检索结果-内蒙古大学图书馆

2023 International Conference on Intelligent Systems, Advanced Computing and Communication, ISACC 2023

作者： Basumatary, Habila Chowdhuri, Rajib Deb Barma, Mrinal Kanti Tezpur University Department of Computer Science and Engineering Assam India National Institute of Technology Department of Computer Science and Engineering Agartala India

ISBN: (纸本)9798350399387

In modern days, with the fastest growing technology trends, the benefits of Wireless Sensor Networks (WSNs) are also increasing rapidly. In these networks, very small-sized wireless sensor nodes are used widely which are capable of sensing and doing computations. These sensor nodes are resource-limited in nature i.e., they have limited storage capacity, power supply, computation capability, bandwidth, etc. WSNs are mostly used in outdoor application areas like environmental monitoring, land mines detections or different military applications where the power supply to the sensor nodes does the major role. In these applications, without any external power supply, the sensor nodes run the whole network by collecting data from its surroundings and also communicate these data to the end-user. Hence, conserving energy for the sensor nodes is one of the most challenging tasks in WSNs. In this paper, we have done detailed study on the existing literature which are proposed with the objective to improve the energy efficiency issue in WSNs. Here, we have selectively highlighted some of the recently proposed methodologies to understand the present research scenario. We have also shown comparative analysis on the techniques and tools which are used to propose these works and their variation of the results are discussed accordingly. © 2023 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Exploring Different Techniques for Emotion Detection Through Face Recognition

Exploring Different Techniques for Emotion Detection Through...

引用

2023 International Conference on Advanced Computing and Communication Technologies, ICACCTech 2023

作者： Rana, Saurabh Chaudhary, Rachit Gupta, Malvika Garg, Puneet Abes Engineering College Computer Science & Engineering Ghaziabad India St. Andrews Institute of Technology &management Computer Science & Engineering Delhi-NCR India

ISBN: (纸本)9798350380880

A vital part of affective computing, artificial intelligence, and human-computer interaction is emotion recognition from visual material. The creation of an emotion identification system utilizing open-source tools like OpenCv, TensorFlo w, and several Python libraries is explored in this research article. With the use of facial expressions in pictures and videos, the suggested framework seeks to precisely classify and detect various emotions. Additionally, in order to improve the robustness and context awareness of the emotion detection system, this research discusses the significance of labeled datasets for training and validation as well as the incorporation of multi-modal datasources, such as audio and text sentiment analysis. Convolutional neural networks (CNNs) have become a game-changing force in computer vision, with uses ranging from object identification to picture categorization. In order to further our knowledge and practical use of these technologies, we investigate the synergistic link between CNNs, Facial Recognition Systems (FRS) which is to recognize the basic features of the Humanface using Deep Learning concepts, and Facial Emotion Recognition (FER) which will detect the emotion of the face after the full recognition of the face using CNN and the datasets in this study. © 2023 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Different Hardware Platforms in Wireless Sensor Networks 4

Performance Analysis of Different Hardware Platforms in Wire...

引用

4th International Conference on Signal Processing and Communication, ICSPC 2023

作者： Jebarani, P. Esther Jone, Amir Anton Jose, Tony Paul, J. John Jose, Shelja Kumar, Pradeep Kovai Kalaimagal College of Arts and Science Coimbatore Dept. of Computer Science India Karunya Institute of Technology and Sciences Coimbatore Dept. of Electronics and Communication Engineering India Indira Gandhi Institute of Engineering and Technology Dept. of Electronics and Communication Engineering Kothamangalam India

ISBN: (纸本)9798350300772

Wireless Sensor Networks (WSN) encompasses rapid development in research area through large scale applications. The main objective is to compare four different hardware platforms such as Rene, Mica, Spec and Blue in order to find efficient hardware platform that can provide best performance within certain constraints while working on TinyOS as operating system. The four different hardware platforms are compared on the basis of certain constraints such as data communication, rendezvous(mJ/day), alarm checking, sensing, sleep (units in mJ/day), expected lifetime (units in years). According to this investigation, mica outperforms the four different platforms in terms of decoupling between RF and data path speed, bit rate, and timing accuracy. However, future specifications will be found to be more efficient based on CMOS processes and RF radio technology, which results in lower costs, smaller sizes, lower power requirements, and a decrease in complexity. © 2023 IEEE.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

