检索结果-内蒙古大学图书馆

Device Intelligence, Computing and communication Technologies, (DICCT), International Conference on

作者： Deepak Upadhyay Sonal Malhotra Mridul Gupta Somesh Mishra Dept. of Computer Science and Engineering Graphic Era Hill University Dehradun India Dept. of Electronics and Communication Engineering Graphic Era deemed to be University Dehradun India Dept. of Computer Science and Engineering Graphic Era Deemed to be University Dehradun India

ISBN: (数字)9798350372847

ISBN: (纸本)9798350372854

In This research investigates the streamlined implementation of Semantic Segmentation Neural Networks through advanced techniques: pruning and quantization. Leveraging the CamVid dataset, our study achieved remarkable reductions in computational complexity and memory usage. Pruning removed redundant connections, effectively reducing learnable parameters, while quantization significantly minimized memory footprint. Despite these optimizations, the networks maintained high semantic segmentation accuracy. The implications of our findings are pivotal, particularly in resource-constrained applications like autonomous driving and image analysis. By enhancing efficiency without compromising accuracy, this research facilitates the seamless integration of deep learning models into real-time systems. Our study not only advances the field of computer vision but also underscores the practical feasibility of deploying sophisticated neural networks in practical, resource-efficient contexts.

关键词： computer vision Quantization (signal) Image analysis Semantic segmentation Computational modeling Artificial neural networks Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Prostate Cancer Classification using Cat Swarm Optimization with Deep Learning on MRI Images 7

Prostate Cancer Classification using Cat Swarm Optimization ...

引用

7th International Conference on electronics, communication and Aerospace Technology, ICECA 2023

作者： Haritha, V. Archana, K.V. Balasubramaniam, D. Uma Maheswari, S. Sasireka, P. Suja, G.P. RMK Engineering College Department of CSE Chennai Kavarapettai India School of Engineering Department of Electronics and Communication Engineering Avinashilingam Institute for Home Science and Higher Education for Women Coimbatore India VelTech Rangarajan Dr Sagunthala R&D Institute of Science and Technology Department of Biomedical Engineering Tamilnadu Chennai India Saveetha Institute of Medical and Technical Sciences Department of Biosciences Saveetha School of Engineering Chennai India S. A. Engineering College ECE Department Chennai India Research Center of Computer Science Muslim Arts College Kanyakumari Thiruvithancode629174 India

ISBN: (纸本)9798350340600

Prostate Cancer (PC) is a common malignancy amongst men globally, and accurate classification plays a significant part in its diagnoses and treatment planning. Due to its superior soft tissue contrast, Magnetic Resonance Imaging (MRI) has developed as a valuable imaging modality for the assessment of PC. PC classification on MRI is a major task in medical imaging analysis, and deep learning (DL) approaches are employed to accomplish automated and accurate classification. In recent times, Convolutional Neural Network (CNN) structure was selected for the classification of PC. This manuscript introduces an automated Prostate Cancer Classification using Cat Swarm Optimization with Deep Learning (PCC-CSODL) technique on MRI Images. The main purpose of the PCC-CSODL algorithm lies in the effectual and accurate identification of PC. For achieving this, the PCC-CSODL technique involves NASNet feature extractor at the initial stages. In addition, the CSO algorithm is used for the optimum hyperparameter selection of the NASNet model. For classification purposes, attention based long short term memory (ALSTM) model can be used. The results demonstrated the effectiveness of the PCC-CSODL technique in accurately classifying PC on MRI. It has the potential to assist clinicians in making informed decisions and enhancing patient outcomes in PC management. © 2023 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Socio-technical Approaches to Solid Waste Management in Rural India: A Case Study of Smart Pipe Composting in Raichur District, Karnataka 8th

Socio-technical Approaches to Solid Waste Management in Rura...

