检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Pal, Rikathi Bhaumik, Anik Basu Murmu, Arpan Hossain, Sanoar Maity, Biswajit Sen, Soumya A. K. Choudhury School of Information Technology University of Calcutta Kolkata India Department of Computer Application and Science Institute of Engineering and Management Kolkata India

Diseases in plants cause significant danger to productive and secure agriculture. Plant diseases can be detected early and accurately, reducing crop losses and pesticide use. Traditional methods of plant disease identification, on the other hand, are generally time-consuming and require professional expertise. It would be beneficiary to the farmers if they could detect the disease quickly by taking images of the leaf directly. This will be a time-saving process and they can take remedial actions immediately. To achieve this a novel feature extraction approach for detecting tomato plant illnesses from leaf photos using low-cost computing systems such as mobile phones is proposed in this study. The proposed approach integrates various types of Deep Learning techniques to extract robust and discriminative features from leaf images. After the proposed feature extraction comparisons has been done on five cutting-edge deep learning models: AlexNet, ResNet50, VGG16, VGG19, and MobileNet. The dataset contains 10,000 leaf photos from ten classes of tomato illnesses and one class of healthy leaves. Experimental findings demonstrate that AlexNet with an accuracy score of 87%, with the benefit of being quick and lightweight, making it appropriate for use on embedded systems and other low-processing devices like smartphones. © 2024, CC BY.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

Classifying the DNA sequence using Optimized Naive Bayes Approach: A Comparative Analysis of Machine Learning Algorithms

Classifying the DNA sequence using Optimized Naive Bayes App...

引用

Computational Intelligence, Communication Technology and Networking (CICTN), International Conference on

作者： Aditya Pai H Chandrappa S Guru Prasad M S Ganesh Pathak Atul Thakare Pratik Kumar MIT School of Computing MIT Art Design and Technology University Pune India Dept. of Computer Science and Engineering JAIN (Deemed-to-be University) Bengaluru India Dept. of Computer Science and Engineering Graphic Era (Deemed to be University) Dehradun India Department of Computer Application Graphic Era (Deemed-to-be University) Dehradun India

ISBN: (数字)9798331530389

ISBN: (纸本)9798331530396

In bioinformatics, the exact classification of DNA sequences is essential to increasing comprehension of genetic structures and functionalities. This research introduces an enhanced Naive Bayes approach (ENB) specifically designed to handle more complexities related to DNA sequence data. This research integrates advanced feature weighting and optimized probability estimation techniques to enhance classification accuracy substantially. The proposed work demonstrated superior efficacy to traditional ML algorithms like Random Forest, SVM, Decision-Trees, K-Nearest Neighbors, Gradient Boosting etc. The proposed method attained a level of accuracy of 98%, and proposed approach performs better than the other models, with 94% accuracy in Logistic Regression coming in second.

关键词： Support vector machines Logistic regression Accuracy Machine learning algorithms Nearest neighbor methods Boosting Bayes methods Complexity theory Medical diagnosis Random forests

来源：评论

学校读者我要写书评

暂无评论

IOT-based Smart Ground water Recharge System

IOT-based Smart Ground water Recharge System

引用

Computational Intelligence, Communication Technology and Networking (CICTN), International Conference on

作者： Manas Uniyal Chandradeep Bhatt Noor Mohd Devendra Kumar Computer Science Department Graphic Era Hill University Dehradun India Computer Science Department Graphic Era Deemed to be University Dehradun India Computer Application Department ABES Engineering College Ghaziabad India

Water is the most important commodity for the existence of life. In India, the main sources of water are rainwater(monsoon) that fills the rivers with water and underground water. However, we have seen a steady decline in underground water levels across India at an alarming rate that affects the agriculture and daily water needs of the citizens. This paper suggests a smart ground water recharge system that automatically recharges the ground water after rain falls. The system uses smart IOT devices, solar panels, and a filter to filter out unwanted materials that come along the rainwater. In this paper a fully automatic rainwater harvesting is introduced that collects rainwater and filters out dirt and unwanted materials(trash) that comes along the rain. It also senses the acidic content of rain and filters it out when needed. Later on, the filtered water can be directly recharged in ground, or it can also be collected in artificial pools for irrigation purposes. Polluted water can be very harmful for our environment and food cycle.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Brain Tumor Diagnosis with Convolutional Neural Networks 6

Revolutionizing Brain Tumor Diagnosis with Convolutional Neu...

