检索结果-内蒙古大学图书馆

International Conference on Advancement in Electrical and Electronic Engineering (ICAEEE)

作者： Ashraf Hussan Babor Umme Habiba Choity Most. Kaspia Subrata Kumer Paul Rakhi Rani Paul Md. Momenul Haque Md. Ekramul Hamid Dept. of Computer Science and Engineering Bangladesh Army University of Engineering & Technology (BAUET) Qadirabad Dayarampur Natore Bangladesh Department of Computer Science and Engineering University of Rajshahi Rajshahi Bangladesh

ISBN: (数字)9798350388282

ISBN: (纸本)9798350388299

Efficient currency detection and counting systems are crucial for the smooth operation of any financial ecosystem. This paper explores the development, implementation, and potential impact of a specialized currency detection and counting system for Bangladeshi coin currencies. Through this comprehensive study, this paper addresses the unique challenges and opportunities in Bangladesh’s coin currency management landscape, highlighting the motivations and results of such a system’s introduction. computer vision technology includes currency detection. In this paper, we present a coin currency detection system that can detect coin currency from images. Designing a CNN-based coin recognition system for the recognition of Bangladeshi coins of denominations ‘1tk’, ‘2tk’, and ‘5tk’. We have created a dataset that contains more than 10,000 images. We photographed coin currencies from both sides, and the system can recognize coin currencies from both sides. For high efficiency, we test on various backgrounds. Experimental results are presented successfully with a training accuracy of 99.99% with VGG16, 99.38% with VGG19, and 99.99% with EfficientNetB0. We also got validation accuracy with VGG16 of 90.90%, 99.96% with VGG19, and 99.51% with EfficientNetB0.

关键词： Training Deep learning Technological innovation computer vision Accuracy Ecosystems Collaboration

来源：评论

学校读者我要写书评

暂无评论

LabObf: A Label Protection Scheme for Vertical Federated Learning Through Label Obfuscation

arXiv

引用

arXiv 2024年

作者： He, Ying Niu, Mingyang Hua, Jingyu Mao, Yunlong Huang, Xu Li, Chen Zhong, Sheng Dept. Computer and Science Technology Nanjing University Nanjing China Beijing Science and Technology Co Three Fast Online Beijing China

Split Neural Network, as one of the most common architectures used in vertical federated learning, is popular in industry due to its privacy-preserving characteristics. In this architecture, the party holding the labels seeks cooperation from other parties to improve model performance due to insufficient feature data. Each of these participants has a self-defined bottom model to learn hidden representations from its own feature data and uploads the embedding vectors to the top model held by the label holder for final predictions. This design allows participants to conduct joint training without directly exchanging data. However, existing research points out that malicious participants may still infer label information from the uploaded embeddings, leading to privacy leakage. In this paper, we first propose an embedding extension attack manipulating embeddings to undermine existing defense strategies, which rely on constraining the correlation between the embeddings uploaded by participants and the labels. Subsequently, we propose a new label obfuscation defense strategy, called ‘LabObf’, which randomly maps each original integer-valued label to multiple real-valued soft labels with values intertwined, significantly increasing the difficulty for attackers to infer the labels. We conduct experiments on four different types of datasets, and the results show that LabObf significantly reduces the attacker’s success rate compared to raw models while maintaining desirable model accuracy. Copyright © 2024, The Authors. All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Multiple Branch Fusion Network for Feature Learning and Hyperspectral Image Classification

A Multiple Branch Fusion Network for Feature Learning and Hy...

引用

International Conference on Computing and Networking technology (ICCNT)

作者： Murali Kanthi K. Venkateshwara Rao Sudha Pavani K Nuthanakanti Bhaskar Shankar Nayak Bhukya T. Hitendra Sarma Dept. of Computer Science & Engineering (Data Science) CMR Technical Campus Hyderabad Telangana India Dept. of Computer Science & Engineering CMR College of Engineering & Technology Hyderabad Telangana India Dept. of Computer Science & Engineering CMR Technical Campus Hyderabad Telangana India Dept. of Information Technology Vasavi College of Engineering Hyderabad Telangana India

