检索结果-内蒙古大学图书馆

EAI Endorsed Transactions on Industrial Networks and Intelligent Systems 2024年第1期11卷 1-12页

作者： Saifullah, Khalid Khan, Muhammad Ibrahim Jamal, Suhaima Sarker, Iqbal H. Department of Computer Science and Engineering Chittagong University of Engineering and Technology Chittagong4349 Bangladesh Dept. of Information Technology Georgia Southern University StatesboroGA United States Centre for Securing Digital Futures School of Science Edith Cowan University PerthWA6027 Australia

In the contemporary digital age, social media platforms like Facebook, Twitter, and YouTube serve as vital channels for individuals to express ideas and connect with others. Despite fostering increased connectivity, these platforms have inadvertently given rise to negative behaviors, particularly cyberbullying. While extensive research has been conducted on high-resource languages such as English, there is a notable scarcity of resources for low-resource languages like Bengali, Arabic, Tamil, etc., particularly in terms of language modeling. This study addresses this gap by developing a cyberbullying text identification system called BullyFilterNeT tailored for social media texts, considering Bengali as a test case. The intelligent BullyFilterNeT system devised overcomes Out-of-Vocabulary (OOV) challenges associated with non-contextual embeddings and addresses the limitations of context-aware feature representations. To facilitate a comprehensive understanding, three non-contextual embedding models GloVe, FastText, and Word2Vec are developed for feature extraction in Bengali. These embedding models are utilized in the classification models, employing three statistical models (SVM, SGD, Libsvm), and four deep learning models (CNN, VDCNN, LSTM, GRU). Additionally, the study employs six transformer-based language models: mBERT, bELECTRA, IndicBERT, XML-RoBERTa, DistilBERT, and BanglaBERT, respectively to overcome the limitations of earlier models. Remarkably, BanglaBERT-based BullyFilterNeT achieves the highest accuracy of 88.04% in our test set, underscoring its effectiveness in cyberbullying text identification in the Bengali language. Copyright © 2024 K. Saifullah et al., licensed to EAI. This is an open access article distributed under the terms of the CC BY-NC-SA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the original work is properly cited.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Automating Neural Model Selection in Spiking Neural Networks Using AutoML Techniques 22

Automating Neural Model Selection in Spiking Neural Networks...

引用

22nd International Learning and Technology Conference, L and T 2025

作者： Sanaullah Honda, Hirotada Roy, Kaushik Schneider, Axel Wasmuth, Joachim Jungeblut, Thorsten University of Applied Sciences and Arts Dept. of Mathematics and Engineering Bielefeld Germany Toyo University Dept. of Information Networking Tokyo Japan A&T State University Dept. of Computer Science NC United States

ISBN: (纸本)9798331532215

The selection of optimal neural models in Spiking Neural Networks (SNNs) traditionally depends on a trial-and-error approach, which is both time-consuming and sometimes tends to suboptimal selection of the neural model. This research study explores the integration of Automated Machine Learning (AutoML) techniques into SNNs to simplify the process of designing an SNN model by automatically selecting the most optimal neural model. For example, in traditional neural networks, AutoML proves that it has the potential to significantly reduce the time and effort required to identify the best-performing architectures, by automating the selection and updating of loss functions and hyper-parametric values. To this end, we present a stand-alone framework for applying AutoML in SNNs, highlighting how this approach can improve accuracy, efficiency, and reliability in the selection process of optimal neural models, as these neural models are the core principle of designing SNN architecture. The proposed method not only accelerates the development of SNN models but also enhances their performance by systematically identifying optimal configurations that might be overlooked through manual methods. Therefore, to validate our approach, the proposed architecture was tested using different well-known benchmarks with different sets of neurons, ranging from 100 to 3000 neurons, and demonstrated state-of-the-art results in image classification tasks. © 2025 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Deciphering Deceit: Multimodal Classification of Optimal Algorithms for Fake Website Detection 3

Deciphering Deceit: Multimodal Classification of Optimal Alg...

