检索结果-内蒙古大学图书馆

A hybrid convolutional neural network and support vector machine classifier for Amharic character recognition

Neural Computing and Applications 2024年第27期36卷 16839-16856页

作者： Tsegaye, Muluken Zemed Shashi, Mogalla Department of Information Technology Andhra University College of Engineering AP Visakhapatnam530003 India Department of Computer Science Andhra University College of Engineering AP Visakhapatnam530003 India

Optical character recognition is a way of converting scanned images of printed or handwritten documents into machine-encoded text, making it easier to store, browse, retrieve, and process electronic data. In this research, a Printed Amharic Characters Recognition dataset is prepared to train and test a model. Images in the dataset only contain 231 basic Amharic characters that are normalized to 32 × 32 pixels. In this work, a hybrid model of the two super classifiers is developed: the convolutional neural network (CNN) and the support vector machine (SVM). In this novel hybrid CNN-SVM model, CNN works as an automatic feature extractor from the raw images, and then, the extracted feature vectors are given as input to SVM for classification and recognition. A 99.84% accuracy was achieved on the own-prepared dataset and 95.59% accuracy on the benchmark Amharic Optical Character Recognition Database in classifying the testing dataset images. The proposed hybrid CNN-SVM model gave better results than the CNN with a fully connected layer. Moreover, the proposed model outperforms previously existing works attempted by others to recognize printed Amharic characters on the same and different datasets. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

EARLY PREDICTION OF ALZHEIMER'S DISEASE USING MAGNETIC RESONANCE IMAGES (MRI) IN LEVERAGING DEEP LEARNING MODELS 2

EARLY PREDICTION OF ALZHEIMER'S DISEASE USING MAGNETIC RESON...

引用

2nd International Conference on computer Vision and Internet of Things, ICCVIoT 2024

作者： Kalpana, T. ThamilSelvan, R. Chitra, K. Rojaa, K.M. Santhiya, M. Sowmiyavarshan, A.D. Department of Computer Applications Kongu Engineering College Erode India Department of Computer Science and Engineering Kongu Engineering College Erode India

ISBN: (纸本)9781837242672

Alzheimer's disease is a well-known illness characterized by memory loss and cognitive decline. Since current treatments work best in the early stages, early detection is vital for effective management. The Magnetic Resonance Imaging (MRI) plays a key role in diagnosing Alzheimer's by providing detailed images of brain structures. Advances in deep learning have further improved MRI-based diagnosis through automated image ***2 and MobileNetV3 are lightweight convolutional neural networks (CNNs) known for their high performance and speed, making them ideal for resource-limited and real-time ***3 is a widely used CNN, known for its strong performance in image classification tasks. By training these deep learning models on complete MRI datasets, they offer the potential to aid doctors in making accurate and timely diagnoses. This approach couldlead to better outcomes and improved quality of life for *** research aims to enhance early detection and treatment methods for Alzheimer's disease, contributing to advancements in deep learning models. © The Institution of engineering & Technology 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing COVID-19 and Pneumonia Detection with a Hybrid ACGAN-CNN Model 15

Enhancing COVID-19 and Pneumonia Detection with a Hybrid ACG...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Sasipriyaa, N. Ravikumar, R. Sharmila, C. Gothai, E. Krishnakumar, B. Nithya Sri, R.K. Kongu Engineering College Department of Computer Science and Engineering Tamilnadu India The Erode College of Pharmacy Pharmaceutical Analysis Tamilnadu India SRM IST Trichy Department of Computer Science and Engineering India Kongu Engineering College Department of Computer Science and Engineering Tamilnadu India

ISBN: (纸本)9798350370249

Corona Virus caused a pandemic outbreak all over the world during 2020-2021. Identification of such diseases in the X-ray images needs help of deep learning methodologies involving classifiers. Achieving proficiency in training convolutional neural networks requires a considerable volume of data. Higher accuracy is needed while dealing with medical fieldrelated problems especially. When dealing with small datasets, networks tend to exhibit overfitting problems. In order to get larger dataset, techniques for data augmentation serve to enhance the neural networks' capacity for generalization by expanding existing training data more efficiently. While conventional data augmentation methods do enhance performance, their scope remains restricted. Generative Adversarial Networks (GANs) have proven instrumental in producing fresh data, thereby elevating the performance of CNNs. Methodologies for augmenting data with the help of GAN's is not as much notable in Convolutional neural networks. In this research study, a GAN architecture is used for augmenting X -ray images of chest in order to expand the dataset. Auxiliary Classifier Generative Adversarial Network model has been used to produce images. It consists of a generator that produces new images with random noise and a discriminator whose job is to identify fake & real images. The results showcase that the new image generated is fine-tuned over each epoch and the significance can be seen in the output images. We compare the quality of our ACGAN images with the conventionally augmented images. © 2024 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

An Energy Efficient IoT Based Smart Street Lighting Using Low Cost SOC 1

An Energy Efficient IoT Based Smart Street Lighting Using Lo...

