检索结果-内蒙古大学图书馆

2nd International Conference on Intelligent Computing Systems and Applications, ICICSA 2023

作者： Menaga, S. Vanithamani, R. Anandkumar, A. Gomathi, N. Department of Electronics and Communication Engineering Jai Shriram Engineering College Tamil Nadu Tirupur India Department of Biomedical Instrumentation Engineering School of Engineering Avinashilingam Institute for Home Science and Higher Education for Women Tamil Nadu Coimbatore India Department of Artificial Intelligence and Data Science Karpagam Institute of Technology Tamil Nadu Coimbatore India

ISBN: (纸本)9789819754113

Wireless Body Area Network (WBAN) offer a viable solution for continuous health monitoring and are receiving a lot of attention from academicians and researchers due to recent technological advancements. In WBAN, sensors are placed throughout the body to collect physiological data and transmit it to a sink node. Thus, transmitting medical information between sensor nodes and sink nodes while consuming minimal energy, causing little packet loss, and extending the lifespan of the network is challenging. A linear regression buffalo optimization algorithm (LRBOA) for WBAN is introduced in this paper to enable the timely transmission of vital patient data. The linear regression method is used to identify normal, aberrant, and vital patient data in LRBOA. After the classification, the protocol schedules the priority for classified data. Within the specified timeframe, high-priority patient data can be transmitted first. Energy, link dependability, bandwidth, and distance-based optimal pathways are needed for data transfer. The suggested algorithm could determine the best path based on several variables, including energy, link dependability, bandwidth, and distance. The highest-priority node data is finally sent to the sink node for further processing. In this way, priority-based, energy-aware data transmission is performed in WBAN. The proposed algorithm is tested using a MATLAB with a health monitoring dataset in WBAN. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Linear Random Early Detection for Congestion Control at the Router Buffer

引用

Informatica (Slovenia) 2022年第5期46卷 105-114页

作者： Abu-Shareha, Ahmad Adel Al-Kasasbeh, Basil Shambour, Qusai Y. Abualhaj, Mosleh M. Alsharaiah, Mohmmad Abdalla Al-Khatib, Sumaya N. Department of Computer Science Faculty of Information Technology Al-Ahliyya Amman University Amman Jordan Riyadh Saudi Arabia Department of Software Engineering Faculty of Information Technology Al-Ahliyya Amman University Amman Jordan Department of Networks and Information Security Faculty of Information Technology Al-Ahliyya Amman University Amman Jordan Department of Data Science and Artificial Intelligence Faculty of Information Technology Al-Ahliyya Amman University Amman Jordan

Active Queue Management (AQM) methods control the router's buffer to maintain high network performance and control congestion at the router buffer. Random Early Detection (RED) method is the most well-known and the most utilized AQM. RED suffers from a high dropping rate, which motivates the later AQM methods to use more complex processes, which reach the limits of using fuzzy systems as a processing technique. Yet, high computational cost affects the router's performance specifically and the network as a whole, with so-called processing delay. In this paper, a linear version of RED (LRED) is presented to reduce the computational cost of the original RED and maintain the network performance in terms of throughput, delay, dropping, and loss. LRED is built based on two distinctive features, simplifying the congestion indicator calculation and reducing the operations in calculating the dropping probability. The experimental results showed that the proposed method reduces the delay and the processing time while maintaining the throughput and loss of the RED method. © 2022 Slovene Society Informatika. All rights reserved.

关键词： Network performance

来源：评论

学校读者我要写书评

暂无评论

Advancing Oncology Outcomes: Deploying Advanced Machine Learning Models for Early Detection and Optimized Treatment

Advancing Oncology Outcomes: Deploying Advanced Machine Lear...

引用

2024 International Conference on artificial intelligence and Quantum Computation-Based Sensor Applications, ICAIQSA 2024

作者： Khobragade, Prashant Dhankar, Praveen Kumar Motghare, Manish Golghate, Ashish Rakesh, Nitin Turkar, Hemantkumar Computer Science and Engineering G H Raisoni College of Engineering Nagpur India Pune India G H Raisoni College of Engineering and Management Dept of Artificial Intelligence Nagpur India Nagpur India S.B.Jain Institute of Technology Management and Research Department of Data Science Nagpur India

