检索结果-内蒙古大学图书馆

Water Quality Parameters Modeling of Thamirabarani River

Water Quality Parameters Modeling of Thamirabarani River

2024 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication, IConSCEPT 2024

作者： Sri Dhivya Krishnan, K. Prabhakaran, A. Danesh, K. Dinesh Kumar, E. Saai Srivathsan, R. Sachin M, P. Sri Sairam Engineering College Department of Computer Science and Engineering Artificial Intelligence and Machine Learning Chennai India Kumaraguru college of technology Department of Automobile Engineering Coimbatore India SRM Institute of science and technology Department of Electronics and Communication Engineering Chennai India

ISBN: (数字)9798331540685

ISBN: (纸本)9798331540685

An extensive water quality analysis of the water quality of the Thamirabarani River located in the Tirunelveli and Thoothukudi districts of Tamil Nadu, India, is conducted. This investigation focuses on 28 exclusive water parameters divided into physical, chemical, and biological parameters, including ammonia, biological oxygen demand, pH, and significant indicators. The dataset utilized for this analysis is sourced from the Tamil Nadu Pollution Control Board. This study employs machine learning algorithms inclusive of prediction and classification algorithms. Multiple-Linear Regression, Polynomial Regression, Elastic Net regression, Support Vector machine, k-Nearest Neighbors and Random Forest are used to classify the 5 Designated Best Use classes. These algorithms iterate through various combinations of considered water parameters until convergence for providing accurate insights into their interrelationships. The random forest produces 77% accuracy which is high compared to other algorithms. The outcomes of this research hold significance for policymakers and environmentalists, offering valuable insights into the water quality of the Thamirabarani River. © 2024 IEEE.

关键词： Rivers

来源：评论

学校读者我要写书评

暂无评论

Movie Recommendation System Using Hybrid Based Method 3

Movie Recommendation System Using Hybrid Based Method

引用

3rd IEEE International Conference on Automation and Computation, AUTOCOM 2025

作者： Kamble, Khushi Bhadarge, Pradnyanand Bhakte, Shreejit Kulkarni, Omkaresh Kadam, Rutuja Pinjarkar, Latika Vishwakarma Institute of Information Technology Computer Science and Engineering - Artificial Intelligence and Machine Learning Department Pune India Maharashtra Pune India Nagpur Campus Pune India

ISBN: (纸本)9798331542375

The rise of digital platforms has increased user engagement and satisfaction through personalized recommendation systems. The research paper presents a hybrid approach to movie recommendation, which uses content-based filtering and collaborative filtering techniques to mitigate the cold start problem, data sparsity, and scalability issues. The proposed system will utilize methodologies from machine learning, such as cosine similarity and vectorization, and the K-Nearest Neighbors (KNN) algorithm, for recommending movies based on their precise and personalized values. The dataset TMDB5000 will then be used for two datasets involving movie features, cast, and crew information while preprocessing techniques in cleaning, feature extraction, and merging are undertaken to ensure robust foundation for the model building. The hybrid model uses the bag-of-words technique to vectorize and compute cosine similarity to determine movies' relationships in a multidimensional space. The KNN algorithm then refines the collaborative filtering process by the clustering of user preferences and makes recommendations using nearest-neighbor analysis. Our current approach overcomes these weaknesses by combining both content-based and collaborative methods, resulting in a system which handles diverse user preferences while maintaining high recommendation accuracy. As the evaluation of precision, recall, F1-score, and mean squared errors further validates that this system performance is good and also scalable and efficient for processing large datasets for which it explains some practical aspects related to implementation in real time. The future work includes deep learning models like neural collaborative filtering to further improve semantic understanding and recommendation accuracy. This paper addresses the current system's limitations by proposing a novel, efficient, and user-centric hybrid approach, which can be extended to other domains, such as e-commerce, music, and book recommendati

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Non-Destructive Detection of Fillet Fish Quality Using MQ135 Gas Sensor and Neutrosophic Logic-Enhanced System

引用

Neutrosophic Sets and Systems 2025年 80卷 540-563页

作者： Shams, M.Y. Darwesh, M.R. Bhatnagar, Roheet Al-Sattary, N.S.A. Salama, A.A. Ghoname, M.S. Deptartment of Machine Learning Faculty of Artificial Intelligence Kafrelsheikh University Kafrelsheihk33516 Egypt Department of Agriculture Engineering Faculty of Agriculture Tanta University Tanta31527 Egypt Department of Food Processing Faculty of Industry and Energy Samannoud Technological University Egypt Department of Computer Science and Engineering Manipal University Rajasthan Jaipur India Department of Mathematics and Computer Science Faculty of Science Port Said University Egypt

