检索结果-内蒙古大学图书馆

PerimetryNet: A multiscale fine grained deep network for three-dimensional eye gaze estimation using visual field analysis

学校读者我要写书评

暂无评论

PerimetryNet: A multiscale fine grained deep network for thr...

作者： Yu, Shuqing Wang, Zhihao Zhou, Shuowen Yang, Xiaosong Wu, Chao Wang, Zhao College of Information Science and Electronic Engineering Zhejiang University Hangzhou China School of Software Technology Zhejiang University Hangzhou China Department of Ophthalmology Sir Run Run Shaw Hospital Hangzhou China School of Medicine Zhejiang University Hangzhou China National Centre for Computer Animation Bournemouth University Bournemouth United Kingdom School of Public Affairs Zhejiang University Hangzhou China

Three-dimensional gaze estimation aims to reveal where a person is looking, which plays an important role in identifying users' point-of-interest in terms of the direction, attention and interactions. Appearance-based gaze estimation methods could provide relatively unconstrained gaze tracking from commodity hardware. Inspired by medical perimetry test, we have proposed a multiscale framework with visual field analysis branch to improve estimation accuracy. The model is based on the feature pyramids and predicts vision field to help gaze estimation. In particular, we analysis the effect of the multiscale component and the visual field branch on challenging benchmark datasets: MPIIGaze and EYEDIAP. Based on these studies, our proposed PerimetryNet significantly outperforms state-of-the-art methods. In addition, the multiscale mechanism and visual field branch can be easily applied to existing network architecture for gaze estimation. Related code would be available at public repository https://***/gazeEs/PerimetryNet. © 2023 John Wiley & Sons Ltd.

关键词： Eye tracking

A Fuzzy AHP-Based Approach for Prioritization of Cost Overhead Factors in Agile software Development

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Abusaeed, Syed Khan, Saif Ur Rehman Mashkoor, Atif Islamabad45550 Pakistan Department of Computer Science and Software Engineering Johannes Kepler University Altenbergerstraße 69 Linz4040 Austria

Agile software development (ASD) is a widely-used practical approach to project management and software development that satisfies all clients through continuous testing and frequent delivery. Cost estimation plays a significant role in ASD because the project’s success and failure depend on significant factors such as the software project’s effort, cost, and quality. For accurate cost estimation, it is beneficial knowing all the factors and challenges that influence the project cost. Agile accepts the changing requirements of the projects, so it is difficult to acquire precise effort estimation. According to the best of our knowledge, the current state-of-the-art lack in considering additional cost factors that can improve ASD estimation accuracy. Motivated by this, the current work aims to identify various factors from the literature and validate them through a questionnaire-based survey with agile project managers. We have performed a systematic literature review and an empirical approach to answer the formulated research questions. The current work classified and prioritized the validated factors using the multi-criterion decision making Fuzzy AHP technique and developed a thematic taxonomy of cost factors and their categories. The study also proposes a quantitative framework supporting overhead cost drivers prioritization based on (4P’s) people, project, process, and product. Fuzzy AHP is applied to various organizations’ data values to obtain different perspectives. The result of implementation provides a complete list of prioritized cost overhead factors that would assist agile practitioners in their cost estimation process. © 2022, The Authors. All rights reserved.

关键词： Project management

DeltaFS: Pursuing Zero Update Overhead via Metadata-Enabled Delta Compression for Log-structured File System on Mobile Devices

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wu, Chao Ji, Cheng Yuan, Geng Pan, Riwei Guo, Weichao Yu, Chao Zhu, Zongwei Wang, Yanzhi Department of Electrical and Computer Engineering Northeastern University United States School of Computer Science Nanjing University of Science and Technology China Department of Computer Science City University of Hong Kong Hong Kong Guangdong Oppo Mobile Telecommunications Corp. Ltd China School of Software Engineering University of Science and Technology of Chinese China

Data compression has been widely adopted to release mobile devices from intensive write pressure. Delta compression is particularly promising for its high compression efficacy over conventional compression methods. However, this method suffers from non-trivial system overheads incurred by delta maintenance and read penalty, which prevents its applicability on mobile devices. To this end, this paper proposes DeltaFS, a metadata-enabled Delta compression on log-structured File System for mobile devices, to achieve utmost compressing efficiency and zero hardware costs. DeltaFS smartly exploits the out-of-place updating ability of Log-structured File System (LFS) to alleviate the problems of write amplification, which is the key bottleneck for delta compression implementation. Specifically, DeltaFS utilizes the inline area in file inodes for delta maintenance with zero hardware cost, and integrates an inline area manage strategy to improve the utilization of constrained inline area. Moreover, a complimentary delta maintenance strategy is incorporated, which selectively maintains delta chunks in the main data area to break through the limitation of constrained inline area. Experimental results show that DeltaFS substantially reduces write traffics by up to 64.8%, and improves the I/O performance by up to 37.3%.1 © 2022, CC BY.

