检索结果-内蒙古大学图书馆

50th Annual Conference of the IEEE Industrial Electronics Society, IECON 2024

作者： Huang, Wenli Deng, Ye Xin, Xiaomeng Zhao, Zhihong He, Jinbao Wang, Jinjun School of Electronic and Information Engineering Ningbo University of Technology Ningbo China School of Computing and Artificial Intelligence Southwestern University of Finance and Economics Chengdu China Institute of Artificial Intelligence and Robotic Xi’an Jiaotong University Xi’an China Research Institute of Intelligent Control and Systems Harbin Institute of Technology Harbin China School of Electronics and Information Engineering Ningbo University of Technology Ningbo China

ISBN: (纸本)9781665464543

In typical image inpainting tasks, the locations and shapes of damaged or masked areas are often random and irregular. Vanilla convolutions, commonly employed in learning-based inpainting models, treat all spatial features as valid and share parameters across different regions. This approach can struggle with irregular damage patterns, leading to inpainted results that may suffer from color discrepancies and blurriness. In this paper, we introduce a novel operator known as Semi-Independent Convolution (SIConv) to tackle this challenge. The proposed SIConv, on top of the regular convolution with shared weights, also introduces dynamic terms that assign their own independent weights to each part of the image, and the overall computation is formulated as a shared convolution parameter with an additional term to describe the local structure. Qualitative and quantitative experiments demonstrate that our method outperforms the state-of-the-art, yielding clearer, more coherent, and visually convincing inpainting results. © 2024 IEEE.

关键词： convolution Image inpainting semi-independent

来源：评论

学校读者我要写书评

暂无评论

Enhancing Communication Accessibility:UrSL-CNN Approach to Urdu Sign Language Translation for Hearing-Impaired Individuals

引用

Computer Modeling in Engineering & Sciences 2024年第10期141卷 689-711页

作者： Khushal Das Fazeel Abid Jawad Rasheed Kamlish Tunc Asuroglu Shtwai Alsubai Safeeullah Soomro Department of Computer Engineering Modeling Electronics and Systems EngineeringUniversity of CalabriaRende Cosenza87036Italy Department of Information Systems University of Management and TechnologyLahore54770Pakistan Department of Computer Engineering Istanbul Sabahattin Zaim UniversityIstanbul34303Turkey Department of Software Engineering Istanbul Nisantasi UniversityIstanbul34398Turkey Department of Computer Science COMSATS University IslamabadLahore CampusLahore54700Pakistan Faculty of Medicine and Health Technology Tampere UniversityTampere33720Finland Department of Computer Science College of Computer Engineering and Sciences in Al-KharjPrince Sattam Bin Abdulaziz UniversityP.O.Box 151Al-Kharj11942Saudi Arabia Second Department of Computer Science College of Engineering and ComputingGeorge Mason UniversityFairfaxVA 4418USA

Deaf people or people facing hearing issues can communicate using sign language(SL),a visual *** works based on rich source language have been proposed;however,the work using poor resource language is still *** other SLs,the visuals of the Urdu Language are *** study presents a novel approach to translating Urdu sign language(UrSL)using the UrSL-CNN model,a convolutional neural network(CNN)architecture specifically designed for this *** existingworks that primarily focus on languageswith rich resources,this study addresses the challenge of translating a sign language with limited *** conducted experiments using two datasets containing 1500 and 78,000 images,employing a methodology comprising four modules:data collection,pre-processing,categorization,and *** enhance prediction accuracy,each sign image was transformed into a greyscale image and underwent noise *** analysis with machine learning baseline methods(support vectormachine,GaussianNaive Bayes,randomforest,and k-nearest neighbors’algorithm)on the UrSL alphabets dataset demonstrated the superiority of UrSL-CNN,achieving an accuracy of ***,our model exhibited superior performance in Precision,Recall,and F1-score *** work not only contributes to advancing sign language translation but also holds promise for improving communication accessibility for individuals with hearing impairments.

