检索结果-内蒙古大学图书馆

lassi onk: a system framework to annotate and classify vehicular honk from road traffic

Environmental Monitoring and Assessment 2024年第10期196卷 1-29页

作者： Maity, Biswajit Alim, Abdul Rama Charan, Popuri Sree Nandi, Subrata Bhattacharjee, Sanghita Computer Application and Science Institute of Engineering and Management Kolkata India CSE National Institute and Technology Durgapur India

Some recent studies highlight that vehicular traffic and honking contribute to more than 50% of noise pollution in urban or sub-urban areas in developing countries, including Indian cities. Frequent honking has an adverse effect on health and hampers road safety, the environment, etc. Therefore, recognizing the various vehicle honks and classifying the honk of different vehicles can provide good insights into environmental noise pollution. Moreover, classifying honks based on vehicle types allows for the inference of contextual information of a location, area, or traffic. So far, the researchers have done outdoor sound classification and honk detection, where vehicular honks are collected in a controlled environment or in the absence of ambient noise. Such classification models fail to classify honk based on vehicle types. Therefore, it becomes imperative to design a system that can detect and classify honks of different types of vehicles to infer some contextual information. This paper presents a novel framework $${\varvec{\mathcal {A}}}{\varvec{\mathcal {C}}}$$ lassi $${\varvec{\mathcal {H}}}$$ onk that performs raw vehicular honk sensing, data labeling, and classifies the honk into three major groups, i.e., light-weight vehicles, medium-weight vehicles, and heavy-weight vehicles. Raw audio samples of different vehicular honking are collected based on spatio-temporal characteristics and converted them into spectrogram images. A deep learning-based multi-label autoencoder model (MAE) is proposed for automated labeling of the unlabeled data samples, which provides 97.64% accuracy in contrast to existing deep learning-based data labeling methods. Further, various pre-trained models, namely Inception V3, ResNet50, MobileNet, and ShuffleNet are used and proposed an Ensembled Transfer Learning model (EnTL) for vehicle honks classification and performed comparative analysis. Results reveal that EnTL exhibits the best performance compared to pre-trained models and ac

关键词：

来源：评论

学校读者我要写书评

暂无评论

Text2NKG: Fine-Grained N-ary Relation Extraction for N-ary relational Knowledge Graph Construction 38

Text2NKG: Fine-Grained N-ary Relation Extraction for N-ary r...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Luo, Haoran Haihong, E. Yang, Yuhao Yao, Tianyu Guo, Yikai Tang, Zichen Zhang, Wentai Peng, Shiyao Wan, Kaiyang Song, Meina Lin, Wei Zhu, Yifan Tuan, Luu Anh School of Computer Science Beijing University of Posts and Telecommunications China School of Automation Science and Electrical Engineering Beihang University China Beijing Institute of Computer Technology and Application China Inspur Group Co. Ltd. China College of Computing and Data Science Nanyang Technological University Singapore

Beyond traditional binary relational facts, n-ary relational knowledge graphs (NKGs) are comprised of n-ary relational facts containing more than two entities, which are closer to real-world facts with broader applications. However, the construction of NKGs remains at a coarse-grained level, which is always in a single schema, ignoring the order and variable arity of entities. To address these restrictions, we propose Text2NKG, a novel fine-grained n-ary relation extraction framework for n-ary relational knowledge graph construction. We introduce a span-tuple classification approach with hetero-ordered merging and output merging to accomplish fine-grained n-ary relation extraction in different arity. Furthermore, Text2NKG supports four typical NKG schemas: hyper-relational schema, event-based schema, role-based schema, and hypergraph-based schema, with high flexibility and practicality. The experimental results demonstrate that Text2NKG achieves state-of-the-art performance in F1 scores on the fine-grained n-ary relation extraction benchmark. Our code and datasets are publicly available. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Study on the Design of Eye and Eyeball Method Based on MTCNN 1

引用

13th International Conference on Frontier Computing, FC 2023

作者： Hsueh, Cheng-Yu Hung, Jason C. Tzeng, Jian-Wei Huang, Hui-Chun Huang, Chun-Hong Department of Computer Science and Information Engineering National Taichung University of Science and Technology Taichung404348 Taiwan Department of Information Management National Taichung University of Science and Technology Taichung404348 Taiwan Department of Innovation Application and Management Chang Jung Christian University Tainan71101 Taiwan Department of Computer Information and Network Engineering Lunghwa University of Science and Technology Taoyuan33306 Taiwan

