检索结果-内蒙古大学图书馆

7th International Conference on Trends in Electronics and informatics, ICOEI 2023

作者： Raavi, Sowmya Chandu, Phani Babu SudalaiMuthu, T. Hindustan Institute of Technology and Science Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350397284

The underwater object detection is a difficult task due to the unclear visibility and lack of objects underwater in kovalam, it was expected to have visibility up to three to five meters but it is very complicated to detect deeper/underwater objects like shoals of anchovy and silver moony, Bluefin trevally, puffer fish, box fish, etc., The existing method focuses on identifying a single object underwater and have low accuracy (78%) to detect multiple objects in a single instance. The proposed solution intends to improve the accuracy of identifying objects underwater. The proposed work can be used in submarines, military purposes, and archeology to identify objects effectively. The proposed system employs novel techniques for precise object detection and techniques like YOLO and SSD along with precise object detection methods and algorithms like Convolutional Neural Networks (CNN). These artificial intelligence algorithms allow to detect every object in an image by the area it takes up in a highlighted rectangular box, identify every object, and tag every object. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive analysis of 5G Communication and Its Health Care Management Models 2

A Comprehensive analysis of 5G Communication and Its Health ...

引用

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Kumar Sagar, Lalit Goel, Dipti Gupta, Sonali Saraswat, Manish Sharma, Ashish Srm Institute of Science and Technology Delhi Ncr Campus Department of Computer Applications UP Modinagar India Raj Kumar Goel Institute of Technology Department of Information Technology UP Ghaziabad India Computer Science & Engineering Graphic Era Hill University Uttarakhand Dehradun India Lloyd Institute of Engineering & Technology Department of Mechanical Engineering UP Greater Noida India Gla University UP Mathura India Gla University Department of Computer Engineering & Applications UP Mathura India

ISBN: (纸本)9798350371055

This paper provides an in-intensity examination of 5G conversation and its health care management models. 5G era, the imminent 5th technology of cellular cell communications, is expected to revolutionize the cellular enterprise with its build-up of excessive velocity, low latency, and big capability. however, it also increases new demanding situations for healthcaredelivery, in addition to data protection, privateness and tool management. This paper will are seeking for to deal with those troubles by using exploring numerous 5G fitness care management fashions. extra mainly, this paper will discover the demanding situations of 5G in healthcare, how the current healthcare infrastructure can facilitate 5G's use, and the principle elements of numerous 5G healthcare management fashions. finally, this paper will discuss the destiny implications of 5G in healthcare, and what groups want to do in order to make certain the most green and cozy healthcare shipping. by means of delving into this rely, this paper will provide a complete view of 5G conversation and its healthcare control fashions, main to progressed healthcare delivery within the close to future. This paper presents a complete analysis of fifth-technology (5G) communique applied to healthcare control fashions. To make sure functionality and efficacy., 5G networks and their related services need to adhere to a strict set of requirements and requirements, which can be evaluated in regard to latency, community useful resource requirements, and safety protocols. several important additives and capabilities of 5G-enabled healthcare models are mentioned, which include far off patient monitoring offerings, personalized healthcare services, and pervasive healthcare get right of entry to. additionally, this paper discusses the measures for successful implementation of 5G technology into healthcare, in conjunction with some potential dangers and ethical issues that have to be taken under consideration. in the end, the pap

关键词： cellular demanding models revolutionize

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Students Grievance and Database 2

Design and Implementation of Students Grievance and Database

引用

2nd International Conference on Applied Artificial Intelligence and Computing, ICAAIC 2023

作者： Kuhan, Sakthi Grace, L.K.Joshila Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9781665456302

Tracking student data and complaints is critical to track student performance in the classroom even while studying. This research study aims to address the grievances of the students and presents the website as a portal built using Javascript, HTML, Python, and MySQL, where students may file concerns, and the department handling the case is notified. The student has complete access to the complaint's history and may see if it has been examined, investigated, sent, rejected, or handled. The proposed technique is totally transparent, and if a complaint remains unanswered for several days, the system will automatically transmit it to the person specified further up the hierarchy. Any correctional system should be concerned about language quality since it may be used to spread incorrect information by making comments about people's gender, color, or religion. Employing the state-of-the-art technologies like deep learning and machine learning helps to detect hate speech. After training 11,325 tweets and analyzing the outcomes using evaluation metrics including F1 score, recall, and precision. Bi-LSTM, LSTM, and SVM models are utilized. By reaching the metrics values of 0.884, 0.84, and 0.86, the LSTM model outscores the other models. © 2023 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Logic Based Deep Learning Approach (FRNN) for Autism Spectrum Disorder Detection

Fuzzy Logic Based Deep Learning Approach (FRNN) for Autism S...

