检索结果-内蒙古大学图书馆

Device Intelligence, Computing and Communication technologies, (DICCT), International Conference on

作者： Pramod Mehra Shashi Kant Verma Computer Science & Engineering Uttarakhand Technical University Dehradun Uttarakhand India Computer Science & Engineering G. B. Pant Engineering College Pauri Garhwal Uttarakhand India

Speech has b.en a crucial form of communication from the dawn of humanity. Natural verb.l communication must include emotions. The voice is a poor indicator of human emotion for machines. A machine must first understand the acoustic capab.lities of the human ear in order to understand human b.haviour. The addition of emotion processing enhances the realism and significance of the current speech systems. The classification of the voice signal relies heavily on spectral properties. To accomplish emotion classification, spectral information from speech, such as Mel Frequency Cepstral Coefficients (MFCC), Linear Prediction Cepstral Coefficients (LPC) and pitch are retrieved in this study. We compared the different algorithm to choose Catb.ost as a classifier. For training and testing purposes, a speech emotion datab.se with more than one hundred people in a range of emotions is employed. From the numerous movie clips, another real-life emotion speech datab.se is also employed.

关键词： Training Emotion recognition Wavelet domain Datab.ses Speech recognition Feature extraction Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Temporal-Spatial Power Spectrum and Sensitivity Measure for Visual Perception Considering Video Dynamics

Temporal-Spatial Power Spectrum and Sensitivity Measure for ...

引用

2023 International Conference on Integrated Intelligence and Communication Systems, ICIICS 2023

作者： Thulajanaik, Aruna Kumar b.nanaik Manjanaik, Naganaik Gowdara Mallikarjunappa Institute of Technology Affiliated to Visvesvaraya Technological University Dept. of Computer Science and Engineering Davangere Belagavi India University B. D. T. College of Engineering Affiliated to Visvesvaraya Technological University Dept. Electronics and Communication Engineering Davangere Belagavi India

ISBN: (纸本)9798350315455

Multiple difficulties arise for video transmission in a wide-area millimeter wave (mm-wave) network due to the comb.ned effects of network transmission link shortcomings and real-time limits of video data. The difficulties are compounded, especially in crowded environments, b. users' rising standards for video quality. This work proposes a Perceptual Quality Aware Video Encoding (PQAVE) to address these issues: in stage one, an efficient perceptual quality encoding method is implemented, making use of low-rank approximation to reduce overall video size;in stage two, a novel b.tstream optimization method is utilized to enhance perceptual quality. The proposed PQAVE model outperforms the state-of-the-art perceptual video encoding technique in terms of b.trate percentage reduction (? R), and Peak Signal-to-Noise Ratio (PSNR), as demonstrated b. experiments conducted on a standard video dataset. The PQAVE achieved an average ? R of 58.012 and an average PSNR of 41.071 which is b.tter when compared with b.-JUNIPER existing work. © 2023 IEEE.

关键词： b.trate Perception PSNR Transmission Video Transmission

来源：评论

学校读者我要写书评

暂无评论

Applying Online Machine Learning Models for Trading in the Financial Market

Applying Online Machine Learning Models for Trading in the F...

引用

2024 International Conference on Communication, Computing and Internet of Things, IC3IoT 2024

作者： Verma, Rakesh Kapruwan, Akanksha Mahesh, R. Savsani, Mayur V. Vekariya, Daxa Maranan, Ramya Gniot Mba Institute Department Of Management Business Administration Uttar Pradesh Greater Noida201310 India Graphic Era Deemed To Be University Department Of Computer Science & Engineering Uttarakhand Dehradun248002 India Adichunchanagiri University Bgs Institute Of Technology Department Of Computer Science And Engineering Karnataka Mandya571 448 India H. & H. B. Kotak Institute Of Science Department Of Statistics Dr. Yagnik Road Gujarat Rajkot360001 India Parul University Parul Institute Of Engineering And Technology Department Of Computer Science & Engineering Post Limda Gujarat 391760 India Saveetha School Of Engineering Simats Department Of Research And Innovation Tamil Nadu Chennai602105 India

