检索结果-内蒙古大学图书馆

Paddy disease classification using machine learning technique

Materials Today: Proceedings 2022年 64卷 883-887页

作者： Sobiyaa, P. Jayareka, K.S. Maheshkumar, K. Naveena, S. Rao, Koppula Srinivas Department of Information Technology Bannari Amman Institute of Technology Sathyamangalam Tamil Nadu Erode India Department of Computer Science & Engineering Sona College of Technology Erode Erode India Department of Computer Engineering Sri Ranganathar Institute of Polytechnic College Athipalayam Tamil Nadu Coimbatore India Department of Computer Science & Engineering MLR Institute of Technology Hyderabad Hyderabad India

Early disease detection plays a vital role in protection of paddy crops. In earlier days the detection of disease was done through seeing or by examining in a laboratory. The observation made visually needs experts and it might vary for each individual which leads to error and laboratory testing requires more time and might not be able to deliver the outcome within a time. To get the better of this issue, image processing-based Machine learning approach used to detect the diseases and classify the diseases. We mainly focused on rice (Oryza sativa) diseases. The images contain the leaves and stems which are affected by disease collected from the paddy fields. The dataset contains five different classes of diseases (1) Rice Blast (2) Bacterial Leaf Blight (3) Sheath Blight (4) Healthy leaves. The early detection of diseases will help farmers to increase their yield. © 2022

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Improving Online Education in Educational Institutions through the Integration of Internet of Things (IoT) 8

Improving Online Education in Educational Institutions throu...

引用

8th International Conference on Electronics, Communication and Aerospace technology, ICECA 2024

作者： Ramaraj, Kottaimalai Mathews, Ann Lynsha Helena Pratheeba, Hp Ramani, U. Sujitha, K.L. Thilagaraj, M. Kalasalingam Academy of Research and Education Department of Electronics and Communication Engineering Tamilnadu Krishnankoil India Cmr Institute of Technology Department of Computer Science and Engineering Bengaluru India K Ramakrishnan College of Engineering Department of Electrical and Electronics Engineering Trichy India Mvj College of Engineering Department of Computer Science and Engineering Bengaluru India Mvj College of Engineering Department of Industrial Internet of Things Bengaluru India

ISBN: (纸本)9798350367904

A key facilitating infrastructure for building intelligent structures that enable efficient in-person and virtual learning environments is the Internet of Things (IoT). The shift to smart learning, that includes IoT and Artificial Intelligence (AI) into the educational system, is enticing since it directly affects the motivation of learners, enrolment, participation, and in-depth understanding. Teaching and learning, management, examination, and class monitoring are only a few of the numerous issues that afflict conventional education. Many ingenious approaches to many facets of our lives are being made possible by modern advancements in information and communication technology (ICT);nonetheless, these imaginative concepts aren't adequately incorporated into the framework of education. The COVID-19 pandemic scenario, in specific, has brought out the need for innovative, creative approaches in the field of teaching. The present research examines previous investigations in the field and discusses the following topics: (i) issues with the current educational system and potential fixes;(ii) the shift to smart learning;and (iii) scientific hurdles (such as technological and cultural barriers) in making the move to smart learning. In accordance with these outcomes, creative approaches to the issues with the conventional system-such as smart teaching, smart evaluation, smart school environment, and smart management-are presented. The business and academic community may now include IoT, AI, and ICT into smart learning owing to the aforementioned experimental research's novel developments. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Diagnosis of Multi-Class Open-Circuit Switch Faults in Three-Phase Front-End Converters

Data-Driven Diagnosis of Multi-Class Open-Circuit Switch Fau...

引用

2024 International Conference on computer, Electronics, Electrical engineering and their Applications, IC2E3 2024

作者： Ghosh, Sourabh Singh, Vikash Singh, Asheesh Kumar Hassan, Ehtesham Singh, Sri Niwas Motilal Nehru National Institute of Technology Allahabad Electrical Engineering Department Prayagraj India Kuwait College of Science and Technology Department of Computer Science and Engineering Kuwait Atal Bihari Vajpayee Indian Institute of Information Technology and Management Gwalior India

