检索结果-内蒙古大学图书馆

Machine Learning and Deep Learning Approaches for Guava Disease Detection

SN computer science 2025年第4期6卷 1-28页

作者： Paramesha, K. Jalapur, Shruti Hanok, Shalini Puttegowda, Kiran Manjunatha, G. Kumara, Bharath Department of Computer Science and Engineering Vidyavardhaka College of Engineering Karnataka Mysuru India Department of Computer Science and Engineering Christ University Karnataka Bengaluru India Department of Electronics and Communication Engineering ATME College of Engineering Karnataka Mysuru India Department of Electronics and Communication Engineering Vidyavardhaka College of Engineering Karnataka Mysuru India Department of CSD PES Institute of Technology and Management Karnataka Shivamogga India Department of ECE MS Ramaiah University of Applied Science (MSRUAS) Karnataka Bangalore India

A larger proportion of crops face disease outbreaks, making agricultural output difficult. Detecting and predicting diseases at an early stage can enhance productivity. Guava, a tropical and subtropical fruit, is cultivated in various countries. In regions such as Bangladesh, Pakistan, India, and South America, guava cultivation faces significant challenges due to diseases like Canker, Dot, Mummification, Phytophthora, Scab, and Styler and Root. Traditional diagnosis methods based on visual observation are often unreliable and time-consuming. To address this, we developed an automated system leveraging deep learning techniques. Our study utilized a dataset comprising 4046 guava leaf images categorized into these seven disease classes. We compared the performance of traditional methods with deep learning approaches using vision transformers and transfer learning. The results demonstrate the superiority of deep learning methods over traditional approaches, where traditional machine learning model SVM gave accuracy near 78% and deep learning methods gave over 90%. The transfer learning method gave an accuracy of nearly 97% and on the other hand, the vision transformer gave accuracy of 98%. This offers a promising solution for early disease detection in guava crops. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Accuracy Deep learning Guava disease Leaf images Machine learning

来源：评论

学校读者我要写书评

暂无评论

Correntropy-Based Data Selective Adaptive Filtering

引用

IEEE Transactions on Circuits and Systems I: Regular Papers 2024年第2期71卷 754-766页

作者： Chien, Ying-Ren Wu, Sheng-Teng Tsao, Hen-Wai Diniz, Paulo S.R. Adaptive and Autonomous Communication Laboratory Department of Electrical Engineering National Ilan University Yilan City260007 Taiwan College of Electrical Engineering and Computer Science Graduate Institute of Communication Engineering National Taiwan University Taipei10617 Taiwan Program of Electrical Engineering Department of Electronics and Computer Engineering COPPE/Poli Universidade Federal do Rio de Janeiro Rio de Janeiro68504 Brazil

Data selection can be used in conjunction with adaptive filtering algorithms to avoid unnecessary weight updating and thereby reduce computational overhead. This paper presents a novel correntropy-based data selection method as an alternative to conventional data selection mechanisms based on squared error values. We developed a variable correntropy sensing algorithm to maximize the instantaneous correntropy function for the Gaussian kernel function to mitigate the impact of impulse noise and other forms of noise that can be disregarded in data selection. The proposed data selection mechanism can be implemented with any adaptive filtering algorithm. In simulations, the proposed method (implemented with the least mean squared algorithm) outperformed comparable error-based data selection schemes in terms of hit rate and miss rate, and the resulting weight updating ratio was close to the expected weight updating ratio. © 2023 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission.

关键词： Adaptive filters

来源：评论

学校读者我要写书评

暂无评论

A Novel Hybrid CNN-LSTM Framework with Ant Colony Optimization for Robust Fake News Detection

A Novel Hybrid CNN-LSTM Framework with Ant Colony Optimizati...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Santosh Kumar, B. Viji, M. Gowtham, T. Sekar, G. Sharmila, S. Saravanan, M. New Horizon College of Engineering Department of Computer Science and Engineering Bengaluru560103 India E.G.S. Pillay Engineering Engineering Department of Computer Science and Business Systems Nagapattinam611002 India P.A. College of Engineering and Technology Department of Electronics and Communication Engineering Pollachi642002 India Vsb College Of Engineering Department of Electronics and Communication Engineering Technical Campus Coimbatore642109 India Sir Issac Newton College of Engineering and Technology Department of Computer Science and Engineering Nagapattinam6111002 India Sri Eshwar college of engineering Department of Electronics and Communication Engineering Coimbatore641202 India