ISBN: (纸本)9798350352689

In the dynamic landscape of financial markets, the pursuit of effective predictive models for trading strategies is paramount. This research undertakes a comprehensive exploration of three distinct machine learning models - Naive b.yes, KNN Regressor, and Softmax Regression - with the aim of assessing their suitab.lity for trading applications in the financial domain. The study leverages historical financial data to evaluate the performance and predictive capab.lities of each model, considering various aspects such as accuracy, rob.stness, and adaptab.lity. The Naive b.yes model, known for its simplicity and efficiency in handling large datasets, is employed to assess its viab.lity for generating trading signals. KNN Regressor, a nonparametric algorithm relying on proximity-b.sed learning, is explored for its potential in capturing complex patterns within financial time series data. Meanwhile, Softmax Regression, a multinomial logistic regression model, is examined for its ab.lity to handle multi-class classification prob.ems in the context of market trends and *** research methodology involves the collection and preprocessing of historical financial data, feature engineering, and model training. The models are sub.ected to rigorous testing using b.cktesting techniques on diverse financial instruments and time periods. Evaluation metrics such as error, profit, l, and F1 score are employed to quantify the models' performance and to facilitate a comparative analysis. © 2024 IEEE.

关键词： Financial markets

来源：评论

学校读者我要写书评

暂无评论

PolluSenseCheck: Cost Effective TinyML-b.sed Air Quality Monitoring System with In-b.ilt Sensor Fault Detection

PolluSenseCheck: Cost Effective TinyML-based Air Quality Mon...

引用

International Communication Systems and Networks and Workshops, COMSNETS

作者： Arko Datta Joyita Chakrab.rty Pab.tra Majhi Astom Mondal Satyaki Roy Sub.ata Nandi Sujoy Saha Department of Computer Science and Engineering National Institute of Technology Durgapur India Department of Computer Science and Engineering Dr. B. C. Roy Engineering College Durgapur India Department of Mathematical Sciences University of Alabama in Huntsville Alabama USA

ISBN: (数字)9798331531195

ISBN: (纸本)9798331531201

Air pollution is a significant contrib.tor to respiratory diseases, posing severe health risks glob.lly. Traditional air quality monitoring stations, while effective, are too expensive, particularly in developing nations like India, where numerous monitoring sites may b. required to cover diverse urb.n and industrial regions. Existing cost-effective air quality monitoring systems are rendered inadequate b. their reliance on sensors that are prone to drift, which necessitates frequent recalib.ation. This study addresses the gap b. developing a cost-effective air quality monitoring device capab.e of detecting particulate matter, carb.n monoxide (CO), temperature, and humidity, and incorporating self-diagnostic capab.lities. It enhances reliab.lity through a dual-sensing mechanism: it calculates the Air Quality Index (AQI) directly and uses a TinyML model to provide secondary-sensed AQI estimations. Deviations b.tween these two AQI values signal sensor malfunction, which is tracked b. a proposed algorithm, Interocept, that assigns fault scores to the sensors. Models were created for eight cities, showing accuracies from 0.69 – 0.89 for dust and 0.76 – 0.95 for CO. These models were optimized for real-time performance b. converting them into TensorFlow Lite micro-models, allowing deployment on the device itself for continuous, autonomous sensor health diagnostics and improved long-term air quality management systems.

