检索结果-内蒙古大学图书馆

作者： Nazir, Faria Majeed, Muhammad Nadeem Ghazanfar, Mustansar Ali Maqsood, Muazzam Department of Software Engineering University of Engineering and Technology Taxila Taxila Pakistan Department of Data Science University of the Punjab Lahore Pakistan School of Architecture Computing and Engineering University of East London London United Kingdom Department of Computer Science COMSATS University Islamabad Attock Campus Pakistan

Nowadays, the demand for language learning is increasing because people need to communicate with other people belonging to different regions for their business deals, study, etc. During language learning, a lot of pronunciation mistakes occur due to unfamiliarity with a new language and differences in accent. In this paper, we perform speech mistakes analysis using deep feature-based clustering. We proposed two novel methods for speech analysis, one to deal with phonemic errors (confusing phonemes) and the other to deal with the prosodic errors (partially changed pronunciation variation of phones). For accurate and efficient language learning, it is important to learn both phonemic as well as prosodic error corrections. In our first method, we perform speech analysis by combining deep CNN features and clustering algorithm to detect the phonemic errors. We classify the phonemes using K-nearest neighbor, Naïve Bayes, and support vector machine (SVM). We perform experiments on the six most frequently mispronounced confusing pairs of Arabic to handle phonemic errors and achieve an accuracy of 94%. In our second method, we proposed the unsupervised phone variation model (PVM) to detect prosodic errors. In PVM, each phone is extended to represent the different types of pronunciation variation of that phone with different proficiency levels. We use an Arabic dataset of 28 individual phones for speech analysis and provide feedback based on the variation of each phone and achieves an accuracy of 97%. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Error correction

来源：评论

学校读者我要写书评

暂无评论

LIAS: A Lightweight Incentive Authentication Scheme for Forensic Services in IoV

LIAS: A Lightweight Incentive Authentication Scheme for Fore...

引用

作者： Zhang, Mingyue Zhou, Junlong Cong, Peijin Zhang, Gongxuan Zhuo, Cheng Hu, Shiyan Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing210094 China Institute of Computing Technology Chinese Academy of Sciences State Key Laboratory of Computer Architecture Beijing100190 China Zhejiang University Department of Information Science and Electronic Engineering Hangzhou310027 China University of Southampton School of Electronics and Computer Science SouthamptonSO17 1BJ United Kingdom

Internet of Vehicles (IoV) has become an indispensable data sensing and processing platform in Internet of Things (IoT) for intelligent transportation. The mounted cameras on the vehicles along with the fixed roadside cameras are utilized to provide pictorial services for IoV users and law enforcement agencies. For such forensic services, ensuring the security and privacy of vehicles while guaranteeing the efficiency of data transmission among vehicles is important. In this paper, we propose a lightweight incentive authentication scheme (LIAS) for forensic services in IoV. LIAS is developed on a three-tier architecture containing cloud layer, fog layer, and user layer. LIAS uses pairing-free certificateless signcryption, pseudonym update mechanism, and incentive mechanism to realize a secure anonymous authentication efficiently. We conduct correctness and security analysis, as well as performance analysis and evaluation to validate the high security and efficiency of LIAS. Experimental results reveal that, the communication and computation overheads as well as the message delay and packet loss of LIAS are much lower than those of state-of-the-art techniques. Note to Practitioners - This paper is motivated by the security and privacy issues of forensic services in IoV for intelligent transportation. Our goal is to improve the security and privacy of vehicles while guaranteeing the lightweight and incentive of data transmission among the vehicles. Fog-assisted IoV is introduced to fully utilize the capacities of near-user edge devices as well as the connections between fog nodes and devices. However, it still faces the difficulties in ensuring vehicles' security and privacy. Moreover, vehicles' information dissemination could be easily monitored because of the unavoidable defect of wireless communication. Thereby, it is essential to guarantee the security and privacy of vehicles while enhancing the efficiency of vehicles' data transmission during the forensic service.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

A Multiband Tri-branch Monopole Antenna Base on Step Impedance Technique for WLAN, WiMAX, 5G technology, and IoT Application 20

A Multiband Tri-branch Monopole Antenna Base on Step Impedan...

