检索结果-内蒙古大学图书馆

5th International Conference on Information Management and Machine Intelligence, ICIMMI 2023

作者： Mutha, Rakhi Reddy Gantla, Harish Pandey, Sunil Kr Sayeed Ahmad, Sayed Ahuja, Vandana Bhattacherjee, Abhishek Mamodiya, Udit Dept. of Information Technology Amity University Rajasthan Jaipur India Department of Computer Science and Engineering Vignan Institute of Technology and Science Hyderabad India Department of Information Technology Institute of Technology & Science Uttar Pradesh Ghaziabad India School of Engineering and Computing De Montfort University Dubai United Arab Emirates Dept. of CSE Swami Vivekanand Institute of Engineering and Technology Punjab Ramnagar India Department of Computer Science Engineering Lovely Professional University Punjab India Poornima University Jaipur India

ISBN: (纸本)9798400709418

Data mining uses artificial intelligence and other methods to extract hidden potential information from large data sets, which provides an effective way to obtain valuable knowledge from a large amount of information. Data mining is also ubiquitous in the process of using deep learning to solve point cloud registration tasks. Global feature extraction and rigid body transformation estimation are two critical stages of uncorrelated point cloud registration. Mining the rich information hidden in the two stages is one of the essential tasks of point cloud registration. However, the recently proposed methods tend to ignore low-dimensional local features when extracting global features, resulting in the loss of a large amount of point cloud information, which makes the accuracy of solving transformation parameters in the subsequent rigid body transformation estimation stage unsatisfactory. In this paper, a feature mining network based on multi-dimensional information fusion is proposed, which thoroughly mines the high-dimensional global and low-dimensional local information in the point cloud, and effectively makes up for the lack of local features in the worldwide feature extraction stage of point cloud registration. Dual quaternions are used to estimate pose in the rigid body transformation estimation stage, which can simultaneously represent rotation and translation in a standard frame, providing a compact and accurate representation for pose estimation. Finally, extensive experiments on the ModelNet40 dataset show that compared with the existing state-of-the-art point cloud registration methods without corresponding points, the proposed method can achieve higher accuracy and is more robust to noise. © 2023 ACM.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Robust Phishing URL Classification Using FastText Character Embeddings and Hybrid Deep Learning

Robust Phishing URL Classification Using FastText Character ...

引用

Robotics, Automation, Artificial-intelligence and Internet-of-Things (RAAICON), 2019 IEEE International Conference on

作者： Abdullah Al-Sakib Zishad Hossain Limon Anamul Sakib Md Nuruzzaman Pranto Md Ariful Islam Shayma Sultana Md. Redwan Ahmed Shafiur Rahman Dept. of Information Technology Westcliff University CA USA Dept. of Computer Science Westcliff University CA USA Dept. of Business Administration International American University CA USA Dept. of Management Information System International American University CA USA Dept. of Computer Science and Engineering East West University Dhaka Bangladesh Dept. of Software Engineering Daffodil International University Dhaka Bangladesh

ISBN: (数字)9798331534400

ISBN: (纸本)9798331534417

Phishing attacks are a major cybersecurity threat that resulted in over 1.2 million incidents in the first half of 2020. These attacks caused substantial financial losses and posed risks to individuals and organizations. Being able to identify fraudulent websites is crucial in order to effectively address these potential risks. This study introduces a novel method for detecting phishing URLs by using word and character embeddings to capture complex URL patterns. We used a dataset of 80,000 URLs, including 50,000 legitimate ones and 30,000 phishing instances, and applied thorough preprocessing techniques. We utilized word embeddings in FastText to handle unseen words, with the added advantage of n-gram representations. Additionally, we captured character-level features through dense character embeddings. We trained several machine learning and deep learning models, and one model, the Convolutional Bidirectional LSTM (CBiLSTM), stood out with an accuracy of 99.01% and an F1-score of 99.08%. Furthermore, we made a thorough comparison with the most advanced techniques available, and our findings demonstrated clear superiority over previous research. This study presents an effective approach for classifying phishing URLs, providing a valuable tool to combat fraud and protect against identity theft, thereby helping to minimize the financial and emotional harm experienced by victims.

关键词： Deep learning Uniform resource locators Training Adaptation models Phishing Prevention and mitigation Encoding Tokenization Real-time systems Robots

来源：评论

学校读者我要写书评

暂无评论

A Feasibility Study of Hybrid Hydrokinetic and Solar Power Generation at Bandarban Hill Tracts for Off-Grid Communities

A Feasibility Study of Hybrid Hydrokinetic and Solar Power G...

