检索结果-内蒙古大学图书馆

Intelligent Cybersecurity Conference (ICSC)

作者： Yousef Sharrab Dimah Al-Fraihat Mohammad Alsmirat Dept. of Data Science and Artificial Intelligence Isra University Amman Jordan Dept.of Software Engineering Isra University Amman Jordan Dept. of Computer Science University of Sharjah Sharjah UAE

Text data forensics, a rapidly developing field that focuses on analyzing textual content to identify criminal or suspicious activities, is becoming increasingly important due to the popularity and the huge number of text posts on social media platforms. This study aims to improve the detection of suspicious text on social media using deep neural networks. Suspicious text is defined as any text that is likely to be associated with criminal activity or is unusual or out of the ordinary. This study could make a significant contribution to the field of text data forensics by helping to improve the detection of such text. We leveraged the “CIC Truth Seeker dataset 2023” [1], which is widely recognized as a comprehensive and representative dataset for text data forensics research. The dataset contains over 180,000 tweets related to 700 real and 700 fake pieces of news, labeled by experts. In this study, we enhance text data forensics in social media by leveraging the powerful analytical capabilities of deep neural networks. More specifically, we investigate the effectiveness of Long Short-Term Memory (LSTM) in the detection of suspicious text. The results are very promising as we achieved an accuracy of 96% during preliminary evaluations. We plan to explore future work on the model's potential applications, including criminal activity identification, misinformation detection, and online harassment prevention.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Perceptions Unveiled: Analyzing Public Sentiment on IoT and AI Integration in Revolutionizing Social Interactions

Perceptions Unveiled: Analyzing Public Sentiment on IoT and ...

引用

International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)

作者： Shweta Saraswat Shashi Sharma Ruchi Kulshrestha Nootan Verma Monica Lamba Dept. of Artificial Intelligence With Data Science Arya College of Engineering Jaipur India Dept. Of CSE JECRC University Jaipur India Dept. Of CSE Mody University Jaipur India Dept. of CSE Arya College of Engineering Jaipur India

The IoT and AI are transforming social connections and communication. The article investigates how this symbiotic relationship impacts Twitter sentiment. Using the Twitter Sentiment dataset," this study analyzes how IoT and AI are changing linked experiences. Analyzing Twitter sentiment on this historic merger shows positive and negative sentiments. Social media allows people to express their thoughts and feelings. This evolving digital environment reflects society and reveals technology adoption sentiment. The merging of IoT with AI is a key technological achievement. Tweets provide a real-time snapshot of worldwide dialogues and reactions to understand public opinion on integration. This study examines the complicated sentiment landscape using the "Twitter Sentiment dataset," which captures IoT and AI sentiments. Social media sentiment analysis has been used to study public reactions to technological advances. Several studies show that sentiment analysis can predict technological adoption, examine attitudes and concerns, uncover issues, influence legislation, and address ethical issues. Research also emphasizes sentiment polarization's enthusiasm-realism balance and how sentiment predicts technical impact. The research used the "Twitter Sentiment dataset," with over 1.6 million tweets. Lowercase, punctuation, and stopwords were removed from the dataset. After that, NLP algorithms like sentiment analysis examined the text. The training and test sets were split, and TF- IDF vectorization retrieved features. This research tested sentiment analysis machine learning models (Bernoulli Naive Bayes, Linear Support Vector Classification, and Logistic Regression). Later, the best model was stored. The main measure of sentiment analysis model accuracy was accuracy. Logistic regression outperformed with 83% accuracy. The models accurately captured IoT and AI integration tweets, including joy and concerns. Sentiment analysis can disclose society's feelings, making IoT-AI integ

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Smart Intelligent Detecting and Alerting System for Industrial Gas Leakage using IoT in Sensor Network

An Enhanced Smart Intelligent Detecting and Alerting System ...

