检索结果-内蒙古大学图书馆

Congress on Evolutionary Computation

作者： Xiaoming Xue Liang Feng Cuie Yang Songbai Liu Linqi Song Kay Chen Tan Department of Computer Science City University of Hong Kong Hong Kong SAR China College of Computer Science Chongqing University Chongqing China State Key Lab of Synthetic Automation for Process Industries Northeastern University Shenyang China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Department of Computing The Hong Kong Polytechnic University Hong Kong SAR China

ISBN: (数字)9798350308365

ISBN: (纸本)9798350308372

In cases of frequent problem-solving of multiobjective optimization tasks from a domain due to changing conditions or problem features, a growing number of individual tasks will be solved and stored in a database, providing an opportunity for a target task at hand to achieve better optimization performance through knowledge transfer from the previously-solved tasks, which is also known as sequential transfer optimization. Despite a variety of transfer algorithms that have been developed over the years, the research on the design of benchmark problems for evaluating such algorithms received far less attention. Oftentimes, the source and target tasks in existing test problems are manually assembled or extended from specific practical problems, limiting their ability to represent the diverse yet complex source-target similarity relationships in real-world problems. In light of this, we propose design methods to generate multiobjective sequential transfer optimization problems (MSTOPs) systematically in this work, wherein the Pareto manifolds of individual tasks and the manifold-based similarity between the tasks can be customized with ease, enabling a broad spectrum of representation of the diverse similarity relationships between the source-target Pareto manifolds of MSTOPs. Lastly, a benchmark suite with 12 test problems is developed using the proposed methods, which would serve as an arena for electing superior multiobjective sequential transfer optimization algorithms. The source code is available at https://***/XmingHsueh/MSTOP.

关键词： Manifolds Uncertainty Limiting Shape Design methodology Source coding Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Autonomic ZTA-based Network Management Engine (AZNME)

Autonomic ZTA-based Network Management Engine (AZNME)

引用

IEEE International Conference on software Reliability engineering Workshops (ISSRE Wksp)

作者： Cihan Tunc James Durflinger Charif Mahmoudi Valerio Formicola Computer Science & Engineering University of North Texas Denton Texas Siemens Technology US Princeton New Jersey Electrical and Computer Engineering California Polytechnic State University Pomona California

ISBN: (数字)9781665476799

ISBN: (纸本)9781665476805

The advancements in computer and networking technologies created closely connected cyberspaces. Nevertheless, this also invalidated many traditional and isolated/local network solutions and introduced higher cybersecurity risk. As a solution, NIST's Zero-Trust Architecture (ZTA) with “never trust, always verify” principle has been widely accepted; yet, its implementation, enforcement, and compliance-check mechanisms are still immature as the solutions are generally applied manually. In this paper, we present an autonomic computing based management engine for networking of a cyberspace, we refer as Autonomic ZTA-based Network Management Engine (AZNME), which monitors an asset's network connections, checks if these connections fulfill ZTA requirements, and evaluates trust continuously, and takes mitigation actions as needed. As a proof of concept, we implemented the AZNME focusing on active connections (e.g., IPs and ports) to enforce policies and create firewall rules based on trust evaluation.

关键词： Firewalls (computing) Conferences Cyberspace Focusing NIST software reliability Distributed computing

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Approach for Identification of Potato Leaf Diseases Using Wrapper Feature Selection and Feature Concatenation

arXiv

引用

arXiv 2025年

作者： Naeem, Muhammad Ahtsam Saleem, Muhammad Asim Sharif, Muhammad Imran Akber, Shahzad Saleem, Sajjad Akhtar, Zahid Siddique, Kamran School of Information and Software Engineering University of Electronic Science and Technology of China China Faculty of Computing Riphah International University Faisalabad Campus Pakistan Department of Computer Science COMSATS University Islamabad Wah Campus Pakistan Department of Information and Technology Washington University of Science and Technology AlexandriaVA United States Department of Network and Computer Security State University of New York Polytechnic Institute United States Department of Computer Science and Engineering University of Alaska Anchorage Anchorage United States

The potato is a widely grown crop in many regions of the world. In recent decades, potato farming has gained incredible traction in the world. Potatoes are susceptible to several illnesses that stunt their development. This plant seems to have significant leaf disease. Early Blight and Late Blight are two prevalent leaf diseases that affect potato plants. The early detection of these diseases would be beneficial for enhancing the yield of this crop. The ideal solution is to use image processing to identify and analyze these disorders. Here, we present an autonomous method based on image processing and machine learning to detect late blight disease affecting potato leaves. The proposed method comprises four different phases: (1) Histogram Equalization is used to improve the quality of the input image;(2) Feature extraction is performed using a Deep CNN model, then these extracted features are concatenated;(3) Feature selection is performed using wrapper-based feature selection;(4) Classification is performed using an SVM classifier and its variants. This proposed method achieves the highest accuracy of 99% using SVM by selecting 550 features. © 2025, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Straightline: From-Development-To-Deployment Multiple Resources-Aware Machine Learning Application Pipeline