引用

8th International Conference on Information and communication Technology for Competitive Strategies, ICTCS 2023

作者： Chethan, R.K. Jambha, Aniketh V. Pathania, Chirag Siddhartha, Mutyala Sai Sri Sanjay Arifuzzaman Darshan, K. Cornet, Souresh Jayaprakash, Sajithkumar K. Department of Commerce and Management School of Arts Humanities and Commerce Amrita Vishwa Vidyapeetham Mysuru India Department of Computer Science and Engineering Amrita School of Engineering Amrita Vishwa Vidyapeetham Bengaluru India Department of Electrical and Electronics Engineering Amrita School of Engineering Amrita Vishwa Vidyapeetham Bengaluru India Department of Artificial Intelligence Amrita School of Engineering Amrita Vishwa Vidyapeetham Bengaluru India Department of Computer Science Amrita School of Computing Amrita Vishwa Vidyapeetham Mysuru Campus Karnataka Mysuru India Department of Visual Communication School of Arts Humanities and Commerce Amrita Vishwa Vidyapeetham Mysuru India Amrita School for Sustainable Futures Amrita Vishwa Vidyapeetham Amritapuri India

ISBN: (纸本)9789819994885

Rural areas in developing countries are plagued with complex, intricate challenges. In India, rural communities are seriously lagging regarding Sanitation and Waste management facilities. The majority of communities lack the resources to address those issues. Government programs have partly been able to address those issues, but much still needs to be done to solve the challenges completely. This study aimed to understand better the challenges associated with Solid Waste Management in rural India. It specifically explores how technology can help to complete the last mile of sustainability through a user-centered and participatory problem-solving approach. Taking the case of a community in Raichur district, Karnataka, a smart pipe composting design is proposed to address the Solid Waste Management challenges in the community. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Waste management

来源：评论

学校读者我要写书评

暂无评论

End-to-End SNR Capacity and throughput enhancement Using Non-Orthogonal Multiple access and Massive MIMO in 5G

End-to-End SNR Capacity and throughput enhancement Using Non...

引用

Intelligent Technologies (CONIT), International Conference on

作者： Deepak Upadhyay Abhay Upadhyay Mridul Gupta Kunj Bihari Sharma Dept. of Computer Science and Engineering Graphic Era Hill University Dehradun India Dept. of Computer Science and Engineering Graphic Era deemed to be University Dehradun India Dept. of Electronics and Communication Engineering Graphic Era deemed to be University Dehradun India

ISBN: (数字)9798350349900

ISBN: (纸本)9798350349917

This study provides a detailed analysis of the potential improvements in 5G network performance due to the adoption of NOMA and Massive MIMO technologies. Obtaining higher data rates, reduced latency, and increased overall network capacities remain a primary objective, and the research provides a comparison based on simulated data. Simulation models are designed to compare the proposed model against the conventional implementation of 5G networks based on a set of primary indicators, namely, throughput and latency. An abstract Wave Efficiency indicator is also presented to showcase a new metric for determining the qualitative improvements in signal processing and spectrum utilization. As the results of the research have demonstrated, the incorporation of NOMA and Massive MIMO increases overall network throughput while reducing latency. This demonstrates the potential contributions of these technologies to making wireless communications systems more efficient and reliable. The introduction of the Wave Efficiency is offered as a measurable variable for displaying the qualitative improvement in the wireless communications technologies, facilitating further implementation of NOMA and Massive MIMO in 5G networks.

关键词： Measurement NOMA 5G mobile communication Wireless networks Massive MIMO Signal processing Throughput

来源：评论

学校读者我要写书评

暂无评论

Development and Performance Evaluation of a Blockchain Associated E-Voting System in IoT-Enabled Smart-Cities 3

Development and Performance Evaluation of a Blockchain Assoc...

