检索结果-内蒙古大学图书馆

Ubiquitous Computing and Intelligent Information Systems (ICUIS), International Conference on

作者： Meher Langote Saniya Saratkar Chetan Puri Department of Artificial Intelligence and Data Science Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Wardha Maharashtra India Department of Artificial Intelligence and Data Science Faculty of Engineering and Technology Datta Meghe Higher Education and Research Wardha Maharashtra India Department of Computer Science Design Faculty of Engineering and Technology Datta Meghe Higher Education and Research Wardha Maharashtra India

ISBN: (数字)9798331529635

ISBN: (纸本)9798331529642

Recently, angle measurements have been performed using a goniometer, but the complex motion of shoulder movement has made these measurements intricate. The angle of rotation of the shoulder is particularly difficult to measure from an upright position because of the complicated base and moving axes. This article presents a real-time shoulder angle measurement system utilizing computer vision and machine learning techniques, specifically designed for the rehabilitation of frozen shoulder and related conditions. The system leverages MediaPipe, an open-source framework, to capture and analyze shoulder movements accurately. With its modular architecture, the system processes video feeds in real time, detecting key body points and calculating shoulder angles, thereby providing immediate feedback to patients and therapists. The study evaluates the system's effectiveness in clinical and home-based environments, highlighting its potential to enhance physiotherapy by enabling precise, data-driven treatment plans. This research study also identifies current research gaps, proposes solutions, and explores future enhancements, including environmental adaptation, mobile integration, and the extension to other joints. This study has attempted to estimate the shoulder joint internal/external rotation angle using the combination of pose estimation artificial intelligence (AI), computer vision, and a machine learning mode.

关键词： computer vision Machine learning algorithms Shoulder Medical treatment Machine learning Streaming media Ubiquitous computing Real-time systems Motion measurement Smart phones

来源：评论

学校读者我要写书评

暂无评论

Applications of Machine Learning Techniques in Detecting Skin Cancer 5

Applications of Machine Learning Techniques in Detecting Ski...

引用

5th International Conference on Contemporary Computing and Informatics, IC3I 2022

作者： Kunekar, Pankaj Vaishnav, Rounak Kalaivani, E. Gangodkar, Durgaprasad Kaur, Chamandeep Dhanraj, Joshuva Arockia Vishwakarma Institute of Technology Pune India Mahatma Gandhi University of Medical Sciences and Technology Clinical Research Manager Department of Medical Oncology Sri Ram Cancer and Super Specialty Centre Jaipur India Bannari Amman Institute of Technology Tamil Nadu Sathyamangalam India Graphic Era Deemed to Be University Department of Computer Science & Engineering Uttarakhand Dehradun India Jazan University Department of Computer Science & Information Technology Saudi Arabia Department of Mechatronics Engineering Padur Chennai India

ISBN: (纸本)9798350398267

The most lethal kind of skin cancer is called malignant melanoma. Accurate diagnosis of skin malignancies are aided by dermoscopy, a non-invasive high-resolution imaging procedure. Melanoma is a very dangerous kind of skin cancer because of how quickly it spreads and how aggressive it is. For this reason, malignant melanoma maintains its place as one of the tumors with the highest rates of growth across the globe. Second-order texture feature data may be obtained by the GLCM (Grey Level Co-occurrence Matrix) technique. The reference pixel and neighboring pixels are considered by GLCM to ensure an accurate calculation. Grayscale pictures have a decent number of levels, which is straightforwardly relative to the number of segments and columns in the frameworks used to characterize the scale. Relative recurrence is addressed by the grid component P I j | Dx, Dy), where I and j are force values and Dx and Dy are pixel distances. In total, the co-occurrence matrix considers 14 different attributes, including energy, efficiency, latency, correlation, homogeneity, and contrast. Convolutional Neural networks (CNN) and Gaussian Filters (GF) classifiers were then used to sort these vectors. Comparisons of the results these classifiers provide are also made. © 2022 IEEE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Approximation Algorithm and Applications for Connected Submodular Function Maximization Problems