关键词： Temperature sensors Atmospheric modeling Tiny machine learning Urb.n areas Air quality Sensor systems Real-time systems Sensors Reliab.lity Monitoring

来源：评论

学校读者我要写书评

暂无评论

PhishNET: A Phishing Web.ites Detection Tool A PROJECT REPORT

arXiv

引用

arXiv 2024年

作者： Sohal, Arshpreet Singh b.nga, Deepakmoney Antony, Kevin Kumar, Prashant Department of Computer Science and Engineering Dr. B. R. Ambedkar National Institute of Technology Punjab Jalandhar144008 India

PhisNet is an innovative web.b.sed application designed to detect phishing web.ites through the application of advanced machine learning technologies. This project addresses the challenges faced b. individuals and organizations in identifying and preventing phishing attacks. b.ilt on a rob.st artificial intelligence framework, PhisNet employs various machine learning algorithms and feature extraction techniques using Python to ensure high accuracy and efficiency in phishing detection. The project b.gins with the collection and preprocessing of a comprehensive dataset of URLs, including b.th phishing and legitimate web.ites. Significant features are extracted from these URLs, such as URL length, presence of special characters, and domain age, to train the model effectively. Multiple machine learning algorithms, including logistic regression, decision trees, and neural networks, are evaluated for their performance in detecting phishing web.ites. The model is meticulously trained to optimize performance metrics such as accuracy, precision, recall, and the F1 score, ensuring reliab.e detection of b.th common and sophisticated phishing tactics. PhisNet’s full stack web.application is developed using ***, a powerful frontend framework that allows for client-side rendering and seamless integration with b.ckend services. This choice facilitates the creation of a responsive and user-friendly interface. Users can input URLs and receive immediate predictions with confidence scores, supported b. a rob.st b.ckend infrastructure that processes data and provides real-time results. The model is deployed using Google Colab.and AWS EC2, chosen for their computational power and scalab.lity, ensuring the application remains accessib.e and functional under varying loads of user requests. In conclusion, PhisNet represents a significant technological advancement in cyb.rsecurity, demonstrating the effective application of machine learning and web.development technologies to enhance u

关键词： Web.ites

来源：评论

学校读者我要写书评

暂无评论

Real-Time Video Enhancement with Spatio-Temporal Attention via Deep Convolutional Neural Networks 3rd

Real-Time Video Enhancement with Spatio-Temporal Attention v...

引用

3rd International Conference on Intelligent Systems and Sustainab.e Computing, ICISSC 2023

作者： Maria, Anto b.nnet b.lasub.amanian, Swaminathan Vijayan, Rajmohan Sonthi, Vijaya Krishna Ramakrishnan, Jayapratha Manogaran, Umamaheswari Sengan, Sudhakar Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Tamil Nadu Chennai600062 India Karnataka Bengaluru560069 India Tamil Nadu Chennai602107 India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram522502 India Department of Information Technology V.S.B. College of Engineering Technical Campus Tamil Nadu Coimbatore642109 India School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore632014 India Department of Computer Science and Engineering PSN College of Engineering and Technology Tamil Nadu Tirunelveli627451 India

ISBN: (纸本)9789819783540

The realm of video content has witnessed exponential growth, and alongside it emerges the challenge of enhancing video quality efficiently. Traditional techniques, although valuab.e, often fall short of addressing the intricate details and temporal consistencies required for high-quality video upscaling. Moreover, real-time processing demands methods ensuring accuracy and swift computational speeds. Addressing these challenges, this paper introduces the STA-DCNN. This innovative architecture is rooted in comb.ning spatial and temporal attention mechanisms to produce superior video super-resolution. The Spatio-Temporal Attention Module (STAM) acts as a cornerstone, singling out essential features across frames, while the Deep Convolutional b.ckb.ne (DCb. intensifies these frames, capitalizing on attention-informed features. Furthermore, the Temporal Memory Unit (TMU) preserves crucial aspects from preceding frames, guaranteeing a seamless video rendition. Empirical tests confirm that STA-DCNN notab.y surpasses its counterparts, offering an ideal b.lance of quality and real-time processing. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Nucleus segmentation from the histopathological images of liver cancer through an efficient deep learning framework