ISBN: (数字)9789819993420

ISBN: (纸本)9789819993413

Studies on eye tracking have relied on wearable eye trackers and chin-resting eye trackers, but the high cost of equipment and the need to wear devices during experiments can lead to less natural facial movement. This study collected eye-tracking data by using a raw-video camera without adjusting any parameters. Python was used as the primary programming language. Eye tracking was adjusted through calculations of facial distance, and multitask cascaded convolutional networks were used to collect eye-tracking data. The corrected results were visualized, and linear regression was used to determine correction error. The root mean square error was 221.66, and the mean squared error was 260.48. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Eye tracking

来源：评论

学校读者我要写书评

暂无评论

Enhancing Facial Expression Recognition with a Directional Attentive Neural Network 3

Enhancing Facial Expression Recognition with a Directional A...

引用

3rd IEEE World Conference on Applied Intelligence and Computing, AIC 2024

作者： Singh, Jagendra Shelke, Nitin Arvind Masson, Palak Agrawal, Rishi Sharma, Amit Parashar, Amit Bennett University School of Computer Science Engineering & Technology Greater Noida India Raj Kumar Goel Institute of Technology Greater Noida India Gla University Department of Computer Engineering & Applications Mathura India Lovely Professional University School of Computer Application Phagwara India Pranveer Singh Institute of Technology Basic Science & Humanities-Chemistry Kanpur India

ISBN: (纸本)9798350384598

The proposed DANN was developed for better recognition of facial expression. The proposed DANN combines the attention and directional filters, which filter out features that focus on the informative facial regions while capturing the directional patterns in the facial queue. The average accuracy after benchmarking all the 10 experiment trials was in the very high level with the proposed DANN on datasets combining CK+, FER2013, and RAF-DB, with an average accuracy of 88.04%. The model showed a good trade-off between precision and recall: its average weighted F1 score was 0.881, while the average precision and recall were 0.883. This implies that the model will maximize the identification of true positive samples while, at the same time, minimizing that of false positives and false negatives. All these results are indicative of the robustness and reliability of the DANN architecture in classifying the facial expressions correctly across the different datasets and different experimental settings. The results suggest the high potential of DANN in furthering the state-of-the-art facial expression recognition with prosperous affective computing, human-computer interaction, and psychology. © 2024 IEEE.

关键词： Affective computing Attention mechanisms Deep learning Directional Attentive Neural Network Facial expression recognition

来源：评论

学校读者我要写书评

暂无评论

Vibration-induced bias error reduction using loop gain compensation for high-precision fiber optic gyroscopes

引用

Journal of Systems engineering and Electronics 2025年第1期36卷 224-232页

作者： CHEN Heyu QIN Xuexin XIE Huan KONG Linghai ZHENG Yue School of Instrumentation Science and Opto-Electronics Engineering Beihang UniversityBeijing 100191China Beijing Institute of Computer Technology and Application Beijing 100854China Hunan Shuaiwei Control Technology Co. LTDChangsha 421000China Beijing Institute of Control and Electronic Technology Beijing 100038China

Vibration-induced bias deviation,which is generated by intensity fluctuations and additional phase differences,is one of the vital errors for fiber optic gyroscopes(FOGs)operating in vibration environment and has severely restricted the applications of high-precision *** conventional methods for suppressing vibration-induced errors mostly concentrate on reinforcing the mechanical structure and optical path as well as the compensation under some specific operation parameters,which have very limited effects for high-precision FOGs maintaining performances under *** this work,a technique of suppressing the vibration-induced bias deviation through removing the part related to the varying gain from the rotation-rate output is put ***,the loop gain is extracted out by adding a gain-monitoring *** demodulating the loop gain and the rotation rate simultaneously under distinct frequencies and investigating their quantitative relationship,the vibrationinduced bias error is compensated without limiting the operating parameters or environments,like the applied modulation *** experimental results show that the proposed method has achieved the reduction of bias error from about 0.149°/h to0.014°/h during the random vibration with frequencies from20 Hz to 2000 *** technique provides a feasible route for enhancing the performances of high-precision FOGs heading towards high environmental adaptability.

关键词： vibration-induced error fiber optic gyroscope(FOG) loop gain

来源：评论

学校读者我要写书评

暂无评论

Enhancing Security and Privacy in Health Care Using Cyber-physical Systems Through Machine Learning 8th

Enhancing Security and Privacy in Health Care Using Cyber-ph...