Hyperspectral image (HSI) classification has made extensive use of deep learning approaches, specifically Convolutional Neural Network (CNN). CNN's ability to fully capture local contextual aspects of HSI makes it an excellent HSI classifier. Although, a significant factor in the poor classification performance is the scarcity of training data. Conventional CNN-based methods don't use the integrate-band relationships of HSI as much as they could because they typically employ 2D-CNNs to extract features. On the other hand, 3D-CNNs use a similar procedure to get both spectral and spatial data. This gets around the problem with 2D-CNNs, but it could mean that not enough features are extracted. As a solution, we offer a multi-scale 3D-CNN with multi branch feature fusion, which we call multi branch fusion CNN (MBF-CNN), for HSI classification. We begin by applying 3D-CNN on multiple scales to extract HSI features. After that, the multiple distinct characteristics are streamlined and combined together. The fused features then go through several fully connected layers to get the classification outcomes. The experiments are executed on both the new data sets and the publicly accessible benchmark data sets to expose the efficiency and durability of the proposed model. Empirically, it has been demonstrated that the presented model succeeds over the remaining state-of-the-art approaches in terms of classification accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Breast Cancer Diagnosis with XAI-Integrated Deep Learning Approach

Breast Cancer Diagnosis with XAI-Integrated Deep Learning Ap...

引用

International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies (3ICT)

作者： Sharia Arfin Tanim Gazi Mohammad Imdadul Alam Tahmid Enam Shrestha Maruful Islam Fariha Jahan Kamruddin Nur Dept. of Computer Science American International University-Bangladesh (AIUB) Dhaka Bangladesh School of Science Engineering & Technology East Delta University Chattogram Bangladesh Dept. of Computer Science and Engineering International Islamic University Chittagong Chittagong Bangladesh

ISBN: (数字)9798331533137

ISBN: (纸本)9798331533144

Breast cancer is one of the world's significant health challenges. There is a need to have better techniques in the early diagnosis of this disease to increase patients' survival rates. This paper introduces a robust approach for breast cancer detection by integrating deep-learning and classical machine-learning techniques into a custom lightweight neural network model. This approach is based on integrating conventional machine-learning and deep-learning paradigms using a range of data pre-processing steps, including data cleaning, label converting, scaling, and feature selecting to improve the given dataset's readiness for training. The proposed model demonstrated impressive accuracy in breast cancer detection compared to individual classifiers by achieving an overall accuracy of 97.54 %. Additionally, integrating eXplainable Artificial Intelligence (XAI) techniques gives the application interpretability and transparency for clinicians to make sense of the feature's importance and individual prognosis. It is a more accurate and easy-to-understand tool for clinicians, making it a better use of faulty or confusing reference values. This study presents the need to learn more about making deep learning and eXplainable Artificial Intelligence (XAI) complementary approaches to breast cancer diagnosis and treatment research.

关键词： Deep learning Training Technological innovation Accuracy Explainable AI Neural networks Breast cancer Cleaning Prognostics and health management Informatics

来源：评论

学校读者我要写书评

暂无评论

Cancer Death Cases Forecasting using Supervised Machine Learning 4

Cancer Death Cases Forecasting using Supervised Machine Lear...

引用

4th International Conference on Electronics and Sustainable Communication Systems, ICESC 2023

作者： Degadwala, Sheshang Vyas, Dhairya Kothari, Ankita Khunt, Urmila Sigma University Computer Engineering Department Gujarat Vadodara India University of Baroda The Maharaja Sayajirao Gujarat Vadodara India Krishna School of Emerging Technology and Applied Research Kpgu Dept. of Comp. Sci. & Eng. Vadodara India Itm Vocational University Computer Science Engineering Vadodara India

ISBN: (纸本)9798350300093

In India, like in the rest of the world, cancer is a major killer. This research objective is to predict cancer mortality in India, using supervised machine learning methods. Cancer mortality rates in India between 1990 and 2017 are provided by age group, gender, and region using data from the Global Burden of Disease Study. We employ three distinct supervised learning algorithms - linear regression, decision tree regression, and random forest regression - after performing data preprocessing, which includes missing value imputation and feature engineering. Using a variety of criteria, we analyze the effectiveness of these models and conclude that the random forest regression model is superior to the other two. The scope of research is provide a long-term prediction of cancer mortality in India using the best model so it will help health department to work on it. Our research has implications for policymakers and healthcare providers in India, where it may inform efforts to reduce cancer rates and improve cancer care. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Innovative Framework for Early Estimation of Mental Disorder Scores to Enable Timely Interventions

arXiv

引用

arXiv 2025年

作者： Singh, Himanshi Tiwari, Sadhana Agarwal, Sonali Chandra, Ritesh Sonbhadra, Sanjay Kumar Singh, Vrijendra Dept. of Information Technology IIIT Allahabad Uttar Pradesh Prayagraj India Dept. of Computer Science and Engg. Siksha’O’ Anusandhan University Odisha Bhubaneswar India

