检索结果-内蒙古大学图书馆

5th International Conference on Intelligent Communication Technologies and Virtual Mobile Networks, ICICV 2024

作者： Sriman, B. Stephi, Adlin Annie Silviya, S.H. Sangeetharani, M. Shreya, B. Sivakumar, S. Rajalakshmi Institute of Technology Department of Computer Science and Engineering Chennai India Sree Sastha Institute of Engineering and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350385649

Textual data is a fundamental element of human communication and information exchange, playing a pivotal role in a wide array of applications across various domains. However, the digital age has ushered in an era of unprecedented data growth, resulting in the need for efficient storage, transmission, and processing of vast amount of text. Lossless text compression techniques emerge as a vital solution to this challenge, offering the ability to compactly represent textual content without compromising any information. This research study explores the lossless text compression algorithms by investigating the underlying principles, performance, and applications. © 2024 IEEE.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

U-YOLOv3: A Model Focused on Underwater Object Detection

Informatica (Slovenia)

引用

Informatica (Slovenia) 2025年第6期49卷 87-102页

作者： Sarkar, Pratima De, Sourav Gurung, Sandeep Department of Computer Science and Engineering Sikkim Manipal Institute of Technology Majhitar India Sikkim Manipal University Gangtok India Department of Computer Science and Engineering Techno International New Town Newtown Kolkata India Department of Computer Science and Engineering Cooch Behar Government Engineering College Vill-Harinchowrah West Bengal Cooch Behar736170 India

Underwater image enhancement and object detection has great potential for studying underwater environments. It has been utilized in various domains, including image-based underwater monitoring and Autonomous Underwater Vehicle (AUV)-driven applications such as underwater terrain surveying. It has been observed that underwater images are not clear due to several factors such as low light, the presence of small particles, different levels of refraction of light, etc. Extracting high-quality features from these images to detect objects is a significant challenging task. To mitigate this challenge, MIRNet and the modified version of YOLOv3 namely Underwater-YOLOv3 (U-YOLOv3) is proposed. The MIRNet is a deep learning-based technology for enhancing underwater images. while using YOLOv3 for underwater object detection it lacks in detection of very small objects and huge-size objects. To address this problem proper anchor box size, quality feature aggregation technique, and during object classification image resizing is required. The proposed U-YOLOv3 has three unique features that help to work with the above specified issue like accurate anchor box determination using the K-means++ clustering algorithm, introduced Spatial Pyramid Pooling (SPP) layer during feature extraction which helps in feature aggregation, and added downsampling and upsampling to improve the detection rate of very large and very small size objects. The size of the anchor box is crucial in detecting objects of different sizes, SPP helps in aggregation of features, while down and upsampling changes sizes of objects during object detection. Precision, recall, F1-score and mAP are used as assessment metrics to assess proposed work. The proposed work compared with SSD, Tiny-YOLO, YOLOv2, YOLOv3, YOLOv4, YOLOv5, KPE-YOLOv5, YOLOv7, YOLOv8 and YOLOv9 single stage object detectors. The experiment on the Brackish and Trash ICRA19 datasets shows that our proposed method enhances the mean average precision for b

关键词： Underwater imaging

来源：评论

学校读者我要写书评

暂无评论

A hybrid convolutional neural network for sarcasm detection from multilingual social media posts

引用

Multimedia Tools and Applications 2025年第16期84卷 15867-15895页

作者： Pandey, Rajnish Kumar, Abhinav Singh, Jyoti Prakash Tripathi, Sudhakar Department of Information Technology IET Dr Rammanohar Lohia Awadh University Ayodhya Uttar Pradesh Faizabad India Department of Computer Science and Engineering Motilal Nehru National Institute of Technology Allahabad Prayagraj211004 India Department of Computer Science and Engineering National Institute of Technology Patna Patna India Department of Information Technology Rajkiya Engineering College Uttar Pradesh Ambedkarnagar India

Sarcasm in social media postings significantly impacts automated sentiment extraction due to its potential to invert the overall polarity of phrases. It poses a formidable challenge in extracting genuine sentiments from informal multilingual comments about events or individuals, especially when the message is in a multilingual form. The prevalence of noisy datasets further complicates this task. This work proposes a hybrid convolutional neural network (CNN-H) model to classify sarcastic and non-sarcastic statements. Unlike traditional CNN models, CNN-H integrates character and word embeddings, enhancing its capacity to handle the complexities of multilingual content. Evaluation on five benchmark datasets, including English (news headlines, Ghosh Tweet, Riloff Tweet), Hindi, and multilingual Hindi-English (Hinglish), demonstrates the superior performance of CNN-H. The model surpasses various state-of-the-art conventional machine-learning and deep-learning models, including CNN, achieving an impressive F1-score of 93.0% on the multilingual dataset. The incorporation of character and word embeddings proves pivotal in mitigating the impact of noisy datasets, prevalent in social media posts. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Bald Eagle Search Algorithm with Hierarchical Deep Learning for Internet of Things Assisted Sleep Quality Recognition