引用

6th International Conference on Futuristic Trends in Networks and Computing Technologies, FTNCT 2024

作者： Singh, Aryan Shuaib, Mohd Diwakar, Manoj Joshi, Aditya Singh, Prabhishek Pandey, Neha Department of Computer Application Graphic Era Deemed to Be University Dehradun248001 India Department of Computer Science and Engineering Graphic Era Deemed to Be University Dehradun248001 India School of Computer Science Engineering and Technology Bennett University Greater Noida201310 India Department of Biotechnology Graphic Era Deemed to Be University Dehradun248001 India

Historically, the diagnosis of brain tumors from magnetic resonance imaging (MRI) images has been a careful and extended endeavor that relies heavily on the expertise of radiologists and neurologists. In addition to being time-consuming, the complex nature of brain image analysis makes it vulnerable to cognitive biases and human error, which can affect the precision and effectiveness of diagnosis. Moreover, manual MRI scan interpretation might result in discrepancies between practitioners, which makes diagnosis even more difficult. These difficulties highlight the need for innovative approaches to improve the accuracy and speed of brain tumor identification as the need for quicker and more accurate medical evaluations keeps rising. To meet these difficulties, an innovative method based on image-driven Convolutional Neural Networks (CNNs) has been developed. Meningiomas, pituitary, gliomas, and absence tumors are the four major brain cancer groups that this research focuses on. With the basis of the EfficientNetB3 framework which had been pre-trained on the large-scale ImageNet dataset, the model uses a transfer learning method using a brain tumor dataset of 7023 images by adding extra layers that are exclusively meant to enhance classification and improved performance. The proposed method secures a notable accuracy of 99.84% and a precision of 99.33%. This advanced approach not only improves diagnostic precision but also significantly reduces the time required for neurologists to examine scans, enabling them to focus more on patient care and the development of preventive strategies. The efficiency of the proposed model underlines that it can become a breakthrough in clinical diagnostics and stimulate the progress of medical disciplines' development. For a comprehensive overview of the model architecture and implementation, please visit the GitHub repository https://***/Aryansin1234/***. Additionally, a live demonstration of

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Multiscale Fusion Graph Convolutional Networks for Hyperspectral Image Classification 2

Multiscale Fusion Graph Convolutional Networks for Hyperspec...

引用

2022 2nd International Conference on Artificial Intelligence, Big Data and Algorithms, CAIBDA 2022

作者： Wang, Lei Wang, Xili School of Computer Science Shaanxi Normal University Xi’an China School of Mathematics and Computer Application Shangluo University Shangluo China Engineering Research Center of Qinling Health Welfare Big Data Universities of Shaanxi Province Shangluo726000 China

ISBN: (纸本)9783800760268

Graph neural network (GNN) has shown remarkable performance in many fields, such as edge prediction, node classification, etc. However, the traditional graph neural network can only accept the full graph to train the model, which leads to a very high computational complexity. Besides, the lack of multi-scale mechanism limits the actual classification performance. In this paper, we propose a multiscale fusion model based on graph convolutional network (GCN) and convolutional neural network (CNN) for hyperspectral image (HSI) classification tasks. This model can first sample randomly from the full graph to subgraphs of different scales, then trains GCN on sub-graphs of different scales and extract features, and finally integrates the spatial-spectral features extracted by multi-scale CNN classifier and the structural features extracted by multi-scale GCN for end-to-end mini-batch joint training. Experiments on two real HSI data s demonstrate that the proposed method significantly improves the classification performance compared with other comparison methods. © VDE VERLAG GMBH ∙ Berlin ∙ Offenbach.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Privacy Preserving CSI Fingerprint Device-Free Localization 1

引用

4th International Conference on Machine Learning for Cyber Security, ML4CS 2022

作者： Huang, Tianxin Zhao, Lingjun Dai, Zeyang Lin, Liang Huang, Huakun School of Computer Science and Cyber Engineering Guangzhou University Guangzhou China School of Software Engineering Sun Yat-sen University Zhuhai China Greater Bay Area Institue of Precision Medicine Guangzhou China Guangdong Provincial Key Laboratory of Building Energy Efficiency and Application Technologies Guangzhou University Guangzhou China