引用

3rd International Conference on Intelligent engineering and Management, ICIEM 2022

作者： Bhavani, G. Lakshmi Ramu, M. Gupta, Sonali Akula, Sai Parichit Gomathi, S. Yadav, Aryamaan K D Reddy College of Engineering and Technology Department of Electronics and Communication Engineering Telangana Hyderabad India Vignan Foundation for Science Technology and Research Department of Management Studies AP Vadlamudi India J C Bose University of Science and Technology Department of Computer Engineering Haryana Faridabad India St. Peter's Engineering College Department of Computer Science and Engineering Hyderabad India CADD Centre Training Services Product Lead and Lead Technical Trainer Cloud Campus Tamilnadu Coimbatore India Manipal Institute of Technology Department of Electronics and Communication Engineering Karnataka Manipal India

ISBN: (数字)9781665467568

ISBN: (纸本)9781665467568

An atmosphere is referred by the smart city, in which every available asset and current improvements are conveyed in an orderly and shrewd manner. Insightful detectors (Internet-of-Things (IoT) components) functioning in tandem along 5G innovation have been continually proving to be more inevitable and successful in achieving clients' desires. In the various IoT application conditions, e-voting a ballot has been the key use to IoT, which propels this to the advanced level to the development of smart city innovations. During generalized usages, each of the components have been estimated as pleasant as well as trustworthy. Anyhow, during the practice, uninvited guests can disrupt gadgets in order to operate perniciously to the point of corruption of the organization's administrations. As a result, the protection and security flaws in e-casting a ballot framework, in particular, create a huge concern where gate crashers might use numerous hacks to manipulate the surveys. As a result, the prospective test in distinguishing appropriate IoT components by spiteful with recording the certain parameters over a friendly streamlining agent to establish a real correspondence atmosphere. Furthermore, to prevent future changes to information collected by intelligence gadgets, a BC has been assisted, where squares about entire genuine IoT components have been documented. This paper describes a safe as well as generalized method of e-voting, a ballot using BC IoT, having a goal of identifying also the solution of different risks posed with a gate crasher at different stages. Furthermore, in accepting the scheduled instrument, this has been tested counter to several safety boundaries like information adjustment, DoS as well as DDoS attacks, along with the validation time. © 2022 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Multi-Tap Canceller for Wi-Fi communication in Band with Fill Duplex 6

Multi-Tap Canceller for Wi-Fi Communication in Band with Fil...

引用

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

作者： Saha, Supratim Gautam, Rajni Belwal, Pravesh Hemelatha, S. Kannimuthu, S. Aher, Vijaya N. Swami Vivekanand Subharti University Electronics and Communication Engineering Meerut India School of Basic & Applied Sciences K. R. Mangalam University Department of Physics Gurugram India Dev Bhoomi Uttarakhand University Electronics and Communications Engineering Uttarakhand India Karpagam Academy of Higher Education Department of Computer Science Engineering Coimbatore India Karpagam College of Engineering Department of Information Technology Coimbatore India Vishwakarma Institute of Information Technology E&TC Pune India

ISBN: (纸本)9798350304480

Since they involve the appropriate reduction of self-interference induced by the co-located transmitters, in-band full-duplex wirelessly network is difficult to implement. In order to increase system separation, the straight antennas coupling and multichip effects that make up a normal disturbance channel are both cancelled using a novel input time line RF recycled content structure shown in this work. A four-tap recycled content prototype had been evaluated under various settings and discovered to provide, in isolation situations, an average of 30 dB of signal cancelation above a 30 MHz band centered at 2.45 GHz. The canceller increased the overall analog seclusion to 90 dB for such cases when used in conjunction with only Omni-directional high-isolation antennas. The canceller reduced a +30 dbm OFDM in an enclosed environment. Along a 20 MHz band with a 2.45 GHz center, the device reduced the noise by 22 dB and generated 78 dB of overall analog seclusion. This thorough evaluation establishes the degree of analogue interference cancellation that may be anticipated for the various situations taken into account, as well as the effectiveness constraints of an optimized multi RF attenuator. © 2023 IEEE.