SSRN

引用

SSRN 2023年

作者： Guan, Boyuan Ching, Cheng-Wei Xu, Hailu Zhang, Yinzhe Hu, Liting Florida International University United States Virginia Polytechnic Institute State University United States California State University United States Department of Computer Science and Engineering University of California Santa Cruz Santa CruzCA95064 United States

The life cycle of machine learning (ML) applications has two stages: model development and model deployment. However, traditional ML application systems (e.g., training-specific or inference resource placement systems) focus on one particular stage or phase in one stage of the life cycle of ML applications. These systems often aim at the optimization of model training or acceleration on mode inference, and they often assume the infrastructure for model training or model inference is monotonous. This suggests a need for a new ML application pipeline that provides from-development-to-deployment and multi-resource-aware pipeline to integrate the development and deployment of ML applications in the hybrid *** present StraightLine, an efficient and adaptive ML pipeline that incorporates model development and model deployment of ML applications and provides multi-computing platform ML implementations. The novelty of our work is the incorporation of containerization in ML applications, which defines clear hardware and software modules in the life cycle of ML applications and improves the adaptability in the hybrid and heterogeneous *** build up a hybrid infrastructure that consists in-house data center, local web server, and serverless computing, and results show that StraightLine achieves over 10 times shorter training time with same level of model accuracy in model development and StraightLine significantly reduces response time and failure rate in model deployment, using different computing resources in the hybrid infrastructure. © 2023, The Authors. All rights reserved.

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

Static Gesture Recognition using CNN with Hand Landmark Detection 2

Static Gesture Recognition using CNN with Hand Landmark Dete...

引用

2nd International Conference on Artificial Intelligence, Automation, and High-Performance Computing, AIAHPC 2022

作者： Lyu, Leyu Wang, Dixuan Zhang, Sibo Zhao, Yanran Zhou, Sicheng College of Information Engineering China Jiliang University Hangzhou China Bradly Department of Electrical and Computer Engineering Virginia Polytechnic Institute and State University Blacksburg United States College of Automotive Engineering Jilin University Changchun China College of Mechanical Engineering Donghua University Shanghai China College of Letters and Science University of California Los Angeles Los Angeles United States

ISBN: (纸本)9781510657717

Static Gesture Recognition is an interactive system that enables people, especially the hearing-impaired, to directly communicate with other people and machines without third-party auxiliary equipment. However, it is challenging due to gesture datasets and the recognition accuracy of pre-processing. This paper proposes Convolutional Neural Network (CNN) with hand landmark detection to recognize Static Gestures and improve the pre-processing accuracy significantly. First, this paper makes a dataset by taking 5,800 photos from 4 people, including 13 one-handed gestures and 3 two-handed. Then, it pre-processes the dataset in both ways of skin color detection and hand landmark detection to select a highaccuracy method. Finally, CNN is trained for both pre-processed datasets to classify the samples into 16 classes. To verify the method's effectiveness, this paper also compares a baseline model that comprises the Support Vector Machine and the Principle Component Analysis. The experimental result shows that CNN eclipses the other model with higher accuracy of 99% for Static Gesture Recognition. © 2022 SPIE. All rights reserved.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Deep Transfer Learning for Classification of Rabbit Behaviour Using Publicly Available Datasets

Deep Transfer Learning for Classification of Rabbit Behaviou...

引用

Advancements of Artificial Intelligence in African Context (AAIAC), International Conference on the

作者： Oluwadamisola Joshua Adedeji Adebayo Abayomi-Alli Oluwasefunmi ‘Tale Arogundade Olusola Abayomi-Alli Bayo Olushola Omoyiola Department of Computer Science Federal University of Agriculture Abeokuta Ogun State Nigeria Department of Software Engineering Kaunas University of Technology Kaunas Lithuania University of the People Pasadena California United States

