检索结果-内蒙古大学图书馆

IAENG International Journal of computer Science 2024年第7期51卷 754-764页

作者： Teng, Yue Yang, Kai Yue Teng is a postgraduate student at the School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan114051 China

In today’s society, communication among people has become more frequent and extensive due to the rapid development of science, technology, and the Internet. This vast communication occurs in real life and virtual online worlds. However, with the overwhelming amount of information available, people often struggle with finding and accessing the information they need, leading to frustration. To address this challenge, we conducted a study to extract valuable information and insights from users’ social relationships. While existing models can help us understand and analyze users’ social relationships to some extent, there are still significant challenges in extracting valuable insights. Therefore, we conducted in-depth research to improve the GraphRec model and created a new social recommendation model called the CWYGNN model. The CWYGNN model is unique because it can identify deeper connections in users’ social interactions through in-depth learning of the social sequences between users. This is important for understanding users’ behavioral patterns, predicting their needs, and providing personalized services. To validate the effectiveness of the CWYGNN model, we conducted experiments and comparisons on several public datasets. The experimental results show that the CWYGNN model outperforms similar approaches in processing user social relationships and extracting valuable insights. This result provides a new way of thinking and methodology to help us better understand and serve users and ultimately enhance their overall experience. © (2024) International Association of Engineers. All rights reserved.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Using the CNN architecture based on the EfficientNetB4 model to efficiently detect Deepfake images 1

Using the CNN architecture based on the EfficientNetB4 model...

引用

IEEE AITU: 1st International student Conference: "Digital Generation", AITU 2024

作者： Zhalgasbayev, Arman Aiteni, Tolegen Khaimuldin, Nursultan Sofrware Engineering Student Astana IT University Astana Kazakhstan Computer Science Student Astana IT University Astana Kazakhstan Senior lecturer of Computer Engineering Educational Program Astana IT University Astana Kazakhstan

ISBN: (纸本)9798350364378

This study evaluates the effectiveness of using the EfficientNetB4 model architecture for deepfake image detection and identifies the main challenges in developing an accurate model for deepfake image detection. Deepfake image detection is a complex task that requires lots of data, advanced models and new approaches for handling features in face images which shows that image is real or fake. This research is based on the Deepfake Detection Challenge (DFDC), which took place in 2019-2020, where world experts showed new approaches to solving this problem. During the research and development of the model, the best practices and experience of experts were used to identify the deepfake images. ©2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Classification of network slicing threats based on slicing enablers: A survey

引用

International Journal of Intelligent Networks 2023年第1期4卷 103-112页

作者： Abood, Mohammad J.K. Abdul-Majeed, Ghassan H. PhD Student Dept of Information Networks University of Babylon Iraq Dept of Computer Engineering University of Baghdad Iraq

One of the Main expectation of the 5G environment is supporting various services in many areas such as healthcare, education, energy, streaming, V2X (vehicle to everything) communication, etc. To implement such an expectation, there is a need to assign dedicated resources and functionalities for each service by slicing the network which means creating a virtual network for each service inside a physical network. Each virtual network (Slice) should be isolated from the other virtual network (Slice), and the security of that slice becomes a core issue in most research and studies. In this study, after focusing on security challenges in network slices, we describe the network slicing idea, the isolation concept, and the enablers of the network slicing, as well as the prevention of related attacks, risks, and concerns in each enabler. The research also lists the previous surveys and maps out taxonomies to illustrate the contribution of each survey in presenting threats and attacks against network slicing. © 2023 The Authors

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

An In-Depth Exploration of Advanced Driver Drowsiness Detection Systems for Enhanced Road Safety 2

An In-Depth Exploration of Advanced Driver Drowsiness Detect...

引用

2nd International Conference on computer, Communication and Control, IC4 2024

作者： Abirami, A. Bhuvaneswari, S. Vishnuvardhan, M. Karthik, Yadam Shankar, Saisuraj Easwari Engineering College Dept. of Computer Science and Engineering Chennai India Student of Easwari Engineering College Dept. of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350387933

Drowsiness, among drivers, plays a role in causing road accidents leading to loss of life, injuries, and financial setbacks. To address the issue of driver fatigue related accidents it is crucial to develop methods for detecting driver fatigue. This survey paper presents an overview of approaches used to identify driver fatigue. These approaches can be grouped into three categories: Behavioural, Vehicular and Physiological parameters. Behavioural parameters, such as eye closure percentage, blink rate patterns, yawning, head movements and facial expressions offer intrusive techniques that examine the physical state of the driver's body and provide information about their drowsiness level. Vehicular parameter-based techniques evaluate drowsiness by observing vehicle behaviour such as lane deviations, pedal usage, and unpredictable steering movements. Physiological indicators are also employed to detect tiredness. The paper also discusses the methodology employed in the research study including image processing techniques classifiers used and measurement metrics utilized, proposed methodology of fatigue detection with adding some extra features and Lastly the paper presents conclusions based on a study that can guide future researchers in identifying potential areas for further exploration in this field. © 2024 IEEE.