关键词： Adaptive canceller analog cancellation IBFD in-band full-duplex wireless communication interference cancellation RF cancellation simultaneous transmit and receive STAR

来源：评论

学校读者我要写书评

暂无评论

Joint Power and Channel Allocation in Fading Channels Using Deep Reinforcement Learning

Joint Power and Channel Allocation in Fading Channels Using ...

引用

Advanced Computing & communication Technologies (ICACCTech), International Conference on

作者： Deepak Upadhyay Abhay Upadhyay Mridul Gupta Kunj Bihari Sharma Dept. of Computer Science and Engineering Graphic Era Hill University Dehradun India Dept. of Computer Science and Engineering Graphic Era Deemed to be University Dehradun India Dept. of Electronics and Communication Engineering Graphic Era deemed to be University Dehradun India

ISBN: (数字)9798331519056

ISBN: (纸本)9798331519063

This paper investigates joint power and channel allocation under fading communication channels using Deep Reinforcement Learning (DRL). To this end, we design a DRL to allocate dynamic resources with different network condition properly and achieve the spectral efficiency improvement while reducing latency to meet lower bound in cost function as well keeping target fairness. Results show that our DRL-based approach can achieve better spectrum efficiency and latency than traditional algorithms while at the same time, sustaining a higher value of fairness index. In addition, it is observed that the DRL method also offers both adaptability (with fast adaptation to network changes) and robustness in performance but at a higher computational expense. Our results illustrate that the DRL-based technique may serve as a strong, scalable candidate in future wireless systems up to several orders of magnitude better than existing resource allocation schemes.

关键词： Fading channels Wireless communication Lower bound Spectral efficiency Heuristic algorithms Neural networks Deep reinforcement learning Robustness Resource management Next generation networking

来源：评论

学校读者我要写书评

暂无评论

Leveraging Machine Learning Algorithms to Optimize Diet Maintenance Based on User Food Intake and Fitness Data

Leveraging Machine Learning Algorithms to Optimize Diet Main...

引用

Sustainable communication Networks and Application (ICSCNA), International Conference on

作者： K. Clarinda N. Deepa R. Dhamotharan R. Santhana Krishnan J. Relin Fransis Raj J. V. Anchitaalagammai Department of Management Studies SCAD College of Engineering and Technology Cheranmahadevi India Department of Artificial Intelligence and Data Science PSNA College of Engineering and Technology Dindigul India Department of Computer Science and Information Technology Kalasalingam Academy of Research and Education Krishnankoil India Department of Electronics and Communication Engineering SCAD College of Engineering and Technology Cheranmahadevi India Department of Electronics and Communication Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India Department of Computer Science and Engineering Velammal College of Engineering and Technology Madurai India

ISBN: (数字)9798331530013

ISBN: (纸本)9798331530020

The increasing prevalence of lifestyle-related health issues has necessitated the development of innovative approaches to diet management. This research introduces the Adaptive Eating Pattern Predictor (AEPP), a novel machine learning algorithm designed to optimize diet maintenance by analyzing user food intake and fitness data. The AEPP combines the predictive capabilities of Artificial Neural Networks (ANN) with the probabilistic modeling of Markov Chains, enabling accurate forecasting of future eating patterns based on historical dietary and activity data. A comprehensive simulation analysis was conducted to evaluate the performance of the AEPP against existing algorithms, including traditional recommendation systems and basic machine learning models. Various simulation metrics, such as accuracy, precision, recall, and F1 score, were employed to compare the effectiveness of the AEPP in providing personalized dietary recommendations. The results demonstrate that the AEPP significantly outperforms existing algorithms, highlighting its potential as a valuable tool for individuals seeking to maintain a balanced diet in alignment with their fitness goals. This study contributes to the field of nutritional science by showcasing the advantages of integrating advanced machine learning techniques in personal diet management.