引用

International Conference on Electrical, computer and Communication engineering (ECCE)

作者： Md. Imam Uddin Forkan Md. Kamrul Hasan Md. Tohidul Islam Khan Adnan Sami Sarker Ishraq Samiha Md. Manjurul Gani Dept. of Electrical Electronic Engineering Chittagong University of Engineering and Technology Chattogram Bangladesh Dept. of Computer Science and Engineering Chittagong University of Engineering and Technology Chattogram Bangladesh

ISBN: (数字)9798350357509

ISBN: (纸本)9798350357516

Likely two million people in the Chittagong Hill Tracts live without access to digital technology due to an unreliable electricity supply. Efforts to electrify these hill track areas face significant challenges, including long transmission distances from the grid, a scattered population, and mountainous terrain. This study explores the feasibility of developing a green hybrid energy system incorporating hydrokinetic and solar power to provide reliable, affordable, and sustainable electricity to the Chittagong Hill Tracts, particularly Bandarban, where adequate water resources are available. Simulations were conducted using the Hybrid Optimization Model for Electric Renewable (HOMER) to meet the electricity demands of Bandarban. The proposed system includes PV panels, hydrokinetic energy, storage and a converter, with a total Net Present Cost (NPC) of $169,821 and a Levelized Cost of Energy (LCOE) of $0.250. The main contribution of this study is to address the electricity needs of the communities along the Sangu River by leveraging its water resources through a hybrid hydrokinetic and solar power model, aiming to create a GHG emission-free solution.

关键词： Renewable energy sources Design engineering Software packages Electricity Computational modeling Solar energy Hybrid power systems Rivers Solar power generation Water resources

来源：评论

学校读者我要写书评

暂无评论

Multi-Point Positional Insertion Tuning for Small Object Detection

arXiv

引用

arXiv 2024年

作者： Goto, Kanoko Karasawa, Takumi Hirose, Takumi Kawakami, Rei Inoue, Nakamasa Dept. of Computer Science Institute of Science Tokyo Tokyo Japan Dept. of Systems and Control Engineering Institute of Science Tokyo Tokyo Japan

Small object detection aims to localize and classify small objects within images. With recent advances in large-scale vision-language pretraining, finetuning pretrained object detection models has emerged as a promising approach. However, finetuning large models is computationally and memory expensive. To address this issue, this paper introduces multi-point positional insertion (MPI) tuning, a parameter-efficient finetuning (PEFT) method for small object detection. Specifically, MPI incorporates multiple positional embeddings into a frozen pretrained model, enabling the efficient detection of small objects by providing precise positional information to latent features. Through experiments, we demonstrated the effectiveness of the proposed method on the SODA-D dataset. MPI performed comparably to conventional PEFT methods, including CoOp and VPT, while significantly reducing the number of parameters that need to be tuned. Copyright © 2024, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Big Data Analytics for Proactive Financial Fraud Detection and Prevention

Big Data Analytics for Proactive Financial Fraud Detection a...

引用

Technology Innovation and Its Applications (ICTIIA), International Conference on

作者： Yehezkeil Hasudungan Fitra Putri Oganda Ora Plane Maria Daeli Raihan Nesti Anggraini Santoso Dept. of Informatics Engineering University of Raharja Tangerang Indonesia Dept. of Information System University of Raharja Tangerang Indonesia Dept. of Digital Business University of Raharja Tangerang Indonesia Dept. of Computer System University of Raharja Tangerang Indonesia

ISBN: (数字)9798350351613

ISBN: (纸本)9798350351620

Financial fraud poses a significant challenge to the financial industry, with increasing complexity and scale threatening global economic stability. This paper explores the use of Big Data Analytics for proactive detection and prevention of financial fraud. By analyzing large and diverse datasets, this approach aims to identify patterns and anomalies that may indicate fraudulent activities before they harm financial institutions. In this study, Smart PLS is employed as the primary method to test the structural model and the influence of various variables on the effectiveness of fraud prevention. The findings reveal that integrating Big Data Analytics into fraud prevention strategies can enhance early detection and response to fraud threats, positively impacting financial risk management. This research contributes significantly to the field of risk management by offering a framework that can be implemented to enhance financial security through advanced data analytics.

