检索结果-内蒙古大学图书馆

5th International Conference on Electrical Information and Communication Technology, EICT 2021

作者： Shariar, Sarjil Hossain, Md. Safayet Azharul Hasan, K.M. Dept. of Computer Science and Engineering Khulna Bangladesh

ISBN: (纸本)9781665409063

Scientific and engineering computing demands multi-dimensional data processing in various domains including big data, machine learning, graph processing, object recognition, etc. In this paper, we process the multi-dimensional data model, also called high order tensor, with parallel computation on Graphics Processing Unit (GPU). We introduce a dimension conversion technique to construct the Converted Matrix Structure (CMS) that transforms the n-dimensional tensor data into 2-dimensional matrix data with the dynamic memory allocation. With this scheme, we can extend the dimension size during runtime for the further inclusion of tensor elements. Therefore the proposed scheme can handle the dynamic dataset that can expand during runtime. We also propose the parallel processing of matrix multiplication with the CMS scheme for improved and faster performance. To conduct the parallel processing of the multi-dimensional matrix multiplication (MDMMP), we first distribute the n-dimensional tensor elements on GPU threads to retrieve the 2-dimensional matrices, and then we process the Row-By-Column (RBC) wise multiplications of the matrices simultaneously. We perform these parallel processing in such a way that the load balance is ensured by the dynamic use of parallel threads based on the multi-dimensional data size. We found good speed up using our algorithm. © 2021 IEEE.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

Perceptual Crack Detection for Rendered 3D Textured Meshes

Perceptual Crack Detection for Rendered 3D Textured Meshes

引用

International Workshop on Quality of Multimedia Experience, QoMEx

作者： Armin Shafiee Sarvestani Wei Zhou Zhou Wang Dept. of Electrical & Computer Engineering University of Waterloo Canada School of Computer Science and Informatics Cardiff University United Kingdom

ISBN: (数字)9798350361582

ISBN: (纸本)9798350361599

Recent years have witnessed many advancements in the applications of 3D textured meshes. As the demand continues to rise, evaluating the perceptual quality of this new type of media content becomes crucial for quality assurance and optimization purposes. Different from traditional image quality assessment, crack is an annoying artifact specific to rendered 3D meshes that severely affects their perceptual quality. In this work, we make one of the first attempts to propose a novel Perceptual Crack Detection (PCD) method for detecting and localizing crack artifacts in rendered meshes. Specifically, motivated by the characteristics of the human visual system (HVS), we adopt contrast and Laplacian measurement modules to characterize crack artifacts and differentiate them from other undesired artifacts. Extensive experiments on large-scale public datasets of 3D textured meshes demonstrate effectiveness and efficiency of the proposed PCD method in correct localization and detection of crack artifacts. Moreover, to quantify the performance of the proposed detection method and validate its effectiveness, we propose a simple yet effective weighting mechanism to incorporate the resulting crack map into classical quality assessment (QA) models, which creates significant performance improvement in predicting the perceptual image quality when tested on public datasets of static 3D textured meshes. A software release of the proposed method is publicly available at: https://***/arshafiee/crack-detection-VVM

关键词： Image quality Solid modeling Visualization Three-dimensional displays Quality assurance Visual systems Predictive models

来源：评论

学校读者我要写书评

暂无评论

A Feedback-based Decision-Making Mechanism for Actor-Critic Deep Reinforcement Learning

A Feedback-based Decision-Making Mechanism for Actor-Critic ...

引用

IEEE International Conference on Big Data

作者： Guang Yang Ziye Geng Jiahe Li Yanxiao Zhao Sherif Abdelwahed Changqing Luo Dept. of Computer Science Virginia Commonwealth University Richmond VA USA Dept. of Electrical and Computer Engineering Virginia Commonwealth University Richmond VA USA