ISBN: (数字)9783031200960

ISBN: (纸本)9783031200953

Device-Free Localization (DFL) method based on wireless signal fingerprint is a mainstream indoor location method at present. The main concerns in this field are location accuracy and complexity of computing, while the problem of privacy protection is easily neglected. Since the leakage of wireless signal data is likely leading to the leakage of location information, this paper proposes a privacy-preserving Channel State Information(CSI) fingerprint device-free localization method based on federated learning(PPDFL). Through federated learning, each client trains a local model using the collected local data and then transmits the trained parameters to the server. The server consolidates these parameters and then distributes the resulting parameters to each client for local model’s updating. After several rounds of training and updating, each client ends up with a fully trained model. Compared with the existing DFL methods, this method would not share the data of each client, and only transmits model parameters between server and client, thus achieving the effect of privacy protection. Several experiments are performed to prove the effectiveness of the proposed PPDFL. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Channel state information

来源：评论

学校读者我要写书评

暂无评论

Unmasking the Reality: A Comprehensive Study of Deepfake Identification Techniques and Their Expanding Terrain

Unmasking the Reality: A Comprehensive Study of Deepfake Ide...

引用

Computational Intelligence, Communication Technology and Networking (CICTN), International Conference on

作者： Shubh Sharma Disha Mohini Pathak Dhyanendra Jain Somya Srivastava Prashant Vats Govind Murari Upadhyay Department of Computer Science ABES Engineering College Ghaziabad U.P India Department of Computer Science Engineering-AIML ABES Engineering College Ghaziabad U.P India Dept. of CSE School of CSE Manipal University Jaipur Jaipur Rajasthan India Dept. of Computer Application Manipal University Jaipur Jaipur Rajasthan India

ISBN: (数字)9798331530389

ISBN: (纸本)9798331530396

The swift progression of deepfake-generating technologies has elicited much apprehension about their potential misuse in digital media, necessitating the development of efficient detection methods. This research aims to improve the precision of deepfake detection by the application of spatial-temporal feature engineering methods. A comparative comparison of advanced preprocessing techniques is performed to enhance the extraction of spatial and temporal indicators essential for detecting deepfake abnormalities. The study investigates the amalgamation of sophisticated machine learning and deep learning models with designed characteristics to get enhanced detection efficacy. Experimental assessments are conducted on benchmark datasets to verify the effectiveness of the suggested methodologies. The findings highlight the importance of effective preprocessing strategies in enhancing model generalizability and dependability, hence supporting the overarching goal of preserving digital authenticity.

关键词： Deep learning Deepfakes Accuracy Computational modeling Refining Media Benchmark testing Feature extraction Real-time systems Resilience

来源：评论

学校读者我要写书评

暂无评论

Exploring Consumer Behavior in E-Commerce with AI Personalization and Market Trends Analysis Models 3

Exploring Consumer Behavior in E-Commerce with AI Personaliz...

引用

3rd International Conference on Integrated Circuits and Communication Systems, ICICACS 2025

作者： Kumar, Gaurav Devayani, G. Saraswathi, C. Melba Kani, R. Dongre, Sandeep Mallick, M. S. Mohamed School of Computer Application Lovely Professional University Phagwara India M.Kumarasamy College of Engineering Department of Computer Science and Business Systems Karur India School of Management Studies Bannari Amman Institute of Technology Erode India Mar Ephraem college of Engineering and Technology Kanyakumari India Nagpur India Department of Computer Science Engineering Chennai India

ISBN: (纸本)9798331508456

Online retailers must monitor and respond to changing consumer trends to stay competitive. AI-driven customization's revolutionary impact on market trends is the focus of this study on online buying and customer behavior. As AI advances, e-commerce platforms will be able to customize user experiences. Preprocessing, feature extraction, and model training comprise the AI-driven personalization process. Customer data from online marketplaces is collected first. It manages missing values, balance the data, encode categorical variables, scale the features, and minimize the dimensions as part of our thorough data preprocessing to ensure fair and applicable results. To trained the algorithms with CNN and Convolutional LSTM Based on key criteria, the AI model beat LSTM and CNN. It provides personalized insights and recommendations with an average accuracy of 92.03%. Personalized experiences and product suggestions enabled by AI-powered personalization have transformed e-commerce. It's important to use smart algorithms to engage customers and examine large databases. This proposed approach to shows that AI can transform online shopping and improve customer experiences. © 2025 IEEE.

关键词： Marketplaces

来源：评论

学校读者我要写书评

暂无评论

Two-Stream Holographic Convolutional Network for Speech Emotion Recognition Using Korean Audio 4

Two-Stream Holographic Convolutional Network for Speech Emot...

