检索结果-内蒙古大学图书馆

International Conference on computer Supported Cooperative Work in Design

作者： Chen Chen Jie Zhu Haiping Huang Yingmeng Gao Nanjing University of Posts & Telecommunications Nanjing China State Key Laboratory Chinese of Computer Architecture Institute of Computing Technology Academy of Sciences Beijing China Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks Nanjing China

The resource-constrained task scheduling problem has been one of the popular research topics in cloud computing systems. By employing the dynamic voltage and frequency scaling (DVFS) techniques, the task scheduling can be further constrained by energy consumption. The paper investigates the DAG task scheduling considering both the resource and energy constraints in heterogeneous distributed systems. The objective is to minimize the scheduling length. An energy-constrained task scheduling framework is employed, where tasks are initially scheduled according to their upward rank values. Then two heuristics are proposed to improve the initial solution, namely, the simulated annealing local search method and the frequency adjustment method. Experiments are conducted by testing a large number of instances with multiple parameter settings, and the results show that the proposed algorithms are effective and efficient.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Platform Urbanism for Resident Safety: A Real-Time Predictive Microclimate Risk Monitoring and Alert System

SSRN

引用

SSRN 2025年

作者： Hossain, Sk Tahsin Yigitcanlar, Tan Nguyen, Kien Xu, Yue City 4.0 Lab School of Architecture and Built Environment Queensland University of Technology 2 George Street BrisbaneQLD4000 Australia School of Electrical Engineering and Robotics Queensland University of Technology 2 George Street BrisbaneQLD4000 Australia School of Computer Science Queensland University of Technology 2 George Street BrisbaneQLD4000 Australia

Urban microclimates significantly impact public health, liveability, and emergency preparedness, yet traditional weather alert systems often rely on centralised data that fails to capture the spatial variability of conditions within cities. This study presents an innovative platform that integrates ArcGIS GeoEvent Server with AIoT-driven predictive analytics to deliver hyper-localised weather alerts. The platform’s adaptable design enables the incorporation of location-specific AI/ML-based predictive models and context-aware notifications, tailored to at-risk populations based on their location, health conditions, and disabilities. Featuring three GeoEvent Services and two ArcGIS Notebook Schedules, the system facilitates real-time data ingestion, processing, predictive modelling, and dissemination. A case study in Brisbane, Australia, demonstrates its capacity to address microclimatic variability, revealing significant differences in thermal stress and precipitation patterns across suburbs. Unlike traditional city-wide alerts, the platform provides targeted notifications prioritising vulnerable groups such as children, the elderly, and individuals with chronic conditions or disabilities. This approach enhances urban resilience and offers a scalable framework for applications in health monitoring, emergency response, and public safety. © 2025, The Authors. All rights reserved.

关键词： Emergency services

来源：评论

学校读者我要写书评

暂无评论

DACB-NET: DUAL ATTENTION GUIDED COMPACT BILINEAR CONVOLUTION NEURAL NETWORK FOR SKIN DISEASE CLASSIFICATION

arXiv

引用

arXiv 2024年

作者： Ahmad, Belal Usama, Mohd Ahmad, Tanvir Saeed, Adnan Khatoon, Shabnam Chen, Min School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Departments of Diagnostics and Intervention and Biomedical Engineering Umea University Sweden School of Information and Control Engineering Xi'an University of Architecture and Technology Xian China School of Civil and Hydraulic Engineering Huazhong University of Science and Technology Wuhan China School of Management Science and Engineering China University of Geosciences Wuhan China

This paper introduces the three-branch Dual Attention-Guided Compact Bilinear CNN (DACBNet) by focusing on learning from disease-specific regions to enhance accuracy and alignment. A global branch compensates for lost discriminative features, generating Attention Heat Maps (AHM) for relevant cropped regions. Finally, the last pooling layers of global and local branches are concatenated for fine-tuning, which offers a comprehensive solution to the challenges posed by skin disease diagnosis. Although current CNNs employ Stochastic Gradient Descent (SGD) for discriminative feature learning, using distinct pairs of local image patches to compute gradients and incorporating a modulation factor in the loss for focusing on complex data during training. However, this approach can lead to dataset imbalance, weight adjustments, and vulnerability to overfitting. The proposed solution combines two supervision branches and a novel loss function to address these issues, enhancing performance and interpretability. The framework integrates data augmentation, transfer learning, and fine-tuning to tackle data imbalance to improve classification performance, and reduce computational costs. Simulations on the HAM10000 and ISIC2019 datasets demonstrate the effectiveness of this approach, showcasing a 2.59% increase in accuracy compared to the state-of-the-art. © 2024, CC BY.

