检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Zhong, Xiaojing Su, Yukun Wu, Zhonghua Lin, Guosheng Wu, Qingyao School of Software Engineering South China University of Technology China School of Computer Science and Engineering Nanyang Technological University Singapore Key Laboratory of Big Data and Intelligent Robot Ministry of Education China Peng Cheng Laboratory China Tencent Wechat Department China SenseTime Research

3D virtual try-on tasks aim to generate realistic try-on results for full- body garments, allowing them to be observed from arbitrary perspectives. Recent methods often represent the 3D human form with a fixed topol- ogy, limiting garment representation and leading to higher computational demands. Furthermore, the challenge of flexible transfer over various body parts remains. To address these problems, we introduce DI-Net(Decomposed Implicit Garment Transfer Network), where garment transfer is decomposed into 2D image layout transfer and 3D texture layout transfer. We propose a complementary warping module that leverages dense correspondence learn- ing and sparse flow learning to align the body appearance and garments with the target pose for image layout transfer. Subsequently, the transferred garments are lifted to the 3D human mesh by constructing a pixel-aligned implicit function and predicting the texture based on geometric priors. By applying different semantic masks for garment transfer, we efficiently control the texture of the generated mesh. Experimental results show the effective- ness and superiority of our method in the 3D virtual try-on task. © 2024, The Authors. All rights reserved.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

VIKOR decision making method based on multi-granularity hesitant fuzzy linguistic term sets

VIKOR decision making method based on multi-granularity hesi...

引用

Cyber-Physical Social Intelligence (ICCSI), International Conference on

作者： Jin Qian Wei Jin Xuanyuan Wang Ying Yu Mingchen Zheng Duoqian Miao School of Software East China Jiaotong University Nanchang Jiangxi School of Transportation Engineering East China Jiaotong University Nanchang Jiangxi Department Computer Science and Technology Tongji University Shanghai China

In the existing multi-attribute decision making researches, most of the hesitant fuzzy linguistic multi-attribute decision making methods assume the decision makers use the linguistic term set under the same granularity to express their linguistic evaluation informations. However, in actual decision making, due to different cultural and educational backgrounds, decision makers may use different sets of linguistic terms at different granularities, which leads to the mismatch of decision information and inaccuracy of decision results. To address this problem, this paper proposes VIKOR decision making method based on multi-granularity hesitant furzy linguistic term sets, which consider both the overall benefits of the group and the regret values of individuals to select the optimal solution. Specifically, a VIKOR decision making method based on the multi-granularity hesitant fuzzy linguistic term set is first proposed, which employs to convert the multi-granularity hesitant fuzzy linguistic term set of each decision maker to the same granularity for aggregation, and obtains the corresponding membership level linguistic term set. Secondly, using the VIKOR method, the positive and negative ideal solutions are determined, and all alternatives are ranked based on their proximity to the positive ideal solution. This ranking facilitates the selection of the optimal solution. Secondly, combined with the VIKOR method, the positive and negative ideal solutions are determined, and all alternatives are ranked in order of merit according to the magnitude of the closeness of the preference value setting of each alternative to the positive ideal solution, so as to achieve the selection of the optimal solution. Finally, an arithmetic example is used to prove the accuracy, rationality and feasibility of the method, and the stability of the proposed method is further illustrated by experimentally analyzing the decision mechanism coefficients.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mental Workload Classification from fNIRS Signals by Leveraging Machine Learning

Mental Workload Classification from fNIRS Signals by Leverag...

引用

IEEE Signal Processing in Medicine and Biology Symposium (SPMB)

作者： M. Hasan M. Mahmud S. Poudel K. Donthula K. Poudel Computational and Data Science Middle Tennessee State University Murfreesboro TN USA Department of Electrical and Computer Engineering University of Memphis TN USA Computer Science Middle Tennessee State University Murfreesboro TN USA Senior Software Engineer Optum Inc Murfreesboro TN USA

