检索结果-内蒙古大学图书馆

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Potluri, Pandarinath Jayakarthik, R. Agarwal, Shivam Shobana, S. Venkata Padmavathi, S. Aarthi, R. Swarnandhra College of Engineering and Technology Cse Department Sitarampuram West Godavari district Narsapuram534275 India Saveetha College of Liberal Arts and Sciences Simats Dept of Computer Science India Gl Bajaj Institute of Technology and Management Department of Information Technology Gr. Noida India R.M.K Engineering College Department of It Chennai India Gst Gitam Deemed to be University Electrical and Electronics Engineering Hyderabad campus Telangana India R.M.D Engineering College Department of Ece R. S. M Nagar Gummidipoondi601206 India

ISBN: (纸本)9798350376425

In the field of electronic voting systems, ensuring secure and reliable authentication mechanisms is paramount to safeguarding the integrity and fairness of the democratic process. Face biometric authentication has emerged as a promising approach, integrating advanced deep learning algorithms for accurate and efficient verification of voters based on their facial features. This paper presents a comprehensive overview of the system architecture and design considerations for integrating face biometric authentication into electronic voting systems. It describes the hardware and software components essential for system functionality, discusses the selection of appropriate technologies for face recognition and encryption, and elaborates on the design of user interfaces, database structures, and ballot generation systems. Furthermore, the paper delves into the implementation of face detection and recognition algorithms, emphasizing the importance of anti-spoofing measures and multi-factor authentication mechanisms to enhance security. It also addresses voter registration processes, ballot generation, the voting process, and vote counting and verification procedures within the context of face biometric authentication. Additionally, the paper highlights the significance of robust security measures, including encryption techniques, access controls, and regular security audits, to mitigate cyber threats and ensure the integrity of the electoral process. By integrating face biometric authentication into electronic voting systems, this paper aims to contribute to the development of secure, transparent, and inclusive electoral systems, fostering trust and confidence in democratic governance, with an accuracy rate of 96%. © 2024 IEEE.

关键词： Voting machines

来源：评论

学校读者我要写书评

暂无评论

A High-Band Compact Microstrip Patch Antenna for 5G Wireless Technologies 6

A High-Band Compact Microstrip Patch Antenna for 5G Wireless...

引用

6th International Conference on Contemporary Computing and Informatics, IC3I 2023

作者： Santhakumar, G. Muthukumar, R. Asa Jyothi, G. Balakumar, S. Maranan, Ramya Bonde, Roshan Sri Krishna College of Technology Department of Electronics and Communication Engineering Tamil Nadu Coimbatore India Erode Sengunthar Engineering College Department of EEE Tamil Nadu Erode India Malla Reddy Engineering College ECE Department Maisamma Guda Telangana Hyderabad India Arba Minch University Faculty of Electrical & Computer Engineering Arba MinchPin: 21 Ethiopia Saveetha School of Engineering Department of Research and Innovation SIMATS Tamil Nadu Chennai India Dr. Babasaheb Ambedkar Technological University Lonere Raigad India

ISBN: (纸本)9798350304480

This examination presents a High Increase, Overhauled Bandwidth Patch antenna for 5G Undertakings. Using an inset-took care of taking care of method for the microstrip patch antenna wave band, the double band is achieved. Two rectangular apertures are embedded on the patch's transmitting component to provide it a high increase. The anticipated antenna Consolidating three stages at the edge of the rectangular patch increases bandwidth. Fifth-generation (5G) networks clearly outperform 4G because to reduced idleness, more transmission speed, greater bandwidth, and a higher possibility of integrating with more notable various devices. For impending 5G association technologies, this paper studies and presents a microstrip patch antenna working at 28 GHz. The outcome of this reenactment is superior to the previous one. It typically acts as a dependable choice for 5G wireless innovation as a result. The performance of the suggested antenna is superior to that of earlier antennas spread in logical diaries. © 2023 IEEE.