ISBN: (纸本)9798331509828

In the digital age, the spread of fake news has become ubiquitous: it weakens public speech and weakens public trust. In this paper we propose a novel method of detecting fake news using a deep learning framework. To do text analysis, we propose a hybrid model that incorporates Convolutional Neural Network and Long Short-Term Memory Network by utilizing on the strengths of each for effective text analysis. However, the LSTM layer is good in learning the context and sequence of the text, and the CNN component beats in extracting local and spatial details in textual data. The effectiveness of the proposed work is tested on a comprehensive data set of news sources (covering different sources, from different countries, and labeled for authenticity). We trained and evaluated the model on this dataset which mainly included features of linguistic and semantic nature to differentiate between genuine and fake news. We show that our results exhibit the biggest accuracy, precision, recall, and Fl-score improvement over old models. Automated fake news detection is a growing field, and this research proposes a robust and scalable solution to cut off the spread of misinformation. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An Efficient, Affordable and Reliable SMPS Battery Chargers for Automobile Industry 2

An Efficient, Affordable and Reliable SMPS Battery Chargers ...

引用

2nd International Conference on Advances in Computation, communication and Information Technology, ICAICCIT 2024

作者： Niveditha, J. Venkatesh, T. Reethika, A. Ramya, U. Sreejaa, S. Vinothini, V. Department of Electronics and Communication Engineering KPR Institute of Engineering and Technology Coimbatore India Department of Electronics and Communication Engineering Sri Ramakrishna Engineering College Coimbatore India Department of Computer Science and Engineering Sri Ranganathar Institute of Engineering and Technology Coimbatore India

ISBN: (纸本)9798331541217

As we are utilizing Conventional vehicles, Electric Vehicles require charging the batteries, so the chargers for batteries are becoming more and more crucial within the automobile industry. While the current chargers mostly rely on bulky and inefficient transformer models, this proposed work aims to explore the integration of Switched-Mode Power Supply (SMPS) technology. The method employed in this work is that replaces the charging based on transformers with SMPS technology, with the goal of improving efficiency, reducing size, and reducing heat generation. The result of the project has a successfully developed battery charger that utilizes SMPS technology. It has achieved increased efficiency, reduced size, and lower heat generation in comparison to traditional models. Furthermore, the revised charger exhibits a simpler and more affordable circuit, catering to a wider consumer base. As a result, this product can be used in both workshops and automobile showrooms with more efficiency at an affordable cost. © 2024 IEEE.

关键词： Automotive industry

来源：评论

学校读者我要写书评

暂无评论

Identification of Tamil Sign Language using Hamiltonian deep neural network

引用

International Journal of Systems, Control and communications 2025年第1期16卷 62-78页

作者： Lingeswari, Ponnusamy Pavunraj, Daniel Kanagavalli, Mariappan Manikandan, Karuppasamy Department of Electronics and Communication Engineering P.S.R. Engineering College Tamil Nadu Sivakasi India Department of Artificial Intelligence and Data Science Vel Tech Multi Tech Dr. Rangarajan Dr. Sakunthala Engineering College Tamil Nadu Chennai India Department of Electronics and Communication Engineering P.S.R.R. College of Engineering Tamil Nadu Sivakasi India Department of Computer Science and Engineering P.S.R. Engineering College Tamil Nadu Sivakasi India

Sign language consisting of various hand patterns, serves as a vital communication medium for conveying messages, sharing knowledge, and expressing ideas among the deaf community. This research addresses the challenge of recognising Tamil Sign Language (TSL) by proposing a novel identification method using a Hamiltonian deep neural network (HDNN). The primary objective is to maximise the accuracy and reliability of TSL recognition, especially for real-time applications. The dataset comprises real-time images of 12 vowels, 1 Aayutha Ezhuthu, and 18 consonants, collected from 110 different signers. To address noise in the images, an iterative guided filtering (IGF) method is employed for preprocessing. Subsequently, feature extraction is performed using residual exemplars local binary pattern (RELBP). HDNN is then applied to classify the signs. The performance of the proposed approach achieves 23.32%, 25.07%, 21%, 27.53%, and 30% higher accuracy and 14.09%, 19.63%, 28%, 18.45%, and 10.54% lower error rates compared to existing methods. Copyright © 2025 Inderscience Enterprises Ltd.