关键词： Convolutional neural networks Pakistan sign language visual language

来源：评论

学校读者我要写书评

暂无评论

SSpose: Self-Supervised Spatial-Aware Model for Human Pose Estimation

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第11期5卷 5403-5417页

作者： Yu, Linfang Qin, Zhen Xu, Liqun Qin, Zhiguang Choo, Kim-Kwang Raymond University of Electronic Science and Technology of China Network and Data Security Key Laboratory of Sichuan Province Chengdu610054 China Industrial Research Institute Chengdu610213 China University of Electronic Science and Technology of China Network and Data Security Key Laboratory of Sichuan Province School of Information and Software Engineering Chengdu610054 China Industrial Research Institute Chengdu610213 China University of Texas at San Antonio Department of Information Systems and Cyber Security San AntonioTX78249 United States

Human pose estimation (HPE) relies on the anatomical relationships among different body parts to locate keypoints. Despite the significant progress achieved by convolutional neural networks (CNN)-based models in HPE, they typically fail to explicitly learn the global dependencies among various body parts. To overcome this limitation, we propose a spatial-aware HPE model called SSpose that explicitly captures the spatial dependencies between specific key points and different locations in an image. The proposed SSpose model adopts a hybrid CNN-Transformer encoder to simultaneously capture local features and global dependencies. To better preserve image details, a multiscale fusion module is introduced to integrate coarse- and fine-grained image information. By establishing a connection with the activation maximization (AM) principle, the final attention layer of the Transformer aggregates contributions (i.e., attention scores) from all image positions and forms the maximum position in the heatmap, thereby achieving keypoint localization in the head structure. Additionally, to address the issue of visible information leakage in convolutional reconstruction, we have devised a self-supervised training framework for the SSpose model. This framework incorporates mask autoencoder (MAE) technology into SSpose models by utilizing masked convolution and hierarchical masking strategy, thereby facilitating efficient self-supervised learning. Extensive experiments demonstrate that SSpose performs exceptionally well in the pose estimation task. On the COCO val set, it achieves an AP and AR of 77.3% and 82.1%, respectively, while on the COCO test-dev set, the AP and AR are 76.4% and 81.5%. Moreover, the model exhibits strong generalization capabilities on MPII. © 2024 IEEE.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Assessing AI Detectors in Identifying AI-Generated Code: Implications for Education

Assessing AI Detectors in Identifying AI-Generated Code: Imp...

引用

software Engineering: software Engineering Education and Training (ICSE-SEET), IEEE/ACM International Conference on

作者： Wei Hung Pan Ming Jie Chok Jonathan Leong Shan Wong Yung Xin Shin Yeong Shian Poon Zhou Yang Chun Yong Chong David Lo Mei Kuan Lim School of Information Technology Monash University Malaysia Subang Jaya Malaysia School of Computing and Information Systems Singapore Management University Singapore Singapore

ISBN: (数字)9798400704987

ISBN: (纸本)9798350352115

Educators are increasingly concerned about the usage of Large Language Models (LLMs) such as ChatGPT in programming education, particularly regarding the potential exploitation of imperfections in Artificial Intelligence Generated Content (AIGC) Detectors for academic misconduct. In this paper, we present an empirical study where the LLM is examined for its attempts to bypass detection by AIGC Detectors. This is achieved by generating code in response to a given question using different variants. We collected a dataset comprising 5,069 samples, with each sample consisting of a textual description of a coding problem and its corresponding human-written Python solution codes. These samples were obtained from various sources, including 80 from Quescol, 3,264 from Kaggle, and 1,725 from Leet-Code. From the dataset, we created 13 sets of code problem variant prompts, which were used to instruct ChatGPT to generate the outputs. Subsequently, we assessed the performance of five AIGC detectors. Our results demonstrate that existing AIGC Detectors perform poorly in distinguishing between human-written code and AI-generated code.

关键词： Training Codes Detectors Chatbots Encoding Programming profession software engineering

来源：评论

学校读者我要写书评

暂无评论

Using Sentiment Analysis to Explore the Accommodation Experience in the Sharing Economy through Topic Modeling 4

Using Sentiment Analysis to Explore the Accommodation Experi...

引用

4th International Conference on Advancements in computing, ICAC 2022

作者： Bandara, H.M.A.P. Charles, J. Lekamge, L.S. Department of Computing and Information Systems Sabaragamuwa University of Sri Lanka Sri Lanka Department of Physical Sciences and Technology Faculty of Applied Sciences Sri Lanka