关键词： 5g High-Band Microstrip Patch Antenna Wireless Technologies

来源：评论

学校读者我要写书评

暂无评论

Paddy Leaf Disease Detection Using an Optimized Deep Neural Network

引用

computers, Materials & Continua 2021年第7期68卷 1117-1128页

作者： Shankaranarayanan Nalini Nagappan Krishnaraj Thangaiyan Jayasankar Kalimuthu Vinothkumar Antony Sagai Francis Britto Kamalraj Subramaniam Chokkaligam Bharatiraja Department of Computer Science&Engineering University College of EngineeringBIT CampusAnna UniversityTiruchirappalli620024India School of Computing SRM Institute of Science and TechnologyKattankulathur603203India Department of Electronics and Communication Engineering University College of EngineeringBIT CampusAnna UniversityTiruchirappalli620024India Department of Electronics&Communication Engineering SSM Institute of Engineering and TechnologyDindigul624002India Department of Mechanical Engineering Rohini College of Engineering and TechnologyPalkulam629401India Department of ECE Karpagam Academy of Higher EducationCoimbatore641021India Department of Electrical and Electronics Engineering SRM Institute of Science and TechnologyChennai603203India

Precision Agriculture is a concept of farm management which makes use of IoT and networking concepts to improve the *** diseases are one of the underlying causes in the decrease in the number of quantity and quality of the farming *** of diseases from the plant images is an active research topic which makes use of machine learning(ML)approaches.A novel deep neural network(DNN)classification model is proposed for the identification of paddy leaf disease using plant image *** errors were minimized by optimizing weights and biases in the DNN model using a crow search algorithm(CSA)during both the standard pre-training and fine-tuning *** DNN-CSA architecture enables the use of simplistic statistical learning techniques with a decreased computational workload,ensuring high classification *** leaf images were first preprocessed,and the areas indicative of disease were initially extracted using a k-means clustering *** was then applied to eliminate regions not indicative of ***,a set of features were extracted from the previously isolated diseased ***,the classification accuracy and efficiency of the proposed DNN-CSA model were verified experimentally and shown to be superior to a support vector machine with multiple cross-fold validations.

关键词： Leaf classification paddy leaf deep learning metaheuristics optimization crow search algorithm

来源：评论

学校读者我要写书评

暂无评论

An Automation Innovation of Gearbox Vehicle Control by Using Machine Learning Based Robotic Operation

An Automation Innovation of Gearbox Vehicle Control by Using...

引用

2023 International Conference on Disruptive Technologies, ICDT 2023

作者： Ramakrishna, M.M. Atyam, Nageswara Rao Chaurasia, Nikhil Sahaya Senthamil, L. Shah, Mohd Asif Raja, V.L. Dr. M.G.R Educational and Research Institute Dept of ECE/ICE Tamil Nadu Chennai India Cmr Institute of Technology Electrical and Electronics Department Karnataka Bengaluru India Sage University Department of Computer Science & Engineering Madhya Pradesh Bhopal India Psna College of Engineering and Technology Electrical and Electronics Engineering Tamil Nadu Dindigul India University School of Business Chandigarh University Punjab Mohali India School of Computing Science Tamil Nadu Pallavaram Chennai India

ISBN: (纸本)9798350323887

There are many vehicle exchanges around the world are using the manual transmission and automatic transmission are the most popular. At this time, many popular manufacturers have started using the robot version in their new products. The gearbox of the robot is, in fact, mechanical;it has an additional automatic clutch and gear shift. Accordingly, the operation of the transmission is not completely dependent on the driver, as in other options, but on the electronic control unit. For the proper functioning of the transmission the driver needs to correctly transmit only the incoming information. In this paper an automation innovation was proposed to control the vehicle gear shifting functions by using the machine learning based on the robotic operation model. An automaton or robot, after some time, must first learn the device of a new invention. The automatic gearbox received a friction type clutch. It is a disk set or a built-in separate mechanism. The most reliable and durable design can be called the double clutch design. © 2023 IEEE.