关键词： Physiological models

来源：评论

学校读者我要写书评

暂无评论

Fine-tuning the Gemma model for Kaggle Assistant 1

Fine-tuning the Gemma model for Kaggle Assistant

引用

IEEE AITU: 1st International student Conference: "Digital Generation", AITU 2024

作者： Zhalgasbayev, Arman Khauazkhan, Ali Sarsenova, Zhibek Sofrware Engineering Student Astana IT University Astana Kazakhstan Big Data Analysis Student Astana IT University Astana Kazakhstan Computer Engineering department Astana IT University Astana Kazakhstan

ISBN: (纸本)9798350364378

The emergence of advanced open-source large language models (LLMs) opens new opportunities for researchers and accelerates the development of generative AI. This study focuses on harnessing the potential of Gemma, Google's recently released open source LLM, to develop the Kaggle assistant through fine-tuning. The main objective of the study was to investigate the Low-Rank Adaptation (LoRA) fine-tuning method of Gemma model for building a robust AI assistant in Kaggle. Using the Gemma 2B variant, this study applies the Latent Consistency Model - LoRA method to improve interpretability and performance. The fine-tuning of the model achieved a sparse categorical cross-entropy (Loss) of 0.4943 and a sparse categorical precision of 0.7753. Although experiments with epochs and batch sizes revealed potential overbuilding after 10 epochs, the model shows acceptable performance in this range. The integration of LoRA fine-tuning enhances the model's ability to provide accurate recommendations and conclusions to users solving Kaggle problems, thereby improving the user experience and reinforcing its utility as a valuable resource for data scientists. Further refinement and adaptation of the Gemma model, especially through techniques such as LoRA fine-tuning, are critical to ensure its continued effectiveness in assisting Kaggle users in their data science endeavors. ©2024 IEEE.

关键词： Gemma model Kaggle LLM LoRA fine-tuning

来源：评论

学校读者我要写书评

暂无评论

Identifying Children's Personality Styles through Drawing Analysis using Machine Learning 14

Identifying Children's Personality Styles through Drawing An...

引用

14th International Conference on Information and Knowledge Technology, IKT 2023

作者： Mosharraf, Maedeh Banabazi, Faezeh Shahid Beheshti University Faculty of Computer Science and Engineering Tehran Iran Shahid Beheshti University Computer Engineering Student Tehran Iran

ISBN: (纸本)9798350349412

The impact of personality styles on individuals' behavior and choices is undeniable. With the advancements in datamining and machine learning techniques, various methods have been proposed to automatically identify personality styles by processing extensive data and exploring some human behavioral patterns. In this article, we examine children's personality styles by analyzing their drawings using some machine learning techniques. We employ the Murphy-Meisgeier Type Indicator for Children (MMTIC) questionnaire results to train k-nearest neighbors, random forest, and decision tree classifiers. Although we focus on a limited set of drawing features in this study, the results obtained are remarkably significant. We believe that the findings of this study will have a profound impact on early identification of children's personality styles and their decision-making throughout their lives. © 2023 IEEE.

关键词： Behavioral research

来源：评论

学校读者我要写书评

暂无评论

Real-Time Drowsiness Detection System using Facial Landmarks and Eye Blink Analysis 5

Real-Time Drowsiness Detection System using Facial Landmarks...

引用

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

作者： Manhas, Vishal Singh Sahani, Prince Upase, Shankar Venkatrao Ashtagi, Rashmi Under Graduate Student Department Of Computer Engineering Vishwakarma Institute Of Technology Pune India Department Of Computer Engineering Vishwakarma Institute Of Technology Pune India

ISBN: (纸本)9798400709418

This paper explores the critical issue of driver drowsiness and its significant contribution to road accidents. A real-time drowsiness detection system that harnesses the power of computer vision and facial landmark recognition to enhance safety and prevent accidents in situations where drowsiness poses a significant risk, such as drowsy driving. This system combines various libraries and techniques, including Dlib for face detection and facial landmark identification and OpenCV for image processing. Its core functionality involves capturing video frames from a camera feed, locating faces within each frame, and then focusing on the eyes and eyebrows to assess the individual's level of alertness. This assessment is primarily based on the analysis of eye blinking patterns, with specific attention to the blink ratio, which serves as a key indicator. Depending on the calculated blink ratio, the system classifies the person's state into three distinct categories: "SLEEPING,""Drowsy,"or "Active."These categories are conveyed to the user through real-time text overlays on the video feed, each represented by a specific color. The value of this project lies in its potential to prevent accidents caused by drowsiness, a major factor contributing to road accidents worldwide. By continuously monitoring and evaluating the individual's state of alertness, this system provides immediate feedback and intervention when drowsiness is detected, thus contributing to safer driving and potentially extending its applicability to other domains where alertness is critical, such as operating heavy machinery or monitoring individuals in critical work environments. Furthermore, this project offers a foundation for further development and integration with advanced technologies, potentially evolving into a comprehensive safety system with broader applications in areas where real-time alertness assessment is essential for reducing risks and enhancing overall safety. © 2023 ACM.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Integration AI techniques in Low-Resource Language: the case of Kazakh language 1

Integration AI techniques in Low-Resource Language: the case...