引用

2023 IEEE International Conference on Integrated Circuits and Communication Systems, ICICACS 2023

作者： Kavitha Nair, R. Ranjana, P. Hindustan Institute of Technology and Science Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350398465

Autism Spectrum Disorder (ASD) is regarded as a spectrum of developmental problems with neurological roots that affect communication, social interaction, and behavior. As it has a detrimental effect on both psychological and physical health, the anxiety experienced by the average individual concerns the physician, especially for those with ASD. Researchers are working very hard to understand the genetic underpinnings of autism and use the genetic information to choose logical targets for efficient therapy. International consortiums are using linkage analysis to pinpoint chromosomes and their correlation with ASD in order to pinpoint potential genetic illnesses. This study applies a recurrent neural network with fuzzy logic and provides an empirical assessment of how well it can diagnose autism using data from an MRI scan of the brain. To evaluate their performances, precision, sensitivity, specificity, and classification accuracy metrics are used. The experimental results show that FRNN, a deep learning-based classifier, produces the best outcome. © 2023 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

OptFog: Optimized Mobility-Aware Task Offloading and Migration Model for Fog Networks 17

OptFog: Optimized Mobility-Aware Task Offloading and Migrati...

引用

17th IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2023

作者： Alam, Mehbub Matam, Rakesh Barbhuiya, Ferdous Ahmed Indian Institute of Information Technology Guwahati Department of Computer Science & Engineering India

ISBN: (纸本)9798350307672

Due to the increased usage of mobile devices, there are now diverse application needs that favor the use of Fog computing architecture over the Cloud's centralized architecture. Fog Computing arises in this circumstance, which moves certain processing resources to the edge or among themselves and provides low-latency access to networked devices. However, minimizing the number of migrations to utilize the limited resources at the fog devices is essential and challenging. In this regard, this paper presents OptFog (optimized mobility-aware predicted task migration model for fog-assisted networks) as a migration assistance model. Three machine learning models are employed to anticipate mobility and make proactive migration decisions. The data used in OptFog is from active users provided Luxembourg SUMO Traffic (LuST) from the city of Luxembourg. Machine learning models like Decision Tree, k-Nearest Neighbors (k-NN), and Random Forest are evaluated to estimate the user's future position. Thereafter, the best approach is determined by comparing them. The Random Forest model produces a significant result, with an overall accuracy of 97.47%. OptFog shows the overall time, downtime and energy consumption when employed with a prediction-based migration strategy and also analyzes the most elevated scenarios for task migration. Simulations have shown that migration can result in satisfactory effectiveness for supporting mobility in fog-assisted networks. © 2023 IEEE.

关键词： Fog computing

来源：评论

学校读者我要写书评

暂无评论

A Robust Approach for Malaria Parasite Identification with CNN Based Feature Extraction and Classification using SVM 14

A Robust Approach for Malaria Parasite Identification with C...

引用

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Ohdar, Kanak Nigam, Akriti Birla Institute of Technology Mesra Department of Computer Science & Engineering Ranchi India

ISBN: (纸本)9798350335095

Malaria is a fatal illness caused by the transmission of the Plasmodium parasite through Anopheles mosquitoes. It causes symptoms like fever, chill, headache, and fatigue. In severe cases, it also leads to organ failure and death. The conventional method of detecting malaria is through microscopy. The development of new tools and algorithms for malaria diagnosis and treatment is crucial. In this study, a CNN-based model has been proposed for the feature extraction from raw thin blood smear images. The extracted features are then classified into one of the four species types of namely Falciparum, Vivax, Ovale and Malariae using an SVM classifier. The proposed model achieves a significantly good accuracy of 98%, demonstrating the effectiveness of deep learning techniques in Malaria diagnosis and species classification. This study has significant implications for the development of new tools for Malaria diagnosis and treatment, which could help to speed up the process of detection and help the medical practitioner make an accurate analysis of infection, particularly in rural areas, where medical facilities are scarce. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A Novel Long Term Evolution -Based Technique for Vehicle-to-Vehicle Communication as Design Implementation and Performance Evaluation

引用

SN computer Science 2025年第5期6卷 1-25页

作者： Chauhan, Mamta Astya, Rani Rakesh, Nitin Department of Computer Science & Engineering Sharda School of Engineering & Technology Sharda University Greater Noida India Symbiosis Institute of Technology Nagpur Symbiosis International Deemed University Pune India

This work investigates the security problems associated with LTE networks that use automation. Mobile networks expansion creates substantial security risks because integrating automated systems for operational efficiency control. These security weaknesses through potential use cases while developing effective defense methods by using existing research findings and innovative security testing. Wireless networks control systems experience automated migration from manual to automated operations which delivers better performance efficiency and cost savings. The research focuses on analyzing security flaws in automated LTE networks especially those affecting V2V communication systems. LTE-based automation network development raises mobile network vulnerabilities that allow cyber threats to exploit protocol weakness through rogue base stations. The work evaluates these system weaknesses by demonstrating real attack models with Cisco Packet Tracer along with Kali Linux and Wire shark to detect network security loopholes. This work showcases how detrimental packet injections with unauthorized access and manipulated handover procedures affect LTE-V2X communication security. The proposed solutions from this research center on developing advanced authentication systems while implementing real-time monitoring frameworks together with regulatory improvements for securing vehicular communications. The study shows that effective V2V network protection needs multiple security measures to defeat upcoming cyber threats which will protect both efficiency and safety of the communication channels. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Cisco packet tracer Cloud connecting Kali linux LTE V2V communication Wire shark Wireless technologies

