检索结果-内蒙古大学图书馆

International Conference on Information Security, Privacy, and Digital Forensics, 2022

作者： Jones, G. Maria Santhiya, P. Winster, S. Godfrey Sundar, R. Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India Department of Computer Science and Engineering SRM Institute of Science and Technology and Panimalar Engineering College Chennai India

ISBN: (纸本)9789819950904

Smartphones are compatible and easily accessible compared to computers irrespective of place and time. Smartphones merge with our routine which acts as a medium of communication in several ways such as messaging, voice and video calling, sharing of audio and video contact, and many multimedia contents. We express our emotions through words and these communications can be analyzed by a technique called Natural Language Processing (NLP). Many researchers in the field of text mining and NLP have analyzed the polarity of online product reviews, blogs, social media comments, tweets, and many more. Mobile forensics investigation will be more effective by providing the evidences based on sentimental analysis of the text where the suspected messages contain a negative content of having threats, harassments, text against the community guidelines, and some keywords related to the cases which may be the turning point during the forensics investigation. In this paper, a novel framework called Integrated Mobile Device Forensic Investigation Process (IMDFIP) with inclusion of sentimental analysis techniques in the text which is used to emotionally analyze the texts during the communication process. This framework provides additional information to forensic analysts which will trap the suspect during investigation. The proposed framework of IMDFIP identifies the important terms, emotions, and polarity of the text during the crime. IMDFIP capitulates results compared with the previous models. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Enhancing Malware Detection: A Comparative Analysis of Ensemble Learning Approaches 1

Enhancing Malware Detection: A Comparative Analysis of Ensem...

引用

1st International Conference on Technological Innovations and Advance Computing, TIACOMP 2024

作者： Ajvad Haneef, K. Shashank, N.S. Madhu Kumar, S.D. National Institute of Technology Department of Computer Science & Engineering Calicut India National Institute of Technology Department of Computer Science & Engineering Calicut India

ISBN: (数字)9798350392111

ISBN: (纸本)9798350392111

Malware represents the greatest threat to cybersecurity and serves as the weapon of choice for carrying out nefarious activities in the digital realm. The proliferation of malware poses significant risks to individuals and organizations. Therefore, malware detection is essential for companies to strengthen their cyberspace, protect sensitive data and minimize financial losses from cyberattacks. Ensemble learning methods have emerged as powerful tools in this domain, leveraging the strengths of multiple models to enhance detection accuracy and reliability. We present a comparative analysis of ensemble learning approaches for malware detection using the EMBER dataset. We evaluate six ensemble models, including Random Forest, AdaBoost, Extra Trees, XGBoost, LightGBM, and Bagging, based on key performance metrics such as accuracy, precision, recall, and F1-score. Our findings reveal that all ensemble models demonstrate strong performance in malware detection, with Bagging ensemble achieving the highest accuracy and overall performance. The results highlight the effectiveness of ensemble learning techniques in enhancing malware detection capabilities. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Manipify:An Automated Framework for Detecting Manipulators in Twitter Trends

引用

Journal of Social Computing 2023年第1期4卷 46-61页

作者： Soufia Kausar Bilal Tahir Muhammad Amir Mehmood Al-Khawarizmi Institute of Computer Science University of Engineering and Technology Lahore Pakistan

The rapid adoption of online social media platforms has transformed the way of communication and *** these platforms,discussions in the form of trending topics provide a glimpse of events happening around the world in ***,these trends are used for political campaigns,public awareness,and brand ***,these trends are sensitive to manipulation by malicious users who aim to mislead the mass *** this article,we identify and study the characteristics of users involved in the manipulation of Twitter trends in *** propose“Manipify”-a framework for automatic detection and analysis of malicious users in Twitter *** framework consists of three distinct modules:(1)user classifier,(2)hashtag classifier,and(3)trend *** user classifier module introduces a novel approach to automatically detect manipulators using tweet content and user behaviour ***,the module classifies human and bot ***,the hashtag classifier categorizes trending hashtags into six categories assisting in examining manipulators behaviour across different ***,the trend analyzer module examines users,hashtags,and tweets for hashtag reach,linguistic features,and user *** user classifier module achieves 0.92 and 0.98 accuracy in classifying manipulators and bots,*** further test Manipify on the dataset comprising 652 trending hashtags with 5.4 million tweets and 1.9 million *** analysis of trends reveals that the trending panel is mostly dominated by political *** addition,our results show a higher contribution of human accounts in trend manipulation as compared to bots.