引用

IEEE/ACM Transactions on Networking 2024年

作者： Wang, Ziming Li, Jing Xue, He Xu, Wenzheng Liang, Weifa Xu, Zichuan Peng, Jian Zhou, Pan Jia, Xiaohua Das, Sajal K. Sichuan University College of Computer Science and West China Second Hospital Chengdu610065 China City University of Hong Kong Department of Computer Science Hong Kong Hong Kong Sichuan University College of Computer Science Chengdu610065 China Sichuan Fire Science and Technology Research Institute of Mem Chengdu610065 China Dalian University of Technology School of Software Dalian116621 China Huazhong University of Science and Technology School of Cyber Science and Engineering Wuhan430074 China Missouri University of Science and Technology Department of Computer Science RollaMO65409 United States

In this paper, we study a connected submodular function maximization problem, which arises from many applications including deploying UAV networks to serve users and placing sensors to cover Points of Interest (PoIs). Specifically, given a budget $K$ , the problem is to find a subset $S$ with $K$ nodes from a graph $G$ , so that a given submodular function $f(S)$ on $S$ is maximized and the induced subgraph $G[S]$ by the nodes in $S$ is connected, where the submodular function $f$ can be used to model many practical application problems, such as the number of users within different service areas of the deployed UAVs in $S$ , the sum of data rates of users served by the UAVs, the number of covered PoIs by placed sensors, etc. We then propose a novel $\frac{1-1/e}{2h+2}$ (Formula Presented) -approximation algorithm for the problem, improving the best approximation ratio $\frac{1-1/e}{2h+3}$ for the problem so far, through estimating a novel upper bound on the problem and designing a smart graph decomposition technique, where $e$ is the base of the natural logarithm, $h$ is a parameter that depends on the problem and its typical value is 2. In addition, when $h=2$ , the algorithm approximation ratio is at least $\frac{1-1/e}{5}$ and may be as large as 1 in some special cases when $K\le 23$ , and is no less than $\frac{1-1/e}{6}$ (Formula Presented) when $K\ge24$ , compared with the current best approximation ratio $\frac{1-1/e}{7}(=\frac{1-1/e}{2h+3})$ (Formula Presented) for the problem. Finally, experimental results in the application of deploying a UAV network demonstrate that, the number of users within the service area of the deployed UAV network by the proposed algorithm is up to 7.5% larger than those by existing algorithms, and the throughput of the deployed UAV network by the proposed algorithm is up to 9.7% larger than those by the algorithms. Furthermore, the empirical approximation ratio of the proposed algorithm is between 0.7 and 0.99, which is close to t

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Risk estimation in a Markov cost process: lower and upper bounds 24

Risk estimation in a Markov cost process: lower and upper bo...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Gugan Thoppe Prashanth L. A. Sanjay P. Bhat Dept. of Computer Science and Automation Indian Institute of Science (IISc) Bengaluru India and Robert Bosch Centre for Data Science and Artificial Intelligence IIT Madras Chennai India Dept. of Computer Science and Engineering Indian Institute of Technology Madras Chennai India TCS Research Hyderabad India

We tackle the problem of estimating risk measures of the infinite-horizon discounted cost of a Markov cost process. The risk measures we study include variance, Value-at-Risk (VaR), and Conditional Value-at-Risk (CVaR). First, we show that estimating any of these risk measures with ε-accuracy, either in expected or high-probability sense, requires at least Ω(1/ε2) samples. Then, using a truncation scheme, we derive an upper bound for the CVaR and variance estimation. This bound matches our lower bound up to logarithmic factors. Finally, we discuss an extension of our estimation scheme that covers more general risk measures satisfying a certain continuity criterion, such as spectral risk measures and utility-based shortfall risk. To the best of our knowledge, our work is the first to provide lower and upper bounds for estimating any risk measure beyond the mean within a Markovian setting. Our lower bounds also extend to the infinite-horizon discounted costs' mean. Even in that case, our lower bound of Ω(1/ε2) improves upon the existing Ω(1/ε) bound (Metelli et al., 2023).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Geometric Programming for System-Level Performance Optimization

Data-Driven Geometric Programming for System-Level Performan...