引用

International Conference on Smart Systems and Inventive Technology (ICSSIT)

作者： G.A Senthil P Suganthi R. Prabha M. Madhumathi S. Prabhu S Sridevi Dept. of Information Technology Agni College of Technology Chennai India Dept. of Electronics and Communication Engineering Sri Sai Ram Institute of Technology Chennai India Dept. of Artificial Intelligence and Data Science Karpaga Vinayaga College of Engineering and Technology Chennai India Dept. of Computer Science and Engineering Sri Ramachandra Engineering and Technology Chennai India

Leakage of any type of gas has emerged as a hazard in recent years, whether in a typical workplace, boiler, a commercial setting, a café, or a canteen, industries natural gas, coal, refinery products, crude oil, cement, electricity, steel, and fertilizers etc. In this article, I proposed a new invention of an IoT-based gas waste monitoring, leak detection, and alerting system. The research extends on the development of such an intelligent system that can intelligently preserve gas, ensure the safety precaution and pre vent accidents. The technique must be connected to the stove. The design incorporates ultrasonic sensors which identify bio gas leakage in circumstance with in square metre is usage area of industries or cooking place. The Proposed work smart intelligence system is cuts off the gas supply using an automated shutting off device. Whenever a gas leak is detected, consumers will be notified through SMS via GSM, location using GPRS, and will be able to resolve the situation as quickly as feasible. The flame sensor in the technology will supervise flame and fire. The buzzer starts to sound when a fire is detected. Aside from that, the system may save data on the cloud. With the help of this cloud storage solution, every user’s daily gas use may be traced. Finally, this approach will aid in recognizing per user natural gas consumption. The system has been examined and is capable of monitoring gas loss, evacuation, and sending an SMS notification and location aid to the user. The precipitate demonstrated its usefulness in conserving a considerable amount of domestically squandered gas.

关键词： Industries GSM Cloud computing Vents Fires Sensor systems Intelligent sensors

来源：评论

学校读者我要写书评

暂无评论

YOLOv8-Based Person Detection, Distance Monitoring, Speech Alerts, and Weapon Identification with Email Notifications

YOLOv8-Based Person Detection, Distance Monitoring, Speech A...

引用

Expert Clouds and Applications (ICOECA), International Conference on

作者： V. Jyothsna Chamundi Alle Ragavendra Kurnutala Ganesh K N KushalKarthik K R Bhasha Pydala Dept. of IT Mohan Babu University (Erstwhile Sree Vidyanikethan Engineering College) Tirupathi India Dept of Data Science Mohan Babu University (Erstwhile Sree Vidyanikethan Engineering College) Tirupathi India

ISBN: (数字)9798350385793

ISBN: (纸本)9798350385809

An advanced security system utilizing the YOLOv8 algorithm for comprehensive object detection enables real-time identification of individuals and weapons. Innovative features include precise distance estimation and email alerts upon weapon detection, enhancing communication during security breaches. Rigorous testing ensures reliability, while ethical considerations ensure adherence to standards. This project represents a significant contribution to automated threat detection and response, exemplifying advancements in security technology within ethical boundaries, effectively addressing contemporary challenges. The integration of YOLOv8 for object, person, and weapon detection in audio, alongside distance estimation and email notification, marks a substantial leap in security surveillance technology, offering swift threat detection and coordinated response capabilities. Rigorous validation confirms its efficacy, promising to fortify security protocols and proactive threat mitigation strategies, thereby paving the way for further advancements in audio-based threat detection systems.

关键词： Protocols Weapons Surveillance Prevention and mitigation Estimation Threat assessment Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Robust Sensor Networks: Applying AI for Fault Identification in Challenging Operational Contexts

Robust Sensor Networks: Applying AI for Fault Identification...

引用

IoT Based Control Networks and Intelligent Systems (ICICNIS), International Conference on

作者： Manjunatha A S Venkatramana Bhat P Ramakrishna M Matti Nidhi Prabhu Dept. of Computer and Communication Engineering NITTE (Deemed to be University) NMAM Institute of Technology Nitte Mangaluru Karnataka Dept. of Computer Science and Engineering NITTE (Deemed to be University) NMAM Institute of Technology Nitte Mangaluru Karnataka Dept. of Data Science and Computer Applications Manipal Academy of Higher Education Manipal Institute of Technology Manipal India

ISBN: (数字)9798331518097

ISBN: (纸本)9798331518103

Wireless Sensor Networks (WSNs) are highly implemented in harsh and dynamic environments. In such configurations, faults and anomalies easily occur, causing unwanted disruptions in data accuracy and network performance. In the context of reliability and stability in WSN operations, effective fault detection techniques are vital. This research work discusses how several machine learning models may be applied, including Logistic Regression, Decision Tree, Random Forest, and K-Nearest Neighbors in order to detect fault in WSNs. The performance evaluation was performed based on major criteria, which are accuracy, precision, recall, and Fl score. This, therefore, makes these approaches to machine learning effective in identifying faults efficiently, hence offering a well-balanced solution that is scalable and robust for integrity and operational effectiveness of WSN s.