引用

4th International Conference on Ubiquitous Computing and Intelligent Information Systems, ICUIS 2024

作者： Venkateswaran, N. Mudadla, Balaji. Jasmine, R. Rajitha Nalini, J. Rajasekar, M. Jayasudha, T. Panimalar Engineering College Department of Master of Business Administration Tamil Nadu Chennai600123 India CMR Technical Campus KandlaKoya Medchal Telangana Hyderabad501401 India R.M.K. Engineering College Department of Information Technology Tamil Nadu Kavaraipettai601206 India Vignan's Institute of Engineering for Women Department of Computer Science Andhra Pradesh Visakhapatnam530049 India Saveetha College of Liberal arts and Sciences Saveetha Institute of Medical and Technical Sciences Department of Computer Science And Application Tamil Nadu Chennai602105 India Kpr Institute of Engineering and Technology Department of English Tamil Nadu Coimbatore641407 India

ISBN: (纸本)9798331529635

Speech Emotion Recognition (SER) has become an important area of research in the AI domain, helping systems comprehend people's feelings with speech, in such areas as healthcare, automated customer support, and virtual companionship. Emotion detection from Korean speech raises learning issues and demand an understanding of all high-frequency spectrum and time selective features. Despite that these layers work effectively, typical convolutional networks may lose phase information which is so important for emotion distinction especially in languages with tone and phonetics. For this research, the AI-Hub Speech Emotional Database, a large scale Korean speech dataset, is employed to create a Two-Stream Holographic Convolutional Network (TSHCN) for SER. However, the TSHCN architecture employed a two-path structure in which one branch encoded the spectral feature and the other branch encoded the temporal dynamics in sequence, while the phase information was retained using holodynamic convolutions for better classification of emotions. In order to increase the efficiency of the model, the Kookaburra Optimization Algorithm (KOA) is used on the parameters of the weight network, reducing the number of mistakes and the load of calculations as well as increasing the accuracy of the model. As more evident from the previously discussed results, SER performance is notably enhanced by the use of TSHCN with KOA;specifically, the accurate representation of Korean speakers' speech emotions will help pave the way for the development of SER for the Korean language and other complex languages as well. This study thus takes up the shortcoming in the conventional approaches to the task and proposes an optimal and language-independent SER model. The introduced approach attains higher accuracy as 99%. © 2024 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Empirical Analysis of Deep Learning for Big Data and Its applications using CNN 2

Empirical Analysis of Deep Learning for Big Data and Its App...

引用

2nd International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2022

作者： Arya, Rakesh Khanduja, Manisha Rani, P.Shobha Pundhir, Prachi Tiwari, Mohit Shelke, Chetan Jagannath Cs&it Himgiri Zee University Uttarakhand Dehradun India Uttaranchal University Department of Computer Application Uttarakhand Dehradun India R.M.D.Engineering College Anna University Department of CSE India Computer Science and Engineering Ajay Kumar Garg Engineering College U.P. Ghaziabad India Bharati Vidyapeeth's College of Engineering Department of Computer Science and Engineering Delhi India Alliance University Department of Information Technology Bengaluru India

ISBN: (纸本)9781665437899

Deep Learning has taken an utmost interest in the field of big data analytics due to its feature extraction and classification properties. Traditionally, researchers used Machine Learning algorithms to classify big data;however, the feature extraction was carried out by a human-driven process. Thus, researchers discovered the deep learning approaches to carry out the feature extraction by using algorithms. In this research, a 'Convolutional Neural Network' or CNN algorithm has been selected to understand the accuracy of big data analytics. Primary research has been carried out to understand how hidden layers and nodes impact the accuracy of this neural network. Moreover, CNN has been compared with other neural networks to understand if CNN is out-competing the rest algorithms or not (other two algorithms selected are 'Recurrent Neural Network' or RNN and 'Artificial Neural Network' or ANN). In the primary research, CNN and other algorithms were tasted for accuracy against hidden layers, nodes, training and validation time. Regression and Correlation analyses have been carried out where independent variables were: Training time, Validation time, Hidden layers and Hidden nodes. Dependent variables were CNN, ANN and RNN. Findings showed that CNN is 92% accurate whereas other neural networks possess less than 90% of accuracy in big data analytics. The hidden nodes have significant positive impact on the accuracy of CNN. © 2022 IEEE.

关键词： Big data

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：