引用

International Conference on Information and Communication technology Convergence (ICTC)

作者： Soihem Gonmei Junhwan Lee Taesoo Kwon Department of Computer Science and Engineering Seoul National University of Science and Technology Seoul South Korea Electronics and Telecommunications Research Institute Daejeon South Korea

More than often, the output of a comprehensive network-wide performance modeling is a non-linear and non-convex function of the input data. To estimate the non-linear relationship of such a procedure, this paper employs a data-driven methodology. By formulating the non-linear objective as a geometric program, we leverage Levenberg-Marquardt algorithm to fit a convex log-sum-exponential function to data obtained through system-level simulation. Focusing on the downlink energy efficiency in mmWave cellular networks, we formulate a convex optimization problem and numerically obtain the optimal BS density and transmit power.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The effect of deep brain structure modeling on transcranial direct current stimulation-induced electric fields: An in-silico study

The effect of deep brain structure modeling on transcranial ...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Chae-Bin Song Cheolki Lim Jongseung Lee Donghyeon Kim Hyeon Seo Research Institute Neurophet Inc. Seoul South Korea School of Electrical Engineering and Computer Science Gwangju Institute of Science and Technology Gwangju South Korea Department of Computer Science Gyeongsang National University South Korea

To study transcranial direct current stimulation (tDCS) and its effect on the brain, it could be useful to predict the distribution of the electric field induced in the brain with given tDCS parameters. As a solution, simulation with realistic computational models using magnetic resonance images (MRIs) have been widely used in the fields. With the recent advance of deep learning-based segmentation techniques of the brain, questions have been raised about if tDCS-induced electric field is affected by the deep brain structures. This study aimed to investigate the effect of the deep brain structure modeling on the induced electric field. To this end, we generated models with and without the deep brain structures by using an open MRI dataset comprising tDCS parameters, electric field simulation results and in-vivo intracranial recordings in the deep brain structures. We investigated the difference between the simulation results of the two models with a statistical analysis. Our results indicated that tDCS-induced electric fields and current flow in the brain are significantly different when the deep brain structures are considered.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hard-Label Black-Box Attacks on 3D Point Clouds

arXiv

引用

arXiv 2024年

作者： Liu, Daizong Tao, Yunbo Zhou, Pan Hu, Wei Wangxuan Institute of Computer Technology Peking University No. 128 Zhongguancun North Street Beijing China The Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China

With the maturity of depth sensors in various 3D safety-critical applications, 3D point cloud models have been shown to be vulnerable to adversarial attacks. Almost all existing 3D attackers simply follow the white-box or black-box setting to iteratively update coordinate perturbations based on back-propagated or estimated gradients. However, these methods are hard to deploy in real-world scenarios (no model details are provided) as they severely rely on parameters or output logits of victim models. To this end, we propose point cloud attacks from a more practical setting, i.e., hard-label black-box attack, in which attackers can only access the prediction label of 3D input. We introduce a novel 3D attack method based on a new spectrum-aware decision boundary algorithm to generate high-quality adversarial samples. In particular, we first construct a class-aware model decision boundary, by developing a learnable spectrum-fusion strategy to adaptively fuse point clouds of different classes in the spectral domain, aiming to craft their intermediate samples without distorting the original geometry. Then, we devise an iterative coordinate-spectrum optimization method with curvature-aware boundary search to move the intermediate sample along the decision boundary for generating adversarial point clouds with trivial perturbations. Experiments demonstrate that our attack competitively outperforms existing white/black-box attackers in terms of attack performance and adversary quality. Copyright © 2024, The Authors. All rights reserved.

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

Advanced Machine Learning Algorithms for 1Predictive Analytics in Healthcare to Enhance Patient Outcomes with Data-Driven Insights

Advanced Machine Learning Algorithms for 1Predictive Analyti...

引用

Recent Advances in science and engineering technology (ICRASET), International Conference on

作者： Rajkumar Pandiarajan J. Jagannathan P.S. Ramesh A. Ponmalar Sudha Department of Information and Technology School of Computing Kalasalingam Academy Of Research and Education Krishnankoil Virudhunagar India Department of Software and Systems Engineering School of Computer Science Engineering and Information Systems Vellore Institute of Technology Katpadi Vellore India Department of Computer Science and Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai Tamilnadu India R.M.K. Engineering College Chennai Tamilnadu India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences SIMATS University Chennai Tamil Nadu India