OntoMG: a unique and ontological-based intelligent framework for early identification of myasthenia gravis (MG)

引用

International Journal of Information technology (Singapore) 2024年第6期16卷 3847-3853页

作者： Mahajan, Prerna Agarwal, Trapty Vekariya, Daxa Gupta, Rajesh Malviya, Ashwini Anandaraj, S.P. Jain, Garima Anand, D. Department of Computer Science and Information Technology Jain (Deemed to Be University) Bengaluru India Maharishi School of Engineering and Technology Maharishi University of Information Technology Lucknow India Department of Computer Science and Engineering Faculty of Engineering and Technology Parul University Gujarat Vadodara India Department of Management Sanskriti University UP Mathura India Department of UGDX ATLAS SkillTech University Mumbai India Department of Computer Science Engineering Presidency University Bengaluru India Department of Computer Science and Business Systems (CBS) Noida Institute of Engineering and Technology Uttar Pradesh Greater Noida India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram India

Myasthenia Gravis (MG) is a neuromuscular disease causing extreme muscular fatigue, triggering problems with vision, swallowing, speech, mobility, dexterity, and breathing. However, early detection and prediction of MG is a crucial and quite challenging task for medical practitioners. So, in our proposed work, we are focused on introducing an ontology-based intelligent system for the prognosis of patients affected by this neuromuscular disease. The given paper presents a novel framework that employs the concepts of ontology, semantic web rules, and reasoner for deriving whether the patient is tested positive or negative. The suggested framework's effectiveness is assessed by comparing it to machine learning classifiers using parameters from the NIH repository for Myasthenia Gravis. The experimental results show that the ontological-based framework is able to achieve higher accuracy (80.85%), higher precision (78.37%), and higher recall (76.55%) than the existing classifiers used in the recent studies. © Bharati Vidyapeeth's institute of computer Applications and Management 2024.

关键词： Machine learning (ML) Myasthenia gravis disease Ontology Reasoners Semantic web rules language (SWRL)

来源：评论

学校读者我要写书评

暂无评论

Achieving high strength-ductility synergy in a Mg_(97)Y_(1)Zn_(1)Ho_(1) alloy via a nano-spaced long-period stacking-ordered phase

引用

Journal of Magnesium and Alloys 2023年第4期11卷 1321-1331页

作者： Mingyu Fan Ye Cui Yang Zhang Xinghao Wei Xue Cao Peter K.Liaw Yuansheng Yang Zhongwu Zhang Key Laboratory of Superlight Materials and Surface Technology Ministry of EducationCollege of Materials Science and Chemical EngineeringHarbin Engineering UniversityHarbin 150001PR China College of Computer Science and Technology Harbin Engineering UniversityHarbin 150001PR China Department of Materials Science and Engineering The University of TennesseeKnoxvilleTN 37996-2100USA Institute of Metal Research Chinese Academy of SciencesShenyang 110016PR China

Achieving high strength in Mg alloys is usually accompanied by ductility ***,a novel Mg97Y1Zn1Ho1 at.%alloy with a yield strength of 403 MPa and an elongation of 10%is *** strength-ductility synergy is obtained by a comprehensive strategy,including a lamella bimodal microstructure design and the introduction of nano-spaced solute-segregated 14H long-period stacking-ordered phase(14H LPSO phase)through rare-earth Ho *** lamella bimodal microstructure consists of elongated un-recrystallized(un-DRXed)coarse grains and fine dynamically-recrystallized grains(DRXed regions).The nano-spaced solute-segregated 14H LPSO phase is distributed in DRXed *** outstanding yield strength is mainly contributed by grain-boundary strengthening,18R LPSO strengthening,and fiberlike reinforcement strengthening from the nano-spaced 14H LPSO *** high elongation is due primarily to the combined effects of the bimodal and lamellar microstructures through enhancing the work-hardening capability.

