检索结果-内蒙古大学图书馆

An Optimal Weighted Ensemble of 3D CNNs for Early Diagnosis of Alzheimer’s Disease

SN computer science 2024年第2期5卷 252页

作者： Dharwada, Sriram Tembhurne, Jitendra Diwan, Tausif Department of Computer Science and Automation Indian Institute of Science Bangalore India Department of Computer Science and Engineering Indian Institute of Information Technology Maharashtra Nagpur 441108 India

Alzheimer disease (AD) is a chronic neurological disorder in which the loss of brain cells causes dementia. Early and accurate diagnosis of AD will lead to better treatment of the disease before irreversible brain damage has been occurred. This paper proposes the classification of Alzheimer's disease using 3D structural Magnetic Resonance Imaging (sMRI) images through 3D convolutional neural networks (CNNs). Most existing methods utilizing 3D subject-level CNNs for Alzheimer's disease classification design a single model which relies on a very large training dataset for improved generalization. Herein, we address this issue through 3D transfer learning which makes use of knowledge gained from a pre-trained task. We train 3D versions of five classical 2D image classification architectures—ResNet, ResNeXt, SE-ResNet, SE-ResNeXt, and SE-Net—by initializing each model with pre-trained weights from their 2D counterparts, and combine their predictions through a weighted average method. The weights assigned to each model of the ensemble are optimized to achieve a performance better than any single 3D CNN model. With a relatively smaller training dataset, the proposed model obtains 97.27%, 82.33%, 90.41%, 84.22%, 84.26%, and 77.1% accuracies for the Alzheimer’s disease (AD) versus cognitively normal (CN), early mild cognitive impairment (EMCI) versus CN, late mild cognitive impairment (LMCI) versus CN, EMCI versus AD, LMCI versus AD, and EMCI versus LMCI classification tasks, outperforming current state-of-the-art methods, and indicating the effectiveness of our proposed model. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd 2024.

关键词： Alzheimer’s disease Convolutional neural networks Ensemble learning Transfer learning

来源：评论

学校读者我要写书评

暂无评论

TISCMB: design of a highly efficient blockchain consensus model with trust integrated self-correcting miner selection

引用

International Journal of information technology (Singapore) 2023年第4期15卷 1845-1858页

作者： Ravi Kumar, Shipra Goyal, Mukta Department of Computer Science Engineering and Information Technology Jaypee Institute of Information Technology Noida India

Blockchain is rapidly becoming the de facto standard for storage applications requiring high transparency, record traceability, immutable data, and distributed processing. Researchers have proposed a large number of such models, including Proof-of-Work (PoW), Proof-of-Stake (PoS), Proof-of-Authority (PoA), etc. Due to their respective limitations, each of these models is applied to context-specific blockchain deployments. In addition, the selection of the most efficient miners for hash calculation and verification is a complex task that must be executed with high efficiency in order to improve network performance. The novel contribution of this work is to design a hybrid consensus model which uses a combination of Proof-of-Work and Proof-of-Stake consensus methods for fast hash computations. Proposed model is supported by a highly efficient trust-based miner selection method that aids in choosing the most optimal miner nodes with low processing delay and high energy efficiency. In addition, this text proposes a self-correcting mechanism for the designed blockchain, which assists in the blockchain's correction in the event of any internal or external attacks. Due to these characteristics, it is observed that the proposed model has 20% less delay, 8% less energy consumption, and 15% higher levels of trust than standard PoS and PoW consensus models. The model was also subjected to various attack scenarios, and it was determined that it is capable of self-correcting the node's internal blockchain with a 99.9% success rate, thereby enhancing its real-time deployment capabilities. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's institute of computer Applications and Management.

