检索结果-内蒙古大学图书馆

"affectAlchemy": An Affective Dataset Based on Plutchik's Psychological Model for Text-Based Emotion Recognition and its Analysis Using ML Techniques 8

"affectAlchemy": An Affective Dataset Based on Plutchik's Ps...

引用

8th IEEE International Conference on Computing, Communication, Control and Automation, ICCUBEA 2024

作者： Kapase, Ajay Uke, Nilesh Savant, Jatin Desai, Mrunali Ghatage, Shravani Rahangdale, Atul Vishwakarma Institute of Information Technology Computer Science & Engineering Pune India Trinity Academy of Engineering Computer Science & Engineering Pune India KITs College of Engineering Computer Science & Engineering Kolhapur India

ISBN: (纸本)9798350391770

A technique to identify people's attitudes, and sentiments towards specified targets such as things, services, and subjects, is called sentiment analysis. As a dedicated subset of NLP, it deals with predicting specific reactions broadly characterizing sentiments as positive, negative, or neutral. However, the accuracy and depth vary since there are a variety of human emotions that exist rather than just positive, negative, and neutral. In the past few decades, the term affective computing has become well-liked which involves the use of AI for identifying, interpreting, and responding to human emotions. A part of it called text-based affective systems are artificial emotional intelligent systems that often categorize the text into core wide range of emotions like fear, sadness, anger, and happiness. These affective systems use various psychological models for emotion recognition. Our study incorporates the development of a dataset based on Robert Plutchik's psychological model of emotions, which sets forth eight primary emotions which are combined to form more complex emotions, resulting in a total of 24 secondary emotions resulting total of 32 variety of emotions. The work introduces the "AffectAlchemy"dataset which is validated using multiclass classification machine learning techniques. This dataset can contribute to the field of affective computing for the development of models that can do enhanced emotion recognition, and improved emotional context understanding to develop emotion-aware applications and facilitating research in affective systems. © 2024 IEEE.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Machine Learning based Phishing Website Detection 18

Machine Learning based Phishing Website Detection

引用

18th INDIAcom;11th International Conference on Computing for Sustainable Global Development, INDIACom 2024

作者： Kawale, Manav Maru, Bhavik Dagu, Sakshi Varghese, Maya Gupta, Vikas Vidyavardhini's College of Engineering & Technology Department of Computer Science and Engineering Mumbai India

ISBN: (纸本)9789380544519

Phishing websites are those where a person can imitate a legitimate website and trick an innocent user into thinking he is visiting a legitimate website while stealing sensitive information. Statistics from the Anti-Phishing Website Group (APWG) show that in the second quarter of 2023, 1,286,208 phishing attacks were recorded. This was the APWG's third-highest quarterly total ever. To address this issue, a Phishing website detection system was made that automatically detects and notifies the user of any phishing website. The system will be based on supervised learning wherein machine learning models such as k-nearest Neighbors, Logistic Regression, Support Vector Classifier, Naive Bayes, Decision Tree, and Random Forest are selected for training. Random Forest was found to have the highest accuracy among them. As a result, Randomforest was chosen with an accuracy of 96.7 and a combination of 32 features, among which features like status bar customizing, website forwarding, stats report, pop windows, server form handler were uniquely identified and implemented to the proposed system to improve the overall accuracy of the model. © 2024 Bharati Vidyapeeth, New Delhi.

关键词： Machine learning technique Phishing phishing feature extraction Random Forest

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Cross-Domain Few-Shot Visual Recognition: A Survey

引用

ACM Computing Surveys 2025年第8期57卷 1-37页

作者： Xu, Huali Zhi, Shuaifeng Sun, Shuzhou Patel, Vishal Liu, Li College of Computer Science Nankai University Tianjin China College of Electronic Science and Technology National University of Defense Technology Changsha China Faculty of Information Technology and Electrical Engineering University of Oulu Oulu Finland Johns Hopkins University Baltimore United States