引用

SN computer science 2024年第5期5卷 1-10页

作者： Duhayyim, Mesfer Al Sharif, Mahir Mohammed Munjal, Muskaan Hilal, Anwer A. Department of Computer Science College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz University Al-Kharj 16273 Saudi Arabia Department of Computer Science Faculty of Computer Science and Information Technology Omdurman Islamic University Omdurman Sudan Computer Engineering Thapar Institute of Engineering and Technology Punjab Patiala India Department of Information System Faculty of Computer Science and Information Technology Omdurman Islamic University Omdurman Sudan

Sleep quality prediction in Internet of Things (IoT) involves leveraging a system of interrelated devices to gather as well as analyse related data. Smart devices like wearable devices or smart mattresses endlessly monitor many parameters such as body movement, heart rate, and environmental situations in bedroom. Real-time recommendations and feedback transported to consumers, allowing them to create informed lifestyle changes for superior sleep hygiene. As IoT ecosystem continues to develop, a combination of various data streams as well as classy analytics holds assurance for further refining sleep quality forecasts and improving overall well-being. The article designs a Bald Eagle Search Algorithm with Hierarchical Deep Learning for Internet of Things Assisted Sleep Quality Recognition (BESHDL-SQP) technique. The purpose of the BESHDL-SQP technique is to recognize and classify the quality of the sleep level in the IoT environment. In the presented BESHDL-SQP technique, the preliminary stage of data pre-processing using min–max normalization involved to normalize the input data. For predicting sleep quality, hierarchical long short-term memory (LSTM) technique exploited. Lastly, BES model utilized for optimal hyperparameter selection of LSTM method which helps in attaining enhanced results. To validate better performance of BESHDL-SQP technique, a huge range of simulation analysis is carried out. The extensive results stated that the BESHDL-SQP technique exhibits supreme performance over other models. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Bald eagle search Internet of things LSTM Sleep quality recognition Smart devices

来源：评论

学校读者我要写书评

暂无评论

A cross-lingual syntactic investigation of gender bias and stereotyping in GPT-4o: English vs Hindi

AI and Ethics

引用

AI and Ethics 2024年第3期5卷 2497-2514页

作者： Arora, Suvrat Srivastava, Aditi Computer Science and Engineering Department Thapar Institute of Engineering and Technology Patiala India

Beneath the vast capabilities and potentials of AI systems lie some crucial predicaments. Though Large Language Models (LLMs) such as ChatGPT have proven to be transformative, the ingrained gender biases and stereotypes in such models are a societal concern. The propagation of such biases is detrimental to men, women and all gender-diverse groups alike. Addressing these issues is imperative for ensuring equity and inclusivity. Thus, there is a need to identify and analyze such biases in LLMs and drift these models towards Responsible AI. In this research, we endeavor to investigate gender biases and occupation-based stereotyping in ChatGPT (GPT-4o), focusing on a comparative analysis between English and Hindi language responses. The dataset curated for this analysis comprises ChatGPT’s responses to selected gender-neutral prompts. The gender-determining syntactic structure of languages is employed as a metric for bias determination. In the English language, pronouns are the gender-determining part of speech, whereas, in Hindi, verb conjugations determine the gender of the subject. This formed the foundation of the gender bias identification in this study. We observe that ChatGPT tends to incline towards yielding male nouns in both languages. The biases have a higher degree of being male-skewed in English than in Hindi. In addition, the investigation further confirms that ChatGPT harbours occupation-based stereotypes. These biases and stereotypes do not necessarily depict the present disparities in society, indicating that ChatGPT reflects the biases of its training data. Conclusively, this research serves as a foundation for the identification of AI-generated biases and, subsequently, their annihilation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing real time object detection for autonomous driving using YOLO-NAS algorithm with CLEO optimizer

引用

International Journal of Information technology (Singapore) 2025年第3期17卷 1321-1328页