关键词： Economics Technological innovation Prevention and mitigation Finance Big Data Stability analysis Real-time systems Fraud Security Financial industry

来源：评论

学校读者我要写书评

暂无评论

Prediction and Modelling of Suicidal Mental Tendencies

Prediction and Modelling of Suicidal Mental Tendencies

引用

IEEE Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER)

作者： Sunitha Guruprasad Arnav G Rao Shreeraksha Shivani K Varsha S N Yashoda K Dept. of Computer Science & Engineering St Joseph Engineering College Mangaluru India Visvesvaraya Technological University Belagavi Karnataka India Dept. of Computer Science & Engineering Ramaiah Institute of Technology Bengaluru India

ISBN: (数字)9798350350593

ISBN: (纸本)9798350350609

Suicide remains a pressing public health concern worldwide, necessitating effective predictive and preventive strategies. Predicting suicidal tendencies is a complex endeavor, as it involves multifaceted interactions between biological, psychological, and environmental factors. Advances in computational modeling and machine learning have provided promising avenues for understanding and forecasting these tendencies. Such models often integrate clinical data, including psychiatric history, symptom severity, and demographic information, with biological markers and psychosocial variables. The objective of our work is to identify patterns and risk factors that may indicate heightened suicidal risk. Ongoing research seeks to refine predictive models, incorporate real-time monitoring, and develop targeted interventions, aiming to reduce the incidence of suicide and provide timely support to those at risk. The application of suicide text analysis extends to user-friendly interfaces, allowing individuals to input text, receive predictions, and access relevant support. The analysis involves preprocessing techniques such as text normalization, stop-word removal, and stemming to enhance the quality of input data. Various machine learning algorithms, ranging from Naive Bayes to sophisticated ensemble methods, are explored to determine their effectiveness in predicting suicidal ideation.

关键词： Text analysis Computational modeling Soft sensors Predictive models Very large scale integration Natural language processing Real-time systems Bayes methods Wearable devices Robots

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning Method for Detecting Behavior-Based Malware 5

A Machine Learning Method for Detecting Behavior-Based Malwa...

引用

5th International Conference on Inventive Research in Computing Applications, ICIRCA 2023

作者： Venkatarao, Javvaji Deeban Chakravarthy, V. Ramya, Singaraju Siva Prasad, V. Cherukuvada, Srikanth Soujanya, Annaram Sree Vidyanikethan Engineering College Dept. of Computer Science and Engineering Tirupati517 102 India Srm Institute of Science and Technology Department of Computing Technologies Chennai India School of Computing Srm Institute of Science and Technology Department of Computing Technologies Chennai India Mohan Babu University Dept. of Ai&ml Tirupati India School of Computing Srm Institute of Scienceand Technology Department of Networking and Communications Chennai India Cvr College of Engineering Department of Computer Science and Engineering Telangana India

ISBN: (纸本)9798350321425

While malware has posed a danger to businesses for years, advances in malware detection have lagged. Malware can cause damage to a system by starting unneeded services, which increases the system's workload and prevents it from operating smoothly. Malware detection can be done in one of two ways: the traditional signature-based approach or the more modern behavior-based approach. When malware is activated on a system, it conducts specific actions, such as launching malicious OS services or downloading malicious files from the web, that characterize its behaviour. The described technique detects malicious software based on its actions. The suggested model in this paper combines Support Vector Machine and Principal Component Analysis. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Next Sentence Prediction: The Impact of Preprocessing Techniques in Deep Learning 10

Next Sentence Prediction: The Impact of Preprocessing Techni...

引用

10th International Conference on computer, Control, Informatics and its Applications, IC3INA 2023

作者： Yuyun Latief, Andi Djalal Sampurno, Tri Hazriani Arisha, Andriansyah Oktafiandi Mushaf National Research and Innovation Agency Research Center for Data and Information Science Bandung Indonesia National Research and Innovation Agency Research Center for Data and Information Science Jakarta Indonesia Handayani University Dept. of Computer System Makassar Indonesia Dipa Makassar University Dept. of Informatics Management Makassar Indonesia