While deep learning excels in computer vision tasks with abundant labeled data, its performance diminishes significantly in scenarios with limited labeled samples. To address this, Few-shot learning (FSL) enables models to perform the target tasks with very few labeled examples by leveraging prior knowledge from related tasks. However, traditional FSL assumes that both the related and target tasks come from the same domain, which is a restrictive assumption in many real-world scenarios where domain differences are common. To overcome this limitation, Cross-domain few-shot learning (CDFSL) has gained attention, as it allows source and target data to come from different domains and label spaces. This article presents the first comprehensive review of Cross-domain Few-shot Learning (CDFSL), a field that has received less attention compared to traditional FSL due to its unique challenges. We aim at providing both a position article and a tutorial for researchers, covering key problems, existing methods, and future research directions. The review begins with a formal definition of CDFSL, outlining its core challenges, followed by a systematic analysis of current approaches, organized under a clear taxonomy. Finally, we discuss promising future directions in terms of problem setups, applications, and theoretical advancements. © 2025 Copyright held by the owner/author(s).

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

CNN Based Smart Waste Segregation and Collection System 4

CNN Based Smart Waste Segregation and Collection System

引用

4th IEEE International Conference on Data engineering and Communication Systems, ICDECS 2024

作者： Lavanya, V. Abikash Shivam, G. Shanmugasundaram, S. Deepalakshmi, R. Velammal College of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu India

ISBN: (纸本)9798350393354

Waste management is an increasing concern in urban areas worldwide, because of population growth and environmental sustainability goals. To address this challenge, this paper presents a Convolutional Neural Network (CNN)-based waste segregation and collection system that uses the power of computer vision and machine learning. The proposed system is used to automate the process of waste segregation, optimizing the sorting of waste into bio-degradable, reusable, recyclable waste and trash in real time. Utilizing a camera for capturing the images of incoming waste materials and moving the waste at their respective collection points. The images are processed using a deep learning YOLOv8 model, which identifies and classifies the waste items into bio-degradable, recyclable and non-recyclable categories with high accuracy. This innovative waste management solution holds the potential to change the waste collection and recycling processes, making them more cost-effective, environmentally friendly, and aligned with the ability for sustainable waste management practices. © 2024 IEEE.

关键词： Waste management

来源：评论

学校读者我要写书评

暂无评论

Campus Sync - One Central Hub for Attendance, Events, and On-Duty Management 9

Campus Sync - One Central Hub for Attendance, Events, and On...

引用

9th International Conference on science, technology, engineering and Mathematics, ICONSTEM 2024

作者： Rohini, M. Vijayvenkatajalapathi, G. Selvakumar, S. Sugavanesh, M. Viswanath, S. Gowthamani, R. Sri Krishna College of Engineering And Technology Department of Computer Science And Engineering Coimbatore India

ISBN: (纸本)9798350365092

Our comprehensive application provides a versatile solution for managing attendance, events, and on-duty assignments within college administrative operations. Developed meticulously, our application comprises three core modules: Attendance Management, Event Management, and On-Duty Management. The Attendance Management module enables administrators to efficiently take attendance across various platforms, including mobile devices, tablets, and PCs. It offers the flexibility to configure hourly attendance and access detailed statistics within custom date ranges. Similarly, the Event Management feature facilitates seamless scheduling of events and mapping of rooms and event halls, thereby enhancing the organization and execution of campus activities. Additionally, our On-Duty Management module simplifies the handling of on-duty requests, approvals, and event mapping, promoting efficient coordination and coverage. Noteworthy is our platform's integration of these modules within a single application, fostering departmental coordination. Its multi-platform support via Flutter ensures ease of use and accessibility. By centralizing essential tasks and streamlining administrative processes, our platform aims to enhance overall efficiency and productivity for educational institutions. Moreover, by digitizing administrative tasks and eliminating paperwork, our application addresses existing administrative challenges, offering a more streamlined and effective campus management system. © 2024 IEEE.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Detecting Inaudible Voice Commands via Acoustic Attenuation by Multi-channel Microphones

