检索结果-内蒙古大学图书馆

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

作者： Ebenezer, V. Daniel, Arsha Anna Getzi Jeba Lillipushpam, P. Edwin, E.Bijolin Roshni Thanka, M. Devassy, Rosebel Karunya Institute of Technology and Science Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350300093

Peanut is a key food commodity, and diseases of its leaves can have a negative impact on the quantity and quality of the product. The seed has high levels of potassium, magnesium, calcium, riboflavin, niacin, folic acid, vitamin E, resveratrol, and amino acids. It also contains 36% to 54% oil, 16% to 36% protein, and 10% to 20% carbs. Early, late, and rusty leaf spots, among other frequent illnesses, are recognized by this equipment. Techniques for image augmentation have been used, such as twisting, rotating, and scaling. The variant employs a Multi Class Convolutional neural network with 5 output which include Normal Leaf, Images Without Leaf and the images with the leaf been infected by the diseases. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Solar Powered Smart Irrigation Using IoT 8

Design and Implementation of Solar Powered Smart Irrigation ...

引用

8th IEEE International Conference on science, technology, engineering and Mathematics, ICONSTEM 2023

作者： Santhosh Kumar, C. Brindasri, S. Krishnamoorthy, J. Vidhya, B. Saranya, G. Madhan, K. Er.Perumal Manimekalai College of Engineering Department of Computer Science and Engineering Hosur India Hindustan Institute of Technology and Science Department of Computer Science and Engineering India Sri Krishna College of Technology Department of ECE Coimbatore India Mailam Engineering College Department of Computer Science and Engineering Mailam India

ISBN: (纸本)9798350347791

The farming is one concerning the indispensable assets due to the fact of advent of ingredients but assumes sizeable portion about the economic regulation about each and every United States on America via which include after Today, coast owners hold a snack troubles within agribusiness appropriate according to the fact of non-appearance about downpours after shortage about water. So, between that task, we wish raise external computerized wind law case due to the fact bank lords as like intention maintain time, value then after on Manual inclusion is wished due to the fact the farmland strategies. By construction use over soil humidity sensor degrees involving ground dampness/mugginess may additionally keep checked. At some also is an harmony the trade yet sends signal in conformity over the microcontroller or relying upstairs that the cloud provision framework works. Robotized cloud government litigation uses valves in accordance in accordance with Engines work continue to be robotized effectively by using construction use of regulators yet no assistance over guide intervention among accordance about flirt apparatus ON then OFF. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Heuristic Data Placement in Distributed Hierarchical Storage Network Using Deep Reinforcement Learning 22

Heuristic Data Placement in Distributed Hierarchical Storage...

引用

22nd IEEE Consumer Communications and Networking Conference, CCNC 2025

作者： Kaler, Ravi Toshniwal, Durga Indian Institute of Technology Roorkee Computer Science and Engineering Department Uttarakhand India

ISBN: (纸本)9798331508050

Intelligent data placement in hierarchical distributed storage networks (DSNs) has become crucial due to advancements in storage devices, an increase in big data applications, and strict time constraints. Inefficient data placement can lead to significant delays in data movement and increased service latency, impacting the overall performance of a distributed environment. It is a complex online decision-making problem due to its varying access patterns, dynamic network conditions, and ever-changing distributed environment, which traditional network optimization techniques fail to address efficiently. Reinforcement learning is best suited to address this problem as it learns from the environment dynamically and performs action. This paper presents a novel deep reinforcement learning (DRL) framework, soft actor-critic-2 (SAC-2), for heuristic data placement in the distributed network, leveraging the state-of-the-art SAC technique to improve efficiency, reduce latency, and subsequently minimize storage costs. We formulate the problem as a Markov Decision Process (MDP) model and incorporate a prioritized replay buffer for efficient learning. The heuristic data placement technique improves distributed hierarchical storage system efficiency compared to baseline strategies, as demonstrated by extensive experiments on Microsoft Research Cambridge (MSR) network traces. © 2025 IEEE.

关键词： Cloud storage

来源：评论

学校读者我要写书评

暂无评论

Enhanced Convolutional Neural Network for Sign Character Recognition with Mixed Pooling and Mish Activation Function

Enhanced Convolutional Neural Network for Sign Character Rec...