关键词： Adaptation models Machine learning algorithms Accuracy Adaptive systems Collaboration Artificial neural networks Predictive models Prediction algorithms Maintenance Wearable devices

来源：评论

学校读者我要写书评

暂无评论

A Network for Medical Segmentation of Images with Multiple Centers That Preserves Privacy 2

A Network for Medical Segmentation of Images with Multiple C...

引用

2nd IEEE Global Conference on communications and Information Technologies, GCCIT 2024

作者： Jayaprakash, B. Bordoloi, Dibyahash Mehta, Pradnya Amudha, A. Marwaha, Pradeep Selvan, K. Senthamil School of Sciences Computer Science & It Karnataka Bangalore India Graphic Era Hill University Dehradun India Graphic Era Deemed to be University Uttarakhand Dehradun248002 India Vishwakarma Institute of Technology Pune India Karpagam Academy of Higher Education Department of Electrical and Electronics Engineering Coimbatore641021 India Chitkara University Centre of Research Impact and Outcome Punjab Rajpura140417 India Prince Shri Venkateshwara Padmavathy Engineering College Department of Electronics and Communication Engineering Chennai127 India

ISBN: (纸本)9798350388916

An innovative system for safe medical image segmentation in multi-center collaborations, the Multi-Center Privacy-Preserving Network is introduced in this research. Reduce data transmission traffic while improving data privacy protection with our methodology's novel method for multi-center collaborative learning. Our solution relies on a single encrypted data transfer, as opposed to federated learning's round-by-round model data communication among the central server as well as local servers. The suggested CNN is a three-layer architecture that includes networks for encryption, segmentation, and decryption. Consequently, we provide a method for secure and adaptable cloud-based medical picture segmentation using a convolutional neural network. This research demonstrates that three cloud-based servers can train the algorithm using user-provided photos;nevertheless, they are unable to access comprehensive data on the model's variables and user input. The experiment verifies that the technique, when put into effect, can guarantee the system's security and efficiency while simultaneously reducing the user's compute and storage loads. We use an encryption network to transform the raw picture data into ciphertext, and then we present a refined U-Net to separate the encrypted image data. The last step is to use a decryption network to get the segmentation mask. Computable image encryption is made possible by this design, which allows for ciphertext-based picture segmentation. We test our method on three datasets, one of which is a CTPA dataset, and two of which are cardiac MRI datasets. We show that MP-Net may safely use data from many sources to build a more accurate and comprehensive segmentation model. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Spatiotemporal dynamics in a network of modified Morris–Lecar neurons with nonlinear magnetic flux diffusion

引用

The European Physical Journal Special Topics 2025年 1-19页

作者： Seralan, Vinoth Leela Lakshmi, S. Suresh Babu, Kunchala Rajagopal, Karthikeyan Center for Nonlinear and Complex Networks SRM Institute of Science and Technology Chennai India Department of Electronics and Communication Engineering Vemu Institute of Technology Chittoor India Department of Computer Science Engineering PSCMR College of Engineering and Technology Vijayawada India Center for Cognitive Science Trichy SRM Medical College Hospital and Research Center Trichy India Center for Research Easwari Engineering College Chennai India

In this work, a network of Morris–Lecar neurons with electromagnetic induction is imposed with nonlinear magnetic flux diffusion. We study wave propagation in a network of Morris–Lecar (ML) neurons with magnetic flux diffusion, connected to the local nodes of the nearest neighbors in a $$110 \times 110$$ lattice of neurons with periodic boundary conditions. First, we explore the effect of various initial conditions on the modified ML neuron network without imposing external stimuli. Subsequently, we apply external stimuli at different positions and study wave propagation by changing the amplitude and frequency of the stimuli. The effects of varying Nernst potential of potassium ions, coupling strengths, and flux constants are also analyzed. The resulting collective dynamics of the considered neuronal network are provided in snapshots with different model parameters. This study offers a novel perspective on wave propagation in networks of biological neurons.

关键词：

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：