关键词： Vehicle transmissions

来源：评论

学校读者我要写书评

暂无评论

Study of the splicing/coupling influence of cabling to fibers test links measurements

引用

Journal of Optical Communications 2024年第0期45卷 s1369-s1381页

作者： Rashed, Ahmed Nabih Zaki Babu, Gade Harish Nagendram, Sanam Anwer, Twana Mohammed Kak Ahammad, Shaik Hasane Hossain, Md. Amzad Ibrahim, Anas Electronics and Electrical Communications Engineering Department Faculty of Electronic Engineering Menoufia University Menouf32951 Egypt Department of VLSI Microelectronics Institute of Electronics and Communication Engineering Saveetha School of Engineering SIMATS Tamilnadu Chennai602105 India Department of ECE CVR College of Engineering Hyderabad India Department of Artificial Intelligence KKR & KSR Institute of Technology and Sciences Guntur India Department of Physics College of Education Salahaddin University-Erbil Kurdistan Region Erbil44002 Iraq Department of ECE Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram522302 India Faculty of Electrical Engineering and Information Technology Institute of Theoretical Electrical Engineering Ruhr University Bochum Bochum44801 Germany Department of Electrical and Electronic Engineering Jashore University of Science and Technology Jashore7408 Bangladesh

This article has analyzed the splicing and coupling influence of cabling to fibers test links measurements. The simulative study for different free/forced vibration mechanics in MEMS is performed. Relative amplitude frequency plot for a cantilever beam, a double clamped beam (DCB), a cantilever beam with end mass, normal vibration of a clamped beam mass, a double clamped beam with axial force, normal vibration of a clamped beam mass are demonstrated by using MEMSolver simulation version 3.3. The frequency shift for DCB with axial force is clarified. The lowest modal frequencies of a square and round diaphragm are also reported. The lowest modal frequency of a bent beam suspension is simulated also. The dependence of mid-section of the folded beam on the resonance frequency and on the short leg of the serpentine beam are clarified. The displacement plot for a structure under free vibration with damping, the displacement plot for vibration under a step force with damping, amplitude frequency plot for vibration under harmonic force with damping and amplitude frequency plot for the vibration driven by the base excitation are also outlined in this work. © 2023 Walter de Gruyter GmbH, Berlin/Boston.

关键词： Natural frequencies

来源：评论

学校读者我要写书评

暂无评论

Jellyfish Search Optimizer with Deep Learning Driven Cervical Cancer Recognition and Classification Model on Biomedical Images 2

Jellyfish Search Optimizer with Deep Learning Driven Cervica...

引用

2nd IEEE International Conference on Advances in Information Technology, ICAIT 2024

作者： Anand, M. Suresh Venkatramulu, S. Vidhya, Sesha S. Chembian, W.T. Yashaswini, B.M. Kumar, Magesh B. Department of Computing Technologies School of Computing SRM Institute of Science & Technology Kattankulathur603203 India Department of CSE Kakatiya Institute of Technology and Science Warangal India Department of ECE RMK College of Engineering and Technology India Department of CSE Vel Tech High Tech Dr Rangarajan Dr Sakuntala Engineering College Avadi Morai India Electronics & Communication Engineering JSS Academy of Technical Education JSSATE-B Campus Dr. Vishnuvardhan Rd Uttarahalli-Kengeri Main Road JSS Campus Rd Srinivaspura Karnataka Bengaluru560060 India Department of Computer Science and Engineering Bannari Amman Institute of Technology Erode Sathyamangalam India

ISBN: (纸本)9798350383867

The emergence of Cervical Cancer (CC) Recognition and Classification Model for Biomedical Images is a main advancement in fields of medical imaging and diagnostics. Leveraging state-of-the-art image processing and machine learning algorithms, this model can accurately detect and classify CC-related abnormalities in medical images, namely colposcopy or Pap smear images. By providing automated and precise assessments, the model empowers medical experts to make timely and informed decisions, which leads to earlier interference and potential life-saving treatment. With its potential to improve diagnostic accuracy and reduce human error, the model holds great promise in the fight against CC, especially in resource-constrained healthcare settings where medical practitioners may be limited. This study presents a Jellyfish Search Optimizer with Deep Learning Driven CC Recognition and Classification (JSODL-CCRC) model on Biomedical Images. The JSODL-CCRC technique is mainly developed to investigate the medical images for detection and classification of CC. The JSODL-CCRC approach comprises median filtering (MF) for noise reduction, followed by feature extraction utilizing Inceptionv3 to derive complex image patterns. Besides, the JSO based hyperparameter selection process is performed for the Inception v3 model. At last, Extreme Learning Machine (ELM) algorithm is applied to categorize the images which validates efficacy in handling complex biomedical image data. The experimental results stated that the JSODL-CCRC model enables effective detection results over other models. © 2024 IEEE.