引用

2024 IEEE International Conference on Intelligent Systems and Advanced Applications, ICISAA 2024

作者： Sur, Hritajit Mandal, Gourab Das, Koushik Nandia, Apurba Das, Avik Kumar Ghosh, Arijeet Institute of Engineering and Management University of Engineering and Management Cybersecurity & Blockchain Technology Department of Computer Science Engineering Kolkata India

ISBN: (纸本)9798331539948

Communication is an essential part of our daily lives, especially for deaf and dumb people who face difficulty in communicating with others. This paper introduces a method of using sign languages, i.e., to convert various hand gestures to appropriate text. The proposed method will help people with disabilities communicate or express their thoughts and opinions to others. By offering cutting-edge methods for sign character recognition, this neural network model aims to close the communication gap and enhance the quality of life for those it serves. In this work, a dataset of hand gestures is divided into training, validation, and testing sets to apply a convolutional neural network (CNN) that has been used to properly recognise the characters on the image. The CNN is further tested on random test data to obtain a reliable interpretation of the sign language we want. The uniqueness of this model lies in the fact that it makes use of mixed pooling operation and mish activation function which train the data more smoothly and in a strong, robust way, which overall improves the accuracy and precision in recognising sign characters. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Efficient Lane Detection and Keeping for Autonomous Vehicles in Real-World Scenarios 26

Efficient Lane Detection and Keeping for Autonomous Vehicles...

引用

26th International Conference on computer and Information technology, ICCIT 2023

作者： Azad, Farhana Islam, Yumna Ruslan, Ch Zakauddin Md Aye Mong Marma, C. Kalpoma, Kazi A. Ahsanullah University of Science and Technology Department of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798350359015

In this study, we developed an auto-lane-keeping assist system to contribute to autonomous driving. The system will keep the vehicle in its designated lane to reduce road accidents. The main challenge of this research is to make the system suitable for real-world road conditions. To achieve an efficient lane-keeping system, we detected the lane lines automatically using canny edge detection and a sliding window algorithm. The proposed lane-keeping system has another stage: lane-keeping. The lane-keeping task includes the calculation of the offset value, meaning how much the vehicle deviates from its lane or if the vehicle is in the center line of the lane, and the steering angle correction of the vehicle to be in the lane. We use the Sliding Window Algorithm for the offset value calculation, which makes the detection of curved lane lines more accurate than the previous works and also performs well in various weather and lighting conditions. The proposed system's performance is evaluated using the IROADS dataset in this work. We implemented lane keeping in both software and hardware models, introducing the AURIX TC-375 microcontroller for hardware integration, which enhances overall lane-keeping system output through the integration of detection and keeping processes. © 2023 IEEE.

关键词： AURIX TC-375 Micro-controller Automotive ECU Lane Detection Lane Keeping Sliding Window Algorithm

来源：评论

学校读者我要写书评

暂无评论

The Use of Recurrent Neural Networks in the Optimization of computer science Algorithms 1

The Use of Recurrent Neural Networks in the Optimization of ...

引用

1st IEEE International Conference on Emerging Research in Computational science, ICERCS 2023

作者： Franklin, Ramya G Ronald Doni, A. Poornima, D. Sabasti Prabu, S. Igni Sathyabama Institute of Science & Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350359756

A new era of computational efficacy and problem-solving abilities has begun with the combination of Recurrent Neural Networks (RNNs) and computer science methods. It is crucial in modern computing to combine RNNs with methods from the field of computer science. RNNs bring a dynamic learning paradigm, making algorithms more efficient and flexible by allowing them to process sequential input and complicated dependencies. Their usefulness goes beyond one specific area of study, and into others such as optimization issues, recommendation systems, image processing, and natural language processing. RNNs serve a vital role in addressing the severe challenges that algorithms confront, including processing sequential input, identifying temporal connections, and optimizing in high-dimensional environments. By providing dynamic and adaptive modeling, RNNs aid algorithms in navigating these obstacles. Recurrent Neural Network-Based Optimization Algorithm (RNN-OA) is an innovative novel approach presented in this research. RNN-OA is an approach to algorithmic optimization that makes use of RNNs' dynamic learning capability. Mechanisms for selective data processing with attention, regularization methods for model stability, and interpretability improvements for openness are all a part of it. Quickening the process of optimization in many different types of problems is transfer learning and fine-tuning approaches. There are a wide variety of computer science fields where RNN-OA can be useful. Time-series analysis, language modeling, picture recognition, and recommendation systems all benefit greatly from its ability to handle sequential data. The efficacy, scalability, and robustness of the method are thoroughly evaluated by simulating various problem scenarios and data streams. The results of these simulations provide illumination for the benefits and drawbacks of RNN-OA, paving the way for its development toward actual application in algorithmic optimization. © 2023 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Fake Account Detection on Social Media using Random Forest Classifier 7

Fake Account Detection on Social Media using Random Forest C...