ISBN: (纸本)9798331517953

The field of oncology is changing quickly as more advanced machine learning (ML) models are added to help find cancer earlier and improve treatment results. This paper looks at how machine learning could change oncology by focusing on how it can be used to find cancer early, predict how it will progress, and create personalized treatment plans. Early identification is very important for increasing the number of people who survive, but standard testing methods aren't always accurate or quick enough. Machine learning calculations can discover patterns and exceptions that conventional investigations might miss by utilizing enormous datasets from an assortment of sources, such as electronic wellbeing records, hereditary information, and imaging thinks about. We see at cutting-edge machine learning models, like deep learning neural systems, support vector machines, and gathering strategies, to see how well they work at finding diverse sorts of cancer prior. The paper discuss about some important examples of how these models have done much better than standard diagnostic tools, allowing for earlier treatments and better patient results. The study emphasize about how natural language processing (NLP) can be used to get useful information from unorganized clinical notes. This can help with diagnosis and give us a fuller picture of the patient's background and risk factors. The study also talks about how predictive models can be used to make treatment plans better. Machine learning models can help doctors adjust treatments to each patient's unique profile by looking at patient data and how they respond to treatment. This makes treatments more effective while reducing side effects. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Identification and Classification of Crowd Activities

引用

Computers, Materials & Continua 2022年第7期72卷 815-832页

作者： Manar Elshahawy Ahmed O.Aseeri Shaker El-Sappagh Hassan Soliman Mohammed Elmogy Mervat Abu-Elkheir Department of Information Technology Faculty of Computers and InformationMansoura UniversityEgypt Department of Computer Science College of Computer Engineering and SciencesPrince Sattam Bin Abdulaziz UniversityAl-Kharj11942Saudi Arabia Department of Information Systems Faculty of Computers and Artificial IntelligenceBenha UniversityEgypt Faculty of Computer Science and Engineering Galala University435611SuezEgypt Department of Computer Science Faculty of Media Engineering and TechnologyGerman UniversityEgypt

The identification and classification of collective people’s activities are gaining momentum as significant themes in machine learning,with many potential applications *** need for representation of collective human behavior is especially crucial in applications such as assessing security conditions and preventing crowd *** paper investigates the capability of deep neural network(DNN)algorithms to achieve our carefully engineered pipeline for crowd *** includes three principal stages that cover crowd analysis ***,individual’s detection is represented using the You Only Look Once(YOLO)model for human detection and Kalman filter for multiple human tracking;Second,the density map and crowd counting of a certain location are generated using bounding boxes from a human detector;and Finally,in order to classify normal or abnormal crowds,individual activities are identified with pose *** proposed system successfully achieves designing an effective collective representation of the crowd given the individuals in addition to introducing a significant change of crowd in terms of activities *** results onMOT20 and SDHA datasets demonstrate that the proposed system is robust and *** framework achieves an improved performance of recognition and detection peoplewith a mean average precision of 99.0%,a real-time speed of 0.6ms non-maximumsuppression(NMS)per image for the SDHAdataset,and 95.3%mean average precision for MOT20 with 1.5ms NMS per image.

关键词： Crowd analysis individual detection You Only Look Once(YOLO) multiple object tracking kalman filter pose estimation

来源：评论

学校读者我要写书评

暂无评论

Cardiovascular Disease Prediction with Convolutional Neural Networks and Hyperparameter Tuning 8th

Cardiovascular Disease Prediction with Convolutional Neural ...

引用

8th International Conference on Information System Design and Intelligent Applications, ISDIA 2024

作者： Hossain, Mohammad Alamgir Metwally, Abdelnasser Abdelwakil Khan, Asif Ali Amin, Sherif Tawfik Hamdan, Alfadil Ahmed Limkar, Suresh Department of Computer Science College of Engineering and Computer Science Jazan University Jazan Saudi Arabia Department ofComputer Science College of Engineering and Computer Science Jazan University Jazan Saudi Arabia Department ofComputer and Network Engineering College of Engineering and Computer Science Jazan University Jazan Saudi Arabia Department of Artificial Intelligence & Data Science AISSMS Institute of Information Technology Maharashtra Pune India