引用

IEEE Transactions on Dependable and Secure Computing 2024年 1-17页

作者： Ji, Xiaoyu Zhang, Guoming Li, Xinfeng Qu, Gang Cheng, Xiuzhen Xu, Wenyuan Electrical Engineering of Zhejiang University Hangzhou China School of Computer Science and Technology of Shandong University Qingdao China Department of Electrical and Computer Engineering at the University of Maryland College Park MD USA

DolphinAttacks (i.e., inaudible voice commands) modulate audible voices over ultrasounds to inject malicious commands silently into voice assistants and manipulate controlled systems (e.g., doors or smart speakers). Eliminating DolphinAttacks is challenging if ever possible since it requires to modify the microphone hardware. In this paper, we design EarArray, a lightweight method that can not only detect such attacks but also identify the direction of attackers without requiring any extra hardware or hardware modification. Essentially, inaudible voice commands are modulated on ultrasounds that inherently attenuate faster than the one of audible sounds. By inspecting the command sound signals via the built-in multiple microphones on smart devices, EarArray is able to estimate the attenuation rate and thus detect the attacks. We propose a model of the propagation of audible sounds and ultrasounds from the sound source to a voice assistant, e.g., a smart speaker, and illustrate the underlying principle and its feasibility. We implemented EarArray using two specially-designed microphone arrays and our experiments show that EarArray can detect inaudible voice commands with an accuracy of above 99% and recognize the direction of the attackers with an accuracy of 97.89% and can also detect the laser-based attack with an accuracy of 100%. IEEE

关键词： Microphones

来源：评论

学校读者我要写书评

暂无评论

Enhanced Criminal Identification through MTCNN: Leveraging Advanced Facial Recognition technology 9

Enhanced Criminal Identification through MTCNN: Leveraging A...

引用

9th International Conference on science, technology, engineering and Mathematics, ICONSTEM 2024

作者： Gowthamani, R. Sasi Kala Rani, K. Gayathri, D. Geetha, R. Harish, S. Rohini, M. Sri Krishna College of Engineering And Technology Department of Computer Science And Engineering Coimbatore India

ISBN: (数字)9798350365092

ISBN: (纸本)9798350365092

Due to the rise in crime, it is harder for police to identify criminals in public. Constantly reviewing surveillance footage is a laborious process that requires careful attention to detail and is not cognitively stimulating, which increases the likelihood of mistakes. Even though many existing systems for the identification of criminals have been developed, their accuracy in recognizing them is very low. The project's goal is to use Multi-task Cascaded Convolutional Neural Networks to create an advanced criminal detection and alert system. The MTCNN model is trained using a variety of datasets that include the face features, attire, and other distinguishable traits of well-known criminals. Improving the network's capacity to identify patterns and characteristics that are essential for precise criminal identification is part of the training process. During real-time operation, the system continuously analyzes video streams from surveillance cameras, applying the trained MTCNN model to detect and identify potential criminals in public places. The utilization of MTCNN s enables the system to overcome challenges such as varying lighting conditions, partial obstructions, and changes in appearance, ensuring reliable performance in dynamic environments. Upon the detection of a potential match, the system triggers an alert mechanism, notifying law enforcement agencies in real-time. Relevant information is included in the notifications, such as the image, location, and details of the identified person. Our proposed system has the potential to enhance accuracy to 96.2 % for the identification of criminals in both public and private places. © 2024 IEEE.

关键词： Crime

来源：评论

学校读者我要写书评

暂无评论

Enhancing Network Security: A Comparative Analysis of Deep Learning and Machine Learning Models for Intrusion Detection

Enhancing Network Security: A Comparative Analysis of Deep L...