Individuals’ general well-being is greatly impacted by mental health conditions including depression and Post-Traumatic Stress Disorder (PTSD), underscoring the importance of early detection and precise diagnosis in order to facilitate prompt clinical intervention. An advanced multimodal deep learning system for the automated classification of PTSD and depression is presented in this paper. Utilizing textual and audio data from clinical interview datasets, the method combines features taken from both modalities by combining the architectures of LSTM (Long Short-Term Memory) and BiLSTM (Bidirectional Long Short-Term Memory).Although text features focus on speech’s semantic and grammatical components;audio features capture vocal traits including rhythm, tone, and pitch. This combination of modalities enhances the model’s capacity to identify minute patterns connected to mental health conditions. Using test datasets, the proposed method achieves classification accuracies of 92% for depression and 93% for PTSD, outperforming traditional unimodal approaches and demonstrating its accuracy and robustness. © 2025, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Comparing Transfer Learning and Rollout for Policy Adaptation in a Changing Network Environment

Comparing Transfer Learning and Rollout for Policy Adaptatio...

引用

IEEE Symposium on Network Operations and Management

作者： Forough Shahab Samani Hannes Larsson Simon Damberg Andreas Johnsson Rolf Stadler Dept. of Computer Science KTH Royal Institute of Technology Sweden Ericsson Research Sweden Department of Information Technology Uppsala University Sweden

ISBN: (数字)9798350327939

ISBN: (纸本)9798350327946

Dynamic resource allocation for network services is pivotal for achieving end-to-end management objectives. Previous research has demonstrated that Reinforcement Learning (RL) is a promising approach to resource allocation in networks, allowing to obtain near-optimal control policies for non-trivial system configurations. Current RL approaches however have the drawback that a change in the system or the management objective necessitates expensive retraining of the RL agent. To tackle this challenge, practical solutions including offline retraining, transfer learning, and model-based rollout have been proposed. In this work, we study these methods and present comparative results that shed light on their respective performance and benefits. Our study finds that rollout achieves faster adaptation than transfer learning, yet its effectiveness highly depends on the accuracy of the system model.

关键词： Adaptation models Accuracy Transfer learning Reinforcement learning Dynamic scheduling Resource management

来源：评论

学校读者我要写书评

暂无评论

Clustering Optimization via Centroid Neural Network Ensemble

Clustering Optimization via Centroid Neural Network Ensemble

引用

2024 IEEE International Conference on Future Machine Learning and Data Science, FMLDS 2024

作者： Tran, Chung Nguyen Tran, Le-Anh Le, Ngoc-Phu Carrabina, Jordi Castells-Rufas, David Nguyen, Minh Son Dang, Nhan Cach Universitat Autònoma de Barcelona Departament de MiSE Bellaterra Spain Mindintech Inc. Dept. of Research and Development Seoul Korea Republic of Unilever Plc Dept. of Data and Analytics Ho Chi Minh City Viet Nam University of Information Technology Dept. of Computer Engineering Ho Chi Minh City Viet Nam Hcmc University of Transport Iiteee Ho Chi Minh City Viet Nam

ISBN: (纸本)9798350391213

A cluster analysis approach based on an ensemble of unsupervised competitive neural networks for clustering optimization is proposed in this paper. The proposed method utilizes centroid neural network (CentNN) as its backbone, which has been recognized as an effective data clustering algorithm that can yield more satisfactory clustering error rates compared to conventional methods. In an attempt to further enhance the clustering results, this study investigates a centroid neural network ensemble (CentNN-E). By leveraging the strengths of multiple CentNN models, the proposed CentNN-E scheme aims to mitigate individual biases and achieve more robust and reliable clustering results. For one specific cluster, the prototypes (centroid candidates) produced by multiple CentNN models (with different initializations) are grouped by using Euclidean distance and are convexly combined using error-based weighting on a per-cluster basis. The resulting prototypes from the ensemble are subsequently utilized as initial prototypes for a final execution. Experimental results on various synthetic test data sets demonstrate that the proposed CentNN-E approach can yield superior results and surpass a single CentNN algorithm in terms of clustering error criterion. © 2024 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Double Cancelable Hashing for Protecting Biometrics of Users in Crowd 18

Double Cancelable Hashing for Protecting Biometrics of Users...