Deep learning has emerged successfully as a utilised technology for animal monitoring and classification. However, there exists limited research when it comes to rabbit monitoring and classification. This study presents real time models for detection and tracking of rabbits, along with a classification model for their behaviour. The detection model was trained on a dataset obtained from Robflow and YouTube, while the classification models utilised over 1100 curated images representing seven different physical behaviours of rabbits: digging, humping and mating, eating, periscoping, jumping and binkying, laying, and flopping and loafing. For object tracking, transfer learning was applied using a pretrained ResNet18 model for feature extraction, and YOLOv8 was employed for tracking, supported by ByteTRACK for consecutive frame tracking. Additionally, VisionTransformer, ResNet18, and EfficientNet models were finetuned to adapt their representations for behaviour classification. The experimental result demonstrated that the finetuned VisionTransformer model achieved an accuracy of 86%, outperforming ResNet18 and EfficientNet models with accuracies of 76% and 80% respectively. In the object detection experiment, the YOLOv8 model achieved a mean Average Precision (mAP50) score of 0.96. These results indicate the effectiveness of the proposed approach for accurate detection, tracking, and classification of rabbit behaviour in real-time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Approach to Cost-effective Management of Typhoid Fever in Children

An Intelligent Approach to Cost-effective Management of Typh...

引用

International Conference on Signal Processing and Communication (ICSC)

作者： Kingsley T. Igulu Thipendra P Singh Tosin C. Olayinka Ojei H. Onyijen Edwin Onatuyeh Wilson Nwankwo Department of Computer Science Kenule Beeson Saro-Wiwa Polytechnic Bori Bori Nigeria Bennett University Greater Noida India Department of Software Engineering Wellspring University Benin City Edo State Nigeria Department of Physics Edo State University Uzairue Edo State Nigeria Department of Accounting Delta State University of Science & Technology Ozoro Nigeria Department of Cyber Security Delta State University of Science & Technology Ozoro Nigeria

ISBN: (数字)9798331511890

ISBN: (纸本)9798331511906

Typhoid fever poses a significant health concern among children, due to its potential for severe complications and high treatment costs. This paper proposes an intelligent approach to modelling the prognosis and management of paediatric typhoid infections leveraging machine learning and data analytics to optimize healthcare resources and improve patient outcomes. The dataset was sourced from hospitals in Edo state, Nigeria. The dataset comprises laboratory tests of blood samples of children, from age zero (0) to five (5) years. Six (6) attributes that exhibit the highest information gain: widal test, malaria count, monocyte, platelets, HB, eosinophils, cost of treatment respectively, were selected and ranked thus: 0.6759, 0.4936, 0.3147, 0.2843, 0.2416, 0.2127, and 0.20. Five different classification algorithms (J48_Consolidated, LMT, RepTree, MultiBoost Decision Stump) were employed. and Random Forest) and their results were compared. Performance analysis on the five (5) classifiers shows that Multiboost Decision Stump exhibited the best accuracy of 94% and least MAE of 0.0604. The finding shows that the developed model when integrated into automated disease diagnostic workflows will provide an enhanced and flexible solution for quick prognosis of typhoid fever in children in the tropics with significant cost savings with respect to hospitalization. The finding presupposes that we can enhance the efficiency of typhoid fever management while ensuring the delivery of quality care to children in resource-limited settings.

关键词： Pediatrics Machine learning algorithms Costs Signal processing algorithms Predictive models Prediction algorithms Classification algorithms Performance analysis Prognostics and health management Random forests

来源：评论

学校读者我要写书评

暂无评论

Transformer-Based Ensemble Model for Binary and Multiclass Oral Cancer Segmentation

Transformer-Based Ensemble Model for Binary and Multiclass O...

引用

International Conference on Electrical, computer and Communication engineering (ECCE)

作者： Amira Hossain Anamul Sakib Al Shahriar Uddin Khondakar Pranta Jesika Debnath Md Tanvir Rahman Tarafder Sazzadul Islam Shamim Forhad Md. Redwan Ahmed Rezaul Haque Shafiur Rahman Dept. of Computer Science Westcliff University Irvine CA USA Dept. of Business Administration International American University CA USA Dept. of Computer Science Wright State University Dayton OH USA Dept. of Information Technology Westcliff University Irvine California Dept. of Computer Science and Engineering BRAC University Dhaka Bangladesh Dept. of Electrical and Electronics Engineering American International University Bangladesh Dept. of Computer Science and Engineering East West University Dhaka Bangladesh Dept. of Software Engineering Daffodil International University Dhaka Bangladesh