ISBN: (数字)9798350388602

ISBN: (纸本)9798350388619

This research aims to explore the use of modern complex defensive machine learning algorithms in the provision of predictive analytics for health improvement. Incorporating electronic health records, medical image information, and genomic data the work proposes and assesses multiple machine learning models including deep learning, ensemble learning, and reinforcement learning. The main findings shown very high performance in disease prediction, in chronic illness and in the application of efficiency improvements in hospitals as a whole. Overall, such threats as data quality, data privacy, and model interpretability have been discussed in the research and emphasize the importance of the machine learning approach in healthcare. It is highlighted that further development and integration of the interdisciplinary approaches as well as the use of the transparent and interpretable artificial intelligence and machine learning models can be urgent to increase the acceptance among the healthcare staff. This paper enhances the literature on applying machine learning in healthcare systems adding to the repertoire of knowledge for improved patient care.

关键词： Data privacy Machine learning algorithms Hospitals Data integrity Machine learning Reinforcement learning Predictive models Data models Predictive analytics Diseases

来源：评论

学校读者我要写书评

暂无评论

research on Cross-Project Vulnerability Detection Method for Open Source Software

Research on Cross-Project Vulnerability Detection Method for...

引用

computer Applications and Information technology (ISCAIT), International Symposium on

作者： Xiaorong Feng Laiping Zhang Jingyun Wu Leyu Shi China Electronic Product Reliability and Environmental Testing Research Institute Guangzhou Guangdong China School of Computer Science and Engineering South China University of Technology Guangzhou Guangdong China

ISBN: (数字)9798331542856

ISBN: (纸本)9798331542863

This paper centers on applying and advancing Embedding models within open-source software for cross-project vulnerability detection. It reviews relevant studies and delves into how Embedding technology captures open-source software features from multiple angles, such as code structure, community activity, and developer behavior. By transforming high-dimensional sparse data into low-dimensional dense vectors, it enhances the accuracy and reliability of feature representation. Moreover, it comprehensively examines the strengths, limitations, and future research directions of current methods, aiming to offer comprehensive theoretical and practical guidance for the intelligent analysis and security enhancement of open-source software.

关键词： Accuracy Reviews Reliability theory Feature extraction Vectors Data models Software reliability Security Information technology Open source software

来源：评论

学校读者我要写书评

暂无评论

Prioritizing Test Cases Through Dual-Uncertainty Evaluating for Road Disease Detection System 31

Prioritizing Test Cases Through Dual-Uncertainty Evaluating ...

引用

31st Asia-Pacific Software engineering Conference, APSEC 2024

作者： Niu, Chenxu Liu, Huijun Li, Ao Xiao, Tianhao Ruan, Zhimin Xu, Ling Ge, Yongxin College of Computer Science Chongqing University Chongqing China School of Big Data & Software Engineering Chongqing University Chongqing China China Merchants Chongqing Communications Technology Research&Design Institute Co. Ltd. Chongqing China

ISBN: (纸本)9798331534011

Road damage detection system based on deep learning models has been extensively researched, capable of intelligently detecting damages in roads. However, to ensure reliability, a large number of images usually need to be collected and annotated to test the model. Collecting images is often a straightforward work, but annotating them is both time-consuming and costly. To minimize annotation costs during the testing phase, we can evaluate images using Test Prioritization method to select more meaningful samples for system testing. Yet, most mainstream work currently only evaluates cases based on classification result, neglecting the impact of localization. At the same time, these methods do not provide higher evaluation results to complex images that may detect errors or images where targets cannot be detected at all. To address these issues, we propose a new Test Prioritization tool, Dual-u, to evaluate road damage cases. It consists of two components: (1) Localization Uncertainty Evaluation, which evaluates the localization of damages while considering the value of the image, ensuring that complex images and images where targets cannot be detected also have higher priority;(2) Classification Uncertainty Evaluation, which evaluates the classification of damages. To evaluate Dual-u, we conduct extensive experiments using two object detection model architectures on multiple road disease datasets, and the results demonstrate that Dual-u outperforms existing methods in evaluating cases. Moreover, Dual-u can also be used to improve the accuracy and robustness of road disease detection models. © 2024 IEEE.

关键词： Road Disease Detection System Testing Test Prioritization

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：