关键词： Blockchain Consensus Delay Energy Self-correcting Trust

来源：评论

学校读者我要写书评

暂无评论

Effective Customer Review Analysis Using Combined Capsule Networks with Matrix Factorization Filtering

引用

computer Systems science & engineering 2023年第3期44卷 2537-2552页

作者： K.Selvasheela A.M.Abirami Abdul Khader Askarunisa Department of Computer Science and Engineering Sree Sakthi Engineering CollegeCoimbatoreTamilnadu641104India Department of Information Technology Thiagarajar College of EngineeringMaduraiTamilnadu625015India Department of Computer Science and Engineering Sethu Institute of TechnologyVirudhunagarTamilnadu626115India

Nowadays,commercial transactions and customer reviews are part of human life and various business *** technologies create a great impact on online user reviews and activities,affecting the business *** reviews and ratings are more helpful to the new customer to purchase the product,but the fake reviews completely affect the *** traditional systems consume maximum time and create complexity while analyzing a large volume of customer ***,in this work optimized recommendation system is developed for analyzing customer reviews with minimum ***,Amazon Product Kaggle dataset information is utilized for investigating the customer *** collected information is analyzed and processed by batch normalized capsule networks(NCN).The network explores the user reviews according to product details,time,price purchasing factors,etc.,ensuring product quality and *** effective recommendation system is developed using a butterfly optimized matrix factorizationfiltering *** the system’s efficiency is evaluated using the Rand Index,Dunn index,accuracy,and error rate.

关键词： Recommendation system customer reviews amazon product kaggle dataset batch normalized capsule networks butterfly optimized matrix factorizationfiltering

来源：评论

学校读者我要写书评

暂无评论

Integration of Blockchain and IPFS: healthcare data management & sharing for IoT Environment

引用

Multimedia Tools and Applications 2024年 1-22页

作者： Mishra, Rajiv Kumar Yadav, Rajesh Kumar Nath, Prem Department of Computer Science & amp Engineering Jaypee Institute of Information Technology Noida India Department of Computer Science & amp Engineering Delhi Technological University Delhi India Department of Computer Science HNB Garhwal University Srinagar India

The immense volume of data generated and collected by smart devices has significantly enhanced various aspects of our daily lives. However, safeguarding the sensitive information shared among these devices is crucial. Ensuring the security of the Internet of Things (IoT) ecosystem from unauthorized access is imperative. Blockchain technology emerges as a promising solution to address these security concerns. Nevertheless, the effectiveness of Blockchain in handling the extensive data generated by smart devices is challenged by the rapid pace of IoT data generation and the slower transaction validation speed within Blockchain networks. This research aims to resolve these issues by integrating Blockchain with the Inter-Planetary File System (IPFS), creating a robust framework for secure data recording on a distributed storage network while enabling authorized access to the stored data. The proposed mechanism involves defining and recording access policies and cryptographic hash content on the Blockchain network, while storing the actual IoT-generated data on IPFS to enhance the confidentiality, integrity, and availability (CIA) triad. Performance assessments of the proposed scheme demonstrate its security and practicality, validating its potential for real-world application. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

A deep learning-based early alzheimer’s disease detection using magnetic resonance images

引用

Multimedia Tools and Applications 2025年第16期84卷 16561-16582页

作者： Suchitra, S. Krishnasamy, Lalitha Poovaraghan, R.J. Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R &D Institute of Science and Technology Avadi Tamil Nadu Chennai India Department of Information Technology Nandha Engineering College Tamil Nadu Erode India Department of Information Technology Jaya Engineering College Tamil Nadu Thiruninravur Chennai India