引用

2024 International Conference on E-Mobility, Power Control and Smart Systems, ICEMPS 2024

作者： Ajeesh, Arunima Mathew, Tessy Mar Baselios College of Engineering and Technology Department of Computer Science and Engineering Thiruvananthapuram India

ISBN: (纸本)9798350394399

The escalating reliance of computer networks on security systems exposes them to increasing threats. In response, an advanced security system is proposed, utilizing machine learning and deep learning techniques and leveraging the NSLKDD and CSE-CIC-IDS2018 datasets. Addressing the class imbalance challenges, the DSSTE algorithm is adopted to optimize model performance. Evaluation involves six, machine learning and deep learning methods: XGBoost, LSTM, Bi-LSTM, CNN, and VGG19, with a focus on assessing speed, false positive rate and detection efficiency. Experimental results underscore DSSTE's efficacy in mitigating class imbalance and enhancing overall intrusion detection. The proposed IDS, empowered by machine learning and DSSTE, ensures early detection and strengthens network security by countering intrusion attempts. Performance is compared with systems utilizing SMOTE and ADAASYN for data balancing. © 2024 IEEE.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Optimized Autonomous Computing with Trusted Resilient Data Management for IoT Emerging Networks

引用

IEEE Sensors Journal 2025年第11期25卷 20778-20785页

作者： Shafique, Ayesha Cheng, Benmao Zhao, Bo Alwakid, Ghadah Naif Haq, Muhammad Inaam Ul Laboratory of Intelligent IOT Technology and Applications in Universities China Jouf University College of Computer and Information Sciences Department of Computer Science Al Jowf Sakaka72341 Saudi Arabia Quanzhou University of Information Engineering School of Computer Science and Software Engineering Quanzhou362000 China

The innovative city network integrates numerous computational and physical components to develop real-time systems. These systems can capture sensor data and distribute it to end stations. Most solutions have been presented based on the centralized computing paradigm, which effectively and systematically increases data flow;however, distributed wireless technologies and heterogeneous network services continue to raise significant research problems. These challenges lower the optimization criteria and reflect communication structure around the network edges. In this research, we proposed a sustainable development for smart networks using efficient big data management with collaborative decisions for network devices. It differs from most existing work in the mentioned aspect. It applies computational lightweight intelligence for forwarding collected data using mobile collectors and reduces the congestion flow between devices on the limited bandwidth of wireless links. Moreover, the energy load is efficiently managed with edge-driven methods, and the incorporation of trusted devices ensures the integrity of the smart network. It also tackles potential communication threats smartly. Based on the experiments conducted in Network Simulator (NS-3), the proposed model enhances the efficacy of smart networks for performance metrics with reliability and effective management of resources in Internet of Things (IoT) network. © 2025 IEEE.

关键词： Mathematical models Computational modeling Intelligent sensors Data aggregation Internet of Things Security Routing Load modeling Silicon Data models

来源：评论

学校读者我要写书评

暂无评论

Improving 5G Positioning Through Signal-to-Noise Ratio Recognition Training

Improving 5G Positioning Through Signal-to-Noise Ratio Recog...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Zheng, Wenqi Chen, Jianing Yang, Junze Chen, Chuhao Li, Wei Yadav, Rahul Meng, Xiangxu College of Computer Science and Technology Harbin Engineering University China

ISBN: (纸本)9798350368741

Fifth-generation communication technology enables advanced indoor positioning with its high bandwidth and frequency capabilities. However, indoor environment variability causes signal propagation fluctuations, making existing models inadequate for accurate location estimation. In this paper, we demonstrate that integrating SNR recognition training with the positioning network can enhance localization performance. Specifically, by leveraging a general neural network to extract common features from 5G Channel State Information (CSI), we employ two carefully designed downstream networks for signal-to-noise ratio (SNR) estimation and location prediction. In order to improve localization performance, we utilize mutual information-based metric to direct each network head towards its specific task, thereby refining and enhancing the features pertinent to each task. Moreover, for enhanced adaptive positioning accuracy, the coefficients linked to the features used in SNR and position estimation are determined based on the hidden features of the corresponding identification head. These coefficients are then utilized to appropriately weigh the hidden features of the location regression module. Experimental results using datasets from real-world scenarios demonstrate that our proposed method significantly improves positioning accuracy over state-of-the-art (SOTA) methods. Code can be available at: https://***/mxx123321/indoor_snr. © 2025 IEEE.

关键词： 5G Channel State Information (CSI) Deep Learning (DL) Fingerprint Indoor positioning

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：