来源：评论

学校读者我要写书评

暂无评论

Multi-lingual Event Identification in Disaster Domain 1

引用

20th International Conference on Computational Linguistics and Intelligent Text Processing, CICLing 2019

作者： Ahmad, Zishan Varshney, Deeksha Ekbal, Asif Bhattacharyya, Pushpak Department of Computer Science and Engineering Indian Institute of Technology Patna Bihta India

ISBN: (数字)9783031243370

ISBN: (纸本)9783031243363

Information extraction in disaster domain is a critical task for effective disaster management. A high quality event detection system is the very first step towards this. Since disaster annotated data-sets are not available in Indian languages, we first create and annotate a dataset in three different languages, namely Hindi, Bengali and English. The data was crawled from the different news websites and annotated with expert annotators using a proper annotation guidelines. The events in the dataset belong to 35 different disaster classes. We then build a deep ensemble architecture based on Convolution Neural Network (CNN) and Bi-directional Long Short Term Memory (Bi-LSTM) network as the base learning models. This model is used to identify event words and phrases along with its class from the input sentence. Since our data is sparse, the model yields a very low F1-score in all the three languages. To mitigate the data sparsity problem we make use of multi-lingual word embedding so that joint training of all the languages could be done. To accommodate joint training we modify our model to contain language-specific layers so that the syntactic differences between the languages can be taken care of by these layers. By using multi-lingual embedding and training the whole dataset on our proposed model, the performance of event detection in each language improves significantly. We also report further analysis of language-wise and class-wise improvements of each language and event classes. © 2023, Springer Nature Switzerland AG.

关键词： Disasters

来源：评论

学校读者我要写书评

暂无评论

Collaborative, Privacy-Preserving Federated Learning Framework for the Detection of Diabetic Eye Diseases

引用

SN computer Science 2024年第8期5卷 1100页

作者： Gulati, Seema Guleria, Kalpna Goyal, Nitin Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura India Department of Computer Science and Engineering School of Engineering and Technology Central University of Haryana Haryana Mahendergarh India

Diabetes Mellitus is one of the chronic metabolic disorders that is easily identified by elevation in blood sugar levels. The high blood sugar levels over time can lead to substantial damage to the blood vessels, heart, eyes, kidneys, and nerves. Diabetic Eye Diseases (DED) such as Diabetic Macular Edema (DME), Diabetic Retinopathy (DR), and glaucoma, are serious complications of diabetes that can result in irreversible vision loss. Thus, affecting the health and quality of life of the population worldwide. The primary objective of the proposed work is to evaluate the efficacy of a privacy-preserved Federated Learning (FL) framework for detecting DEDs. To detect DEDs a collaborative and privacy-preserving Federated Deep Learning (FDL) framework using a lightweight MobileNetV2 architecture is proposed. The aggregation scheme selected for the FDL framework is FedProx and to achieve a high accuracy score the proximal term, µ is tuned with values ranging from µ= (0.01, 0.02, 0.03, 0.04 and 0.05). The impact of the variance in the proximal term on model performance is analyzed, and the results show that higher µ (0.03,0.4 and 0.5) values provide more stable and consistently high precision, recall, and F1-scores. The findings suggest that FedProx aggregation successfully stabilizes the performance of the framework with the least standard deviation of 0.035 in accuracy at µ = 0.05. The balance between accuracy and stability is a key factor in the successful application of federated learning in disease prediction. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Artificial intelligence Collaborative training Diabetic eye diseases Federated learning Privacy-protection

来源：评论

学校读者我要写书评

暂无评论

Recyclable and Non-Recyclable Waste Recognition using Image Processing with Machine Learning: Recycle Mate 3

Recyclable and Non-Recyclable Waste Recognition using Image ...

引用

3rd IEEE International Conference on Intelligent Technologies, CONIT 2023

作者： Nara, Amit Panchal, Smit Dange, Prof. Suchita A.P. Shah Institute of Technology Department of Computer Engineering Thane India

ISBN: (纸本)9798350338607

Waste Management is the effort needed to make our world a better place. As solid waste may cause a problem for our surroundings. Nowadays many people don't even know how to distinguish between recyclable and non-recyclable objects, we know only some general things which are recyclable like paper, plastic, cardboard and drinking cans. To deal with this problem a deep machine-learning Convolution Neural Network (CNN) was created to help us all with an achievable waste management task. The automated task works for everyone as it lets down the burden of work from many people's shoulders. Our model is built using the Keras API. The model categorizes the data into a binary class. It has been tested with many objects which gave an acceptable prediction accuracy. © 2023 IEEE.

关键词： Waste management

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

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

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：