Mental workload (MWL) identification is vital to know human cognitive functioning, performance, and well-being. In this work, we develop models for identifying low vs. high MWL using different genres of machine learning classifiers. We used non-invasive functional near-infrared spectroscopy (fNIRS) signals while participants classified the low vs. high levels of MWL tasks. Our analysis shows the low vs. high MWL can be identified best from the whole brain data. The k-nearest neighbors classifier showed the best performance with an accuracy of 98.8%, an area under the curve (AUC) of 98.8%, F1 score, precision, and recall of 98.0% from the whole brain data without overlapping signals. A separate hemisphere analysis using left hemisphere (LH) and right hemisphere (RH) activity showed that the LH activity has better classification ability than the RH activity. We also examined the classification with the top six features that could identify the low vs. high MWL with an accuracy of 97.4%, (AUC) 97.4%, F1 score, precision, and recall of 97.0%. These findings would be useful for developing more intuitive and user-friendly interfaces in the human-computer interface.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An explainable deep learning approach for stock market trend prediction

引用

Heliyon 2024年第21期10卷 e40095页

作者： Muhammad, Dost Ahmed, Iftikhar Naveed, Khwaja Bendechache, Malika CRT-AI and ADAPT Research Centres School of Computer Science University of Galway Ireland Department of Software Engineering University of Europe for Applied Sciences Potsdam Germany Swedish Center for Digital Innovation University of Gothenburg Sweden ADAPT Research Centre School of Computer Science University of Galway Ireland

Given the intricate nature of stock forecasting as well as the inherent risks and uncertainties, analysis of market trends is necessary to capitalize on optimal investment opportunities for profit maximization and timely disinvestment for loss minimization. In this work, we propose a deep learning model for predicting five distinct stock market trends: upward, downward, double top, rounded bottom, and rounded top. The proposed model surpasses common benchmarks, including support vector machine, random forest, and logistic regression, achieving an average accuracy of 94.9%, compared to 85.7% for random forest, 60.07% for support vector machine, and 52.45% for logistic regression. Furthermore the proposed model excels in F1-score, with a 94.85% performance, compared to 77.95% for random forest, 21.02% for support vector machine and 46.23% for logistic regression, across four real world diverse datasets. Additionally, we employ explainable AI (XAI) techniques, SHAP and LIME, to enhance interpretability, enabling stakeholders to understand the key factors driving predictions. The SHAP analysis reveals the top 10 most important/influential features, enabling feature reduction while maintaining performance. Interestingly, while accuracy slightly decreases with top 10 features, precision, recall, and F1-score improve, suggesting a trade-off between comprehensiveness and performance. These results demonstrate the potential for practical application in financial decision-making, providing a balance between interpretability and predictive power that can support investors in risk management and strategic planning. © 2024 The Author(s)

关键词： Deep neural network Explainable AI Machine learning Stock market trend prediction Time series prediction

来源：评论

学校读者我要写书评

暂无评论

Supporting Experiential Computing Education with the Accessible Learning Labs

Journal of Computing Sciences in Colleges

引用

Journal of Computing sciences in Colleges 2025年第8期40卷

作者： Carla Lopez Samuel Malachowsky Daniel Krutz Farzana Rahman Department of Software Engineering Rochester Institute of Technology Department of Electrical Engineering and Computer Science Syracuse University

The lack of accessible software in modern times continues to exclude people from engaging with technology. To address this, we developed the Accessible Learning Lab (ALL) project, which provides educational resources on accessible computing that enable individuals to create accessible software. ALL project offers a series of experiential educational labs that can be easily integrated into classroom settings and is available online to support adoption. These labs teach essential computing concepts, such as AI, ML, cybersecurity, and inclusive software development. Complete material is publicly available on the website: https://***

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mutual Graph Learning Network and Diffusion Probabilistic Model-based Medical Image Segmentation

Mutual Graph Learning Network and Diffusion Probabilistic Mo...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Huaqiang Su Haijun Lei Guoliang Chen Xin Chen Baiying Lei College of Computer Science & Software Engineering Shenzhen University Shenzhen China Department of Radiology Guangzhou First People’s Hospital Guangzhou China School of Biomedical Engineering & Shenzhen University Medical School Shenzhen University Shenzhen China