ISBN: (纸本)9789819765805

CVD continues to pose a substantial global health burden, demanding the need for the creation of precise predictive models that can aid in the timely identification and evaluation of risks. This research paper aims to provide a thorough examination of the prediction of CVD by utilizing CNN in aggregation with hyperparameter tuning techniques. This paper examines the effectiveness of three widely recognized CNN architectures, namely ResNet, VGGNet, and Xception CVD. The Tree-structured Parzen Estimator (TPE) is utilized as a method for tuning hyperparameters in order to optimize the CNN models. The study commences with a comprehensive examination of the dataset, encompassing a wide array of cardiovascular CT image data. The chosen CNN architectures serve as the fundamental framework for our predictive models. The selection of these architectures is based on their established track record in effectively addressing image analysis tasks and their capacity to accurately capture complex patterns and features present in medical images. The models undergo training using a dataset in order to acquire knowledge about distinctive features that are linked to various cardiovascular conditions. The experimental findings presented in the study indicate that the utilization of the Xception architecture, in aggregation with TPE for hyperparameter optimization, yields the most favorable predictive accuracy. Specifically, the achieved accuracy rate of 98.26% is notably remarkable. This result highlights the significance of not only choosing advanced CNN architectures but also optimizing their hyperparameters to fully exploit their potential in predicting cardiovascular disease. This establishes it as a promising tool for the early diagnosis and risk assessment of CVD. This study establishes a fundamental basis for future investigations in the advancement of precise and dependable predictive models applicable to various medical imaging contexts. © The Author(s), under exclusive license

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

A Novel Framework for Detection of Digital Face Video Manipulation using Deep Learning 3

A Novel Framework for Detection of Digital Face Video Manipu...

引用

3rd International Conference on Computing and Information technology, ICCIT 2023

作者： Chandra, Sanskriti Saxena, Shivam Kumar, Santosh Chaube, Mithilesh Kumar Srinivas, K.G. Alsamhi, Saeed Hamood Curry, Edward Saif, Abdu IIIT-Naya Raipur Department of Data Science and Artificial Intelligence Chhattisgarh India IIIT-Naya Raipur Department of Computer Science and Engineering Chhattisgarh India IIIT-Naya Raipur Department of Mathematical Sciences Chhattisgarh India University of Galway Insight Sfi Research Centre for Data Analytics Galway Ireland Faculty of Engineering & Information Technology Taiz Yemen

ISBN: (纸本)9798350321487

Digital face manipulation and classification have recently attracted the attention of academia and industry worldwide. Researchers have developed deep learning and computer vision techniques for detecting face manipulations, and it has become a challenging task to differentiate between authentic and manipulated face images manually. The challenge results in the decline of authenticity in digital media content. In this paper, we propose a framework for the classification of manipulating face images using the EfficientNet learning model. The proposed framework takes four digital facial forgeries: Face-Swap, Face-2-Face, DeepFakes, and neural textures. Multiple manipulation techniques are used to process manipulated faces, such as the Blaze-face tracking method, to determine the locations of the face images and pixel coordinates. The proposed framework is used first to identify the type of face manipulation and then to perform detection of the tampered regions in the face images. The proposed framework provided an automated benchmark that considers all four modification techniques in a realistic situation. The results show that the proposed framework outperforms existing approaches regarding accuracy and efficiency. Furthermore, the proposed framework is suitable for detecting digital face video manipulation in various applications, including forensics and security. © 2023 IEEE.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Streamlining Deep Learning Based Alzheimers Disease Classification: A Simplified Approach with ADASYN

Streamlining Deep Learning Based Alzheimers Disease Classifi...

引用

Recent Advances in Electrical, Electronics, Ubiquitous Communication, and Computational intelligence (RAEEUCCI), International Conference on

作者： V. Saravanan T. Sidharth S. Vijay S. Sankar Ganesh Department of Artificial Intelligence and Data Science KPR Institute of Engineering and Technology Coimbatore Tamil Nadu India

ISBN: (数字)9798350354539

ISBN: (纸本)9798350354546

Consuming and complex, while existing deep learning (DL) methods may suffer from complexity and overfitting issues. This study proposes an integrated approach that combines Convolutional Neural Networks (CNNs) with the Adaptive Synthetic Sampling (ADASYN) algorithm to address class imbalance and enhance AD classification accuracy. This model architecture prioritizes simplicity and efficiency, utilizing an optimal number of layers to achieve effectiveness. Experimental results on a dataset of brain MRI images demonstrate the efficacy of this approach, with a classification accuracy of 98%. By integrating machine learning techniques with advanced sampling strategies, this research contributes to advancing early detection and diagnosis of Alzheimer's Disease, fostering strides towards improved patient care and management.