引用

IEEE AITU: 1st International student Conference: "Digital Generation", AITU 2024

作者： Kamshat, Asmaganbetova Auyeskhan, Ulanbek Zarina, Nurzhanova Alen, Serikbayev Yeskazina, Malika Department of intelligent systems and cybersecurity Astana IT University Astana Kazakhstan Department of computer engineering Student of Astana IT University Astana Kazakhstan School of creative industries Student of Astana IT University Astana Kazakhstan

ISBN: (纸本)9798350364378

Sentiment analysis is an extensively explored domain within natural language processing (NLP);nevertheless, a significant emphasis has been placed on languages possessing ample resources, such as English. This paper delves into the transformative capabilities of Optical Character Recognition (OCR), Natural Language Processing (NLP), and Speech Recognition, emphasizing their potential impact on low-resource languages, particularly focusing on Kazakh. OCR, a pivotal AI technique, extracts characters from images, revolutionizing the digitization of business records and streamlining mundane tasks. NLP, another powerful AI tool, analyzes and generates human-like text, while Speech Recognition converts spoken words into text. According to findings the OCR model demonstrated effectiveness, achieving an accuracy rate of 85% with losses ranging from 1.5 to 2, while TTS (text -to- speech) method mean opinion score (MOS) results with 95% confidence intervals. In addition, AI Meta research center assessed over 40,000 diverse translations, including Kazakh language directions using the human-translated benchmark, they integrated human evaluation with a unique toxicity benchmark across all 200 languages to ensure translation safety. Achieving a substantial 44% improvement over the prior state-of-the-art, the model by Meta AI establishes a crucial foundation for realizing a universal translation system. However, there remains ample room for exploration and refinement in the integration of these AI technologies, particularly in expanding the scope of evaluation metrics and addressing potential challenges in low-resource language settings. ©2024 IEEE.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

Marine Robot for Underwater Surveillance

Marine Robot for Underwater Surveillance

引用

2025 IEEE International students' Conference on Electrical, Electronics and computer Science, SCEECS 2025

作者： Vishnu Gowda, H.P. Reddy, Deepa N Gowda, Tejas B Shrikala, R. Yogitha, H.N. Bms Institute of Technology and Management Student of Department of Electronics and Communication Engineering Bengaluru560064 India Bms Institute of Technology and Management Department of Electronics and Communication Engineering Bengaluru560064 India Bms Institute of Technology and Management Student of Department of Computer Science Engineering Bengaluru560064 India

ISBN: (纸本)9798331529833

Underwater surveillance has become a crucial area of research, particularly for marine exploration and environmental monitoring, with marine robots playing a vital role. These robots, equipped with sensors and cameras, capture real-time data and images from underwater environments, reducing the need for human intervention in hazardous areas. However, a major challenge in this field is developing reliable communication networks, as underwater environments face limitations in bandwidth, range, and signal attenuation, hindering real-time data transmission. This paper presents a simple marine robot prototype based on the Raspberry Pi Model 4B, utilizing Electronic Speed Controllers (ESCs) and brushless motors for efficient movement. The robot's body is manually designed using 3D printing technology, with PETG (polyethylene terephthalate glycol) material chosen for its water resistance, durability, and buoyancy. The design ensures the robot's stability and functionality underwater, offering a cost-effective solution for marine robotics while underscoring the need for improved underwater communication technologies. © 2025 IEEE.

关键词： Marine communication

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning for Autonomous Systems 4

Reinforcement Learning for Autonomous Systems

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Kulkarni, Shriya Patil, Dipti Durgesh Student of Computer Engineering MKSSS's Cummins College of Engineering Maharashtra Pune India MKSSS's Cummins College of Engineering for Women Savitribai Phule Pune University Department of Information Technology Pune India

ISBN: (纸本)9798331523923

Reinforcement Learning (RL) has emerged as a vital component in the development of autonomous systems. However, several challenges, such as high computational demands, limited generalization in dynamic environments, and the need for extensive training data, hinder its effectiveness. This paper reviews recent advancements in RL techniques for UAVs and AVs, focusing on methods like Double DQN, Actor-Critic, and self-supervised learning to address these challenges. The objective is to analyze decision-making processes, reliability, and adaptability of RL models in real-world applications. © 2025 IEEE.

关键词： Adversarial machine learning

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：