Diffusion probabilistic models (DPM) can generate semantically valuable pixel-level representations and are widely used in medical image segmentation tasks. However, DPM faces challenges when dealing with medical image segmentation problems due to the irregular structure of medical images and the similarity between lesions and their surrounding environments. Therefore, this paper proposes a dual-branch Diff-UNet architecture to solve the medical image segmentation problem. Specifically, this architecture introduces the Transformer internal network on top of the standard UNet architecture based on DPM and realizes the interaction of UNet and Transformer branch features through bidirectional connection units to capture local features and remote dependencies better. In addition, through the feature fusion module (FFM), the global context information extracted by DPM is combined with the local detail features captured by the segmentation network. Simultaneously, this paper introduces a mutual graph learning (MGL) network to decompose the image into two task-specific feature maps, which are used to roughly locate the object position and capture the fine details of the object boundary. Finally, the cross attention (CA) module combines the edge information of the diffusion model with the features of the segmentation network to enhance the network’s ability to perceive images. Experiments demonstrate the effectiveness of our Diff-UNet on challenging datasets, including self-collected databases and LUNA16.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based E-Learning Solution for Identifying and Bridging the Knowledge Gap in Primary Education

Deep Learning-Based E-Learning Solution for Identifying and ...

引用

International Research Conference on Smart Computing and Systems engineering (SCSE)

作者： D.P.H Arunoda S.R Walpola S.M.I Piumira A.D.M.P Athukorala Thusithanjana Thilakarathna Sanjeevi Chandrasiri Department of Computer Science and Software Engineering Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka Department of Information Technology Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka

Educational teaching apps are primarily available in app stores to educate students in various contexts. Lack of educational resources, physical and mental health conditions, and poverty cause some students to skip school and move on to the next school grade without completing the course content of the previous grade. Most of the available apps focus on specific content to cover. The Smart Primary Education Tutor (SPET) teaching app specifically focuses on the missed content by analyzing their knowledge gap and providing lessons to cover the missed content. The main objective of SPET is to develop a methodology to identify the gap in student knowledge and fill the knowledge gap by teaching using smart techniques. SPET is determined to identify students’ interactions (attention, emotions) with the system to identify students’ ability to use the learning tool, identifying gaps in students’ knowledge levels compared to their actual grades using activities and voice-based technologies, teaching to cover the knowledge gap by providing engaging activities and lessons and evaluating students by conducting a final assessment and analyze students’ knowledge and performance obtained through the system. Students between the ages of 5 and 8 are targeted in the community to apply. The solution embeds deep learning-based models including attention classification models using head posture estimation, facial expression recognition, and eye gaze estimation, speech recognition models to identify provided verbal answers, handwriting recognition models to evaluate student performance, and smart teaching. The child emotion recognition model achieved 93% accuracy. The Attention span evaluation model achieved 85% accuracy. The handwritten numerical and English character data recognition model which detects answers for the final assessment paper achieved 85% percent of accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Melting Pot of Evolution and Learning

arXiv

引用

arXiv 2023年

作者： Sipper, Moshe Elyasaf, Achiya Halperin, Tomer Haramaty, Zvika Lapid, Raz Segal, Eyal Tzruia, Itai Tamam, Snir Vitrack Department of Computer Science Ben-Gurion University of the Negev Beer-Sheva8410501 Israel Department of Software and Information Systems Engineering Ben-Gurion University of the Negev Beer-Sheva8410501 Israel DeepKeep Tel-Aviv Israel

We survey eight recent works by our group, involving the successful blending of evolutionary algorithms with machine learning and deep learning: 1. Binary and Multinomial Classification through Evolutionary Symbolic Regression, 2. Classy Ensemble: A Novel Ensemble Algorithm for Classification, 3. EC-KitY: Evolutionary Computation Tool Kit in Python, 4. Evolution of Activation Functions for Deep Learning-Based Image Classification, 5. Adaptive Combination of a Genetic Algorithm and Novelty Search for Deep Neuroevolution, 6. An Evolutionary, Gradient-Free, Query-Efficient, Black-Box Algorithm for Generating Adversarial Instances in Deep Networks, 7. Foiling Explanations in Deep Neural Networks, 8. Patch of Invisibility: Naturalistic Black-Box Adversarial Attacks on Object Detectors. Copyright © 2023, The Authors. All rights reserved.