关键词： Metadata

Metric spaces in which many triangles are degenerate

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Chvátal, Vašek Kantor, Ida Department of Computer Science and Software Engineering Concordia University Emeritus Montreal Canada Department of Applied Mathematics Charles University Visiting Prague Czech Republic Computer Science Institute Charles University Prague Czech Republic

Richmond and Richmond (American Mathematical Monthly 104 (1997), 713–719) proved the following theorem: If, in a metric space with at least five points, all triangles are degenerate, then the space is isometric to a subset of the real line. We prove that the hypothesis is unnecessarily strong: In a metric space on n points, (n3) − n + 5 arbitrarily placed or 3 (n−22) + 1 suitably placed degenerate triangles *** Codes 30L99, 51F99, 54E99 © 2022, CC BY.

关键词： Topology

Real-time Accident Anticipation for Autonomous Driving Through Monocular Depth-Enhanced 3D Modeling

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liao, Haicheng Li, Yongkang Wang, Chengyue Lai, Songning Li, Zhenning Bian, Zilin Lee, Jaeyoung Cui, Zhiyong Zhang, Guohui Xu, Chengzhong State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science University of Macau China Department of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China State Key Laboratory of Internet of Things for Smart City University of Macau China State Key Laboratory of Internet of Things for Smart City Departments of Civil and Environmental Engineering and Computer and Information Science University of Macau China Guangzhou China Transportation Planning and Engineering The Department of Civil and Urban Engineering New York University New York United States School of Traffic and Transportation Engineering Central South University Changsha China School of Transportation Science and Engineering Beihang University Beijing China Department of Civil and Environmental Engineering University of Hawaii HonoluluHI United States

The primary goal of traffic accident anticipation is to foresee potential accidents in real time using dashcam videos, a task that is pivotal for enhancing the safety and reliability of autonomous driving technologies. In this study, we introduce an innovative framework, AccNet, which significantly advances the prediction capabilities beyond the current state-of-the-art 2D-based methods by incorporating monocular depth cues for sophisticated 3D scene modeling. Addressing the prevalent challenge of skewed data distribution in traffic accident datasets, we propose the Binary Adaptive Loss for Early Anticipation (BA-LEA). This novel loss function, together with a multi-task learning strategy, shifts the focus of the predictive model towards the critical moments preceding an accident. We rigorously evaluate the performance of our framework on three benchmark datasets—Dashcam Accident Dataset (DAD), Car Crash Dataset (CCD), and AnAn Accident Detection (A3D), and DADA-2000 Dataset—demonstrating its superior predictive accuracy through key metrics such as Average Precision (AP) and mean Time-To-Accident (mTTA). Copyright © 2024, The Authors. All rights reserved.

关键词： Multi-task learning

Security Considerations for Virtual Reality Systems

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Viswanathan, Karthik Yazdinejad, Abbas Department of Software Engineering Game Development Kennesaw State University GA United States Cyber Science Lab School of Computer Science University of Guelph ON Canada

There is a growing need for authentication methodology in virtual reality applications. Current systems assume that the immersive experience technology is a collection of peripheral devices connected to a personal computer or mobile device. Hence there is a complete reliance on the computing device with traditional authentication mechanisms to handle the authentication and authorization decisions. Using the virtual reality controllers and headset poses a different set of challenges as it is subject to unauthorized observation, unannounced to the user given the fact that the headset completely covers the field of vision in order to provide an immersive experience. As the need for virtual reality experiences in the commercial world increases, there is a need to provide other alternative mechanisms for secure authentication. In this paper, we analyze a few proposed authentication systems and reached a conclusion that a multidimensional approach to authentication is needed to address the granular nature of authentication and authorization needs of a commercial virtual reality applications in the commercial world. © 2022, CC BY.

关键词： Virtual reality

Prediction of Dementia Based on Older Adults' Sleep Disturbances Using Machine Learning

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Nyholm, Joel Ghazi, Ahmad Nauman Ghazi, Sarah Nauman Berglund, Johan Sanmartin Department of Computer Science Blekinge Institute of Technology Blekinge Karlskrona37179 Sweden Department of Software Engineering Blekinge Institute of Technology Blekinge Karlskrona37179 Sweden Department of Health Blekinge Institute of Technology Blekinge Karlskrona37179 Sweden