引用

1st IEEE International Conference on Electronics, Computing, Communication and Control Technology, ICECCC 2024

作者： Velu, Anitha Ramamoorthy, Raghu Manasa, S.M. Navulkumar, Devakirubai Sri Sairam College of Engineering Department of Electronics and Communication Engineering Bengaluru India The Oxford College of Engineering Department of Computer Science and Engineering Bengaluru India Jayam College of Engineering and Technology Department of Computer Science and Engineering Dharmapuri India

ISBN: (纸本)9798350371802

Internet of Things (IoT) has radically improved and modernized in every aspect of human existence. The term IoT is a recent trend that states the development a self-configurable network by connecting a variety of hardware objects, to internet without requiring human input to improve service delivery and automate processes by means of data transmission to the cloud. Streetlights are an essential component of any city, although they provide safer roadways, improved night vision, and increased visibility of public spaces it uses a significant amount of electricity and operates at maximum intensity from dusk till dawn. The wastage of electricity can be secured by having lights turn OFF on their own if it is not in use. This work presents an energy efficient IoT-based smart street lighting by using low-cost System On Chip (SOC) circuit. This work deploys an LDR sensor which acts as a decision device, to choose whether to switch ON or OFF the street light based on the level of ambient light. This simple switch has a relay at its output and is activated by either light or dark. This switching may be done using a cost-effective Wi-Fi module namely, ESP8266 for which the LDR sensed value is given as input. Any user can check the status of a street light whether it is ON/OFF from anywhere using internet in real time. It promises great dependability and remarkable stability for long-term. The proposed work is implemented using a NodeMCU board that is designed to supply the required light intensity at different times. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Federated learning techniques in the healthcare area 4th

Federated learning techniques in the healthcare area

引用

4th International Conference on Computational Methods in science and Technology, ICCMST 2024

作者： Kumar, Sanjay Virk, Ishpreet Singh Puri, Renu Department of Computer Science and Engineering Chandigarh Engineering College-CGC Landran India

ISBN: (纸本)9781032911571

Federated understanding techniques have actually shown prospective, in the medical care sector allowing cooperation as well as information sharing while promoting personal privacy and also safety and security steps. This evaluation explores making uses of federated knowing in health care showcasing its capacity to boost results development medical study and also sustain tailored medication. The evaluation covers the advantages along with barriers of incorporating federated discovering in medical care together with opportunities for expedition as well as development in this area. Furthermore it deals with difficulties as well as chances for research study on medical care applications. The goal is to inspire a journey of linked expertise in health care contexts for it to come to be an approach for securing fragile professional information. The future pattern suggests an expanding fostering of linked knowing in setups, causing sophisticated procedures that focus on personal privacy and also safety and security while successfully using this innovation to resolve crucial problems within the medical care field. © 2025 the Author(s).

关键词：

来源：评论

学校读者我要写书评

暂无评论

RSSN at Multilingual Counterspeech Generation: Leveraging Lightweight Transformers for Efficient and Context-Aware Counter-Narrative Generation 1

RSSN at Multilingual Counterspeech Generation: Leveraging Li...

引用

1st Workshop on Multilingual Counterspeech Generation, MCG 2025 with Shared Task on Multilingual Counterspeech Generation

作者： Ravindran, V. Department of Computer Science and Engineering Sri Sivasubramaniya Nadar College of Engineering India

ISBN: (纸本)9798891762077

This paper presents our system for generating counter-speech (CN) in response to hate speech (HS), developed for the COLING 2025 shared task. We employ lightweight transformer-based models, DistilBART and T5-small, optimized for computational efficiency while maintaining competitive performance. Through comprehensive dataset analysis, we identify linguistic patterns, explore challenges, and propose enhancements. Our findings demonstrate the viability of lightweight models and highlight error patterns that can guide future research directions. We provide a detailed evaluation of results across multiple metrics, including BLEU, ROUGE, and BERTScore, and discuss strategies for enhancing contextual relevance in CNs. © 2025 Association for Computational Linguistics

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Air quality and dust level monitoring systems in hospitals using IoT

引用

Discover Internet of Things 2025年第1期5卷 1-18页

作者： Parkavi, A. Sowmya, B.J. Alex, Sini Anna Supreeth, S. Shruthi, G. Rohith, S. Chatterjee, Sudipta Lingaraj, K. Department of Computer Science and Engineering Ramaiah Institute of Technology Bengaluru560054 India Department of Artificial Intelligence and Data Science Ramaiah Institute of Technology Bengaluru560054 India Ramaiah Institute of Technology Bengaluru560054 India School of Computer Science and Engineering REVA University Bengaluru560064 India Department of Electronics and Communication Engineering Nagarjuna College of Engineering and Technology Bengaluru562164 India Department of Electronics and Communication Engineering Brainware University Barasat West Bengal Kolkata700125 India Department of Computer Science and Engineering Rao Bahadur Y. Mahabaleswarappa Engineering College Bellary583104 India

This system provides a comprehensive overview of hospital environments by tracking air quality, dust, temperature, and humidity simultaneously, offering a more complete picture of indoor conditions than systems that focus on fewer parameters. The use of IoT technology enables real-time monitoring and alerts, allowing hospital staff to respond immediately to any issues. Additionally, predictive analytics anticipate future changes, giving staff time to take preventive measures. The integration with a mobile app and cloud-based data storage ensures easy access to data, convenient monitoring, and the ability to scale the system across multiple hospital facilities, catering specifically to the unique needs of different healthcare environments. © The Author(s) 2025.