关键词： trend manipulation bot classification user analysis text classification manipulator detection

来源：评论

学校读者我要写书评

暂无评论

Enhanced Malware Image Classification through Ensemble model 3

Enhanced Malware Image Classification through Ensemble model

引用

3rd International Conference on Applied Artificial Intelligence and Computing, ICAAIC 2024

作者： Kotha, Eshwar Palivela, Lakshmi Harika Begum, Afruza Vellore Institute of Technology School of Computer Science and Engineering Chennai India Vellore Institute of Technology School of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350375190

Classification of malwares and viruses is a very important work in the cyber security field to protect the computers and systems from threats and attacks. In this paper, we proposed a novel approach for the classification of the malwares by combining 2 models EfficientNet B0 and EffiCBNet models. Here we have used Malimg dataset which is available in Kaggle and it contains around 9,339 malware images and these malwares are from 25 different families, for evaluating the models. EffcientNetB0 is a Convolution Neural Network (CNN) model, which showed great and high results on various image classification works. We used transfer learning to fine tune the EfficientNet model;whereas the proposed EffiCBNet model is a deep learning model which contains of convolution layers and batch normalization layers. The results have shown that the proposed model has given the highest accuracy of 99.70 on the dataset we have used, exceeding all other models. The proposed model is the combination of EfficientNet and EffiCBNet, which showed great results for the classification. The proposed model can also be used in real time applications for detecting malware attacks and threats © 2024 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Railway track fault detection using optimised convolution neural network

引用

International Journal of Reliability and Safety 2024年第2期18卷 163-186页

作者： Chitra, R. Bamini, A.M. Anusha Brindha, D. Jegan, T.M. Chenthil Kirubakaran, S. Stewart Department of Computer Science and Engineering Karunya Institute of Technology and Sciences Tamil Nadu Coimbatore India Department of Mechanical Engineering Sri Ranganathar Institute of Engineering and Technology Tamil Nadu Coimbatore India

Railway accidents are an under-scrutinised cause of death in India. Train accidents are caused by various consequences of collisions, derailments, signal errors and so on. Furthermore, when train derailments become disastrous, they can have tremendous repercussions. It is practically difficult to identify the cause of the derailment efficiently within a limited period. In recent years, we have been making progress in reducing derailments, but even if not deadly, identifying faulty tracks can waste a lot of time and money. And doing this error-free is a pressing matter, as tracks always experience wear and tear with more usage. Here is where neural networks can pitch in their solution. We can train a model to look at train tracks and identify any issues. This paper goes into the methodology of achieving this and optimising a neural network to predict problems in the track with the best possible accuracy that images can provide. The objective of this paper is to identify, develop and optimise neural networks to detect faulty tracks. In this work, a good Convolution Neural Network model is developed to identify the crack in the railway track. The developed model produced 95.54% accuracy in fault classification. Copyright © 2024 Inderscience Enterprises Ltd.

关键词： Derailments

来源：评论

学校读者我要写书评

暂无评论

A Novel Deep Reinforcement Learning Approach for Stability-Based Parallel Disassembly Sequence Planning Problem

引用

SN computer science 2025年第3期6卷 1-19页

作者： Kumar, M. R. Mahesh Ravi, Chandrasekar Department of Computer Science and Engineering National Institute of Technology Puducherry Karaikal India

Parallel Disassembly Sequence Planning (DSP) deals with obtaining the order of disassembling the product with multiple parts disassembling simultaneously. Existing studies derive the product’s disassembly order based on the requirement for liaison data. However, the absence of stability data does not ensure that all the product parts are disassembled without damage. Since the order of retrieval of the product can also be obtained from stability data, this reduces the requirement of an initial precedence graph based on liaison data. The complexity of the problem increases if we adopt different representations for precedence and stability conditions of the product for constraint checking throughout the disassembly process. This paper constructs a stability-based precedence graph based on only the product’s stability data. The developed graph represents the precedence of the stable parts for disassembly, and the same is utilized to formulate the problem as a model-free deep Reinforcement Learning (RL) problem. A novel Exploration–Exploitation (EE) strategy-based Deep Q-Learning (DQL) algorithm is proposed to parallel DSP minimizing direction changes. Our effective reward mechanism accelerates the learning process for all the conditions and objectives of the problem considered. Based on past performance, the proposed algorithm dynamically decides the exploration and exploitation strategy to avoid local optima. We applied the proposed algorithm on five different-scale products and compared the results with uniform-sampling-based model-free deep RL algorithms. It showed significant improvements, particularly in cumulative rewards and disassembling all the parts for large-scale products with early convergence. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Deep Q-learning Deep Q-Networks Disassembly sequence planning Parallel disassembly Precedence graph Stability graph