ISBN: (数字)9798350362480

ISBN: (纸本)9798350362497

Deep reinforcement learning (DRL) has achieved remarkable success in solving sequential decision-making problems across various domains. However, a critical challenge is sample inefficiency, especially in real-world environments with high-dimensional solution spaces due to continuous state and action spaces. Although off-policy actor-critic algorithms have been proposed to mitigate this issue, the gains in sample efficiency remain limited, as decision-making in these algorithms relies solely on the policy function that might not always yield optimal actions. To bridge the gap, we design a novel feedback-based decision-making mechanism (FADA) that incorporates a feedback mechanism into the actor-critic framework to enhance decision-making robustness. Specifically, FADA utilizes feedback from the value function (critic) to calibrate the decisions produced by the policy function (actor). More concretely, FADA comprises four integrated modules: a decision-space expansion module (DEM) to produce a pool of candidate actions, a critic-guided evaluation module (CGEM) that estimates the efficacy of the candidate actions, an adaptive selection module (ASM) that adaptively selects a set of elite actions based on the estimated efficacy and samples the final action, and an iterative refinement module (IRM) that improves the quality of elite actions. We evaluate our approach on multiple tasks in the DeepMind Control Suite, and the experimental results demonstrate a significant improvement in sample efficiency.

关键词： Decision making Big Data Deep reinforcement learning Robustness Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Enhancing Network Function Virtualization and Service Function Chaining: Innovative Optimization Strategies and Their Impact

Enhancing Network Function Virtualization and Service Functi...

引用

Pioneering Developments in computer science & Digital Technologies (IC2SDT), International Conference on

作者： Deepak Upadhyay Mridul Gupta Kunj Bihari Sharma Abhay Upadhyay Dept. of Computer Science and Engineering Graphic Era Hill University Dehradun India Dept. of Electronics and Communication Engineering Graphic Era deemed to be University Dehradun India Dept. of Computer Science and Engineering Graphic Era Deemed to be University Dehradun India

ISBN: (数字)9798350365016

ISBN: (纸本)9798350365023

Throughout this paper, the reader was able to better understand how innovative optimization techniques through NFV and SFC frameworks could and should be applied to address the developing and shifting focus of contemporary network infrastructures. Focusing on performance metrics performance via latency, throughput, resource utilization, and operational cost, the presented algorithms and machine learning models developed and executed due to this research showed innovative and dynamic optimization of network functions. Through further extensive simulations equalling 125 seconds, our findings reported creative results of improving performance in several significant areas: latency was reduced, throughput was enhanced, resource utilization was more efficient, and operational cost was reduced. These results indicated that our optimization strategies can pay off and bring a number of benefits to NFV and SFC that address a clear need for change in the current type of network management models. Therefore, this paper is valuable and serves as a testament of our strategies' power along with opening various doors for following network optimization research. Therefore, one can see how important it is to implement innovation in the face of change.

关键词： Measurement Technological innovation Costs Machine learning algorithms Heuristic algorithms Machine learning Throughput Network function virtualization Resource management Optimization

来源：评论

学校读者我要写书评

暂无评论

Remote Patient Monitoring Innovations Using IoT for Improved Healthcare Outcomes 4

Remote Patient Monitoring Innovations Using IoT for Improved...

引用

4th International Conference on Technological Advancements in Computational sciences, ICTACS 2024

作者： Veeraiah, Vivek Shetty, Aishwarya D. Thejaswini, K.O. Srinivas, P. Tripathi, Sudhanshu Mohammad, Faiz Sri Siddhartha Academy of Higher Education Dept. of Computer Science Karnataka India Nmamit Dept. of Cse Nitte India Sri Siddhartha Academy of Higher Education Dept. of Physiology Karnataka India Sri Siddhartha Academy of Higher Education Dept. of Pediatrics Karnataka India Amity University Tashkent Uzbekistan Rungta College of Engineering and Technology Dept. of Cse Chhattisgarh Bhilai India

ISBN: (纸本)9798350387490

RPM has now become a revolutionary concept in the field of healthcare through IoT technology improvement to patients' care. New RPM systems on IoT have been covered by the study which permits constant health indicators monitoring of the patient even under non-conventional clinical settings by means of real-time capacity. Such systems have RT-PCR using IoT sensors, wearable devices, and data analytics coupled with immediate access to intervention, chronic health checking, and personalized therapies. This article includes a debate of the state-of-the-art in the field of IoT. Among them the enhanced methods of data manipulation, wireless link technologies, and intelligent measurement of critical signs by sensors. Some of the concerns addressed to with regard to RPM based on Internet of Things include patient engagement, privacy of data, and integration. In this paper, RPM is analyzed in context with chronic diseases, with an evaluation of its impact on medication compliance and scenarios of its potential for lessening hospitalization in existing scholarly articles. The findings presented in the paper reveal how advancements in the context of IoT can modify the ways of the healthcare distribution through the promotion of enhanced health result from the patient-centered therapy implemented continuously. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Involutional Neural Network Based Approach for the Detection of Melanoma Cancer

Involutional Neural Network Based Approach for the Detection...