关键词： Gradient methods

来源：评论

学校读者我要写书评

暂无评论

GöwFed - A novel Federated Network Intrusion Detection System

arXiv

引用

arXiv 2022年

作者： Belenguer, Aitor Pascual, Jose A. Navaridas, Javier Department of Computer Architecture and Technology University of the Basque Country UPV/EHU Manuel Lardizabal 1 Donostia-San Sebastian20018 Spain

Network intrusion detection systems are evolving into intelligent systems that perform data analysis while searching for anomalies in their environment. Indeed, the development of deep learning techniques paved the way to build more complex and effective threat detection models. However, training those models may be computationally infeasible in most Edge or IoT devices. Current approaches rely on powerful centralized servers that receive data from all their parties - violating basic privacy constraints and substantially affecting response times and operational costs due to the huge communication overheads. To mitigate these issues, Federated Learning emerged as a promising approach, where different agents collaboratively train a shared model, without exposing training data to others or requiring a compute-intensive centralized infrastructure. This work presents GöwFed, a novel network threat detection system that combines the usage of Gower Dissimilarity matrices and Federated averaging. Different approaches of GöwFed have been developed based on state-of the-art knowledge: (1) a vanilla version;and (2) a version instrumented with an attention mechanism. Furthermore, each variant has been tested using simulation oriented tools provided by TensorFlow Federated framework. In the same way, a centralized analogous development of the Federated systems is carried out to explore their differences in terms of scalability and performance - across a set of designed experiments/scenarios. Overall, GöwFed intends to be the first stepping stone towards the combined usage of Federated Learning and Gower Dissimilarity matrices to detect network threats in industrial-level networks. © 2022, CC BY-NC-SA.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Convolutional Neural Network with Representation Self-challenge for Fingerprint Liveness Detection

引用

computers, Materials & Continua 2022年第10期73卷 719-733页

作者： Jie Chen Chengsheng Yuan Chen Cui Zhihua Xia Xingming Sun Thangarajah Akilan School of Computer Science Nanjing University of Information Science and TechnologyNanjing210044China Key Laboratory of Public Security Information Application Based on Big-Data Architecture Ministry of Public SecurityZhejiang Police CollegeHangzhou310053China Jiangsu Yuchi Blockchain Research Institute Nanjing210044China Department of Software Engineering Lakehead UniversityThunder BayON P7B 5E1Canada

Fingerprint identification systems have been widely deployed in many occasions of our daily ***,together with many advantages,they are still vulnerable to the presentation attack(PA)by some counterfeit *** address challenges from PA,fingerprint liveness detection(FLD)technology has been proposed and gradually attracted people’s *** vast majority of the FLD methods directly employ convolutional neural network(CNN),and rarely pay attention to the problem of overparameterization and over-fitting of models,resulting in large calculation force of model deployment and poor model *** at filling this gap,this paper designs a lightweight multi-scale convolutional neural network method,and further proposes a novel hybrid spatial pyramid pooling block to extract abundant features,so that the number of model parameters is greatly reduced,and support multi-scale true/fake fingerprint ***,the representation self-challenge(RSC)method is used to train the model,and the attention mechanism is also adopted for optimization during execution,which alleviates the problem of model over-fitting and enhances generalization of detection ***,experimental results on two publicly benchmarks:LivDet2011 and LivDet2013 sets,show that our method achieves outstanding detection results for blind materials and *** size of the model parameters is only 548 KB,and the average detection error of cross-sensors and cross-materials are 15.22 and 1 respectively,reaching the highest level currently available.