关键词： Median filters

来源：评论

学校读者我要写书评

暂无评论

Assistive Mobile Robot Navigation and Localization using FastSLAM Algorithm

Assistive Mobile Robot Navigation and Localization using Fas...

引用

International Conference on Inventive Research in Computing Applications (ICIRCA)

作者： R. Sai Lingesh G. Annapoorani Department of Electronics and Computer Specialization Engineering SRM Institute of Science & Technology Ramapuram Chennai India Department of ECE SRM Institute of Science & Technology Ramapuram Chennai India

This study introduces a novel technique to improve a mobile robot's ability to move and navigate on its own in uncharted territory. Robots can navigate a normal human workstation on their own thanks to simultaneous localization and mapping technologies. The SLAM technique is mostly used for mapping and localization in static environments. In this study, a special FastSLAM algorithm augmentation that includes a module for tracking individuals using 2D Lidar sensor data is designed and evaluated. The SLAM algorithm may filter measurements from those measures because of the noise generated by people walking is unstable and dynamic by nature. This has been tested with our mobile robot platform for social support. This approach has a more accurate localization and a clearer depiction of the mapping of the environment. Overall, the range of mobile assistive robots is broad and is expanding as new uses are found and technology develops. These robots have the potential to make a big influence on a lot of different businesses and enhance a lot of different elements of daily life.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Extraction of Mobility from Quantum Transport Calculations of Type-II Superlattices

引用

Physical Review Applied 2023年第4期19卷 044045-044045页

作者： John Glennon Francesco Bertazzi Alberto Tibaldi Enrico Bellotti Division of Material Science and Engineering (MSE) Boston University Boston Massachusetts 02215 USA Department of Electronics and Telecommunications (DET) Politecnico di Torino and IEIIT-CNR Torino 10129 Italy Department of Electrical and Computer Engineering (ECE) Boston University Boston Massachusetts 02215 USA

Type-II superlattices (T2SLs) are being investigated as an alternative to traditional bulk materials in infrared photodetectors due to predicted fundamental advantages. Subject to significant quantum effects, these materials require the use of quantum transport methodologies, such as the nonequilibrium Green’s function (NEGF) formalism to fully capture the relevant physics without uncontrolled approximations. Carrier mobility is a useful parameter that affects carrier collection in photodetectors. This work investigates the application of mobility extraction methodologies from quantum transport simulations in the case of T2SLs exemplified using an InAs/GaSb midwave structure. In a resistive region, the average velocity can be used to calculate an apparent mobility that incorporates both diffusive and ballistic effects. However, the validity of this mobility for predicting device properties is limited to cases of diffusive limited transport or when the entire device can be included in the simulation domain. Two methods that have been proposed to extract diffusive limited mobility, one based on approximating the ballistic component of transport and the other which considers the scaling of resistance with simulation size, were also studied. In particular, the resistance scaling approach is demonstrated to be the method most physically relevant to predicting macroscopic transport. We present a method for calculating the mobility from resistance scaling considerations that accounts for carrier density variation between calculations, which is particularly relevant in the case of electrons. Finally, we comment on the implications of applying the different mobility extraction methodologies to device property predictions. The conclusions of this study are not limited to T2SLs, and may be generally relevant to quantum transport mobility studies.

关键词： Ballistic transport Carrier dynamics Electrical conductivity Optoelectronics Quantum transport III-V semiconductors Superlattices Nonequilibrium Green's function

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Techniques for Image Recognition in IoT-Enabled Surveillance Systems

Deep Learning Techniques for Image Recognition in IoT-Enable...