关键词： Mg wrought alloy Mechanical properties Long-period stacking-ordered(LPSO)phase Age-strengthening behavior Strengthening mechanism

来源：评论

学校读者我要写书评

暂无评论

Movie Recommendation Systems Using Improved Non-Negative Matrix Factorization

Movie Recommendation Systems Using Improved Non-Negative Mat...

引用

2023 Innovations in Power and Advanced Computing Technologies, i-PACT 2023

作者： Sherly Alphonse, A. Verma, Harshit School of Computer Science and Engineering Vellore Institute of Technology Chennai India

ISBN: (纸本)9798350325188

Currently, there exist effective strategies for providing practical recommendations crucial in many industries, this encompasses a range of online platforms, such as electronic commerce, social networking sites, and various web-based services, as a result of the big data explosion. There are numerous customized movie recommendation systems available today that use publicly accessible movie datasets (like MovieLens) and provide enhanced performance measures (such the Root-Mean-Square Error (RMSE)). The ability to scale and the practicality of usage feedback and verification are determined through real-world implementation and assessment, they are two important difficulties that movie recommendation systems currently struggle with. This research suggests a novel approach using non-negative matrix factorization that resolves these issues through similarity and matrix factorization. Finding two matrices, both consisting of non-negative values, and their resulting product when multiplied together closely resembles the original matrix is the goal of non-negative matrix factorization. Additionally, it places the latent elements under non-negative constraints. The suggested approach offers novel update procedures to discover the latent variables for rating prediction. In contrast to the majority of collaborative filtering techniques, the suggested technique can forecast all the unknowable ratings. Its computational complexity is quite low, and it is simple to implement. Empirical research using the MovieLens shows that the suggested approach is more forgiving of the sparsity and scalability issues and produces good results. © 2023 IEEE.

关键词： collaborative filtering matrix factorization Movie ratings recommendation

来源：评论

学校读者我要写书评

暂无评论

Metaverse Creation And Decentralized Land NFTs Over Blockchain 9

Metaverse Creation And Decentralized Land NFTs Over Blockcha...

引用

9th International Conference on Smart Computing and Communications, ICSCC 2023

作者： Janet, S. Shaji, Ayda Sara D'Cruz, Brian Cedric Abraham, Eldhose Philip, Abin Oommen Kamal, Leda Toc H Institute of Science and Technology Department of Computer Science and Engineering Kochi India Indian Institute of Information Technology Kottayam IIIT-K Department of Computer Science and Engineering Cybersecurity India

ISBN: (纸本)9798350314090

A metaverse is a rapidly evolving concept in the realm of virtual reality that refers to a network of three-dimensional virtual environments centered on social interaction. The word is widely used in futurism and science fiction to depict a potential iteration of the internet as a single, universal virtual environment assisted by the usage of virtual and augmented reality headgear. There are several Metaverse currently available, such as Sandbox and Decentraland, each offering unique and immersive experiences for users. Non-Fungible Tokens (NFTs) are a novel form of digital assets that are stored on a blockchain, a decentralized digital ledger that keeps track of transactions. NFTs can prove ownership and validity for these digital assets via a blockchain, increasing their value and collectability. NFTs can be linked to digital assets that can be reproduced, such as images, movies, and audio. To give a public certificate of authenticity or proof of ownership, NFTs use a digital ledger. As part of our ongoing project, the creation of the Metarealm, a metaverse for Kochi city, promises to provide an engaging and cutting-edge platform for users to buy, sell, and trade virtual land and assets. This Metaverse will enable users to explore the city and its landmarks in a fully immersive 3D environment, fostering a sense of community and engagement among its users. As the Metaverse and NFTs continue to evolve, the possibilities for virtual experiences and digital ownership are limitless. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Analysis and Impact of Electromagnetic Field Leakage in WPT on Central Nervous System: A Neural Network Approach 4

Analysis and Impact of Electromagnetic Field Leakage in WPT ...