ISBN: (纸本)9798350398090

The rapid proliferation of internet-based technology has made the sharing economy the next e-commerce business model. Recently, sharing economy lodging platforms have gained a significant market share in the tourism and lodging industry. Tourism and hospitality industries are now being significantly disrupted by Airbnb, an online lodging platform. For businesses and customers who utilize these accommodation platforms, online reviews serve as quality indicators, affecting their decisions to make a transaction. Sentiment analysis and text mining can be used to analyze these online reviews to identify various factors embedded in them that can influence how guests perceive lodging in the sharing economy. Peer-to-peer accommodation platforms can benefit from analyzing these aspects since they can utilize the results to streamline their operations and give customers better services. Current research on this domain has only identified a limited number of important factors, such as trust, quality, security, price, cleanliness, and indoor environmental quality. However, there can be many other factors that can affect the accommodation experience. These factors would require further attention. Therefore, in this study a dataset pertaining to the Airbnb platform was considered which contained a total of 401 964 review comments. Word cloud, frequency distribution, and topic modeling were used as data analysis techniques to identify various factors affecting accommodation experience. Results indicate that factors including location, safety, host-guest interaction, amenities, proximity to restaurants and transit options, and apartment uniqueness can be primarily taken into account to give superior services to their clients. © 2022 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

An Exemplifying Study of the E-Learning Adoption during Covid-19 Pandemic in Oman

An Exemplifying Study of the E-Learning Adoption during Covi...

引用

2022 Applied Informatics International Conference, AiIC 2022

作者： Al Maashri, Issaa Mohamed Hassan Ghosh, Shounak Bukar, Umar Ali University of Technology and Applied Sciences Academic Electronic Systems Center Muscat Oman School of Computing and Technology Malaysia Universiti Putra Malaysia Faculty of Computer Science and Information Technology Malaysia

ISBN: (数字)9781728184289

ISBN: (纸本)9781728184289

As a consequence of the Covid-19 outbreak, students are required to stay at home to prevent the virus from spreading. This has resulted in a quick acceptance of online learning, as students and faculty cannot participate in in-class activities. This study examines the determinants affecting E-Learning uptake in Oman during the Covid-19 outbreak, using 223 student responses and structural equation modeling (SEM). Four hypotheses were supported, while two were rejected. Specifically, perceived ease of use, perceived usefulness, and institutional support affect behavioral intention to adopt E-Learning. However, infrastructure support and privacy risk, on the other hand, were not. Thus, this research serves as a springboard for higher education officials to increase the use of E-Learning and adjust to student hurdles for students to comprehend and effectively use the system. © 2022 IEEE.

关键词： E-learning

来源：评论

学校读者我要写书评

暂无评论

Assessing AI Detectors in Identifying AI-Generated Code: Implications for Education

arXiv

引用

arXiv 2024年

作者： Pan, Wei Hung Chok, Ming Jie Wong, Jonathan Leong Shan Shin, Yung Xin Poon, Yeong Shian Yang, Zhou Chong, Chun Yong Lo, David Lim, Mei Kuan School of Information Technology Monash University Malaysia Subang Jaya Malaysia School of Computing and Information Systems Singapore Management University Singapore Singapore

Educators are increasingly concerned about the usage of Large Language Models (LLMs) such as ChatGPT in programming education, particularly regarding the potential exploitation of imperfections in Artificial Intelligence Generated Content (AIGC) Detectors for academic misconduct. In this paper, we present an empirical study where the LLM is examined for its attempts to bypass detection by AIGC Detectors. This is achieved by generating code in response to a given question using different variants. We collected a dataset comprising 5,069 samples, with each sample consisting of a textual description of a coding problem and its corresponding human-written Python solution codes. These samples were obtained from various sources, including 80 from Quescol, 3,264 from Kaggle, and 1,725 from LeetCode. From the dataset, we created 13 sets of code problem variant prompts, which were used to instruct ChatGPT to generate the outputs. Subsequently, we assessed the performance of five AIGC detectors. Our results demonstrate that existing AIGC Detectors perform poorly in distinguishing between human-written code and AI-generated code. Copyright © 2024, The Authors. All rights reserved.

关键词： software engineering

来源：评论

学校读者我要写书评

暂无评论

Street Light Cum Garbage System Optimal Design Based on IOT 2

Street Light Cum Garbage System Optimal Design Based on IOT

引用

2nd International Conference on Emerging Trends in information technology and Engineering, ic-ETITE 2024

作者： Rajesh, G. Deepa, J. Ezilarasan, M.R. Syed Fiaz, A. Siva Rama Lingham, N. Jagannathan, J. Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Chennai India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Information Technology Chennai India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Electronics and Communication Engineering Chennai India School of Computer Science Engineering and Information Systems Vellore Institute of Technology Department of Software and Systems Engineering Vellore India

ISBN: (纸本)9798350328202

Street lights currently use more energy than other types of lighting because of an inefficient mechanism that makes the bulbs use a lot of electricity. The suggested approach uses various sensors on intelligent streetlights to keep an eye on and manage the lights. It has sensors for measuring temperature, brightness, and power that control dimming levels and keep track of status. One Zigbee network serves as the connection point for these lights. In the modification, a cloud- and IoT-based installation was made. Through Zigbee -based data transmission, sensor values are recorded on a distant server known as the Cloud. Additionally, it lowers electricity theft. We include a trash can notice in addition to this street light idea. When the garbage can is whole, a machine automatically notifies the business as people approach the sun, and the brightness of the street lights changes or is increased. © 2024 IEEE.