引用

18th INDIAcom;11th International Conference on Computing for Sustainable Global Development, INDIACom 2024

作者： Almutairi, Mishaal M. Apostolopoulou, Dimitra Stupples, David Sen, Adnan Ahmed Abi Yamin, Mohammad Halikias, George City University of London School of Science and Technology Dept. of Electrical and Electronic Engg London United Kingdom Islamic University Deanship of Information Technology Madinah Saudi Arabia The Australian National University School of Computing College of Engineering and Computer Science Canberra Australia University of Athens Department of Mathematics Greece

ISBN: (纸本)9789380544519

Smart gates are considered one of the most important methods for managing crowds. Often, methods of authentication and verification of users depend on the user's biometric fingerprints, such as hand or eye prints. Sending a picture of the fingerprint or eye to the server for verification is deemed unacceptable, especially in crowds, as it will significantly impact service performance in addition to imposing a heavy load on the network. Another, more serious challenge is related to the security and privacy of this data. If a user's fingerprint is stolen, it implies that all systems and services related to it, whether financial, medical, or otherwise, will be vulnerable to hacking. Unfortunately, the use of the traditional hash function is not sufficiently strong against a Replay Attack, and integration with blockchain requires substantial resources and suffers from delays that may impact the quality of sensitive services. In this paper, a Hash Function is proposed to enhance the level of privacy and security of biometric information. The hashing process will be doubled on one hand, and fog computing will be employed as an intermediary and additional protection on the other hand. Finally, the proposed technology will provide a solution to the problem of Relay Attack. The effectiveness and applicability of the proposed approach will be implemented and assessed. © 2024 Bharati Vidyapeeth, New Delhi.

关键词： Crowd management data privacy data security encryption hackers

来源：评论

学校读者我要写书评

暂无评论

A Deep Ensemble Learning Approach for Venomous & Non-Venomous Serpents and Insect Species Identification

A Deep Ensemble Learning Approach for Venomous & Non-Venomou...

引用

Innovation in technology (ASIANCON), Asian Conference on

作者： Buddhin Saroj Samarasinghe K.B.N. Lakmali Dept. of Computer Science Informatics Institute of Technology Colombo 06 Sri Lanka Department of Computer Science Informatics Institute of Technology Colombo 06 Sri Lanka

In recent years snake and insect attacks have become a huge problem worldwide. Most species have similar colors and shapes, which makes it hard to tell them apart using typical techniques. Similarly, identifying different species of bees and wasps can be challenging, especially for non-experts in the field. Therefore, developing a reliable and effective method for recognizing these animals is essential to reducing the issues caused by snake and insect attacks and supporting wildlife conservation efforts. The proposed method in this research utilizes deep ensemble learning and transfer learning techniques to identify snakes, wasps, and bees accurately. Deep ensemble learning involves combining several machine learning models to make better predictions, and transfer learning is a technique that allows pre-trained models to be re-used for new tasks, saving time and computational resources. The proposed method utilizes deep ensemble learning and uses three base transfer learning models, DenseNet201, MobileN etV2, and InceptionResN etV2, for classification. The study obtained a training accuracy of 93%. The research classified 11 types of snakes, four types of bees, and four types of wasps, including all 19 classes. Moreover, the author developed a mobile application for user interaction and utilized Flask API for the logic tier. The mobile application enables users to take pictures or upload images of a snake, wasp, or bee and identify the species accurately. This feature makes the proposed method more accessible to people who encounter these animals daily. Overall, this research represents a promising step towards developing an accurate and effective system for identifying snakes, wasps, and bees, with practical implications for human safety and biodiversity conservation.

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：