作者： Nandal, Priyanka Pahal, Sudesh Malik, Sunesh Sehrawat, Neetu Mamta Department of Computer Science and Engineering Maharaja Surajmal Institute of Technology New Delhi India Department of Electronics and Communication Engineering Maharaja Surajmal Institute of Technology New Delhi India Department of Information Technology Maharaja Surajmal Institute of Technology New Delhi India Department of Computer Science and Engineering Panipat Institute of Engineering & Technology New Delhi India

For autonomous driving to operate in a safe and effective manner, efficient and precise object detection is essential. The efficacy of the network model is heavily challenged because of the high-speed movement of vehicles and the dynamic nature of the surrounding environment that need the detection of objects of various scales. With notable improvements over earlier iterations, the You Only Look Once-Neural Architecture Search (YOLO-NAS) algorithm is a strong contender for improving real-time object recognition in autonomous vehicles. YOLO-NAS integrated with chimpanzee leader election optimization (CLEO) has the potential to greatly enhance the safety and dependability of autonomous driving systems by utilizing its sophisticated capabilities and skill fully combining it with the vehicle’s perception system. The BDD100K dataset serves as the training and evaluation set for our suggested technique. The YOLO-NAS model with CLEO optimizer achieves mean average precision (mAP) of 83%, which is significantly higher than the mAP of 65.7% attained by the YOLO-NAS model without the optimizer. This improvement highlights the effectiveness of the CLEO optimizer in enhancing detection precision. The proposed approach was compared with existing algorithms and demonstrated remarkable performance in terms of recall, precision, and mAP. It is seen that our proposed model is better by striking equilibrium between detection speed and accuracy. Based on our findings, object detection performance for autonomous driving applications is much enhanced when utilizing our suggested approach. © Bharati Vidyapeeth's institute of computer Applications and Management 2024.

关键词： Autonomous vehicles Deep learning Object detection YOLO-NAS

来源：评论

学校读者我要写书评

暂无评论

Conv-attention ViT for classification of multi-label class imbalanced data of lung thoracic diseases

引用

Multimedia Tools and Applications 2024年 1-30页

作者： Oommen, Lintu Nikhila Nagajyothi, Chiluka Chebrolu, Srilatha Department of Computer Science and Engineering National Institute of Technology Andhra Pradesh Tadepalligudem India

Chest X-ray image classification is a key study topic, and in order to increase performance and accuracy, the efficiency of vision transformers for this task has been examined. However, imbalanced datasets pose a significant challenge during model training, leading to biased results. The main focus is the classification of multi-labeled lung thoracic diseases using imbalanced data. To tackle class imbalance, synthetic data was generated using GANs and combined with images from diverse data sources, which enhanced generalization. To classify multi-labeled chest X-rays, this work proposes a Conv-Attention Vision Transformer (CA-ViT) model that uses local and global attention mechanisms to improve the average ROC-AUC score and F1-score. Proposed model, CA-ViT’s performance was evaluated on an imbalanced dataset and compared with ResNet-50, VGG-19, and ViT 32/384 models. The studies demonstrated that CA-ViT surpassed the performance of the other models, scoring an average ROC-AUC of 0.76 as opposed to 0.72, 0.75, and 0.68 for ResNet-50, VGG-19, and ViT 32/384 models, respectively. All models displayed improved assessment metrics when the dataset was balanced via synthetic data creation and the combination of several data distributions. When compared to the other models, CA-ViT performed best, earning an average ROC-AUC of 0.81. In contrast, the average ROC-AUC values for the ResNet-50, VGG-19, and ViT 32/384 models were 0.7, 0.73, and 0.79 respectively. CA-ViT achieved micro-average F1-score of 0.70. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

SA-MSVM:Hybrid Heuristic Algorithm-based Feature Selection for Sentiment Analysis in Twitter

引用

computer Systems science & engineering 2023年第3期44卷 2439-2456页

作者： C.P.Thamil Selvi R.PushpaLaksmi Department of Computer science and Engineering Sri Ranganathar Institute of Engineering and TechnologyCoimbatoreTamilnadu641009India Department of Information and Technology PSNA College of Engineering and TechnologyDindigulTamilnadu624622India

