV2 model which acquired an accuracy about 69.52 percentage.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Automated Tracking System for Movement Analysis of C. elegans

An Automated Tracking System for Movement Analysis of C. ele...

引用

International Symposium on computer, Consumer and Control (IS3C)

作者： Yu-Hao Lee Jian-Feng Chiu An-Bang Liu Hsin-Ru Liu Wei-Min Liu Dept.of Computer Science and Information Engineering(CSIE) National Chung Cheng University Chiayi Taiwan Dept.of CSIE National Chung Cheng University Chiayi Taiwan Dept.of Medicine School of Medicine Tzu Chi University Hualien Taiwan Dept.of Medical Research Tzu Chi University Hualien Taiwan

C. elegans is one of the classic model organisms in neuroscience and biology, with its simple nervous system and transparent body serving as useful research tools. High-resolution imaging techniques allow for a detailed recording and analysis of C. elegans’ behaviors, such as locomotion, turning, probing, and jumping. These behaviors can be correlated with its neuronal activity and gene expression, thereby helping researchers understand the regulatory mechanisms of its behaviors and physiological processes. In this study, we propose an automated tracking system capable of rapidly and accurately collecting motion trajectory data of multiple C. elegans using skeletal extraction and SORT multi-object tracking algorithms. Furthermore, we introduce the use of Approximate Entropy to quantify the regularity and unpredictability of motion features, offering a novel approach for the analysis of C. elegans’ motion trajectories and movement features. This system also provides a convenient and automated tracking tool for related microorganism research fields.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Efficient Machine Learning Model for Identification of Seagrasses through Morphometrics

An Efficient Machine Learning Model for Identification of Se...

引用

Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI), IEEE Conference on

作者： Ashwani Kumar Dubey Jibi G Thanikkal E. Dilipan Puneet Sharma Manoj Kumar Shukla Dept.of Electronics and Communication Engineering ASET Amity University Uttar Pradesh Noida UP India Dept.of Computer Science and Engineering ASET Amity University Uttar Pradesh Noida UP India Center for Marine Omics Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamilnadu India School of Computer Science & AI SR University Warangal Telangana India

Seagrasses are marine flowering plants capable of completing their life cycle underwater. Globally, 72 species of seagrasses have been identified, including 15 species from India. Artificial intelligence/ Machine learning techniques are gaining wide use in many fields, and their applications in marine sciences are still in the initial stage. Considering this, a study is attempted to identify seagrass species through Artificial intelligence/ Machine learning techniques. Since the characteristics of seagrass vary depending on location and other environmental factors, identifying seagrass species is regarded as a difficult task. In the present study, a known seagrass species is taken as a reference and its leaf morphological features are considered for shape description and deep learning-based identification. Leaf morphometrics of seagrass species are drawn to develop the databases. Morphological feature extraction algorithm, descriptor generation algorithm, and deep learning-based identification are applied for species identification. Existing artificial intelligence/ machine learning models use image pixels as input to the deep learning model. However, this is the first attempt to recognize seagrasses through their morphological properties. Here, the leaf shape property is utilized for seagrass identification. The proposed machine learning model received 60% accuracy during testing. Additional investigation was possible with the same algorithm for future seagrass species identification. Utilizing Artificial intelligence/ Machine learning algorithms may lead to identifying new seagrass species.

关键词：

来源：评论

学校读者我要写书评

暂无评论

IoT-Based Diagnosis and Recommendation System for Chronic Diseases Using Patient Health Records 3

IoT-Based Diagnosis and Recommendation System for Chronic Di...

引用

3rd International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2023

作者： Umamaheswaran, S.K. Gangodkar, Durgaprasad Samatha, V. Chakrapani, I.S. Dharamvir Buddhi, Dharam Sri Sai Ram Engineering College Department of Mathematics Tamil Nadu Chennai India Graphic Era Deemed to Be University Department of Computer Science & Engineering Uttarakhand Dehradun India AP Nellore524003 India PRRandVS Govt College Dept.of Zoology AP India The Oxford College of Engineering Dept. of MCA Bangalore560068 India Uttaranchal University Uttaranchal Institute of Technology India

ISBN: (纸本)9798350399264

The proliferation of IoT applications, notably in the sphere of health care, has led to discussion of patient health records utilising data gathered from IoT-connected devices. Biological data from patients' medical records is mined for health analysis and diagnosis. Certain types of illness, known as chronic illnesses, are completely quiet yet devastating if left untreated. Recent years have seen an uptick in interest from academics in the utilization of patient health information data for the pre-emptive identification of chronic diseases. On the other side, healthcare and medical assistance have benefited enormously from the implementation of recommender systems that use machine learning techniques. Using an Internet of Things device, this research implemented a medical recommendation system to aid in the early diagnosis and management of chronic conditions. The current technique made use of the dataset of digitised patient health records that is housed in the Physio Net data repository. The current dataset contains patient health records that have been documented in accordance with the diseases that have been identified and the doctor's diagnosis. The recommended technique uses K-nearest neighbour classification to identify the kind of ailment before using collaborative filtering to select the optimal course of treatment for patients. The outcomes of using the suggested methodology show that this technique, which is based on using patient symptom similarity, produces better results than previous methods and has a high precision in diagnosing and forecasting chronic illnesses. After determining the kind of disease using the closest neighbour classification method, the collaborative filtering strategy is utilised to select the optimal course of therapy for patients. The outcomes of using the suggested methodology show that this technique, which is based on using patient symptom similarity, produces better results than previous methods and achieves better accuracy