引用

20th International Conference on Electrical Engineering/Electronics, computer, Telecommunications and Information technology, ECTI-CON 2023

作者： Tangjitjetsada, Maleeya Suangun, Thanakarn Chanwattanapong, Wanchalerm Mahatthanajatuphat, Chatree Phimthai, Kanyanat Akkaraekthalin, Prayoot Faculty of Engineering and Architecture Department of Electronics and Telecommunication Engineering Nonthaburi Thailand University of Phayao Faculty of Engineering Department of Electrical Engineering Phayao Thailand Rajamangala University of Technology Thanyaburi Faculty of Engineering Department of Electronics and Telecommunications Pathum Thani Thailand Faculty of Engineering Department of Electrical and Computer Engineering Bangkok Thailand

ISBN: (纸本)9798350310467

A multiband tri-branch monopole antenna is presented. The antenna structure is constructed of radiating patches with three branches. It is fed by a microstrip transmission line. Essentially, the antenna is a simple structure created by a step impedance technique. In addition, the antenna can be separately regulated for each operational frequency band of 2.44 GHz, 3.36 GHz, and 5.52 GHz by the height of a central patch, a right patch with a thin strip line, and a small patch on the left, respectively. The antenna is manufactured on a size of 50x35 mm2 FR4 substrate with a thickness of 0.8 mm and a permittivity of 4.3. The suggested antenna is appropriate for network board internet of things (NB-IoT) technology working at 2.4 GHz/5.2 GHz/5.8 GHz (WLAN), 3.5 GHz (WiMAX), and 2.3 GHz/2.6 GHz/3.5 GHz (5G technology). The antenna's radiation pattern is omnidirectional, and its average gain is approximately 2dBi. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

NSGA-III and MOACO-based decision-making framework for optimizing time, cost, quality, and carbon footprint in bridge construction: a hybrid approach

引用

Asian Journal of Civil Engineering 2025年第6期26卷 2331-2347页

作者： Behera, Amir Prasad Chauhan, Trupti Ravindra Manjunath, T.C. Chandini, Shaik Chandrakar, Vinay Kumar Singh Verma, Swapnil School of Management Centurion University of Technology and Management Odisha Paralakhemundi India Department of Design Manipal School of Architecture and Planning Manipal Academic of Higher Education Manipal Karnataka Udupi India Department of Computer Science and Engineering Rajarajeswari College of Engineering Bengaluru India Gulf American University Fajairah United Arab Emirates School of Civil Engineering Faculty of Engineering and Technology Madhyanchal Professional University Bhopal India Synviro Solutions Pvt. Ltd. Indore India

This study presents a hybrid optimization framework combining Non-dominated Sorting Genetic Algorithm III (NSGA-III) and Multi-Objective Ant Colony Optimization (MOACO) to optimize time, cost, quality, and carbon footprint in bridge construction projects. The construction industry faces growing demands for sustainable practices while maintaining efficiency and cost-effectiveness. The proposed framework addresses these challenges by leveraging NSGA-III’s capability to maintain diversity in Pareto-optimal solutions and MOACO’s strength in refining local solutions through pheromone-based exploration. The framework models construction activities with multiple execution modes, each characterized by specific costs, durations, quality levels, and carbon emissions. Four objective functions are developed to minimize time, cost, and carbon footprint while maximizing quality. Constraints such as precedence relationships and resource availability ensure realistic project planning. The framework is validated through a case study of a 300-m reinforced concrete girder bridge, using input data derived from practical project scenarios. Results demonstrate the hybrid framework’s superior performance compared to standalone NSGA-III, MOACO, Multi-Objective Teaching-Learning-Based Optimization, and Multi-Objective Particle Swarm Optimization. Trade-off and correlation analyses provide actionable insights, revealing relationships between objectives and enabling informed decision-making. This study contributes to sustainable project management by integrating advanced optimization techniques and practical decision-support tools. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Hybrid optimization MOACO Multi-objective decision-making NSGA-III Sustainable bridge construction

来源：评论

学校读者我要写书评

暂无评论

Advanced IOT Traffic Light Control System 5

Advanced IOT Traffic Light Control System

引用

5th International Conference on Advances in Computational Tools for Engineering Applications, ACTEA 2023

作者： Hamad, Martin Abou El Hajj, Antonio Daou, Roy Abi Zeid Hayek, Ali Haidar, Gaby Abou Lebanese German University Faculty of Public Health Biomedical Technologies Department Lebanon MART Learning Education and Research Center Lebanon University of Kassel Department of Computer Architecture and System Programming Kassel Germany American University of Science and Technology Engineering Faculty Zahle Lebanon