关键词： FLD lightweight multi-scale RSC blind materials

来源：评论

学校读者我要写书评

暂无评论

Göwfeda Novel Federated Network Intrusion Detection System

SSRN

引用

SSRN 2022年

Network intrusion detection systems are evolving into intelligent systems that perform data analysiswhile searching for anomalies in their environment. Indeed, the development of deep learningtechniques paved the way to build more complex and effective threat detection models. However,training those models may be computationally infeasible in most Edge or IoT devices. Currentapproaches rely on powerful centralized servers that receive data from all their parties – violatingbasic privacy constraints and substantially affecting response times and operational costs due to thehuge communication overheads. To mitigate these issues, Federated Learning emerged as a promisingapproach, where different agents collaboratively train a shared model, without exposing training datato others or requiring a compute-intensive centralized infrastructure. This work presents GöwFed,a novel network threat detection system that combines the usage of Gower Dissimilarity matricesand Federated averaging. Different approaches of GöwFed have been developed based on state-ofthe-art knowledge: (1) a vanilla version;and (2) a version instrumented with an attention ***, each variant has been tested using simulation oriented tools provided by TensorFlowFederated framework. In the same way, a centralized analogous development of the Federated systemsis carried out to explore their differences in terms of scalability and performance – across a set ofdesigned experiments/scenarios. Overall, GöwFed intends to be the first stepping stone towards thecombined usage of Federated Learning and Gower Dissimilarity matrices to detect network threats inindustrial-level networks. © 2022, The Authors. All rights reserved.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

AI-based Fuzzy Clustering System for Improving Customer Relationship Management 6

AI-based Fuzzy Clustering System for Improving Customer Rela...

引用

6th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2022

作者： Krishnareddy, Kr Aravinda, T.V. Nair, Kiran Patel, Umesh Kumar Sadvokasova, Gaukhar Shyamala Susan, V. Sjm Institute of Technology Department of Computer Science and Engineering India College Abu Dhabi School of Management. Department of Management United Arab Emirates Chaudhary Charan SIngh University Department of Bca Noida India International Education Corporation Department of Architecture Almaty050042 Kazakhstan A P C Mahalaxmi College for Women Department of Computer Science Tamilnadu Tuticorin India

ISBN: (数字)9781665469418

ISBN: (纸本)9781665469418

Artificial Intelligence (AI) is a technology that is becoming more and more widely recognized with the addition of technologies such as personal helpers and chatbots. To get the most out of AI, your company needs to understand how to implement it better. Today, AI enhances almost every business segment and Customer Relationship Management (CRM), which is the area that has the most benefit in enhancing a better customer experience. The existing literature does not provide sufficient empirical evidence of how social media technologies affect a company's distribution chain relationships. Today, Artificial Intelligence empowers almost every business segment and CRM, providing the greatest benefit in enhancing a better customer experience. The main purpose of this study is to show how to successfully implement chatbot in CRM using AI-based Fuzzy Clustering system (AI-FCS), how to integrate chatbot with CRM and how chatbots affect customer relationship management. From forecast lead scoring to service chatbots to customized marketing operations. Chatbots can provide tools to provide a highly productive and better, personalized customer experience to all employees. Chatbots are now easily accessible to everyone in your organization, analyzing data, predicting and planning the next steps, and automating tasks and decisions. Create an optimal control model for Customer Relationship Management using the optimal control theory, depending on the characteristics of customer relationship management. With this model, it can gain effective management insights into Customer Relationship Management for optimal new customer acquisition and existing customer retention strategies. © 2022 IEEE.

关键词： Fuzzy clustering

来源：评论

学校读者我要写书评

暂无评论

KOP-Fuzzer: A Key-Operation-based Fuzzer for Type Confusion Bugs in JavaScript Engines

KOP-Fuzzer: A Key-Operation-based Fuzzer for Type Confusion ...