关键词： Deep learning Machine learning algorithms Magnetic resonance imaging Computer architecture Streaming media Complexity theory Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

A Brief Summary of Explanatory Virtues

arXiv

引用

arXiv 2024年

作者： Zukerman, Ingrid Department of Data Science and Artificial Intelligence Faculty of Information Technology Monash University ClaytonVIC3800 Australia

关键词：

来源：评论

学校读者我要写书评

暂无评论

Semantic-Based Detection of Ponzi Smart Contracts: Enhancing Bytecode Analysis with Source Code

Semantic-Based Detection of Ponzi Smart Contracts: Enhancing...

引用

Electronic Information engineering and Computer technology (EIECT), International Conference on

作者： Bingjie Weng Jianhui Ma Faculty of Artificial Intelligence and Data Science University of Science and Technology of China Hefei Anhui China Faculty of Computer Science and Technology University of Science and Technology of China Hefei Anhui China

ISBN: (数字)9798331528850

ISBN: (纸本)9798331528867

The rapid development of blockchain technology has led to many innovations, with the widespread use of smart contracts being particularly notable. However, this trend has spawned diverse blockchain scams, including the Ponzi scheme, which takes the form of Ponzi contracts. Due to blockchain users' misunderstanding of blockchain transparency, this scam can often result in significant financial losses. To complicate matters further, the vast majority of smart contracts deployed on blockchain networks are not open source, and users can only see the contract's bytecode. This situation makes Ponzi contracts even more challenging to identify, making it difficult for users to judge the security and legitimacy of a contract beforehand, thus increasing the risk of being defrauded. Most existing work uses only bytecode for detection and cannot fully utilize the corresponding source code information. In this paper, we propose a novel bimodal learning-fusion framework for enhancing Ponzi contract detection only in the presence of bytecode. Firstly, we employ the semantic-aware neural network to extract semantic feature from source code and bytecode. Then, we propose a modal transformation strategy to learn the relationship between source code and bytecode. Finally, a modal attention mechanism is introduced to construct a fusion representation to detect the contract even in the absence of source code modality. Experimental results show that the method performs better than existing methods that use machine learning for detection of Ponzi contracts.

关键词： Technological innovation Attention mechanisms Source coding Smart contracts Semantics Neural networks Feature extraction Market research Blockchains Security

来源：评论

学校读者我要写书评

暂无评论

Video2Reward: Generating Reward Function from Videos for Legged Robot Behavior Learning 27

Video2Reward: Generating Reward Function from Videos for Leg...

引用

27th European Conference on artificial intelligence, ECAI 2024

作者： Zeng, Runhao Zhou, Dingjie Liang, Qiwei Liu, Junlin Li, Hui Huang, Changxin Li, Jianqiang Hu, Xiping Sun, Fuchun Artificial Intelligence Research Institute Shenzhen MSU-BIT University China College of Mechatronics and Control Engineering Shenzhen University China College of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Department of Computer Science and Technology Tsinghua University China

ISBN: (纸本)9781643685489

Learning behavior in legged robots presents a significant challenge due to its inherent instability and complex constraints. Recent research has proposed the use of a large language model (LLM) to generate reward functions in reinforcement learning, thereby replacing the need for manually designed rewards by experts. However, this approach, which relies on textual descriptions to define learning objectives, fails to achieve controllable and precise behavior learning with clear directionality. In this paper, we introduce a new video2reward method, which directly generates reward functions from videos depicting the behaviors to be mimicked and learned. Specifically, we first process videos containing the target behaviors, converting the motion information of individuals in the videos into keypoint trajectories represented as coordinates through a video2text transforming module. These trajectories are then fed into an LLM to generate the reward function, which in turn is used to train the policy. To enhance the quality of the reward function, we develop a video-assisted iterative reward refinement scheme that visually assesses the learned behaviors and provides textual feedback to the LLM. This feedback guides the LLM to continually refine the reward function, ultimately facilitating more efficient behavior learning. Experimental results on tasks involving bipedal and quadrupedal robot motion control demonstrate that our method surpasses the performance of state-of-the-art LLM-based reward generation methods by over 37.6% in terms of human normalized score. More importantly, by switching video inputs, we find our method can rapidly learn diverse motion behaviors such as walking and running. © 2024 The Authors.

关键词： Robots

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：