关键词： Genetic programming

来源：评论

学校读者我要写书评

暂无评论

Exploring the Role of Large Language Models in Cybersecurity: A Systematic Survey

arXiv

引用

arXiv 2025年

作者： Tian, Shuang Zhang, Tao Liu, Jiqiang Wang, Jiacheng Wu, Xuangou Zhu, Xiaoqiang Zhang, Ruichen Zhang, Weiting Yuan, Zhenhui Mao, Shiwen Kim, Dong In School of Software Engineering Beijing Jiaotong University Beijing100044 China School of Cyberspace Science and Technology Beijing Jiaotong University Beijing100044 China School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore School of Computer Science and Technology An hui Province Key Laboratory of Digital Twin Technology in Metallurgical Industry Anhui University of Technology Anhui243002 China College of Computing and Data Science Nanyang Technological University Singapore School of Electronic and Information Engineering Beijing Jiaotong University Beijing100044 China School of Engineering University of Warwick CoventryCV4 7AL United Kingdom Department of Electrical and Computer Engineering Auburn University AuburnAL36849-5201 United States Department of Electrical and Computer Engineering College of Information and Communication Engineering Sungkyunkwan University Suwon16419 Korea Republic of

—With the rapid development of technology and the acceleration of digitalisation, the frequency and complexity of cyber security threats are increasing. Traditional cybersecurity approaches, often based on static rules and predefined scenarios, are struggling to adapt to the rapidly evolving nature of modern cyberattacks. There is an urgent need for more adaptive and intelligent defence strategies. The emergence of Large Language Model (LLM) provides an innovative solution to cope with the increasingly severe cyber threats, and its potential in analysing complex attack patterns, predicting threats and assisting real-time response has attracted a lot of attention in the field of cybersecurity, and exploring how to effectively use LLM to defend against cyberattacks has become a hot topic in the current research field. This survey examines the applications of LLM from the perspective of the cyber attack lifecycle, focusing on the three phases of defense reconnaissance, foothold establishment, and lateral movement, and it analyzes the potential of LLMs in Cyber Threat Intelligence (CTI) tasks. Meanwhile, we investigate how LLM-based security solutions are deployed and applied in different network scenarios. It also summarizes the internal and external risk issues faced by LLM during its application. Finally, this survey also points out the facing risk issues and possible future research directions in this domain. Copyright © 2025, The Authors. All rights reserved.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Deep learning for agriculture

Deep learning for agriculture

引用

2020 ASEE Virtual Annual Conference, ASEE 2020

作者： Pantoja, Maria Kurfess, Franz J. Humer, Irene Cal Poly San Luis Obispo Computer Engineering Computer Science and Software Engineering Office: 14-211 United States Computer Science and Software Engineering Department California Polytechnic State University San Luis Obispo United States

The global population is estimated to reach 8 billion by 2023 [1]. To feed such an immense population in a sustainable way, while also enabling farmers to make a living, requires the modernization of production methods in agriculture. In recent years there has been a lot of excitement in academic research and industry about the application of modern computer technology to farming, making farming one of the favorites for investors. According to Forbes Magazine, the agricultural technology gold rush began in 2013, with Monsanto's purchase of the agricultural data company, The Climate Corporation, for $930 million [16]. The total investment in 2017 topped $1.5 billion, setting a new record. All economic indicators point to a huge increase in technology and in particular software used in the agriculture fields. The need for advanced technology in agriculture is clear. The technology is being developed and ready, but what is still lacking is the number of professionals that have both skills-agriculture and technological knowledge-in particular in advanced computing methods like computer vision and deep learning. The main goal of this paper is to report on our approach to close the gap between domain experts in agriculture and computer scientists by developing a practical, hands-on activity in the form of a workshop or tutorial specifically targeted at agricultural engineers and practitioners interested in applying computer vision techniques to solve agricultural problems. The tutorial consists of specific examples like detecting and counting bees, segmentation of fruit trees and automatic fruit classification. The examples for the tutorials are chosen because of their simplicity of implementation and because they are also easily expandable into more complex projects. For example, the segmentation tutorial can be used to estimate pruning weight which is useful to determine the baseline vigor levels of the fruit trees. It is one of the best ways to quantify areas of the or

关键词： Deep 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：