关键词： Light emitting diodes

来源：评论

学校读者我要写书评

暂无评论

Few-shot Object Detection Algorithm Based on YOLOv8-Mamba-Like Linear Attention 16

Few-shot Object Detection Algorithm Based on YOLOv8-Mamba-Li...

引用

16th International Conference on Communication software and Networks, ICCSN 2024

作者： Wang, Hongliang Wang, Kaizhu Ji, Binglong Deng, Changyi Shenyang Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Liaoning Province Human- Computer Interaction System Engineering Research Center Based on DigitTwin Shenyang China Shenyang Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Shenyang China Institute of Software China Industrial Control Systems Cyber Emergency Response Team Beijing China

ISBN: (纸本)9798331506322

In the production and assembly process, the accuracy of detection is usually low due to limited resources and small quantities. In this paper, we propose a few-shot learning method for object detection based on the combination of YOLOv8 and Mamba-Like Linear Attention (MLLA) module. This method utilizes a high-pixel camera to capture the shape and size of the workpiece. By consistency-based mutual augmentation structure for few-shot samples data augmentation. By introducing the efficient and lightweight MLLA module, the model's speed and accuracy in object detection and segmentation tasks on mobile devices are significantly improved. Specifically, MLLA mainly integrates the two key elements of 'forget gate' and 'block design' in Mamba, and MLLA replaces forget gate by using position coding (RoPE) to provide necessary location information while maintaining parallel computation and fast inference speed. This makes MLLA improves the accuracy of detection and segmentation recognition. Experimental results show that compared to the original YOLOv8 model, the model with the MLLA module exhibits improvements in segmentation precision and recognition accuracy. This method demonstrates high accuracy and robustness in workpiece recognition, making it suitable for real-time industrial applications. © 2024 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Aspect-Based Sentiment Analysis on Amharic Text for Evaluating Ethio-Telecom Services 2

Aspect-Based Sentiment Analysis on Amharic Text for Evaluati...

引用

2nd International Conference on Emerging Trends in information technology and Engineering, ic-ETITE 2024

作者： Tesfa, Tarikwa Belete, Befikadu Abera, Samuel Mohapatra, Sudhir Kumar Das, Tapan Kumar Addis Ababa Science and Technology University Department of Software Engineering Addis Ababa Ethiopia Ethio Telecom Services Addis Ababa Ethiopia Sri Sri University Faculty of Emerging Technologies Cuttack India School of Computer Science Engineering and Information Systems Vellore Institute of Technology Vellore India

ISBN: (纸本)9798350328202

People are increasingly expressing their views and opinions about a company's goods or service on social media these days. For all types of businesses and organizations, sentiment analysis in text can be used to find prospective customers and obtain quick feedback on the services or goods they provided. As a result, the organization has a better chance and opportunity to meet the needs of the consumer. Using sentiment analysis, we may extract important information from the thoughts and emotions of an organization's supporters and clients. It examines natural language content produced about services and goods. Detailed opinion mining at the aspect/feature level to serve consumer and organizational needs. In this study, three different machine learning algorithms, these are Naïve Bayes (NB), Support Vector Machine (SVM), and K- Nearest Neighbor (KNN) are used to build the proposed aspect-based sentiment analysis model from the customer comments in Amharic text which is collected from Ethio-telecom official Facebook page. The collected data is annotated into sentiment polarity and aspect-based sentiment classes by the help of five annotators. After data annotation, different preprocessing tasks were implemented. Bag of words and TF-IDF word representation techniques were used to represent each unique word to their vector representation. The experiment was conducted on those three models and the result was validated. The labeled aspects were not balanced so that a SMOTE class imbalance handling technique was employed to the dataset. Finally, SVM model trained with TF-IDF word representation technique with SMOTE oversampled dataset has achieved the highest accuracy result of 98% as compared to NB and KNN. © 2024 IEEE.

关键词： Sentiment analysis

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：