关键词： Indoor air pollution

来源：评论

学校读者我要写书评

暂无评论

Forecasting Rainfall: Evaluating Machine Learning Models on Australian Weather Data

Forecasting Rainfall: Evaluating Machine Learning Models on ...

引用

2024 International Conference on Communication, computer sciences and engineering, IC3SE 2024

作者： Gupta, Suraj Kumar Sharma, Ravish Trivedi, Shivani Department Of Computer Science And Engineering Abes Engineering College Uttar Pradesh Ghaziabad India Department Of Computer Science And Engineering Abes Engineering College Uttar Pradesh Ghaziabad India

ISBN: (纸本)9798350366846

Rain prediction holds paramount importance across various sectors, necessitating robust forecasting methodologies. This research paper focuses on rain prediction in the Australian context, specifically targeting the anticipation of rainfall for the subsequent day. Utilizing the Rainfall in Australia dataset, encompassing crucial meteorological parameters like temperature, humidity, wind speed, and pressure, this study employs a diverse array of machine learning models like CatBoost, XGBoost, Support Vector Classifier and Random Forest are rigorously evaluated through comprehensive experimentation and comparative analysis. The dataset's extensive parameters, spanning from temperature variations to cloud cover percentages, are meticulously leveraged to optimize model performance. Through meticulous fine-tuning of each ML model and the implementation of tailored preprocessing strategies, this research aims to offer nuanced insights into their relative effectiveness for rain prediction in the Australian landscape. This study aspires to contribute authentically to the advancement of rain prediction methodologies, empowering stakeholders across diverse sectors reliant on precise weather forecasts. © 2024 IEEE.

关键词： Rain

来源：评论

学校读者我要写书评

暂无评论

Privacy preserving using joint 2 K-means clustering and coati optimization algorithm for online social networks

引用

International Journal of Information Technology (Singapore) 2024年第4期16卷 2715-2724页

作者： Gowda, Nithish Ranjan Venkatesh Venugopal, K.R. Department of Computer Science and Engineering University Visvesvaraya College of Engineering Bangalore University Bengaluru India Department Computer Science and Engineering University Visvesvaraya College of Engineering Bangalore University Bengaluru India University Visvesvaraya College of Engineering Bangalore University Bangalore India

Social networks, that have grown so prevalent nowadays, enable users to exchange information and save a significant amount of personal data about them. Although the information that is stored can be useful for enhancing the quality of services provided to users, it also poses a risk to their privacy. This is because social networks contain private information about users. As a result, members of social networks seek to protect the confidentiality of their shared data. The most popular method for protecting confidentiality is anonymizing data, which involves modifying or eliminating some information while trying to preserve as much of the original data as possible. The high level of data loss, similarities attacks, and protection from attribute or link disclosure is problem with existing anonymity approaches. The study proposes a hybrid approach based on K-member k-means clustering and coati optimization algorithm (2KMCOA) as a successful solution for balanced clustering and anonymizing in social networks in order to get over these shortcomings. A K-member K-means clustering algorithm is used to divide the different users into C clusters and each cluster has at least K users, as part of the proposed anonymization procedure. Following clustering, an initial solution is generated that produces the modified data table which should satisfy objective functions and three constraints. The coati optimization algorithm (COA) is then utilized to optimize the primary clusters even more to anonymize the data as well as network graph. The efficiency of the proposed 2KMCOA is compared with other existing anonymity techniques K-means clustering with COA (KMCOA) and K- member K-means clustering without COA (2K) in terms of clustering error, balancing error, distortion rate, objective function, cost function and CPU running time. © The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Anonymization Clusters COA Cost function K-anonymity K-means clustering L-diversity T-closeness

来源：评论

学校读者我要写书评

暂无评论

Exploring AI Innovations in Automated Software Source Code Generation: Progress, Hurdles, and Future Paths

引用

Informatica (Slovenia) 2024年第8期48卷 125-136页

作者： Odeh, Ayman Odeh, Nada Software Engineering and Computer Science Department College of Engineering Al Ain University Al Jimi Al Ain United Arab Emirates

In today's dynamic world of software development, the demand for efficient and rapid creation of high-quality code has never been more pronounced. Automated software source code generation (ASSCG) emerges as a compelling solution to meet this demand, offering significant advantages in terms of speed, accuracy, and scalability. This paper aims to explore the critical role of automated software source code generation and its profound significance in modern software development practices. By navigating through the intersection of ASSCG, AI innovations, and the challenges therein, this paper endeavors to provide a comprehensive understanding of this transformative field and pave the way for informed decision-making and advancements in software development practices. This paper delves into the critical role of ASSCG and its transformative impact on modern software development. In this work, we endeavor to delve into the multifaceted landscape of automated code generation, assessing its significance, the transformative potential of AI innovations, and the challenges and objectives inherent in this evolving domain. © 2024 Slovene Society Informatika. All rights reserved.

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：