ISBN: (纸本)9798350388534

This paper analyzes the application of benchmark classification techniques for multi-class diagnosis of open-circuit switch faults (OCSFs) in three-phase front-end converters (TP-FECs). OCSFs result in harmonic distortion, secondary faults, and unscheduled shutdowns in power utilities. Moreover, due to the inherent difference between OCSFs and short-circuit switch faults, the same diagnosis techniques do not apply to both types of faults. This paper presents a detailed study on a two-level TP-FEC to generate single-, double-, and triple-switch OCSFs, resembling real-world scenarios. The single-moment fault data with 624 observations is captured through 13 distinct features to extract the fault characteristics during each of the 38 classes of OCSFs under varying load demands. Later, the paper analyzes the performance of neural networks (NNs), support vector machines (SVMs), ensemble bagged trees (EBTs), and k-nearest neighbours (KNNs) for multi-class diagnosis of OCSFs. The evaluation employed cross-validation with optimal hyperparameter combinations to train different models. Through rigorous experiments, we demonstrate the superiority of NNs in classifying multi-class OCSFs with a testing accuracy of 97.50%, achieving an improvement of 0.4%, 2.4%, and 3.8% compared to SVM, KNN, and EBT, respectively. Furthermore, our experiments underscore the efficacy of NNs and SVMs over other state-of-the-art methods for diagnosing OCSFs. © 2024 IEEE.

关键词： Harmonic distortion

来源：评论

学校读者我要写书评

暂无评论

Liquidt: stock market analysis using liquid time-constant neural networks

引用

International Journal of Information technology (Singapore) 2024年第2期16卷 909-920页

作者： Gajjar, Pranshav Saxena, Aayush Acharya, Kairav Shah, Pooja Bhatt, Chintan Nguyen, Thanh Thi College of Engineering and Computing George Mason University Fairfax VA United States Electronics and Computer Science University of Southampton Southampton United Kingdom Department of Computer Science & Engineering School of Technology Pandit Deendayal Energy University Gandhinagar India School of Information Technology Deakin University Geelong Australia Institute of Technology Nirma University Ahmedabad India

Accurate and efficient predictions concerning stock prices are an intriguing and sought-after task in the field of computational financial analysis. This paper aims to leverage and validate novel deep learning pipelines for predicting NSE stock prices of Adani Ports, Reliance, and Tata Steel using recurrent neural architectures. The scope of this paper pertains to the utility of Liquid Time-Constant Networks (LTCs) and the development of a novel enhanced computing paradigm centric on LTCs. By assessing the use of bi-directionality for time-series prediction and the existing modality of architectures with LSTM and BiLSTM implications, the authors functioned on developing an LTC-based architecture that is capable of predicting stock market trends in a superlative fashion. The paper thoroughly explains the temporal characteristics and predictive trends and completes a comparative analysis with simple RNNs, GRUs, LSTMs, and their bidirectional counterparts, emphasizing the potential substitutes of the frequently used LSTMs. After sufficient experiments, the paper presents a comparative study for gauging a computational efficiency and accuracy trade-off for the aforementioned task. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： Deep learning Liquid neural networks Machine learning Stock price prediction Time series data

来源：评论

学校读者我要写书评

暂无评论

Protecting SDIIOT Network from Key Breach Attack by using Secret Hash Chain Techniques 2

Protecting SDIIOT Network from Key Breach Attack by using Se...

引用

2nd International Conference Computational and Characterization Techniques in engineering and sciences, IC3TES 2024

作者： Arora, Jatin Saluja, Kamal Ghantasala, G S Pradeep Rajesh Sharma, R. Sungheetha, Akey Singh, Susheel Kumar Vidyullatha, Pellakuri Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Alliance University Department of Computer Science and Engineering Bengaluru India Alliance University Alliance College of Engineering and Design Department of Computer Science and Engineering Bengaluru India Heera Lal Yadav Balika Degree College UP Lucknow India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Andhra Pradesh Guntur India

ISBN: (纸本)9798350364699

Attacks in a software-defined network (SDN) are hard to find. In light of this, this article offers a versatile modular architecture that enables DDoS attack prevention and mitigation in SDN environments. The interlinked computational devices present in the small items over the communication channel, which allows those devices to transmit industrial data, is known as the Industrial Internet of Things (IIoT). Since the conversation is conducted online, security and privacy breaches are possible. As a result, the authenticated key agreement (AKA) of communicating devices is crucial. However, every IOT device is limited in computational resources, so it might be difficult to add robust privacy and security features. AKA research is now focused on forward secrecy (FS) feasibility that provides control over future keys when a secret key is compromised. IoT devices with limited resources cannot process public key cryptosystems because of intensive calculations. The primary goal of AKA with FS for IIoT is to provide a lightweight security framework. Instead of using a public key security framework, it is using multiple hash values. The security strength of the suggested framework is built on challenge-response mechanisms, one-way hash functions, and symmetric key encryption. The inclusion of this suggested architecture demonstrates that it provides a protection against a variety of attacks, secret key negotiation, anonymity, and unlinkability. The proposed approach is analyzed to assess the performance of the security framework and demonstrates that it is a lightweight mechanism for IIoT. © 2024 IEEE.