关键词： Local binary pattern

来源：评论

学校读者我要写书评

暂无评论

Plutchik Wheel of Emotion and Machine Learning-Based Hybrid Sentiment Analysis for the Hindi Language with Minimum Dependency on High Computation Resources

引用

SN computer science 2023年第6期4卷 797页

作者： Kumar, Pravin Vardhan, Manu Department of Computer Science and Engineering Nit Raipur Chhattisgarh Raipur India Department of Electronics and Communication (Computer Science and Engineering) University of Allahabad Prayagraj India

Sentiment analysis is a natural language processing technique for extracting sentimental, opinion, or emotional information from text data. Sentiment analysis of natural language is a complex task that requires high computation resources, and Sentiment analysis becomes more complicated if the language of text data is Hindi. This manuscript proposes a plutchik wheel of emotion and Machine learning-based hybrid sentiment analysis approach for the Hindi language with minimum dependency on high computation resources. In the proposed methodology, we assembled a lexicon for the Hindi language. Each word of the lexicon is mapped with respected plutchik emotion. As very few standardised data sets are available for the sentiment analysis of the Hindi language, thus we drafted a new data set. The data set compiled is a collection of educational kid stories from different publication books. Our experiment study shows that the proposed approach gives 73.45% accuracy on this data set with a lexicon comparable to state-of-the-art machine learning and lexicon-based hybrid sentiment analysis approaches. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Hindi Machine learning Natural language processing Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Agent Based Optimal Scheduling & Congestion Free Routing Scheme to Enhance QoS of NFV Enabled Heterogeneous Wireless Sensor Network Framework 15

An Intelligent Agent Based Optimal Scheduling & Congestion F...

引用

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

作者： Prathap, C. Sivaranjani, S. Sathya, M. Prabhakaran Rajalakshmi, J. Kavin Kumar, K. Gokulchandrasekaran NadarSaraswathi College of Engineering and Technology Department of Computer Science and Engineering Theni India SethuInstituteofTechnology Department of Computer Science and Engineering Virudhnagar India Nadar Saraswathi College of Engineering and Technology Department of Information Technology Theni India Nandha Engineering College Department of Electronics and Communication Engineering Erode India Sethu Institute of Technology Department of Electronics and Communication Engineering Virudhunagar India Kongu Engineering College Perundurai Department of Electronics and Communication Engineering Erode638060 India Karpagam Institute of Technology Department of Electronics and Communication Engineering Coimbatore India

ISBN: (纸本)9798350370249

In wireless sensor network (WSN), congestion is regarded as an unavoidable issue as of today's scenario at which the data traffic is increased to their aggregated channel capacity. This results in the consequence of buffer overflowing which leads to packets drop thereby reducing packet delivery ratio and degrades network throughput. Also, routing is the most favored approaches for the minimization of nodes energy consumption and the enhancement of Heterogeneous WSNs throughput. Since, the problem of routing has been proved to be an NP-hard, it has been realized that optimization-based technique offers better performance. For solving these issues, this paper proposes a congestion free optimal routing scheme based on Genetic algorithm-based distance aware-Low Energy Adaptive Clustering Hierarchy (GADA-LEACH) protocol to predict intelligent agent path. The major intention of this work is to enhance the efficiency of energy and QoS (throughput and delay) in edge-cloud based IoT environment of data transmission. Initially, the system model is initialized and the graph construction is made for the process of clustering using Spectral graph theory (SGT) at which the cluster head (CH) selection is made. Then, the scheduling process is carried by means of Packet weighted based ensemble optimization scheduling (PW-EOS) scheme. The NFV enabled optimal edge node is selected using Reconfigured Cuckoo Search optimizer (RCSO) after which the intelligent agent moving path in the Heterogeneous Network (HetNet) are predicted by GADA-LEACH technique. From this, an effective routing path is determined among CH and an optimized Edge node. Eventually, the performance assessment is carried in terms of throughput, energy consumption, survival rate, PDR, End-to-End delay and the outcomes conquered are compared with existing methods to attest the proficiency of proposed scheme. © 2024 IEEE.