来源：评论

学校读者我要写书评

暂无评论

Con-Fog: Consensus-Driven Fog Node Selection in FU-Serve Platform for IoT Applications

引用

IEEE Internet of Things Journal 2025年第13期12卷 24686-24697页

作者： Imandi, Raju Roy, Arijit Sethi, Kamalakanta Pavan, Kumar Guizani, Mohsen Indian Institute of Information Technology Computer Science and Engineering Group Sri City India Indian Institute of Technology Department of Computer Science and Engineering Patna India Mohamed bin Zayed University of Artificial Intelligence Machine Learning Department Abu Dhabi United Arab Emirates

The rapid expansion of Internet of Things (IoT) devices and applications necessitates the need for more efficient computational and data management strategies. The Fog-enabled UAV-as-a-Service (FU-Serve) platform addresses these demands by integrating fog computing to enhance the operational efficiency of UAVs in IoT environments. Despite its advantages, the FU-Serve platform faces significant challenges, including data transmission latency, resource allocation, and energy management, contributing to the underutilization of UAVs and fog nodes. To address these challenges, this paper introduces a consensus-driven approach, Con-Fog, that optimizes the selection of fog nodes for UAVs within the FU-Serve platform. Con-Fog evaluates potential fog nodes within the communication range by computing utility values based on geographical distance, link quality, available computational resources, and residual energy. UAVs rank these nodes according to their utility values and select the most suitable ones through a consensus-based approach, ensuring alignment with the operational demands of IoT devices. Additionally, we apply an optimal best-fit algorithm to refine fog node allocation, maximizing resource utilization while keeping it below each node’s capacity threshold (T%). Our simulation results show that Con-Fog significantly enhances key IoT performance metrics. Transmission time and the number of unassigned UAVs decrease by 10%-30% and 20%-40%, respectively, while residual energy increases by 30%-50% compared to existing systems. These improvements enhance the management of UAV and fog node resources, thereby advancing the effectiveness of IoT applications within the FU-Serve platform. © 2014 IEEE.

关键词： Fog computing

来源：评论

学校读者我要写书评

暂无评论

Layer-Wise External Attention by Well-Localized Attention Map for Efficient Deep Anomaly Detection

引用

SN computer science 2024年第5期5卷 1-13页

作者： Nakanishi, Keiichi Shiroma, Ryo Hayakawa, Tokihisa Katafuchi, Ryoya Tokunaga, Terumasa Graduate School of Computer Science and Systems Engineering Kyushu Institute of Technology 680-4 Kawazu Fukuoka-ken Iizuka-shi 820-8502 Japan Faculty of Computer Science and Systems Engineering Kyushu Institute of Technology 680-4 Kawazu Fukuoka-ken Iizuka-shi 820-8502 Japan

The external attention mechanism offers a promising approach to enhance image anomaly detection (Hayakawa et al., in: IMPROVE, pp. 100-–110, 2023). Nevertheless, the effectiveness of this method is contingent upon the judicious selection of an intermediate layer with external attention. In this study, we performed a comprehensive series of experiments to clarify the mechanisms through which external attention improves detection performance. We assessed the performance of the LEA-Net (Hayakawa et al., in: IMPROVE, pp. 100–110, 2023), which implements layer-wise external attention, using MVTec AD and Plant Village datasets. The detection performances of the LEA-Net were compared with that of the baseline model under different anomaly maps generated by three unsupervised approaches. In addition, we investigated the relationship between the detection performance of LEA-Net and the selection of an attention point, which means an intermediate layer where external attention is applied. The findings reveal that the synergy between the dataset and the generated anomaly map influenced the effectiveness of the LEA-Net. For poorly localized anomaly maps, the selection of the attention point becomes a pivotal factor in determining detection efficiency. At shallow attention points, a well-localized attention map successfully notably improves the detection performance. For deeper attention points, the overall intensity of the attention map is essential;this intensity can be substantially amplified by layer-wise external attention, even for a low-intensity anomaly map. Overall, the results suggest that for layer-wise external attention, the positional attributes of anomalies hold greater significance than the overall intensity or visual appearance of the anomaly map. © The Author(s) 2024.