关键词： Public key cryptography

来源：评论

学校读者我要写书评

暂无评论

Poster: Towards Accurate and Fast Federated Learning in End-Edge-Cloud Orchestrated Networks 43

Poster: Towards Accurate and Fast Federated Learning in End-...

引用

43rd IEEE International Conference on Distributed Computing Systems, ICDCS 2023

作者： Li, Mingze Sun, Peng Zhou, Huan Zhao, Liang Liu, Xuxun Leung, Victor C. M. College of Computer and Information Technology China Three Gorges University Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering Yichang China College of Computer Science and Electronic Engineering Hunan University Changsha China College of Electronic and Information Engineering South China University of Technology Guangzhou China College of Computer Science and Software Engineering Shenzhen University Shenzhen China

ISBN: (纸本)9798350339864

This work proposes a novel three-layer federated learning (FL) framework with parameter selection and pre-synchronization (PSPFL) to achieve fast and accurate model training. The basic idea of PSPFL is that clients select partial model parameters for transmission and then base stations aggregate them cooperatively (i.e., pre-synchronization) and send the aggregated results to the server for global model update periodically. However, there is an intrinsic trade-off between parameter transmission overhead and model training loss. To strike a desirable balance between them, we investigate the optimal parameter pre-synchronization round and local training round under PSPFL. Specifically, we propose a Deep Q-Network (DQN)-based method to obtain the local training round and parameter pre-synchronization round. Finally, extensive experiments are conducted to evaluate the performance of the proposed method on commonly used datasets. The results show that the proposed method can reduce the sum of FL completion time and training loss by an average of 8.17%-18.82% compared to benchmarks. © 2023 IEEE.

关键词： Synchronization

来源：评论

学校读者我要写书评

暂无评论

Polar Region Climate Dynamics: Deep Learning and Remote Sensing Integration for Monitoring Arctic and Antarctic Changes

引用

Remote Sensing in Earth Systems sciences 2024年第4期7卷 582-595页

作者： Maniraj, Subramanian Pitchiah Rose, Jesuharan Dafni Arunachalam, Rohini Rangasamy, Kotteeswaran Patil, Vishal Ratansing Kathirvelu, Selvakumarasamy Department of Data Science and Business Systems School of Computing SRM Institute of Science and Technology Kattankulathur Campus Chennai India Department of Computer Science and Engineering St. Joseph’s Institute of Technology Chennai India Department of Computer Science and Engineering Anil Neerukonda Institute of Technology and Sciences Andhra Pradesh Visakhapatnam India Joseph’s College of Engineering Chennai 600119 India Department of CSE(AIML) Vishwakarma Institute of Technology Pune India Department of Electronics and Communication Engineering Saveetha School of Engineering (SIMATS) Chennai India

The polar regions of the Earth, specifically the Arctic and Antarctic, play a pivotal role in regulating the planet’s climate systems. These regions are highly sensitive to climate change, with observable shifts such as diminishing sea ice, retreating glaciers, and rising temperatures. Understanding these dynamics is essential for predicting broader global climate impacts. This paper presents a novel approach for monitoring and predicting these changes by integrating an attention-based transformer model with a 3D convolutional neural network (3D-CNN). The proposed model is designed to capture both the spatial features of satellite imagery and the temporal dynamics of climate data, offering enhanced predictive capabilities for key climate variables such as sea ice extent, glacier movement, and temperature variations. The dataset was split into 80% training and 20% testing with tenfold cross-validation, and the model was trained using the Adam optimizer. The results show that the proposed model achieved a remarkable accuracy of 97.43%, outperforming traditional CNN and RNN models. The model also demonstrated a precision of 98.12% for sea ice extent prediction, a 96.45% precision for glacier movement detection, and a mean squared error (MSE) of 0.35 °C for temperature predictions. These findings suggest that deep learning models, specifically the integration of transformer and 3D-CNN architectures, can significantly contribute to polar region climate monitoring, offering improved tools for scientific research and policymaking. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024. corrected publication 2024.

关键词： 3D convolutional neural network Attention-based transformer Climate dynamics Deep learning Glacier movement Polar region Remote sensing Sea ice extent Spatial–temporal analysis Temperature prediction

来源：评论

学校读者我要写书评

暂无评论

Qualitative Research on Wireless Body Area System Packet Size Improvement 11

Qualitative Research on Wireless Body Area System Packet Siz...