Background: The most common degenerative condition in older adults is dementia, which can be predicted using a number of indicators, and appropriate measures can be taken to slow down the progression. One of the indicators of an increased risk of dementia is sleep disturbances. This study examines whether machine learning can predict dementia based on the indicators of sleep disturbance. Methods: This study uses a controlled experiment with five machine learning algorithms (gradient boosting, logistic regression, Gaussian naive Bayes, random forest, and support vector machine) and data on the older population (60+) in Sweden from the Swedish National Study on Ageing and Care – Blekinge (n=4175). Each algorithm uses 10-fold stratified cross-validation to obtain the results, which consist of the Brier score for checking accuracy and the feature importance for examining the factors that impact dementia. The algorithms use 16 features which are on personal and sleep disturbance ***: Logistic regression found an association between dementia and sleep disturbances. However, it is slight for the features in the study. Gradient boosting was the most accurate algorithm with 92.9% accuracy, 0.926 f1-score, 0.974 ROC AUC, and 0.056 Brier score. The significant risk factors were different in each machine-learning algorithm. If the person sleeps more than two hours during the day, their sex, education level, age, waking up during the night, and if the person snores are the variables that most consistently have the highest feature importance in all ***: Machine learning algorithms can efficiently predict dementia through sleep disturbance data. The association found is small, and several other factors might influence the prediction of dementia. However, sleep disturbance screening, especially for factors like sleeping for more than two hours during the daytime, waking up during the night, snoring, and other sociodemographic factors like gender and e

关键词： Logistic regression

Task Delay and Energy Consumption Minimization for Low-altitude MEC via Evolutionary Multi-objective Deep Reinforcement Learning

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Sun, Geng Ma, Weilong Li, Jiahui Sun, Zemin Wang, Jiacheng Niyato, Dusit Mao, Shiwen College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China College of Computing and Data Science Nanyang Technological University Singapore639798 Singapore College of Software Jilin University Changchun130012 China Department of Electrical and Computer Engineering Auburn University AuburnAL36849-5201 United States

The low-altitude economy (LAE), driven by unmanned aerial vehicles (UAVs) and other aircraft, has revolutionized fields such as transportation, agriculture, and environmental monitoring. In the upcoming six-generation (6G) era, UAV-assisted mobile edge computing (MEC) is particularly crucial in challenging environments such as mountainous or disaster-stricken areas. The computation task offloading problem is one of the key issues in UAV-assisted MEC, primarily addressing the trade-off between minimizing the task delay and the energy consumption of the UAV. In this paper, we consider a UAV-assisted MEC system where the UAV carries the edge servers to facilitate task offloading for ground devices (GDs), and formulate a calculation delay and energy consumption multi-objective optimization problem (CDECMOP) to simultaneously improve the performance and reduce the cost of the system. Then, by modeling the formulated problem as a multi-objective Markov decision process (MOMDP), we propose a multi-objective deep reinforcement learning (DRL) algorithm within an evolutionary framework to dynamically adjust the weights and obtain non-dominated policies. Moreover, to ensure stable convergence and improve performance, we incorporate a target distribution learning (TDL) algorithm. Simulation results demonstrate that the proposed algorithm can better balance multiple optimization objectives and obtain superior non-dominated solutions compared to other methods. Copyright © 2025, The Authors. All rights reserved.

关键词： Deep reinforcement learning

Influence of Lung Cancer Model Characteristics on Nanodrugs Tumor Targeting Behavior Based on Convolutional Kernel Extreme Learning Machine Model

学校读者我要写书评

暂无评论

Influence of Lung Cancer Model Characteristics on Nanodrugs ...

Advancement in Technology (ICONAT), International Conference for

作者： Manthan S. Manavadaria Srikanth Chintakindi Rajasree Rajamohanan S Krishna Prasad P. Janardhan Saikumar Neerav Nishant EC Department CSPIT CHARUSAT Changa Petlad Gujarat India Associate Project Manager Cloud Software Group Department of Computer Science (Artificial intelligence and Data Science) Karpagam Academy of Higher Education Coimbatore India Department of Mechanical Engineering Nitte (Deemed to be University) NMAM Institute of Technology Nitte Udupi India Department of ECE Audisankara College of Engineering and Technology Gudur India Department of CSE School of Engineering Babu Banarasi Das University Lucknow India

ISBN: (数字)9798350354171

ISBN: (纸本)9798350354188

One of the main killers on a worldwide basis is cancer. In terms of global persistence, lung cancer stands out among the most frequent cancers. For lung cancer, the standard medical approach includes chemotherapy, surgical removal, and radiation therapy. When compared to other methods, this one isn’t extremely targeted and may even damage surrounding healthy cells. There has been recent recognition of nanotechnology as a possible tool for the treatment and management of lung cancer. Preprocessing, feature selection, segmentation, and model training must be executed in this precise sequence to ensure accuracy. As part of the preprocessing, the proposed approach employ the kernel correlation approach. Splitting the input image into smaller pieces with the goal of reducing the overall representation of the image is called image segmentation. To find features with high predictive power and remove redundant ones, feature selection was done in the training cohort. The model was trained using a Convolutional-KELM. As compared to CNN and ELM, the suggested approach performs better. Following implementation of the technique, the accuracy increased by 94.25%.

关键词： Training Image segmentation Accuracy Lungs Lung cancer Feature extraction Convolutional neural networks Kernel Medical diagnostic imaging Tumors