关键词： Anomaly detection Deep learning MVTec AD Plant science Self-attention Visual attention mechanism Visual inspection AI

来源：评论

学校读者我要写书评

暂无评论

ISO 24617-8 Applied: Insights from Multilingual Discourse Relations Annotation in English, Polish, and Portuguese 20

ISO 24617-8 Applied: Insights from Multilingual Discourse Re...

引用

20th Joint ACL - ISO Workshop on Interoperable Semantic Annotation, ISA 2024

作者： Tomaszewska, Aleksandra Silvano, Purificação Leal, António Amorim, Evelin Institute of Computer Science Polish Academy of Sciences Poland University of Porto Centre for Linguistics of the University of Porto Portugal Institute for Systems and Computer Engineering Technology and Science Portugal

ISBN: (纸本)9782493814326

The main objective of this study is to contribute to multilingual discourse research by employing ISO-24617 Part 8 (Semantic Relations in Discourse, Core Annotation Schema – DR-core) for annotating discourse relations. Centering around a parallel discourse relations corpus that includes English, Polish, and European Portuguese, we initiate one of the few ISO-based comparative analyses through a multilingual corpus that aligns discourse relations across these languages. In this paper, we discuss the project’s contributions, including the annotated corpus, research findings, and statistics related to the use of discourse relations. The paper further discusses the challenges encountered in complying with the ISO standard, such as defining the scope of arguments and annotating specific relation types like Expansion. Our findings highlight the necessity for clearer definitions of certain discourse relations and more precise guidelines for argument spans, especially concerning the inclusion of connectives. Additionally, the study underscores the importance of ongoing collaborative efforts to broaden the inclusion of languages and more comprehensive datasets, with the objective of widening the reach of ISO-guided multilingual discourse research. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： ISO Standards

来源：评论

学校读者我要写书评

暂无评论

Pattern Analysis and Regressive Linear Measure for Botnet Detection

引用

computer systems science & engineering 2022年第10期43卷 119-139页

作者： B.Padmavathi B.Muthukumar Department of Computer Science and Engineering Sathyabama Institute of Science and TechnologyChennaiIndia Department of Computer Science and Engineering Easwari Engineering CollegeChennaiIndia Department of Computer Science and Engineering United Institute of TechnologyCoimbatoreIndia

Capturing the distributed platform with remotely controlled compromised machines using botnet is extensively analyzed by various ***,certain limitations need to be addressed *** provisioning of detection mechanism with learning approaches provides a better solution more broadly by saluting multi-objective *** bots’patterns or features over the network have to be analyzed in both linear and non-linear *** linear and non-linear features are composed of high-level and low-level *** collected features are maintained over the Bag of Features(BoF)where the most influencing features are collected and provided into the classifier ***,the linearity and non-linearity of the threat are evaluated with Support Vector Machine(SVM).Next,with the collected BoF,the redundant features are eliminated as it triggers overhead towards the predictor ***,a novel Incoming data Redundancy Elimination-based learning model(RedE-L)is built to classify the network features to provide robustness towards BotNets *** simulation is carried out in MATLAB environment,and the evaluation of proposed RedE-L model is performed with various online accessible network traffic dataset(benchmark dataset).The proposed model intends to show better tradeoff compared to the existing approaches like conventional SVM,C4.5,RepTree and so ***,various metrics like Accuracy,detection rate,Mathews Correlation Coefficient(MCC),and some other statistical analysis are performed to show the proposed RedE-L model's *** F1-measure is 99.98%,precision is 99.93%,Accuracy is 99.84%,TPR is 99.92%,TNR is 99.94%,FNR is 0.06 and FPR is 0.06 respectively.

关键词： BotNet threat intrusion features linearity and non-linearity redundancy regressive linear measure classification redundancy eliminationbased learning model

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：