引用

4th IEEE International Conference on Sustainable Energy and Future Electric Transportation, SEFET 2024

作者： Shukla, Garima Awasthi, Vanshaj Goswami, Prafull Singh, Sofia Amity School of Engineering and Technology Amity University Department of Computer Science and Engineering Maharashtra Mumbai India Indian Institute of Information and Technology Department of Computer Science and Engineering Sonipat India Amity School of Engineering and Technology Amity University Department of Artificial Intelligence Uttar Pradesh Noida India

ISBN: (纸本)9798350383997

The potential for wireless power transfer (WPT) technologies to transform the charging capabilities of a wide range of applications, from consumer electronics to medical devices has attracted a lot of attention. But uncertainties remain about how these technology's electromagnetic field (EMF) leakage affects human health, especially the central nervous system (CNS). To find a way to assess and forecast all of these consequences, this study explores at the possible effects of EMF leakage from WPT systems on the central nervous system (CNS) and suggests a distinctive approach that employs the applications for neural networks. Using real- world data and computational models, this study will produce an accurate model of EMF absorption and propagation in biological tissues, with a specific focus on the central nervous system. By focusing insights into potential risks to health and informing the emergence of requirements which assure the safe implementation of wireless power technologies, the research will enhance our understanding of the connections between EMF exposure and the central nervous system. The ultimate objective of this study is to encourage safer and more sustainable wireless charging technologies by enhancing the accuracy and efficiency of risk assessment in circumstances of EMF exposure from WPT systems through the implementation of Machine Learning (ML) strategies © 2024 IEEE.

关键词： Inductive power transmission

来源：评论

学校读者我要写书评

暂无评论

A Novel Blockchain Framework for Enhancing Online Transactions

引用

International Virtual Conference on Industry 4.0, IVCI4.0 2021

作者： Shareef, Sk. Khaja Sridevi, R. Raju, V. Rama Rao, K. S. Sadasiva Computer Science and Engineering JNTUH Hyderabad India Computer Science and Engineering JNTUH College of Engineering Hyderabad Hyderabad India Computer Science and Engineering CMR College of Engineering & Technology Hyderabad Hyderabad India Department of MCA Chaitanya Bharathi Institute of Technology Hyderabad India

ISBN: (纸本)9789811999888

In the modern era, blockchain technology has essentially functioned in diverse facilities ranging from online applications like payment transactions, data transactions, healthcare information sharing, supply chain tracking, etc. The research is developed for online applications to exploit the blockchain concept in recording large data transactions. During the transaction, privacy protection is an important concern for securing the data in the cloud database. For this reason, numerous cryptographic algorithms were developed to end this issue. Therefore, in this research, a novel Homomorphic Serpent Blockchain (HSB) algorithm is developed to secure online transactions while avoiding security threats. Consequently, the performance of the proposed algorithm is compared with conventional techniques and attained the finest outcomes with high accuracy and less time duration. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

An Efficient ODR for computer Night Vision Using Multi-Scale Retinex Network-Aided Enhanced Images 4

An Efficient ODR for Computer Night Vision Using Multi-Scale...

引用

4th International Conference on Power, Energy, Control and Transmission Systems, ICPECTS 2024

作者： Charles Prabu, V. Pandiaraja, P. Sathiyamoorthi, V. Durgadevi, P. Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tamilnadu Chennai India Government Polytechnic College Department of Computer Engineering Baisuhalli Tamilnadu Dharmapuri India Srm Institute of Science and Technology Department of Computer Science and Engineering Vadapalani Campus Tamilnadu Chennai India

ISBN: (纸本)9798331508845

In the current scenario, recognizing various objects and tracking their movements in the real-time surveillance footage is the most difficult task. To detect objects, a combination of image processing and computer vision algorithms is utilized. computer-vision based automatic human activity recognition from surveillance video can be utilized for applications such as the identification of violent acts and the study of human behavior. Consequently, this work implements a new "Object Detection and Recognition (ODR)"model for computer night vision utilizing a deep learning technique. In order to improve the supplied input image, the combined images are first transmitted to the "Multi-scale Retinex (MSR)"model. The You Only Look Once Version 7 (YoloV7) model uses the improved image from MSR as input to identify and recognize things. After conducting experiments, the implemented ODR model on the ExDark Dataset obtained an efficiency of 94.8%. © 2024 IEEE.

关键词： Deep learning

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：