引用

computer, Electronics & Electrical engineering & their Applications (IC2E3), International Conference on

作者： Deepak Upadhyay Kunj Bihari Sharma Mridul Gupta Abhay Upadhyay Dept. of Computer Science and Engineering Graphic Era Hill University Dehradun India Dept. of Computer Science and Engineering Graphic Era deemed to be University Dehradun India Dept. of Electronics and Communication Engineering Graphic Era deemed to be University Dehradun India

ISBN: (数字)9798350388534

ISBN: (纸本)9798350388541

This paper presents an extraordinary method to detected melanoma, the most lethal form of skin cancer, using Involutional Neural Networks (INNs). Melanoma's early detection is crucial for effecacius treatment, yet existing diagnostic methods often lack the requiring precision and scalability. INNs offer a solve through their advanced capability to adaptively process spatial information in images, a huge different from traditional convolutional techniques. Our reaserch applies INNs to melanoma detectionair, focusing on their unique involution operations that significant enhance image analysis for accurately classification. The performance of our model, assessed across different metrics including accurate, precision, recall, and F1-scores, demonstrates its superior diagnostic capability. This investigation not only underscores the potency of INNs in medical imagining but also opens up new avenues for their application across diverse analytical needs in healthcare. By advancing melanoma detection methods, we contribute to the broader goal of improving early cancer diagnose and treatment outcomes!

关键词： Measurement Training Accuracy Scalability Neural networks Melanoma Predictive models Stability analysis Reliability Thermal stability

来源：评论

学校读者我要写书评

暂无评论

End-to-End SNR Capacity and throughput enhancement Using Non-Orthogonal Multiple access and Massive MIMO in 5G

End-to-End SNR Capacity and throughput enhancement Using Non...

引用

Intelligent Technologies (CONIT), International Conference on

作者： Deepak Upadhyay Abhay Upadhyay Mridul Gupta Kunj Bihari Sharma Dept. of Computer Science and Engineering Graphic Era Hill University Dehradun India Dept. of Computer Science and Engineering Graphic Era deemed to be University Dehradun India Dept. of Electronics and Communication Engineering Graphic Era deemed to be University Dehradun India

ISBN: (数字)9798350349900

ISBN: (纸本)9798350349917

This study provides a detailed analysis of the potential improvements in 5G network performance due to the adoption of NOMA and Massive MIMO technologies. Obtaining higher data rates, reduced latency, and increased overall network capacities remain a primary objective, and the research provides a comparison based on simulated data. Simulation models are designed to compare the proposed model against the conventional implementation of 5G networks based on a set of primary indicators, namely, throughput and latency. An abstract Wave Efficiency indicator is also presented to showcase a new metric for determining the qualitative improvements in signal processing and spectrum utilization. As the results of the research have demonstrated, the incorporation of NOMA and Massive MIMO increases overall network throughput while reducing latency. This demonstrates the potential contributions of these technologies to making wireless communications systems more efficient and reliable. The introduction of the Wave Efficiency is offered as a measurable variable for displaying the qualitative improvement in the wireless communications technologies, facilitating further implementation of NOMA and Massive MIMO in 5G networks.

关键词： Measurement NOMA 5G mobile communication Wireless networks Massive MIMO Signal processing Throughput

来源：评论

学校读者我要写书评

暂无评论

Automated Classification of Chest CT Scans for Accurate Diagnosis and Risk Stratification: A Deep Learning Approach

Automated Classification of Chest CT Scans for Accurate Diag...