ISBN: (纸本)9798350394870

Text preprocessing in the field of Natural Language Processing (NLP) plays a crucial role in enhancing the model's ability to understand given tasks. This process helps in avoiding potential errors that could interfere with data processing. This study aims to investigate the effectiveness of four preprocessing techniques (tokenization, case-folding, stopword removal, and stemming) in predicting the next word in a sentence. The case focuses on Indonesian language text documents preprocessing using word2vec embedding and the long short-term memory networks (LSTM) classification model. The evaluation was conducted by incorporating human perception approach and evaluation matrix which focused on the suitability of word sequences and pairs on the prediction results. The result reveals that the combination of tokenizing and casefolding can enrich the meaning of the sentences. Meanwhile the combination of tokenizing, casefolding, stopword removal, and stemming can cause lose and overlap meaning in the sentences. The prediction model performs best on one-word n-grams, with precision 0.1, recall 1.0, and F-score 0.1. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Blockchain Integration for Robust Intellectual Property Protection in New Product Development (NPD) 3

Blockchain Integration for Robust Intellectual Property Prot...

引用

3rd International Conference on Electronics and Renewable systems, ICEARS 2025

作者： Chinnasamy, P. Subashini, B. Nijanthan, Nijanthan Madasamy Raja, G. Swetha, Devulapally Sreenivasulu Reddy, L. School of Computing Kalasalingam Academy of Research and Education Department of Computer Science and Engineering Tamilnadu India School of Computing Srmist Department of Data Science and Business Systems Kattankulathur India Paavai Engineering College Tamilnadu Namakkal India Paavai Engineering College Tamilnadu Namakkal India Vaagdevi Engineering College Dept. of Computer Science and Engineering Warangal Dist. Telangana Bolli Kunta506005 India School of Advanced Sciences Kalasalingam Academy of Research and Education Department of Mathematics Tamilnadu Krishnankoil India

ISBN: (纸本)9798331509675

The rapid advancement of Blockchain technology has led to its widespread application in several domains of digital activities, such as e-government concerns and monetary security. This article presents a smart contract-based Blockchain solution for protecting intellectual property rights in new product development. The proposed solution effectively tackles the challenges associated with the confidentiality of personally identifiable information, efficiency in storing transaction-related information, as well as cooperation and monitoring in IPR. Initially, we create a mathematical model based on smart contract enabled Blockchain and intelligent contracts. Subsequently, we develop algorithms for Blockchain generation, and intelligent contracts. The system is suitable for protecting IPR in a blockchain network, by implementation of distributed identity authentication and real-time extensible storage. These features enhance the security and expandability of circuit copyright protection based on blockchain technology. The experimental results demonstrate that the suggested algorithm has decreased the cost for communication and enhanced the effectiveness of storing information and administration. Furthermore, it demonstrates resilience against many common attacks such as double-spending assaults, while maintaining low cost and overhead. Additionally, it exhibits a superior level of security in comparison to three other competing algorithms. © 2025 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

RL-Driven Fine-Grained Power Gating for Modern Processors Using Multi-Layer Perceptron Models

RL-Driven Fine-Grained Power Gating for Modern Processors Us...

引用

IEEE International Symposium on Quality Electronic Design

作者： Naman Kalra Jaynarayan T Tudu Dept. of Electrical Engineering Indian Institute of Technology Tirupati India Dept. of Computer Science Engineering Indian Institute of Technology Tirupati India

ISBN: (数字)9798331509422

ISBN: (纸本)9798331509439

This paper introduces an RL-driven algorithm for fine-grained power gating of functional units in superscalar processors. The proposed algorithm leverages a Multi-Layer Perceptron (MLP) neural network as a policy model, trained by a reinforcement learning (RL) agent, to optimize power states across four modes: On, Sleep-on, Sleep-off, and Off. By statically analyzing features extracted from the control flow graph (CFG) and execution profile of the program, the RL-driven model selects the most energy-efficient power states for each functional unit without compromising performance. Traditional power gating techniques often struggle with tradeoffs between minimizing performance loss (wake-up latency) and reducing power consumption, necessitating a reevaluation of power management strategies. Next-generation complex SoC designs at < 7nm technology nodes require a finer granularity approach to effectively manage power states. Our AI-based algorithm provides an optimized trade-off between power efficiency and performance by enabling power gating across multiple power states and selecting the power state that has the effectively least energy-delay product. Additionally, we propose an architectural circuit design for power gating multiple FU's within a superscalar processor, enabling efficient state transitions. Preliminary experimental results show that the proposed AI-based method achieves 10-20% energy savings while improving performance by 1.5% compared to traditional power gating algorithms.

关键词： Program processors Power demand Power system management Reinforcement learning Performance gain Feature extraction Energy efficiency Circuit synthesis Flow graphs Next generation networking

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：