引用

3rd IEEE International Conference on Blockchain and Distributed Systems Security, ICBDS 2024

作者： Thombre, Supriya Doifode, Vaibhaw Kokardekar, Sakshi Hasija, Udit Wazalwar, Sampada Yeshwantrao Chavan College of Engineering Dept. of Computer Technology Nagpur India Yeshwantrao Chavan College of Engineering Dept. of Electrical Engineering Nagpur India Kpit Technologies Limited Pune India Bhartiya Vidyapeeth College of Engineering Dept. of Computer Science and Engineering New Delhi India G.H. Raisoni College of Engineering Dept. of Information Technology Nagpur India

ISBN: (纸本)9798350354348

Detecting fake website URLs is crucial in today's digital era, where online scams and malicious/ fraudulent activities abound. Such websites pose a myriad of problems in the digital landscape, ranging from financial loss and identity theft to the dissemination of misinformation and the erosion of trust in online platforms. Individuals who fall victim to fraudulent websites may suffer financial repercussions, as they may unknowingly disclose confidential information such as details of credit card or login credentials. Moreover, fake websites can deceive users by spreading false information or promoting illegitimate products and services, which can undermine public trust in online sources and exacerbate societal issues such as misinformation and cybercrime. Therefore, there is a pressing need to detect fake websites promptly to mitigate these risks and protect users' privacy, financial security, and trust in the online environment. This study by the authors evaluates the predictive performance of five machine learning (ML) models - Random Forest (RF) Classifier, Decision Tree (DT)) Classifier, K-Neighbors (KN) Classifier, SGD Classifier and Gaussian NB (GNB) - in the reference of malicious and fake website URL detection. Leveraging a diverse dataset encompassing both benign and malicious URLs, our analysis encompasses rigorous evaluation metrics. The results highlight distinct strengths and weaknesses among the models, offering valuable insights for practitioners seeking to optimize predictive capabilities in the realm of cybersecurity. These findings contribute to the ongoing refinement of machine learning strategies for effective malicious URL detection and mitigation. © 2024 IEEE.

关键词： Phishing

来源：评论

学校读者我要写书评

暂无评论

AI-enabled Clinical Decision Support System 6

AI-enabled Clinical Decision Support System

引用

6th IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics, DISCOVER 2022

作者： Vasudeva Rao, Pv Ashwija Kanmani Kavana Tilak, Sk Kulal, Brinda Jyothika, Rs Sahyadri College of Engineering and Management Dept. of Information Science and Engineering Dept. of Computer Science and Engineering Mangalore India

ISBN: (数字)9781665487160

ISBN: (纸本)9781665487160

Each person's life is extremely important and vital for the country's development. Helping to limit the number of misdiagnoses can save many lives and strengthen families, as some families would lose their primary source of income as a result of misdiagnosis. Misdiagnosis is one of the significant errors in the medical field due to misjudgments by medical professionals eading to increased harm to patients. With 72 percent of errors occurring during the patient-practitioner encounter, it becomes increasingly important to reduce the error in real time. Lowering the mortality rate as a result of misdiagnosis would enhance and build the social well-being of the country. The area of general medicine is very vast and has more than 400 diseases and conditions under it. However, with differing and misleading symptoms for the diseases, it becomes rather confusing for a recent medical graduate to diagnose an individual within the limiting time frame for testing the patient. The developed solution is an artificial intelligence-based system that uses traditional machine learning algorithms and deep learning techniques to help new medical graduates and practitioners with limited experience reliably diagnose a patient's medical condition based on the patient's symptoms recorded during the clinical confrontation. The proposed solution is an AI-enabled Clinical Decision Support System in the form of a web application intended to assist medical graduates and healthcare professionals in accurately diagnosing a patient's health condition based on the symptoms observed during doctor-patient encounters. The developed system has achieved the highest accuracy by using the Ensemble technique which is a combination of Support Vector Classifier, Random Forest, and Naive Bayes technique for textual data analysis and ResNet architecture for analyzing image data. © 2022 IEEE.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

Near-Optimal Content Service Algorithm with Procurement and Placement in Edge Networks

Near-Optimal Content Service Algorithm with Procurement and ...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Yang, Chun-An Chen, Shih-Chieh Peng, Yi-Hsuan Chen, Yu-Wen Kuo, Jian-Jhih Tsai, Ming-Jer National Tsing Hua University Dept. of Computer Science Hsinchu Taiwan National Chung Cheng University Dept. of Computer Science and Information Engineering Chiayi Taiwan New York City College of Technology Computer Systems Technology BrooklynNY United States

ISBN: (纸本)9798350351255

Telecom carriers have announced new content services by making a partnership with content providers and offered popular video streaming to customers. Via the integration with edge networks, telecom carriers can procure various contents from content providers and place them on edge servers proximate to end users to serve real-time requests with high bandwidth and ultra-low latency. Nevertheless, it is challenging to consider the content procurement, placement, and services jointly due to the user preference, user distribution, storage capacity of edge server, economic costs, etc. Telecom carriers would like to balance the procuring, placing, and transfer costs. To address this problem, the paper formulates an optimization problem and then proposes an approximation algorithm. Finally, the simulation results manifest that our algorithm outperforms other baselines. © 2024 IEEE.