One of the drastically growing and emerging research areas used in most information technology industries is Bigdata *** is created from social websites like Facebook,WhatsApp,Twitter,*** about products,persons,initiatives,political issues,research achievements,and entertainment are discussed on social *** unique data analytics method cannot be applied to various social websites since the data formats are *** approaches,techniques,and tools have been used for big data analytics,opinion mining,or sentiment analysis,but the accuracy is yet to be *** proposed work is motivated to do sentiment analysis on Twitter data for cloth products using Simulated Annealing incorporated with the Multiclass Support Vector Machine(SA-MSVM)***-MSVM is a hybrid heuristic approach for selecting and classifying text-based sentimental words following the Natural Language Processing(NLP)process applied on tweets extracted from the Twitter dataset.A simulated annealing algorithm searches for relevant features and selects and identifies sentimental terms that customers ***-MSVM is implemented,experimented with MATLAB,and the results are *** results concluded that SA-MSVM has more potential in sentiment analysis and classification than the existing Support Vector Machine(SVM)***-MSVM has obtained 96.34%accuracy in classifying the product review compared with the existing systems.

关键词： Bigdata analytics Twitter dataset for cloth product heuristic approaches sentiment analysis feature selection classification

来源：评论

学校读者我要写书评

暂无评论

Fuzzy-GEC an Energy-Aware Hybrid Task Scheduling on the Cloud 2nd

Fuzzy-GEC an Energy-Aware Hybrid Task Scheduling on the Clou...

引用

2nd International Conference on Advances in Data-driven Computing and Intelligent Systems, ADCIS 2023

作者： Lalitha Devi, K. Deepa Thilak, K. Shanmuganathan, C. Kalaiselvi, K. Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India Department of Computer Science and Engineering SRM Institute of Science and Technology Kattankulathur Chennai India Department of Computer Science and Engineering SRM Institute of Science and Technology Ramapuram Chennai India

ISBN: (纸本)9789819995172

In an infrastructure cloud environment, task scheduling should focus on optimizing execution time and saving energy. The data center consumes a large amount of energy during the execution of the task. Energy-saving techniques reduce the amount of energy consumed based on proper task scheduling approaches. The existing fuzzy-based hybrid genetic algorithm considers job length to optimize the makespan. However this fuzzy genetic encoded chromosome (fuzzy-GEC) algorithm considers both makespan and energy consumption to optimize the calculation of fitness value for assigning the task to the virtual machine (VM) by considering the characteristics of the task and VM. According to these characteristics, a fuzzy genetic rule-based encoding scheme is developed to schedule the tasks onto the virtual machines to minimize makespan and energy consumption. The effectiveness of the new technique is evaluated against FCFS and conventional genetic scheduling algorithm using Google Cloud trace workload. The results show the efficiency of the developed approach for makespan and energy consumption. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Virtual machine

来源：评论

学校读者我要写书评

暂无评论

The IoT resource allocation and scheduling using Elephant Herding Optimization (EHO-RAS) in IoT environment

引用

International Journal of Information technology (Singapore) 2024年第5期16卷 3283-3293页

作者： Mageswari, Umaa Deepak, Gerard Santhanavijayan, A. Mala, C. Department of Computer Science and Engineering National Institute of Technology Tamilnadu Trichy 620015 India Department of Computer Science and Engineering Manipal Institute of Technology Karnataka Bengaluru 560064 India

IoT is one of the most significant technological breakthroughs and promises a higher level of connection and control in the future. The IoT network continues to expand rapidly, and the IoT ecosystem comprises millions of interconnected ad hoc devices across the network. Effective resource utilization guarantees the improvement of service quality. Everything is connected to the Internet through the distribution system known as the Internet of Things (IoT). Plenty of gateways and resources are in IoT infrastructure. Resource allocation (RA) is challenging due to network heterogeneity and the diversity of IoT devices;numerous practical approaches, strategies, and implementations are being presented and employed to resolve the RA problem (RAP). IoT resource allocation and scheduling (RAS) performance is essential in such a system since RAS allocates resources to open gateways and handles mapping resources and gateways. A gateway is needed to connect to hundreds of resources in the IoT environment. The proposed work is based on the RAS problem and aims to achieve optimal RA in the IoT by using the Elephant Herding Optimization (EHO) algorithm to lower the total Communication Cost between gateways and resources. The proposed EHO algorithm has been contrasted with others already in use, and the results show that the suggested algorithm performs as expected. The proposed solution is superior to others regarding TCC and Convergence rate than Particle Swarm Optimization (PSO), Genetic Algorithm (GA), Ant Colony Optimization (ACO), and Gray Wolf Optimization (GWO). © The Author(s), under exclusive licence to Bharati Vidyapeeth's institute of computer Applications and Management 2024.

关键词： Communication cost EHO Fitness IoT Gateways IoT Resources Resource Allocation ToT

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：