关键词： Fault diagnosis Wireless sensor networks Logistic regression Accuracy Fault detection Nearest neighbor methods Robustness Decision trees Random forests Testing

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Learning Method for Sign Language Detection

An Adaptive Learning Method for Sign Language Detection

引用

Emerging Technology (INCET), International Conference for

作者： A. V. Sriharsha Kodudula Anusha Bramhanapudhuru Naveen Kacheri Sadak Hima Harshitha Reddy G Dept. of Data Science Mohan Babu University (Erstwhile Sree Vidyanikethan Engineering College) Tirupathi India Dept of IT Mohan Babu University (Erstwhile Sree Vidyanikethan Engineering College) Tirupathi India

ISBN: (数字)9798350361155

ISBN: (纸本)9798350361162

Advancements in hand gesture recognition technology are transforming the way we interact with computers, manipulate objects in virtual worlds, and communicate using hand gestures. In this paper, we present a system that leverages the combined power of Media Pipe's holistic model and machine learning to achieve real-time hand gesture recognition with remarkable accuracy and efficiency. The pre-trained machine learning model is employed to classify detected hand gestures, providing a robust framework for gesture recognition. The system operates live, capturing video frames from your camera. Using Media Pipe's magic, it pinpoints key points on your hands, creating a digital map of their position and configuration. Detected hand landmarks are visually overlaid on the video frames, enhancing user understanding and system transparency. This information is then fed into a pre-trained machine learning model, a master of decoding hand movements, which instantly deciphers the gesture you're making. Like a secret code translator, it converts this gesture into a corresponding label, transforming your hand movements into meaningful commands or words.

关键词： Computers Codes Accuracy Computational modeling System performance Machine learning Media

来源：评论

学校读者我要写书评

暂无评论

A Learning Support Method for Multi-threaded Programs Using Trace Tables

arXiv

引用

arXiv 2024年

作者： Murata, Takumi Hashiura, Hiroaki Electronics Information and Media Engineering Major Graduate School of Engineering Nippon Institute of Technology Saitama Japan Dept. of Data Science Faculty of Advanced Engineering Nippon Institute of Technology Saitama Japan

Multi-threaded programs are expected to improve responsiveness and conserve resources by dividing an application process into multiple threads for concurrent processing. However, due to scheduling and the interaction of multiple threads, their runtime behavior is more complex than that of single-threaded programs, making which makes debugging difficult unless the concepts specific to multi-threaded programs and the execution order of instructions can be understood. In this paper, we propose a learning tool for multi-threaded programs using trace tables. Copyright © 2024, The Authors. All rights reserved.

关键词： Application programs

来源：评论

学校读者我要写书评

暂无评论

ChatGPT-guided Semantics for Zero-shot Learning

ChatGPT-guided Semantics for Zero-shot Learning

引用

2023 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2023

作者： Shubho, Fahimul Hoque Chowdhury, Townim Faisal Cheraghian, Ali Saberi, Morteza Mohammed, Nabeel Rahman, Shafin North South University Dept. of Electrical and Computer Engineering Bangladesh University of Adelaide Australian Institute for Machine Learning Australia Data61 Commonwealth Scientific and Industrial Research Organisation Australia University of Technology Sydney School of Computer Science and Dsi Australia