关键词： Video streaming

来源：评论

学校读者我要写书评

暂无评论

Context-aware Container Orchestration in Serverless Edge Computing

Context-aware Container Orchestration in Serverless Edge Com...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Guan, Peiyuan Chen, Chen Chen, Ziru Cai, Lin X. Hao, Xing Taherkordi, Amir University of Oslo Dept. of Informatics Oslo Norway University of Cambridge Dept. of Computer Science and Technology Cambridge United Kingdom Illinois Institute of Technology Dept. of Electrical and Computer Engineering Chicago United States Northwest Univesity School of Information Science and Technology Xi'an China

ISBN: (纸本)9798350351255

Adopting serverless computing to edge networks benefits end-users from the pay-as-you-use billing model and flexible scaling of applications. This paradigm extends the boundaries of edge computing and remarkably improves the quality of services. However, due to the heterogeneous nature of computing and bandwidth resources in edge networks, it is challenging to dynamically allocate different resources while adapting to the burstiness and high concurrency in serverless workloads. This article focuses on serverless function provisioning in edge networks to optimize end-to-end latency, where the challenge lies in jointly allocating wireless bandwidth and computing resources among heterogeneous computing nodes. To address this challenge, We devised a context-aware learning framework that adaptively orchestrates a wide spectrum of resources and jointly considers them to avoid resource fragmentation. Extensive simulation results justified that the proposed algorithm reduces over 95% of converge time while the end-to-end delay is comparable to the state of the art. © 2024 IEEE.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Aggregated Spatio-temporal MLP-Mixer for Violence Recognition in Video Clips 6

Aggregated Spatio-temporal MLP-Mixer for Violence Recognitio...

引用

6th International Symposium on computer, Consumer and Control, IS3C 2023

作者： Shen, Yu-Shian Chen, Jenhui Chang Gung University Guishan Dist Dept. Computer Science & Information Engineering Taoyuan33302 Taiwan

ISBN: (纸本)9798350301953

Existing violent behavior datasets are not perfect in quantity and quality due to the difficulty of collecting. Although the state-of-the-art Transformer models had shown their capability in behavior recognition, it is unsuitable for the task of short-term behavior understanding (e.g., violent behavior recognition) due to the need for a large amount of data to achieve their best performance. Recently, a simple deep learning architecture, an all multilayer perceptron (MLP) architecture called MLP-Mixer, was proposed against Transformer in the task of a few-sample dataset to obtain competitive results. Motivated by spatio-temporal features on neurons, we invent a dual-form dataset for MLP-Mixer-based model training called aggregated spatio-temporal MLP-Mixer (ASM) to handle video understanding tasks. We show that ASM outperforms the state-of-the-art Transformer models as well as some of the best-performed convolutional neural network (CNN) approaches on three public datasets, smart-city CCTV violence detection dataset (SCVD), real-life violence situations (RLVS) dataset, and Hockey fight. Experimental results further validate our idea on short-term behavior scene understanding improvement. © 2023 IEEE.

关键词： Mixers (machinery)

来源：评论

学校读者我要写书评

暂无评论

Mobile Gateways for LoRa End-Devices: Support Connectivity on the Move 29

Mobile Gateways for LoRa End-Devices: Support Connectivity o...