引用

computer, Electronics & Electrical engineering & their Applications (IC2E3), International Conference on

作者： Deepak Upadhyay Mridul Gupta Devansh Yadav Abhay Upadhyay Dept. of Computer Science and Engineering Graphic Era Hill University Dehradun India Dept. of Electronics and Communication Engineering Graphic Era deemed to be University Dehradun India Dept. of Computer Science and Engineering Graphic Era Deemed to be University Dehradun India

ISBN: (数字)9798350388534

ISBN: (纸本)9798350388541

The performance assessment metrics of the topic of classification models, such as recall, accuracy, and F1-score were considered in this work. We examined how many types of events our model categorizes well and view the more detailed metrics for every class. A special account of the precision-recall trade-off even shows that there is an undeniable advantage, and there may be a negative side. The outcomes also show how good the model is. For example, a perfect accuracy score in the 2nd Class demonstrates that the algorithm can differentiate occurrences of such a category. The weighted average metrics consider the fundamental dissimilarity in a group better. The model has an average 0.91 F1-score, indicating that it makes a balanced decision between accuracy and recall. While I can be proud of these results, I understand that the presented weaknesses realized that additional study of potential feature engineering and other model architectures remain. This experiment will be valuable for future research and usage in real-life.

关键词： Measurement Deep learning Accuracy Computed tomography Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Minimize Web Applications vulnerabilities through the early Detection of CRLF Injection

arXiv

引用

arXiv 2023年

作者： Hasan, M.D. Asibul Rahman, Md. Mijanur Dept. of Computer Science and Engineering Southeast University Bangladesh

Carriage return (CR) and line feed (LF), also known as CRLF injection is a type of vulnerability that allows a hacker to enter special characters into a web application, altering its operation or confusing the administrator. Log poisoning and HTTP response splitting are two prominent harmful uses of this technique. Additionally, CRLF injection can be used by an attacker to exploit other vulnerabilities, such as cross-site scripting (XSS). Email injection, also known as email header injection, is another way that can be used to modify the behavior of emails. The Open Web Application Security Project (OWASP) is an organization that studies vulnerabilities and ranks them based on their level of risk. According to OWASP, CRLF vulnerabilities are among the top 10 vulnerabilities and are a type of injection attack. However, CRLF vulnerabilities can also lead to the discovery of other high-risk vulnerabilities, and it fosters a better approach to mitigate CRLF vulnerabilities in the early stage and help secure applications against known vulnerabilities. Although there has been a significant amount of research on other types of injection attacks, such as Structure Query Language Injection (SQL Injection). There has been less research on CRLF vulnerabilities and how to detect them with automated testing. There is room for further research to be done on this subject matter in order to develop creative solutions to problems. It will also help to reduce false positive alerts by checking the header response of each request. Automated alerts from security systems can provide a quicker and more accurate understanding of potential vulnerabilities and can help to reduce false positive alerts. Despite the extensive research on various types of vulnerabilities in web applications, CRLF vulnerabilities have only recently been included in the research. Utilizing automated testing as a recurring task can assist companies in receiving consistent updates about their systems and enhance the

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Adaptive Compressed Sensing with Diffusion-Based Posterior Sampling

arXiv

引用

arXiv 2024年

作者： Elata, Noam Michaeli, Tomer Elad, Michael Dept. of Electric and Computer Engineering Technion - Israel Institute of Technology Haifa Israel Dept. of Computer Science Technion - Israel Institute of Technology Haifa Israel

Compressed Sensing (CS) facilitates rapid image acquisition by selecting a small subset of measurements sufficient for high-fidelity reconstruction. Adaptive CS seeks to further enhance this process by dynamically choosing future measurements based on information gleaned from data that is already acquired. However, many existing frameworks are often tailored to specific tasks and require intricate training procedures. We propose AdaSense, a novel Adaptive CS approach that leverages zero-shot posterior sampling with pre-trained diffusion models. By sequentially sampling from the posterior distribution, we can quantify the uncertainty of each possible future linear measurement throughout the acquisition process. AdaSense eliminates the need for additional training and boasts seamless adaptation to diverse domains with minimal tuning requirements. Our experiments demonstrate the effectiveness of AdaSense in reconstructing facial images from a small number of measurements. Furthermore, we apply AdaSense for active acquisition of medical images in the domains of magnetic resonance imaging (MRI) and computed tomography (CT), highlighting its potential for tangible real-world acceleration. © 2024, CC BY-NC-ND.

关键词： Image reconstruction

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：