ISBN: (纸本)9798350382204

Zero-shot learning (ZSL) aims to classify objects that are not observed or seen during training. It relies on class semantic description to transfer knowledge from the seen classes to the unseen classes. Existing methods of obtaining class semantics include manual attributes or automatic word vectors from language models (like word2vec). We know attribute annotation is costly, whereas automatic word vectors are relatively noisy. To address this problem, we explore how ChatGPT, a large language model, can enhance class semantics for ZSL tasks. ChatGPT can be a helpful source to obtain text descriptions for each class containing related attributes and semantics. We use the word2vec model to get a word vector using the texts from ChatGPT. Then, we enrich word vectors by combining the word embeddings from class names and descriptions generated by ChatGPT. More specifically, we leverage ChatGPT to provide extra supervision for the class description, eventually benefiting ZSL models. We evaluate our approach on various 2D image (CUB and AwA) and 3D point cloud (ModelNet10, ModelNet40, and ScanObjectNN) datasets and show that it improves ZSL performance. Our work contributes to the ZSL literature by applying ChatGPT for class semantics enhancement and proposing a novel word vector fusion method. © 2023 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis of Movie Reviews: Optimizing Predictions Through TF-IDF Vectorization

Sentiment Analysis of Movie Reviews: Optimizing Predictions ...

引用

Intelligent data Communication Technologies and Internet of Things (IDCIoT), International Conference on

作者： Mohd Irfan Anne Sreyas Venkatesam Hariharan Shanmugasundaram Mahendra Kumar Gourisaria Subrata Chowdhury Sudhansu Shekhar Patra Department of Artificial Intelligence and Data Science Vardhaman College of Engineering Hyderabad Telangana India Department of Artificial Intelligence and Data Science Vardhaman College of Engineering Hyderabad India School of Computer Engineering Kalinga Institute of Industrial Technology (KIIT) Deemed to be University Bhubaneswar India Dept. of Computer Science and Engineering Sreenivasa Institute of Technology and Management Studies(A) Chittoor Andhra Pradesh India

ISBN: (数字)9798331527549

ISBN: (纸本)9798331527556

Sentiment analysis model is aimed to accurately interpret movie reviews, addressing challenges like sarcasm and noisy data. By integrating multiple machine learning classifiers Naive Bayes, Random Forest, K-Nearest Neighbors, Logistic Regression, Decision Tree, and XGBoost—the model enhances sentiment prediction accuracy. The Term Frequency-Inverse Document Frequency (TF-IDF) method is used to extract features from a dataset of 50,000 movie reviews. Performance is evaluated using accuracy, precision, recall, and F1-score, with Logistic Regression achieving the best results, including an highest accuracy of 84.33 % and an F1-score of 0.847. In comparison to traditional methods, this multi-classifier approach offers a deeper understanding of movie reviews and its influence on audience decisions. The study demonstrates the potential of using these machine learning techniques to provide real-time, scalable sentiment analysis, which is crucial for filmmakers and marketers seeking insights into audience satisfaction and box office performance.

关键词： Sentiment analysis Logistic regression Accuracy Reviews Predictive models Motion pictures Feature extraction Real-time systems Noise measurement Random forests

来源：评论

学校读者我要写书评

暂无评论

VIR2EM: VIrtualization and Remotization for Resilient and Efficient Manufacturing: Project-Dissemination Paper

VIR2EM: VIrtualization and Remotization for Resilient and Ef...

引用

Forum on Specification, Verification and Design Languages, FDL

作者： Alessandro Beghi Nicola Dall'Ora Davide Dalle Pezze Franco Fummi Chiara Masiero Stefano Spellini Gian Antonio Susto Francesco Tosoni Dept. of Information Engineering University of Padova Padova Italy Dept. of Engineering for Innovation Medicine University of Verona Italy Statwolf Data Science s.r.l. Padova Italy

In this paper, we present the project “VIR2EM: VIrtualization and Remotization for Resilient and Efficient Manufacturing” by providing details on its research themes and its scientific and technological output. The project, centered on virtualization and remotization in the industrial sector, was promoted by Regione Veneto in Italy, and it has seen the participation and collaboration of 3 universities, 1 public research entity, and 10 companies composed of end users of digital solutions and high knowledge-intensive service providers. The project aims to develop and use tools for the virtualization of processes, systems, resources, and remoting of operations in order to: (1) maximize the efficiency of manufacturing systems under normal operating conditions; (2) maintain operations in case of emergency situations; (3) facilitate the restart of operations downstream of emergency situations by ensuring flexibility and predictive capability. Each theoretical proposal has been validated in distinct industrial facilities by constructing ten different prototypes.

关键词：

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：