ISBN: (纸本)9798350309959

For several years, traffic congestion has been a major problem in big cities where the number of cars and different means of transportation has been increasing significantly. The problem of congestion is becoming more and more critical, and if not treated smartly this issue will negatively affect drivers by wasting time and fuel gas while waiting for hours in lanes. This paper presents a new and smart way to mitigate this issue in an affordable cost, minimum processing power, and low power consumption. This concept takes into consideration the majority of the cases that may cause congestion and presents a smart and accurate outputs to ease traffic flow leading to the prediction of the peak hours of traffic congestion for smarter control. A model is designed to study the case of a four lanes crossroad with two traffic lights and two LCD monitors. The strategy in reading data is divided into two parts: real data from sensors and pre collected data from google maps to create a kind of a predicted pattern over a certain time interval. The responsiveness of the system is analyzed thoroughly, and the accuracy of all possible cases is carefully considered and evaluated. Each part of the system was tested alone, and the overall system is still in an ongoing testing phase. The results have shown minimum faulty errors and accepted outputs that can lead to safe traffic control decisions. Finally, integrating more IoT devices and sensors between V2V, V2P, V2I with the help of artificial intelligence will definitely optimize this system with higher accuracy. © 2023 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Enhanced Federated Learning for Iot Systems

SSRN

引用

SSRN 2023年

作者： Mora-Gimeno, Francisco José Elouali, Aya Mora, Higinio Mora Szymanski, Julian Department of Computer Science Technology and Computation University of Alicante Alicante Spain Department of Computer Architecture Faculty of Electronics Telecommunications and Informatics Gdańsk University of Technology Gdańsk Poland

Federated learning consists on training several local models on edge devices where data is collected. These models are then shared with the cloud where the general model is calculated and transmitted back to the edge. This process is repeated several times until the general model achieves the desired accuracy. This technique permits training a model on the largest possible quantity of data without having to share the device’s private data with other devices or the cloud. However, the main drawback of this method is transmitting big size models multiple time on the network from and to every edge device participating in the training. In this paper, we propose a data transmission reduction method in federated learning context which, based on data similarity, reduces the amount of weights to be transmitted to the cloud. Several experiments has been performed to prove the effectiveness of the method and define the best components to use it such as data representation method and change calculation method. The performed experiments revealed that the proposed solution reduces data transmission up to 75% while having only 0.02% accuracy deterioration © 2023, The Authors. All rights reserved.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Quantitative Evaluation to Detect Crack Depth in Beams Based on CNN-RNN-LSTM Approach

Quantitative Evaluation to Detect Crack Depth in Beams Based...

引用

2023 International Conference on Self Sustainable Artificial Intelligence Systems, ICSSAS 2023

作者： Gandhi, Mohammad Asif Swaminathen, A.N. Patil, Deepak T. Ravitheja, A. Kamali, R. Rajput, Akshay Anjuman-I-Islam's Kalsekar Technical Campus Department of Mechanical Engineering Maharashtra Panvel India Adi Shankara Institute of Engineering and Technology Kerala India Bharati Vidyapeeth College of Architecture Maharashtra Navi Mumbai India Svr Engineering College Department of Civil Engineering Andhra Pradesh Kurnool India Knowledge Institute of Technology Department of Computer Science and Engineering Tamilnadu Salem India Graphic Era Deemed to Be University Department of Computer Science & Engineering Uttarakhand Dehradun India

ISBN: (纸本)9798350300857

In this study, the proposed approach offers a novel hybrid image-based deep learning method for autonomous concrete fracture identification. Cracks are easier to spot and false positives are reduced with hybrid images that include visual and infrared thermography data. In specifically, a Visible and infrared camera as well as a line laser make up a hybrid imaging system for spatially scanning unmanned vehicles can efficiently assess large-scale concrete-made constructions like bridges and dams. Crack detection is a commonplace task in many industrial domains, however the current method of relying on expert judgment is typically laborious, time consuming, and inaccurate. The practical benefits of automated decision-making increase as the size of the target concrete construction grows. Cracks can be automatically identified and seen using the proposed method. Preprocessing, segmentation, feature extraction, and model training are the four components of the proposed method. It performs clever edge recognition, scaling, and greyscale conversion as part of its preparation. Improved K-Means segmentation is used for the separation. It employs GLCM for feature extraction, and CNN-RNN-LSTM for model training. The new method is compared to two established approaches, CNN-RNN and CNN-LSTM, and is found to be superior. © 2023 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Leveraging Multimodal Shapley Values to Address Multimodal Collapse and Improve Fine-Grained E-Commerce Product Classification

Leveraging Multimodal Shapley Values to Address Multimodal C...