引用

8th International Conference on Information and Communication Technology for Intelligent Systems, ICTIS 2024

作者： Takale, Dattatray G. Gawali, Piyush P. Deshmukh, Gopal B. Mahalle, Parikshit N. Mehta, Pradnya S. Kashid, Shraddha S. Sule, Bipin Derle, Deepak R. Department of Computer Engineering Vishwakarma Institute of Information Technology SPPU Pune India Department of Artificial Intelligence and Data Science Vishwakarma Institute of Information Technology SPPU Pune India Department of Computer Engineering MIT ADT University Pune India and Humanities Vishwakarma Institute of Technology Pune India Department of Computer Science and Application KTHM College Nashik India

ISBN: (纸本)9789819766772

The importance of securing cyber-physical systems (CPS) is paramount to safeguarding the interconnected networks and devices, especially in sectors such as blockchain, health care, and the "Internet of Things" (IoT). The importance of authentication for users and devices in CPS security is highlighted in this paper. As a result of the intricate interconnectivity of networks, the integration of cyber-physical systems (CPS) in health care has revolutionized the delivery of medical services in an era of rapidly advancing technology. There are, however, serious concerns surrounding the privacy and security of sensitive healthcare data as a result of this integration. In this paper, a revolutionary approach to address these concerns is presented by utilizing machine learning techniques to address these problems. To enhance security measures within healthcare CPSs and protect privacy, Random Forest, a powerful ensemble learning algorithm, is employed as an integral part of the security measures. The proposed system utilizes a combination of anomaly detection, adaptive learning, and multi-attribute feature selection in order to identify potential security breaches while simultaneously ensuring patient confidentiality. As an additional security precaution, encryption protocols are implemented to ensure that the transmission of data is secure, preventing unauthorized access to the data as well. "As a comprehensive evaluation of the system's performance, a number of evaluation metrics are used, including Accuracy, Precision, Recall, F1 Score, and AUC-ROC". Based on these results, it is evident that this approach is effective in providing robust security and privacy protections in healthcare CPS, thereby establishing a new paradigm for delivering safe and confidential health care in the digital age. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Classification and Prediction of Medical Dataset Using Ensemble DeepQ Classifier 4th

Classification and Prediction of Medical Dataset Using Ensem...

引用

4th International Conference on Communication and Intelligent Systems, ICCIS 2022

作者： Salman, Rahama Gupta, Subodhini Jain, Neelesh Department of Computer Science SAM Global University MP Bhopal India Department of Computer Application School of Information Technology SAM Global University MP Bhopal India Department of Computer Science and Engineering SAM Global University MP Bhopal India

ISBN: (纸本)9789819923212

The clinical dataset consists of a huge amount of disease information and which marks negative effects with respect to features. Feature selection is a major key player removing redundant information. It also increases the decision making result in an effective manner. The important step in feature selections is classification and dimensionality reduction. Medical experts and researchers are using various machine learning techniques to predict and analyze the huge volume of data. The large scale volume of medical dataset is having number attributes and dimensions. Dimensions can affect the analytics and diagnose the results. In this paper we evaluate principle component analysis, support vector machine, factor analysis and ranking methods compared with our proposed CNN-based ensemble feature selection using K-nearest classifier. Our proposed method is followed as standard testing features with parameter optimization. Compared with the existing method our method has 94% of accuracy result by using TensorFlow. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Stage Wise Classification and Prediction of Non-Alcoholic Fatty Liver Disease using Hybrid Approach 2

Stage Wise Classification and Prediction of Non-Alcoholic Fa...

引用

2nd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2024

作者： Prabagaran, A. Balamurugan, N.M. Kalavathi, S. Padmanabhan, P. Angelin Blessy, J. Gupshup Technology India Pvt Ltd Bengaluru India Sri Venkateswara College of Engineering Department of Computer Science and Engineering Chennai India Sri Venkateswara College of Engineering Department of Information Technology Chennai India Noida Institute of Engineering & Technology Department of CSE Uttar Pradesh Greater Noida201306 India School of Computing Science and Engineering Galgotias Univeristy Dept of Computer Application India