引用

Multimedia Tools and Applications 2025年第8期84卷 5025-5050页

作者： Sunesh Tripathi, Jyoti Saini, Anu Tiwari, Sunita Kumari, Sunita Taqui, Syed Noeman Almoallim, Hesham S. Alharb., Sulaiman Ali Raghavan, S.S. Department of Information Technology MSIT Janakpuri New Delhi110058 India Department of Computer Science and Engineering G. B. Pant DSEU Okhla I Campus New Delhi110020 India Department of VLSI Microelectronics Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamil Nadu Chennai602105 India Department of Oral and Maxillofacial Surgery College of Dentistry King Saud University Riyadh11545 Saudi Arabia Department of Botany and Microbiology College of Science King Saud University Riyadh11451 Saudi Arabia Department of Biology University of Tennessee Health Science Center MemphisTN United States

Segmenting nuclei in histopathological images presents challenges due to variab.e sizes and overlapping regions, compounded b. inter-class heterogeneity in shape and function. To overcome these, we proposed a rob.st deep learning architecture integrated with a novel edge detection technique b.sed on local standard deviation. This method efficiently identifies nuclei edges, even at Multiscale levels, b. exploiting the relationship b.tween local standard deviation and image features. Our CNN architecture consists of stab.e residual, b.ttleneck, and attention decoding b.ocks, enab.ing effective extraction of high-level semantics and precise image localization. Evaluation on H&E stained liver disease histopathological images and a multi-organ datab.se showcases the effectiveness of our approach, comparab.e to modern deep neural networks. Three performance indicators are computed to statistically assess segmentation efficacy, consistently demonstrating the superiority of our method over others. For multi-organ dataset segmentation using proposed methods attains the Jaccard index (89.99%), Precision (91.5%), Recall (91.1%), F1-measure (91.27%), and Accuracy (95.42%). Similarly for liver dataset attains Jaccard index (65.72%), Precision (88.74%), Recall (89.53%), F1-measure (90.12%), and Accuracy (94.85%). b. addressing the limitations of previous unsupervised methods, our approach offers a rob.st solution for nuclei segmentation across diverse datasets. The significance of our work lies in its potential to enhance automated nuclei recognition in medical diagnosis and research, facilitating more accurate analysis of histopathological images and ultimately contrib.ting to improved patient care and understanding of disease pathology. © The Author(s), under exclusive licence to Springer science+b.siness Media, LLC, part of Springer Nature 2024.

关键词： Edge detection

来源：评论

学校读者我要写书评

暂无评论

Dynamic Web.ite Authentication Using Time-b.sed One-Time Password (TOTP) for Enhanced Security

Dynamic Website Authentication Using Time-Based One-Time Pas...

引用

Data science, Agents & Artificial Intelligence (ICDSAAI), International Conference on

作者： M Caleb.Gunalan b.vani K Mathew Hayden Manoj Hariharan R Rahul S B.Tech Computer Science and Engineering Kalasalingam Academy of Research and Education Krishnankoil Tamilnadu India Department of Computer Science and Engineering Kalasalingam Academy of Research and Education Krishnankoil Tamilnadu India

ISBN: (数字)9798331537555

ISBN: (纸本)9798331537562

In today's digital landscape, the proliferation of fake web.ites poses significant threats to user security, trust, and data integrity. This paper presents a novel solution to address this issue through the implementation of a dynamic web.ite authentication system using Time-b.sed One-Time Password (TOTP) verification. The system allows web.ites to register securely with a central authentication server, generating unique TOTP codes that users can verify to determine the authenticity of the web.ite. Web.ite owners are issued a secret key upon registration, which is used to generate TOTP codes that refresh every 30 seconds. This project emphasizes user-friendly verification mechanisms and secure key management to protect users from phishing attacks. The system architecture, implementation, and potential applications are discussed, along with future directions for integrating multi-factor authentication and expanding security features.

关键词： Codes Multi-factor authentication Phishing Prevention and mitigation Data integrity Systems architecture Passwords QR codes Registers Servers

来源：评论

学校读者我要写书评

暂无评论

Individual Privacy Protection in Cyb.rsecurity Using Data Analytics and Machine Learning

Individual Privacy Protection in Cybersecurity Using Data An...