引用

International Conference on Machine Learning and Applications (ICMLA)

作者： Ajibola Obayemi Khuong Nguyen School of Architecture Technology and Engineering University of Brighton Brighton UK Department of Computer Science Royal Holloway University of London London UK

ISBN: (数字)9798350374889

ISBN: (纸本)9798350374896

Multimodal models can experience multimodal collapse, leading to sub-optimal performance on tasks like fine-grained e-commerce product classification. To address this, we introduce an approach that leverages multimodal Shapley values (MM-SHAP) to quantify the individual contributions of each modality to the model's predictions. By employing weighted stacked ensembles of unimodal and multimodal models, with weights derived from these Shapley values (MM-SHAP), we enhance the overall performance and mitigate the effects of multimodal collapse. Using this approach we improve previous results(f1-score) from 0.67 to 0.79.

关键词： Machine learning Predictive models Electronic commerce

来源：评论

学校读者我要写书评

暂无评论

Building Hierarchical Tree Representations Using Homological-Based Tools 19th

Building Hierarchical Tree Representations Using Homological...

引用

19th International Conference on computer Analysis of Images and Patterns, CAIP 2021

作者： Díaz-del-Río, Fernando Sanchez-Cuevas, Pablo Molina-Abril, Helena Real, Pedro Moron-Fernández, María José Department of Computer Architecture and Technology University of Seville Seville Spain Seville Spain Seville Spain

ISBN: (纸本)9783030891305

A new algorithm for computing the α -tree hierarchical representation of a grey-scale digital image is presented here. The technique is based on an efficient simplified version of the Homological Spanning Forest (HSF) for encoding homological and homotopy-based information of binary digital images. We create one Adjacency Tree (AdjT) for each intensity contrast in a fully parallel manner. These trees, which define a Contrast Adjacency Forest (CAdjF), are in turn transversely interconnected by another couple of trees: the classical α -tree, and a new one complementing it, called here the α∗ -tree. They convey the information of the contours and the flat regions of the original color image, plus the relations between them. Using both the α and α∗ -trees, this new topological representation prevents some classical drawbacks that appear when working with a single tree. An implementation in OCTAVE/MATLAB validates the correctness of our algorithm. © 2021, Springer Nature Switzerland AG.

关键词： Forestry

来源：评论

学校读者我要写书评

暂无评论

Prediction of cognitive scores by joint use of movie-watching fMRI connectivity and eye tracking via Attention-CensNet

引用

Psychoradiology 2023年第1期3卷 193-202页

作者： Jiaxing Gao Lin Zhao Tianyang Zhong Changhe Li Zhibin He Yaonei Wei Shu Zhang Lei Guo Tianming Liu Junwei Han Xi Jiang Tuo Zhang School of Automation Northwestern Polytechnical UniversityXIi'an 710072China Cortical Architecture Imaging and Discovery Laboratory Department of Computer Science and Bioimaging Research CenterThe University of GeorgiaAthensGA 30602USA School of Computer Science Northwestern Polytechnical UniversityXi'an 710072China School of Life Science and Technology MOE Key Laboratory for NeuroinformationUniversity of Electronic Science and Technology of ChinaChengdu 611731China

Background:Brain functional connectivity under the naturalistic paradigm has been shown to be better at predicting individual behaviors than other brain states,such as rest and doing ***,the state-of-the-art methods have found it difcult to achieve desirable results from movie watching paradigm functional magnetic resonance imaging(mfMRI)-induced brain functional connectivity,especially when there are fewer *** other physical measurements into the prediction method may enhance *** tracking,becoming popular due to its portability and lower expense,can provide abundant behavioral features related to the output of human's cognition,and thus might supplement the mfMRI in observing participants'subconscious ***,there are very few studies on how to effectively integrate the multimodal information to strengthen the performance by a unified ***:A fusion approach with mfMRI and eye tracking,based on convolution with edge-node switching in graph neural networks(CensNet),is proposed in this ***:In this graph model,participants are designated as nodes,mfMRI derived functional connectivity as node features,and different eye-tracking features are used to compute similarity between participants to construct heterogeneous graph *** taking multiple graphs as different channels,we introduce squeeze-and-excitation attention module to CensNet(A-CensNet)to integrate graph embeddings from multiple channels into ***:The proposed model outperforms those using a single modality and single channel,and state-of-the-art ***:The results indicate that brain functional activities and eye behaviors might complement each other in interpreting trait-like phenotypes.

关键词： functional connectivity naturalistic stimulus eye movement CensNet attention

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：