ISBN: (纸本)9798350327533

The world's most serious chronic liver condition is Non-Alcoholic Fatty Liver Disease (NAFLD). The early stage prediction saved people's lives. Recent machine and deep learning, help to predict and classify diseases. The main goal of this work is to make an advanced prediction system that uses plasma lipid data and MRI images to predict the stage-wise classification of NAFLD images. The four main stages of liver disease are normal, steatosis, steatohepatitis, and cirrhosis. The machine and deep learning techniques to identify and classify cirrhosis disease in NAFLD. This research study proposes a machine and deep learning techniques with features that classify and predict the NAFLD. The random forest algorithm is used to predict the disease images into binary classifications, and a deep neural network is used for stage-wise classification. Initially, different features are used to classify the liver. This work uses 52 features, such as GLGCM and GLCM to predict and classify the fatty liver. The proposed method combined the initial prediction features using the random forest method and deep neural network to classify different stages of livers images. The experimental work is done with the help of MRI images and various iterations for evaluation. The experimental results were evaluated using three metrics, such as specificity, sensitivity, and accuracy. The predicted values of this methodology were 96.26%, 95.7%, and 97.6%. © 2024 IEEE.

关键词： Cirrhosis Hybrid Method Random Forest-Deep Neural Network Stage Wise Classification

来源：评论

学校读者我要写书评

暂无评论

Automation in Monitoring Temperature, Vibration of Industry and Preventing Accident Using IoT 3

Automation in Monitoring Temperature, Vibration of Industry ...

引用

3rd International Conference on Innovative Practices in Technology and Management, ICIPTM 2023

作者： Uma Maheswari, Sabari L Teotia, Shashiraj Kumaravel, R. Pandey, Himani Dhinakaran, K. Kumar, Ashok R.M.K. Engineering College Department of Electrical and Electronics Engineering Kavaraipettai India Swami Vivekanand Subharti University Department of Computer Application Meerut India Vivekanandha College of Engineering for Women Department of Computer Science and Technology Elayampalam India Baroda University Department of Applied Science and Humanities Vadodara India Misrimal Navajee Munoth Jain Engineering College Department of Computer Science and Engineering Chennai India Banasthali Vidyapith Department of Computer Science Rajasthan India

ISBN: (纸本)9798350336238

Industrial safety is more important in both safety of human being and machines. To ensure this the temperature of the machine is monitored continuously and if any abnormal situation arises, the machine will be isolated from the supply using IoT. Similarly, the sound and vibration inside the factory is monitored using vibration sensor and intimated to the control room if needed. The control room may be located in remote place the information will be sent to them using IoT. Vibration may induce due sudden fall of any heavy materials, braking of machine shaft, fall of objects from Crane, etc. The vibration caused by the unexpected incident will be identified by the vibration sensor provide in the factory/ Industry in various places. The sensor will alarm by siren and intimate to the operator or control room. SMS (Small Message Service) also send to the operator through GSM. © 2023 IEEE.

关键词： Accident prevention

来源：评论

学校读者我要写书评

暂无评论

Enhancing Password Security: Analyzing Password Management Practices Among IT Students 7

Enhancing Password Security: Analyzing Password Management P...

引用

7th IEEE International Conference and Workshop Obuda on Electrical and Power engineering, CANDO-EPE 2024

作者： Kollar, Anita Mihalovicsne Katona, Jozsef Institute of Computer Engineering University of Dunaujvaros Department of Software Development and Application Dunaujvaros Hungary John Von Neumann University GAMF Faculty of Engineering and Computer Science Kecskemet Hungary Budapest Business University Department of Applied Quantitative Methods Faculty of Finance and Accountancy Budapest Hungary

ISBN: (纸本)9798331531119

Today, with the digital world in its full swing, strong password management is key to protecting sensitive information from both internal and external threats. The current research explores the passwords managing behavior of the IT students at the University of Dunaujvaros. A survey made in May 2024 questioned 68 students, 59 males and 9 females, about behaviors such as using passwords with complexity, not repeating them for multiple accounts or machines, changing them regularly, and which applications they use for password management. The findings have depicted that, as a whole, students appear to be moderately sensitive about the password security instructions. Nonetheless, most continue to indulge in unsafe practices, including easily remembered or weak passwords and infrequent password changes. Furthermore, approximately half of the responders use password management applications, indicating room for significant improvement in the future. The results suggest that intervention and special education measures should be taken to enhance the practice of password security among future IT experts. This research has good potential to contribute toward strategies designed for people behaving safely in password management, and hence promote a secure digital environment. © 2024 IEEE.

关键词： Students

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：