引用

11th International Conference on System Modeling and Advancement in Research Trends, SMART 2022

作者： Sengar, Alok Singh Gupta, Anurag Chuhan, Nupa Ram Shukla, Ratnesh Kumar College of Computing Science and Information Technology Computer Science and Engineering UP Moradabad India Shambhunath Institute of Engineering and Technology Computer Science and Engineering Prayagraj India

ISBN: (纸本)9781665487320

Due to the challenging channel conditions in WBANs, lengthier packets might be more problematic. By and large, coupled bundles can withstand the ingenious effects of cleverly visible above. As a result, the best packet size for various WBAN execution tests should be determined. According to the most recent survey, choosing a surprising packet size on WBANs required a few thinking techniques. This study is centered on the mobility of the blasting size in a certain application or streaming scenario. This paper presents proportional models and strategies for refreshing the packet size for nearby associations with bodies removed in order to attract specialists for further evaluation in that specific area. © 2022 IEEE.

关键词： IEEE Standards

来源：评论

学校读者我要写书评

暂无评论

Enhancing Image Quality through Deep Learning-based Super-Resolution Techniques 6

Enhancing Image Quality through Deep Learning-based Super-Re...

引用

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

作者： Mekala, Sreenivas Bhushan, Sushant Shashi, Puja Lavanya, J. Ananda Tiwari, Mohit Narlagiri, Shilpa Sreenidhi Institute of Science and Technology Information Technology Telangana Hyderabad India Mewar University Department of Computer Science Delhi India The Oxford College of Engineering Karnataka Bengaluru India Computer Science & Engineering Visakhapatnam India Bharati Vidyapeeth's College of Engineering Department of Computer Science and Engineering Paschim Vihar Delhi India School of Engineering SR University Department of ECE Telanagana Warangal India

ISBN: (纸本)9798350304480

Significant advancements in super-resolution have been accomplished over the past two decades, particularly using deep learning techniques. Image super-resolution is a key image processing technique for improving an image's resolution in the field of computer vision. In addition to providing a thorough overview of recent developments in single-image super-resolution from the viewpoint of deep learning, this article aims to educate readers about the original conventional approaches for image super-resolution. In this article, we examine significant deep learning-based SR techniques and divide them into two groups based on the contributions they make to the definition of key optimisation targets for deep SISR and the assessment of relevant neural network topologies for SISR. Finally, we wrap up our study with some present issues and potential developments in deep learning-based SISR. © 2023 IEEE.

关键词： high resolution single image super resolution super resolution

来源：评论

学校读者我要写书评

暂无评论

An Investigation in Bahraini Dialect Text to Speech Synthesis Models and Datasets

An Investigation in Bahraini Dialect Text to Speech Synthesi...

引用

2024 International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies, 3ICT 2024

作者： Almahmood, Mohamed Albalooshi, Fatema Al-Ammal, Hesham College of Information Technology University of Bahrain Sakhir Bahrain Department of Computer Engineering University of Bahrain Sakhir Bahrain Department of Computer Science University of Bahrain Sakhir Bahrain

ISBN: (纸本)9798331533137

In the past few years, there has been an accelerated development in the field of Artificial Intelligence (AI) and Machine Learning (ML). Various Text To Speech (TTS) modules have been developed, and successfully implemented in many languages. However, implementations of such systems for the Arabic language have been minimal, with implementations mostly relying on makeshift solutions such as using diacritics to transliterate the Arabic text to English. This study presents the development of a Text To Speech (TTS) system for the Bahraini dialect. The proposed approach uses the Forward Tacotron model integrated with HiFi-GAN vocoder, and Optuna for hyperparameter optimization. Our approach provides a thorough understanding of the requirements for synthesizing natural and expressive Bahraini Arabic speech, and investigates the possibility of training such a system without the use of diacritics or phonetization tools. For the purpose of this study we created a dataset in the Bahraini dialect, containing 9 hours of recordings collected from Sanaa Alsaad’s YouTube channel. However, due to the small dataset size, data augmentation techniques were used expand the dataset to 36 hours. Another version of the dataset was created spanning 8 hours of augmented data and involving only higher quality recordings. The smaller dataset was then AI enhanced using Adobe Podcasts. The sample rate of the recorded data is 22050 Hz, as per the model’s requirements. Our system was first trained on the 36 hours dataset, and then transfer learning was used to fine tune the training on the 8 hours dataset. The system was assessed using metrics such as Attention Score, Mel Loss, Duration Loss, Pitch Loss, Word Error Rate (WER), and Mean Opinion Score (MOS). The model demonstrated promising capabilities in replicating the local dialect given the small dataset size and its subpar quality with an MOS of 3.4, and a WER of 34. ©2024 IEEE.

关键词： Transfer 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：