关键词： Sensor nodes

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

Detection of Diabetic Retinopathy from Retinal Images Using DenseNet Models

引用

computer Systems science & engineering 2023年第4期45卷 279-292页

作者： R.Nandakumar P.Saranya Vijayakumar Ponnusamy Subhashree Hazra Antara Gupta Department of ECE K S R Institute for Engineering and TechnologyTiruchengode637215India Department of Computer Science and Engineering SRM Institute of Science and TechnologyChennai603203India Department of Electronics and Communication and Engineering SRM Institute of Science and TechnologyChennai603203India

A prevalent diabetic complication is Diabetic Retinopathy(DR),which can damage the retina’s veins,leading to a severe loss of *** treated in the early stage,it can help to prevent vision *** since its diagnosis takes time and there is a shortage of ophthalmologists,patients suffer vision loss even before ***,early detection of DR is the necessity of the *** primary purpose of the work is to apply the data fusion/feature fusion technique,which combines more than one relevant feature to predict diabetic retinopathy at an early stage with greater *** procedures for diabetic retinopathy analysis are fundamental in taking care of these *** profound learning for parallel characterization has accomplished high approval exactness’s,multi-stage order results are less noteworthy,especially during beginning phase *** Connected Convolutional Networks are suggested to detect of Diabetic Retinopathy on retinal *** presented model is trained on a Diabetic Retinopathy Dataset having 3,662 images given by *** results suggest that the training accuracy of 93.51%0.98 precision,0.98 recall and 0.98 F1-score has been achieved through the best one out of the three models in the proposed *** same model is tested on 550 images of the Kaggle 2015 dataset where the proposed model was able to detect No DR images with 96%accuracy,Mild DR images with 90%accuracy,Moderate DR images with 89%accuracy,Severe DR images with 87%accuracy and Proliferative DR images with 93%accuracy.

关键词： Convolutional Neural Networks vision loss pathogenic blood vessels DenseNet AlexNet ResNet

来源：评论

学校读者我要写书评

暂无评论

Hybrid Image Compression Using DCT and Autoencoder 7

Hybrid Image Compression Using DCT and Autoencoder

引用

7th IEEE Pune Section International Conference, PuneCon 2024

作者： Nayak, Dibyalekha Kar, Tejaswini Ray, Kananbala Ravindra, J.V.R. Nandan Mohanty, Sachi Shah and Anchor Kutchi Engineering College Electronics and Computer Science Engineering Mumbai India Kiit Deemed to Be University School of Electronics Engineering Bhubaneswar India School of Electronics and Communication Engineering Telengana Hydrabad India VIT-AP University School of Computer Science and Engineering Amaravati India

ISBN: (纸本)9798331527822

Medical image processing is an emerging area that has an effect on recognition, analysis and treatment techniques of the diseases. In medical image processing compression is required to reduce the bandwidth and storage related issues. In this method DCT and Autoencoder based image compression technique is used for the better compression of the medical brain images. To get the separate Region of Interest(ROI) and non-ROI based region Otsu method is considered. DCT and Autoencoder based hybrid compression is achieved on ROI and non-ROI regions of an image respectively. The evaluation parameter of this method are Peak Signal to Noise Ratio (PSNR), Structure Similarity Index matrix (SSIM), Feature Similarity Index Matrix (FSIM), Compression Ratio (CR) and Space saving(SS) percentage. For the medical brain images proposed method has PSNR of 44.45db, SSIM of 0.97, FSIM of 0.99, CR 9.26 and SS of 89.9(%). © 2024 IEEE.

关键词： Image compression

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：