ISBN: (数字)9798350357509

ISBN: (纸本)9798350357516

Early and accurate segmentation of oral cancer is essential for timely diagnosis and treatment. Traditional methods like visual inspections and biopsies are often subjective and costly, which can hinder early detection. To improve segmentation accuracy for binary and multiclass classification, we propose a transformer-based ensemble model that combines Vision Transformer (ViT), Data-efficient Image Transformer (DeiT), Swin Transformer, and BEiT. This ensemble utilizes self-attention mechanisms for better feature extraction and spatial representation. Our study employs two datasets: the MOD dataset (463 images of oral diseases) and a histopathological dataset (1,224 images of oral squamous cell carcinoma and normal epithelium). We applied extensive preprocessing and augmentation techniques, such as grayscale conversion, binary thresholding, and Contrast Limited Adaptive Histogram Equalization (CLAHE), to enhance image quality and model generalization. The performance evaluation showed that our ensemble model outperformed individual architectures, achieving an Intersection over Union (IoU) of 0.9601 and a Dice Coefficient of 0.9598 for binary segmentation, and IoU of 0.9587 and Dice Coefficient of 0.9575 for multiclass segmentation. A comparative analysis with state-of-the-art models confirmed the effectiveness of our approach. These results demonstrate the potential of transformer-based ensemble learning for oral cancer diagnosis, presenting a scalable tool for clinical applications. Future work will focus on expanding dataset diversity, optimizing computational efficiency, and integrating real-time inference for improved usability in healthcare.

关键词： Image segmentation computer vision Adaptation models Visualization Accuracy Computational modeling Transformers Cancer detection Real-time systems Cancer

来源：评论

学校读者我要写书评

暂无评论

Virtual Reality on Assessing the Motor Skills of Individuals with Autism Spectrum Disorder

Virtual Reality on Assessing the Motor Skills of Individuals...

引用

IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)

作者： Ayesha A. Malik Abrar M. Zaki Ngoc Chung Tran Irene X. Liang Ting Liu Damian Valles Dept. of Computer Science University of Central Florida Orlando USA Dept. of Computer Science Rensselaer Polytechnic Institute Troy USA Dept. of Computer Science California State University Fullerton Fullerton USA Cognitive Science Cornell University Ithaca USA College of Graduate Studies Texas A&M University-San Antonio San Antonio USA Ingram School of Engineering Texas State University San Marcos USA

ISBN: (数字)9798331540906

ISBN: (纸本)9798331540913

Children with Autism Spectrum Disorder (ASD) often experience delays in motor skills, which can substantially affect their future motor function. The Movement Assessment Battery for Children - Second Edition (MABC-2) is a widely used tool in evaluating children’s motor skills across different age bands, specifically assessing children ages 3 to 16. It includes eight unique tasks per age band that measure fine and gross motor skills and balance, which explains a child’s motor abilities and classifies them by groups. This study extends previous research by exploring the potential of Virtual Reality (VR) to make the MABC-2 tasks more engaging and interactive for children, which could lead to better outcomes. The previous research created the balance and gross motor tasks of the MABC-2 in VR. We refined those tasks and completed the remaining ones. The VR tool was tested on seven individuals aged 19 to 21. Pre- and post-VR MABC-2 scores were collected and analyzed. Most tasks were accurately replicated in VR; however, significant statistical differences were found in the Threading Lace (p= 0.003) and Catching Ball (p = 0.007) tasks, indicating further refinement. Machine learning analysis was also conducted on data from 268 previous MABC-2 scores of children diagnosed with autism to classify them into motor skill proficiency zones based on their scores and to determine the most influential features for accurate prediction. The analysis revealed that balance scores were particularly influential in determining motor proficiency. This indicates the importance of balance in interventions to improve overall motor proficiency.

关键词： Autism Virtual reality Machine learning Variable speed drives Aging Motors Mobile communication Battery charge measurement Batteries Delays

来源：评论

学校读者我要写书评

暂无评论

Using Gray Literature to Influence software engineering Curricula

arXiv

引用

arXiv 2023年

作者： Kiper, James D. Auernheimer, Brent Sultana, Simon Walia, Gursimran Singh Computer Science and Software Engineering Miami University OxfordOH United States Computer Science California State University Fresno Fresno CA United States Physical Science Reedley College ReedleyCA United States Computer and Cyber Sciences Augusta University AugustaGA United States

software engineering (SE) evolves rapidly, with changing technology and industry expectations. The curriculum review bodies (e.g., ACM and IEEE-CS working groups) respond well but can have refresh cycles measured in years. For computer science and SE educators to be agile, predictive, and adapt to changing technology trends, judicious use of gray literature (GL) can be helpful. Other fields have found GL useful in bridging academic research and industry needs. GL can be extended to SE to aid faculty preparing students for industry. We address two questions: first, given the velocity of technical change, do current curricular guidelines accurately reflect industry practice and need for our graduates? Second, how can we track current and emerging trends to capture relevant competencies? We argue a study of the scholarly literature will have a limited impact on our understanding of current and emerging trends and curriculum designers would do well to utilize GL. We close with recommendations for SE educators. © 2023, CC BY-NC-ND.

关键词： Curricula

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：