引用

Intelligent Technologies (ACOIT), Asian Conference on

作者： V Dankan Gowda Y. Vishnu Tej Vidya Sagar Potharaju Premkumar Reddy Jakkidi Aanchal Sharma N Sudhakar Reddy Department of Electronics and Communication Engineering BMS Institute of Technology and Management Bangalore Karnataka Department of Computer Science and Systems Engineering Andhra University Visakhapatnam India Department of ECE Vignana Bharati Institute of Technology Ghatkesar Hyderabad India 15950 paramount way Frisco Texas DCSA Panjab University Chandigarh India Department of ECE School of Engineering Mohan Babu University Tirupati India

ISBN: (数字)9798350374957

ISBN: (纸本)9798350374964

This paper proposed an improved method that can be used in the identification of images within IoT based surveillance systems through the use of deep learning techniques especially the CNNs. The growth of concern and complexity therefore entails massive feeding from bursts of data from surveillance cameras, hence the need for reliable algorithms for processing the data in real-time with reasonable accuracy. The described system can be described as inclusive of IoT devices communicating with edge computing and cloud services for the purpose of scalability and performance enhancement. In this study, a very sophisticated experimental setup was employed; the authors used a number of datasets for surveillance purposes to evaluate the model. The results revealed that the segments of the method achieve a high accuracy and are continuously running through data in diverse surveillance scenarios while also being scalable. In the results section, we realized that CNN model was able to handle various environmental conditions such as; extreme lightening and occlusion. On the basis of the above mentioned data, it will be possible to suggest that this approach is rather superior compared to the other conventional approaches and therefore can be suggested as the possible solution of the modern conditions of surveillance. It thus provides platform for the advancement of intelligent surveillance system for use in smart city, security and safety application.

关键词： Deep learning Accuracy Image recognition Smart cities Surveillance Computational modeling Real-time systems Internet of Things Security Edge computing

来源：评论

学校读者我要写书评

暂无评论

Building AI-Driven Frameworks for Real-Time Threat Detection and Mitigation in IoT Networks 7

Building AI-Driven Frameworks for Real-Time Threat Detection...

引用

7th IEEE International Conference on Emerging Smart Computing and Informatics, ESCI 2025

作者： Joshi, Manjushri Tiwari, Ankita Dhabliya, Dharmesh Lavate, Santosh H. Ajani, Samir N. Gandhi, Yatin ECE(AI&ML) Department of Polytechnic & Skill Development Dr.Vishwanath Karad MIT World Peace University Pune India Department of Engineering Mathematics College of Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram AP Guntur India Department of Information Technology Vishwakarma Institute of Information Technology Maharashtra Pune India Department of Electronics and Telecommunication Engineering AISSMS College of Engineering Pune India School of Computer Science and Engineering Ramdeobaba University (RBU) Nagpur India Competent Softwares Maharashtra Nagpur India

ISBN: (纸本)9798331515683

The fast growth of Internet of Things (IoT) networks has made security risks more complicated and numerous. To find and stop these threats in real time, we need new and creative solutions. This article talks about an AI-powered system that can make IoT networks safer by finding and stopping threats as they happen. The system uses both machine learning (ML) and deep learning (DL) to look at real-time data from IoT devices and find strange patterns that could be signs of an attack. This is done by using advanced algorithms, like decision trees, neural networks, and reinforcement learning, to learn new things all the time and adjust to new dangers. To improve the efficiency of identification and cut down on false positives, a mixed method is used that combines controlled and unstructured learning. The system also has an automatic mitigating procedure that separates infected devices and stops them from doing more damage when risks are found. Compared to standard security methods, our results show that the proposed structure makes danger identification and prevention much more effective in IoT networks. The system is very good at finding different kinds of threats, like DDoS, malware, and illegal access, and it does this while using very little computing power. This means it can be used in IoT settings with limited resources. This study provides a flexible and scalable way to protect the IoT environment, which is becoming more and more linked. © 2025 IEEE.

关键词： AI-driven framework Anomaly detection Deep learning IoT network security Machine learning Real-time threat detection

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：