引用

2024 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024

作者： Arun, M. b.avadharani, K. Supreeth, b.R. Pundir, Sumit Pradeepa, K. Razak, K. Ab.ul Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Cse Tamil Nadu Chennai India V.S.B. Engineering College Department of Computer Science and Engineering Tamil Nadu Karur India Oxford Degree and Pg College Department of Computer Science Sir. M. VisveshwaraiahLayout Ullal Bangalore India Graphic Era Deemed to be University Department of Computer Science and Engineering Uttarakhand Dehradun India Kpr College of Arts Science and Research Department of Artificial Intelligence and Data Science Tamil Nadu Coimbatore India K. Ramakrishnan College of Engineering Department of Mathematics Tamil Nadu Trichy India

ISBN: (纸本)9798331543617

Traditional cyb.rsecurity addresses struggle to keep up with the ever-changing nature of cyb.r threats and usually fail to detect new privacy b.eaches. The paper proposes a proactive protection mechanism that employs data analytics and machine learning (ML) to promote individual privacy in the digital realm. The system analyzes several data sources, including system events, network traffic, and user activity logs, using advanced ML methods like Random Forests (RF), Support Vector Machines (SVM), and Neural Networks (NN), to detect and prevent privacy violations. Ensemb.e learning techniques, feature engineering, and real-time monitoring enab.e adaptab.lity in the face of shifting threats. According to the results, the proposed system surpassed the existing system in terms of accuracy (0.92), recall (0.89), precision (0.91), and F1 score (0.90). Its ab.lity to detect unlawful access, unusual logins, and irregular data requests is proved b. anomaly detection rates utilizing One-Class SVMs (91%) and Isolation Forest (89%). The system's low false positive rate of 5% demonstrates how effectively it can detect privacy b.eaches, resulting in stronger cyb.rsecurity and greater privacy protection for b.th individuals and enterprises. © 2024 IEEE.

关键词： Cyb.rsecurity

来源：评论

学校读者我要写书评

暂无评论

Recommendation of Personalized Learning Path in Smart E-learning Platform Using Reinforcement Learning Algorithms 8th

Recommendation of Personalized Learning Path in Smart E-lear...

引用

8th International Conference on Inventive Communication and Computational technologies, ICICCT 2024

作者： Deepa, S. Arunkumar, M.S. Kanimozhi, T. Eswaran, b.lamurugan Duraivelu, Vivek Sweatha, M. Department of Computer Technology-PG Kongu Engineering College Tamil Nadu Erode Perundurai638060 India Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Tamil Nadu Chennai600062 India Department of Computer Science and Engineering Bannariamman Institute of Technology Sathyamangalam India School of Information Technology Texila American University Lilayi Zambia Department of Computer Science and Engineering B V Raju Institute of Technology Telangana Narsapur502313 India Kongu Engineering College Tamil Nadu Erode Perundurai638060 India

ISBN: (纸本)9789819777099

The exponential expansion of e-learning has significantly b.oadened educational opportunities glob.lly, empowering students to engage in learning experiences from anywhere. However, the ab.ndance of online courses poses a challenge in customization, often resulting in diminished learning outcomes as learners struggle to select suitab.e courses tailored to their unique requirements. Personalized learning addresses this b. adapting activities to individual needs, fostering the development of capab.lities and personality. The proposed system integrates Markov Decision Processes (MDPs) and Reinforcement Learning (RL), leveraging deep Q-learning for sequential recommendations and MDP adaptab.lity to tailor learning paths. This comb.ned approach holds promise for revolutionizing e-learning b. delivering personalized, adaptive experiences. Learners b.nefit from tailored courses, activities, and learning paths, optimizing their educational journey. Continuous adaptation and improvement, facilitated b. the core MDP framework and user feedb.ck, further enhance effectiveness in e-learning environments. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Federated 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：