引用

IEEE Annual International computer Software and Applications Conference (COMPSAC)

作者： Lili Sun Chenggang Wu Zhe Wang Yan Kang Bowen Tang State Key Laboratory of Computer Architecture Chinese Academy of Sciences Institute of Computing Technology University of Chinese Academy of Sciences Beijing China

ISBN: (数字)9781665488105

ISBN: (纸本)9781665488112

JavaScript (JS) engines are a core component of a lot of software, such as web browsers, PDF readers and flash players. There has been much research on finding JS engine vulnerabilities. However, due to the fact that a JS engine's input space is infinite and the vulnerability triggering conditions are extremely strict, it is difficult to generate test cases that are able to trigger deep logic errors in fuzzing. This paper aims to explore an approach which incorporates the human experience into fuzzing. We propose a Key-Operation-based Fuzzer (KOP-Fuzzer), to explore the type confusion vulnerabilities in JS engines. Based on human knowledge, we summarize a trigger model and extract key operations for type confusion vulnerabilities in JS engines. We use clustering to extract the key-operation methods from the engine's source code and develop a fuzzing system for key -operation mutation. Our experimental results demonstrate that the KOP-Fuzzer generates valid test cases with 1.5x fewer runtime errors, while also improving the edge coverage (2.082 %) and key-operation coverage (6.452 %), when compared with the state-of-the-art JS engine fuzzers. The KOP-Fuzzer discovered a total of 21 new bugs in ChakraCore and JavaScriptCore, where 16 of them are caused by the engine's incorrect handling of key operations and 5 of them are caused by type confusions.

关键词： Codes Runtime Conferences computer bugs Fuzzing Software Browsers

来源：评论

学校读者我要写书评

暂无评论

A Demonstration of an interactive Virtual Reality Prototype for Exploring the Cultural Heritage of Southern African Rock Art 20

A Demonstration of an interactive Virtual Reality Prototype ...

引用

22nd International Conference on Human-computer Interaction with Mobile Devices and Services

作者： Kasper Rodil Martin Kamp Larsen Mikkel Laursen Tobias Frost Andersen Weronika Korbutt Heike Winschiers-Theophilus Architecture & Media Technology Aalborg University Denmark Architecture and Media Technology Aalborg University Denmark Computer Science Namibia University of Science and Technology Namibia

ISBN: (纸本)9781450380522

In this paper, we describe an interactive implementation of a Virtual Reality prototype for creating rock art. The aim was to explore the possibilities of emerging technologies to safeguard the intangible cultural heritage of the San people in Namibia. The VR implementation combines an oral San tale narrative with the display of rock art paintings in a virtual cave. The user becomes a co-illustrator of the narrative being requested to paint or engrave the missing rock art in the cave. A user experience evaluation was conducted by eight San people from the Kalahari Desert. A logging system has been implemented to record detailed movements and interactions of the user throughout the system use. The interpretation of the logging data serves to understand user experiences and guide further system improvements.

关键词： Intangible Cultural Heritage Rock Art demonstration Virtual Reality Game

来源：评论

学校读者我要写书评

暂无评论

EskayApp: An Eskaya-Latin Script OCR Transliteration e-Learning Android Application using Supervised Machine Learning 21

EskayApp: An Eskaya-Latin Script OCR Transliteration e-Learn...

引用

Proceedings of the 5th International Conference on Digital technology in Education

作者： Max Angelo Dapitilla Perin Larmie Santos Feliscuzo Cherry Lyn Cando Sta. Romana Department of Computer Science Cebu Institute of Technology - University Philippines and College of Engineering Architecture and Industrial Design Bohol Island State University - Main Campus Philippines College of Computer Studies Cebu Institute of Technology - University Philippines

ISBN: (纸本)9781450384995

A language dies when the population that speaks it fails to pass it to their future generations. This study aims to address such problems for the Eskayas and Boholanos. The proposed EskayApp is an OCR Transliteration e-Learning Android Application that will serve as a tool to learn Eskaya. The app uses the k-Nearest Neighbors Algorithm (k-NN) for its business logic layer or backend and Supervised Machine Learning to create the application programming interface (API) for the said application. The Android application accesses the camera to capture an image of an Eskaya character and returns the Latin transliteration and the equivalent Latin character. The application got a 4.524-star rating through Google Play Store. After conducting testing, the machine learning model accuracy was 89.93% based on a 2x2 confusion matrix. A usability test was also conducted with members of the tribe as respondents. The usability review has 3 measurement items in which users can respond from 1 (Very Poor) to 5 (Excellent). The average for all the measurement items gathered from the users is 4.3-star and all the respondents want to use the e-Learning application again.

关键词：

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：