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

A Cost Benefit Analysis for Distribution of Threatened Species Based on Climate Change

Research Square

引用

Research Square 2021年

作者： Nandhi Kesavan, R. Latha, K. Anna University Chennai India Dept.of Computer Science& Engineering Anna University BIT Campus Tiruchirappalli India

Among all the threats to global diversity, climate change is the most severe cause. According to the world’s biodiversity conservation organization, reptile species are affected mostly because the biological and ecological traits of the reptiles are strongly linked with climate. To prevent species extinction, we tried to develop a decision support system that incurs the costs and benefits of reintroducing a taxon from its origin to adapt environmental conditions to conserve it from its extinction. The model was developed by applying multiple linear regressions that take the climatic variables and species traits to determine the cost and benefits for the distribution of species. The effectiveness of the model was evaluated by applying it to the Indian Black Turtle, which is an endangered species list in India evaluated by the International Union for Conservation of Nature list. The model recommends moving the species, which is endangered, to the location where it can save itself from climate change. However, the framework demonstrates huge differences in the estimated significance of climate change, and the model strategy helps to recognize the probable risk of increased revelation to critically endangered species. © 2021, CC BY.

关键词： Climate change

来源：评论

学校读者我要写书评

暂无评论

End-User Programming is WEIRD: How, Why and What to Do About It

End-User Programming is WEIRD: How, Why and What to Do About...

引用

IEEE Symposium on Visual Languages and Human Centric Computing (VL/HCC)

作者： Harshit Goel Aayush Kumar Sruti Srinivasa Ragavan Computer science and Engineering Indian Institute of Technology Kanpur Kanpur India Dept.of CSE Indian Institute of Technology Kanpur Kanpur India

End-user programming (EUP) empowers regular computer users to build and customize software on their own, but we suspect that most developments in the field build on the preferences of WEIRD (Western, Educated, Industrialized, Rich, and Democratic) users. This potentially leaves behind 85 % of the world's population that lives in non-WEIRD societies. To validate whether this suspicion has merit, we conducted a systematic mapping study of the research papers (N=217) published on EUP since 2019. Our results indicate that EUP research is heavily WEIRD-centric. First, over 80% of papers in our final analysis (N=159) had WEIRD-only authorship. Second, 51-94% of papers reporting user studies (N=86) recruited WEIRD participants. Finally, our results suggest that research in EUP is largely driven by the advancements in Industrialized societies. We consider the implications of this WEIRD-ness, and discuss avenues through which to serve more diverse end-user programmcrs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Effective Analysis of Machine Learning Models for Prediction of Heart Disease

An Effective Analysis of Machine Learning Models for Predict...

引用

Network, Multimedia and Information Technology (NMITCON) International Conference on

作者： Rudragoud Patil Shambahvi C. Kamkar Shwetha Indudhar Goudar Dept of Computer Science and Engineering K.L.S.Gogte Institute of Technology Belagavi Karnataka India Dept.of Master of Computer Applications K.L.S Gogte Institute of Technology Belagavi Karnataka India

ISBN: (数字)9798350372892

ISBN: (纸本)9798350372908

Heart failure is a chronic illness that impacts millions of individuals worldwide. In order to forecast heart failure health status early and take the necessary activities to address this global issue an effective machine learning-based technique is required. Globally, heart disease is one of the leading causes of death. Medical professionals find it challenging to forecast since it demands experience and a deeper level of predictive knowledge. The healthcare industry operates in a knowledge-deficient but information-rich environment. Healthcare systems have access to a vast amount of data via the internet, but there aren’t many useful tools for analyzing the data to find hidden patterns. Medical efficiency will increase with an automated system, which will also save money and time. This software uses information acquired from Kaggle to forecast the likelihood of a disease developing. To create a prediction model, the following algorithms are used: Random Forest (RF), support vector machine (SVM), K-nearest neighbor (KNN), Decision Tree (DT), and Logistic Regression (LR). Phases for feature selection and data preprocessing were finished before the models were created. When the models were evaluated based on accuracy and the F1-score, the RF model performed the best.

关键词： Heart Support vector machines Radio frequency Medical services Nearest neighbor methods Data models Diabetes Decision trees Random forests Diseases

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：