Alzheimer’s Disease (AD) is a degenerative, chronic condition of the brain for which there is now no effective treatment. However, there are medications that can slow its development. In order to stop and control the development of AD, earlier diagnosis of the disease is quintessential. Our proposed method’s primary objective is to establish a comprehensive model for the prior detection of Alzheimer’s disease and the categorization of distinct AD stages. This work employs a deep learning methodology, especially CNN. The proposed approach makes use of well-known models that have already been trained to classify medical images, like the EfficentNetB7 model, by applying the transfer learning principle. In order to achieve greater accuracy, convolutional neural networks (CNNs) are frequently scaled up as new resources become available at a fixed cost throughout the construction phase. A compound coefficient is used by the CNN architecture and scaling approach, which is the foundation of the pre-trained EfficientNetB7 model, to scale the dimensions equally. This proposed EfficientNetB7 model is quicker, easier, and more effective than other pre-trained models like VGG19 and InceptionV3. The proposed model includes simple structures that have memory requirements, provide manageable time, overfitting, and low computational complexity as well as training and inference speeds. The Alzheimer’s disease Neuroimaging Initiative (ADNI) dataset was employed for a comprehensive assessment of the method proposed, utilizing well-known performance metrics including sensitivity, specificity, and accuracy. The findings revealed that the improvised results achieved the accuracy metric when compared to existing methods. The EfficientNetB7 model has been enhanced, and this model achieves a sensitivity of 98.08%, specificity-98%, accuracy-98.2%, and F-score-98.95%, for multi-class AD stage classifications. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, par

关键词： Magnetic resonance

来源：评论

学校读者我要写书评

暂无评论

IDedupNet: A MobileNetV3-Based Deep Learning Framework for Efficient Image Deduplication in Cloud Computing Environments

Informatica (Slovenia)

引用

Informatica (Slovenia) 2025年第13期49卷 143-162页

作者： Mohiuddin, Mohd Hasan Tamilselvan, Latha Department of Computer Science and Engineering B.S. Abdur Rahman Crescent Institute of Science &Technology Vandalur Chennai600048 India Department of Information & Technology B.S. Abdur Rahman Crescent Institute of Science &Technology Vandalur Chennai600048 India

Image deduplication is becoming increasingly important for cloud storage infrastructures to handle the increasing amount of multimedia material. Through increased storage efficiency, effective picture deduplication may optimize resources and save expenses. It also improves performance by facilitating quicker access, utilizing less bandwidth, and enhancing data integrity. Although heuristic-based classical deduplication techniques work well in various storage infrastructures, they cannot keep up with the dynamic nature of cloud storage resources. This study presents IDedupNet, a revolutionary DL-based framework that improves infrastructure performance in cloud computing by efficiently detecting duplicate and near-duplicate photos. Our approach leverages MobileNetV3 for feature extraction and CNN-based encodings for image deduplication, enabling it to manage duplicate photos in highly dynamic contexts efficiently. Additionally, we provide a Learning-Based Image Deduplication (LBID) approach that improves deduplication performance by extending the use of the IDedupNet model. Experimental evaluation demonstrates a high accuracy of 98.68% on benchmark datasets, consistently outperforming existing models. The underlying technique and deep learning framework may be easily integrated into real-time cloud storage systems to increase customer satisfaction and infrastructure efficiency. © 2025 Slovene Society Informatika. All rights reserved.

关键词： Cloud storage

来源：评论

学校读者我要写书评

暂无评论

DNA Computing with Water Strider Based Vector Quantization for Data Storage Systems

引用

computers, Materials & Continua 2023年第3期74卷 6429-6444页

作者： A.Arokiaraj Jovith S.Rama Sree Gudikandhula Narasimha Rao K.Vijaya Kumar Woong Cho Gyanendra Prasad Joshi Sung Won Kim Department of Networking and Communications College of Engineering and TechnologySRM Institute of Science and TechnologyKattankulathur603203India Department of Computer Science Engineering Aditya Engineering CollegeSurampalemAndhra Pradesh533437India Department of Computer Science and Engineering Vignan’s Institute of Information TechnologyVisakhapatnam530049India Department of Computer Science and Engineering Vignan’s Institute of Engineering for WomenVisakhapatnam530049India Department of Software Convergence Daegu Catholic UniversityGyeongsan38430Korea Department of Computer Science and Engineering Sejong UniversitySeoul05006Korea Department of Information and Communication Engineering Yeungnam UniversityGyeongsan-siGyeongbuk-do38541Korea