引用

7th International Conference on Intelligent Computing and Control Systems, ICICCS 2023

作者： Nikhitha, Kancharla Venkata Bhavya, Karnati Nandini, D. Usha Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350397253

As the growth of online social networks increases, everyone is associated and linked with social media. A massive amount of personal data is being attacked and stolen by cyber attackers. These fraudulent profiles also spread negative publicity, false news, and various malicious programs. One of the best ways is to detect these fake accounts, not only the best way but also it is the first step to stopping the negative news and false rumours. There are many efficient ways and techniques to detect these fake accounts. However, these techniques are based on or depend on the account features. The main aim of this research is to examine three machine learning algorithms i.e., random forest, logistic regression, and decision tree. The level of efficiency in the three mentioned methodologies are compared and the highest accuracy has been achieved for random forest classifier. © 2023 IEEE.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Pre-trained SAM as data augmentation for image segmentation

引用

CAAI Transactions on Intelligence technology 2025年第1期10卷 268-282页

作者： Junjun Wu Yunbo Rao Shaoning Zeng Bob Zhang Yangtze Delta Region Institute(Huzhou) University of Electronic Science and Technology of ChinaHuzhouChina School of Information and Software Engineering University of Electronic Science and Technology of ChinaChengduChina Pattern Analysis and Machine Intelligence Research Group Department of Computer and Information ScienceUniversity of MacaoMacaoChina

Data augmentation plays an important role in training deep neural model by expanding the size and diversity of the ***,data augmentation mainly involved some simple transformations of ***,in order to increase the diversity and complexity of data,more advanced methods appeared and evolved to sophisticated generative ***,these methods required a mass of computation of training or *** this paper,a novel training-free method that utilises the Pre-Trained Segment Anything Model(SAM)model as a data augmentation tool(PTSAM-DA)is proposed to generate the augmented annotations for *** the need for training,it obtains prompt boxes from the original annotations and then feeds the boxes to the pre-trained SAM to generate diverse and improved *** this way,annotations are augmented more ingenious than simple manipulations without incurring huge computation for training a data augmentation *** comparative experiments on three datasets are conducted,including an in-house dataset,ADE20K and *** this in-house dataset,namely Agricultural Plot Segmentation Dataset,maximum improvements of 3.77%and 8.92%are gained in two mainstream metrics,mIoU and mAcc,***,large vision models like SAM are proven to be promising not only in image segmentation but also in data augmentation.

关键词： data augmentation image segmentation large model segment anything model

来源：评论

学校读者我要写书评

暂无评论

Enhancing Education Accessibility: Portable Microservers for computer-Based Testing in Resource-Constrained Environments 22

Enhancing Education Accessibility: Portable Microservers for...

引用

22nd International Learning and technology Conference, L and T 2025

作者： Dhuny, Riyad Ying, Fangli University of Technology School of Innovative Technologies and Engineering 11134 Mauritius East China University of Science and Technology Department of Computer Science Shanghai China

ISBN: (纸本)9798331532215

This study explores the potential of LAMP stack open-source applications for embedded computing to enhance education accessibility, particularly in resource-constrained environments. The research focuses on converting a Raspberry Pi (RPI) device into a portable microserver hosting a computer-Based Testing (CBT) system, specifically TCExam. The methodology involves porting TCExam to RPI hardware, testing its operability, and evaluating its performance under various user loads. Experiments were conducted using RPI versions 4 and 5, with Apache JMeter employed for performance testing. Results demonstrate that RPI4 can sustain at least 30 concurrent users, while RPI5 supports over 50 users in a load-testing environment. The study applies Menascé's equation to estimate the theoretical number of supported users, revealing the potential for microservers to accommodate larger class sizes than initially expected. The research highlights the feasibility of using affordable, portable hardware for deploying CBT systems, which is particularly beneficial in areas with limited internet connectivity or power sources. This approach offers educators a secure, offline assessment environment and the flexibility to prepare and test the system before deployment. The study concludes that microservers like RPI can increasingly run applications previously restricted to server rooms, opening new possibilities for improving education quality in developing countries. Future work suggests integrating local Large Language Models for offline use in remote areas, further enhancing the educational toolkit available to educators in resource-constrained environments. © 2025 IEEE.

关键词： Integration testing

来源：评论

学校读者我要写书评

暂无评论

Pneumonia Detection using Chest X-ray Images using CNN Algorithm 7

Pneumonia Detection using Chest X-ray Images using CNN Algor...

引用

7th International Conference on Intelligent Computing and Control Systems, ICICCS 2023

作者： Mazumdar, Surya Deepta Kumar, Ashish Sethuraman, R. Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350397253

Pneumonia is a serious health condition where the patient's lungs get infected by bacteria, virus or sometimes fungi. This causes burning sensation in the alveoli present in the lungs. In response to this, body forms fluids in the lungs that can cause trouble in breathing, coughing and even chest pain. The increasing demand of medical care for elderly care and children below five years of age requires advanced healthcare technologies. Premature diagnosis is vital for fast recovery. This research study intends to propose a novel technique for detecting pneumonia in chest x-ray images by training a model to classify the patient's condition as normal or pneumonic. The proposed model applies CNN, a deep learning algorithm to detect the health condition of the patient by analyzing their chest X-ray images. The objective of this research study is to attain the model accuracy as high as possible to provide accurate results to the user. © 2023 IEEE.

关键词： Viruses

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：