引用

29th IEEE International Workshop on computer Aided Modeling and Design of Communication Links and Networks, CAMAD 2024

作者： Moysiadis, Vasileios Skoutas, Dimitrios N. Skianis, Charalabos Lagkas, Thomas Argyriou, Vasileios Sarigiannidis, Panagiotis University of the Aegean Dept. of Information and Communication Systems Engineering Samos83200 Greece International Hellenic University Dept. of Computer Science Greece University of Western Macedonia Dept. of Electrical and Computer Engineering Kozani Greece Kingston University Dept. of Networks and Digital Media Kingston upon Thames United Kingdom

ISBN: (纸本)9798350377644

This paper proposes a method enabling mobile LoRa gateways to support mobile end devices. The approach utilizes trilateration and similar approaches based on RSSI to estimate the position of end devices and specify the movement of the gateways to maintain contact. The evaluation of the proposed method tests various parameters such as speed and number of end devices, and it shows that it is able to retain contact even with speeds up to 12 mps. Moreover, the evaluation shows that the ADR-MIN algorithm performs better in this scenario than the default ADR. © 2024 IEEE.

关键词： Gateways (computer networks)

来源：评论

学校读者我要写书评

暂无评论

Sinhala Sign Language Learning System for Hearing Impaired Community 4

Sinhala Sign Language Learning System for Hearing Impaired C...

引用

4th International Informatics and Software engineering Conference, IISEC 2023

作者： Idushan, K.A.S. Dilshan, P.G.T. Jayasundera, P.S. Madhushan, K.L.B. Krishara, Jenny Wijendra, Dinuka Sri Lanka Institute of Information Technology Dept. of Computer Science and Software Engineering Malabe Sri Lanka

ISBN: (纸本)9798350318036

This research aims to develop a comprehensive system for Sinhala Sign Language (SSL) that includes a learning system, dynamic sign detection, audio/video to sign conversion, and vocal training. SSL plays a crucial role in facilitating communication for individuals who are deaf or hard of hearing in Sri Lanka. The learning system provides a platform for learning SSL and includes a text-To-sign language interpreter. The dynamic sign detection system uses computer vision techniques to identify and interpret dynamic signs accurately. The audio/video to sign conversion system bridges the gap between spoken language and SSL by converting auditory information into visual representations. The vocal training system focuses on enhancing the vocal skills of cochlear implanted children. This research contributes to the development of effective communication and language skills for SSL users. © 2023 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

A Sustainable Smart Irrigation and Crop Protection System for Bangladesh 8

A Sustainable Smart Irrigation and Crop Protection System fo...

引用

8th IEEE International Conference on Computational System and information Technology for Sustainable Solutions, CSITSS 2024

作者： Ahmed, Khandakar Rabbi Salam, Towfika Miraz, Shafiun Jahan, Israt Hoque, Aminul Al Noman, Abdullah Miyan Research Institute International University of Business Agriculture and Technology Uttara Model Town Dhaka Bangladesh Dept. of Mechatronics Engineering Kazla Rajshahi6204 Bangladesh Dept. of Computer Science and Engineering Rajshahi Bangladesh International University of Business Agriculture and Technology Dept. of Computer Science and Engineering Uttara Model Town Dhaka Bangladesh Asian University of Bangladesh Dept. of Computer Science and Engineering Bangabandhu Road Tongabari Ashulia Dhaka Bangladesh Jahangirnagar University Dept. of Institute of Information Technology Savar Dhaka Bangladesh

ISBN: (纸本)9798331505462

Bangladesh's most crucial sector for development is agriculture. Rainfall has been irregular in recent years due to climate change. In our country, the untimely rain and hailstorms harm crops and vegetables, especially winter vegetables. Surface water is mainly used for agriculture, but its availability constantly declines. Our current key challenge is to save surface water while protecting crops from rain and hail. IoT is cutting-edge technology in many applications, such as smart homes, smart cities, and intelligent traffic management. The IoT may be implemented in so many different industries and sectors. This research work is about smart irrigation with crop protection systems in agriculture. The system's primary parts are the sensors, water pump, servo motors, embedded systems, and internet connectivity. IoT sensors like soil moisture sensors and rain sensors are used in the suggested methodology. The fields of crops have received water from a pump. A motor has covered the crops. The proposed solution is a straightforward Internet of Things setup that sends data to the Arduino after detecting rainfall and soil moisture levels. Depending on the sensor data, the Arduino sends signals to the motor and pump to irrigate the crops and cover crops as necessary, revealing the crops after rain. The system is constructed economically using bamboo, and poly and plastic nets have been utilized to protect the crops from rain and fog. The system's primary effects are increased productivity, decreased crop damage rate, and saved surface water. © 2024 IEEE.

关键词： Soil moisture

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：