The exponential growth of data necessitates an effective data storage scheme,which helps to effectively manage the large quantity of *** accomplish this,Deoxyribonucleic Acid(DNA)digital data storage process can be employed,which encodes and decodes binary data to and from synthesized strands of *** quantization(VQ)is a commonly employed scheme for image compression and the optimal codebook generation is an effective process to reach maximum compression *** article introduces a newDNAComputingwithWater StriderAlgorithm based Vector Quantization(DNAC-WSAVQ)technique for Data Storage *** proposed DNAC-WSAVQ technique enables encoding data using DNA computing and then compresses it for effective data ***,the DNAC-WSAVQ model initially performsDNA encoding on the input images to generate a binary encoded *** addition,aWater Strider algorithm with Linde-Buzo-Gray(WSA-LBG)model is applied for the compression process and thereby storage area can be considerably *** order to generate optimal codebook for LBG,the WSA is applied to *** performance validation of the DNAC-WSAVQ model is carried out and the results are inspected under several *** comparative study highlighted the improved outcomes of the DNAC-WSAVQ model over the existing methods.

关键词： DNA computing data storage image compression vector quantization ws algorithm space saving

来源：评论

学校读者我要写书评

暂无评论

Empirical techniques for effort estimation in designing effective ML models

引用

International Journal of computers and Applications 2025年第2期47卷 226-234页

作者： Padmanabha Reddy, Y.C.A. Kosuru, Sai Sathwik Sirisalla, Nageswara Rao Vivekananda, G.N. Perala, Venkata Akanksha Department of Artificial Intelligence and Machine Learning Chaitanya Bharati Institute of Technology Telangana Hyderabad India Department of CSE B V Raju Institute of Technology Telangana Narsapur India Department of Computer Science and Engineering K.S.R.M. College of Engineering AP Kadapa India School of Computer Science Engineering and Information Systems Vellore Institute of Technology Vellore India

Machine Learning Research often involves the use of diverse libraries, modules, and pseudocodes for data processing, cleaning, filtering, pattern recognition, and computer intelligence. Quantization of Effort Required for the above cumulative processes is rarely discussed in the existing works and The time to reach the desired level of the model's functionality is essential to gauge the environment training for the model training and pre-deployment testing. In this study, we empirically defined the manual-cum-computational effort required for the model development in terms of 2-time factors: time-to-live (time until 1st code modification) and time-for-modification (time between 2 codebase changes) taken together in a mathematical model to compute Effort Factor(quantitative measure of determining effort needed to design ML algorithms). The study is novel in terms of how the effort required to create ML models is calculated with a particular focus on the manual effort direction. The results and the findings obtained can be used for determining the total time needed to synthesize ML models and frameworks in terms of code change cycles and implementation strategies marking a 25% performance increase in the current method above the Standard Pipeline. © 2025 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Pipeline codes

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

Efficient Collision-Free Motion Planning in Distributed Multi-Robot Systems 17

Efficient Collision-Free Motion Planning in Distributed Mult...

引用

17th International Conference on COMmunication Systems and NETworkS, COMSNETS 2025

作者： Sharma, Om Chakraborty, Nilotpal India Institute of Information Technology Department of Computer Science and Engineering Assam Guwahati India

ISBN: (纸本)9798331531195

In distributed multi-robot systems, ensuring collision-free motion planning is a complex challenge, especially in dynamic environments where multiple robots are operating simultaneously. Traditional path-planning algorithms are effective for individual robot navigation but struggle when dealing with the unpredictable movements of other robots in the system. To overcome these limitations, this research focuses on advanced motion planning techniques that ensure safe and efficient robot coordination. We model the overall motion planning problem into a two-dimensional grid and our objective is to minimize both the time and the energy taken by the robots to reach their destinations from their respective sources. We enhance standard path-finding algorithms such as A∗ search, along with Deep Reinforcement Learning (DRL) with suitable modifications to adapt to real-time changes. DRL allows robots to learn from their environment and make optimal decisions, improving their ability to avoid collisions and navigate efficiently in uncertain conditions. By integrating these algorithms and conducting a comparative analysis, we propose a framework that enables robots to dynamically adjust their paths, ensuring collision-free movement and optimal coordination. © 2025 IEEE.

关键词： Robot programming

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：