This paper demonstrates the feasibility of using an electronic nose to assess fish quality by analyzing air quality and examining volatile organic compounds (VOCs) alongside physical variables, with pH, protein content, and VOCs serving as chemical reference points. artificial intelligence algorithms were employed to predict quality and calculate regression coefficients. Using the reference neural network algorithm based on chemical and physical compounds, regression coefficients (R values) achieved were 0.99, 0.98, and 0.97, respectively. Additionally, ANFIS (Adaptive Neuro-Fuzzy Inference System) produced R values of 0.99, 0.85, and 0.98. Both fuzzy logic and ANFIS proved effective for predicting fish quality. Image processing techniques, including histogram analysis, color mapping, and edge detection, were also applied to assess fish quality. To enhance the inference process, Neutrosophic Logic-Enhanced Fuzzy Logic Systems were utilized, addressing uncertainty and imprecision in fish quality assessment. Neutrosophic logic combines fuzzy logic's partial truth with indeterminacy, represented by three membership functions: truth, indeterminacy, and falsity. Neutrosophic fuzzy inference integrates steps like neutrosophication, rule evaluation, aggregation, and defuzzification, ensuring improved expressiveness and fidelity. For instance, neutrosophic fuzzy rules evaluated fish freshness and appearance to determine quality ratings such as poor, good, or excellent. This integration enhances decision-making by accurately modeling complex real-world uncertainties. These methods, combining electronic nose technology, artificial intelligence, and neutrosophic inference, provide a robust, non-destructive, and cost-effective approach to detecting spoilage in fillet fish. © 2025, University of New Mexico. All rights reserved.

关键词： Volatile organic compounds

来源：评论

学校读者我要写书评

暂无评论

Brain Tumor Detection Using VGG 16 & Efficient Net B3 Model 10

Brain Tumor Detection Using VGG 16 & Efficient Net B3 Model

引用

10th International Conference on Advanced Computing and Communication Systems, ICACCS 2024

作者： Menagadevi, M. Sharmila, S. Thiyagarajan, D. Madian, Nirmala Devaraj, Somasundaram School of Engineering Malla Reddy University Department of Computer Science Engineering Hyderabad India Dr.N.G.P Institute of Technology Department of Biomedical Engineering Coimbatore India School of Engineering Malla Reddy University Department of Artificial intelligence and Machine Learning Hyderabad India Vellore Institute of Technology Vellore India

ISBN: (纸本)9798350384369

A brain tumor is a growth of cells that begins in the brain and develops uncontrollably and unnaturally. Benign, malignant, and pituitary tumors are the different types of brain tumors. The life expectancy of the patients should be increased by appropriate care, careful planning and precise diagnostics. The above knowledge will help in early and accurate Detection of tumor. Magnetic Resonance Imaging (MRI) is generally utilized for diagnosing brain tumors. MRI examination is performed based on injecting contrast agents for enhancing the visibility of tumor. For recognition of brain tumors, machine learning and deep learning algorithms are performed to predictthe brain tumor with high accuracy. In this work modified EfficientN etB3 and VGG16 is proposed to detect the type and location of tumor. Proposed model gives higher prediction accuracy for different types of tumors. VGG 16 gives training accuracy of 95.1 %, testing accuracy of 94.3 % and validation accuracy of 94%. EfficientNetB3 training accuracy of 98.8%, testing accuracy of 98.4% and validation accuracy of 97.8%. EfficientN etB3 have better accuracy for tumor prediction and classification. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

An Optimized Hybrid Deep learning and IoT-Enabled Health System in Retina Image Analysis for Blindness Detection 2

An Optimized Hybrid Deep Learning and IoT-Enabled Health Sys...

引用

2nd International Conference on Self Sustainable artificial intelligence Systems, ICSSAS 2024

作者： Yamini, J. Kanimozhi, T. Jenefa, A. Bagyalakshmi, K. Aarthi, K. Dhivya, P. Kalaignar Karunanidhi Institute of Technology Department of Artificial Intelligence and Machine learning Coimbatore India Sri Eshwar College of Engineering Department of Artificial Intelligence and Data Science Coimbatore India Ppg Institute of Technology Department of Computer Science and Engineering Coimbatore India Sns College of Technology Department of Mathematics Coimbatore India Kalaignar Karunanidhi Institute of Technology Department of Artificial Intelligence and Data Science Coimbatore India Bannari Amman Institute of Technology Department of Computer Science and Engineering Erode India

ISBN: (纸本)9798350368413

Early signs of blind identification and retina disorder in retina image has become prominent. Deep learning techniques are used to improve the accuracy in detecting pathological conditions from the retina images. However, the models have some challenges such as suboptimal feature extraction and inefficient filtering methods. Most of the traditional methods often result in overfitting and under fitting, thus decreasing the generalizability and robustness of the model. The proposed hybrid approach combines bilateral filtering with Convolutional Neural Networks (CNN). In this approach, bilateral filtering acts as a pre-processing technique to enhance image quality by reducing noise and preserving edges for the correct extraction of features. The CNN is applied for feature extraction and it is used to self-learn complex patterns from filtered images. The proposed approach gives an accuracy of 95.65% with a loss of 0.18 without overfitting and underfitting. © 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

An Efficient Biometric Authentication Based on Face Image using Deep Generative Adversarial Network 2

An Efficient Biometric Authentication Based on Face Image us...

引用

2nd IEEE International Conference on Integrated Circuits and Communication Systems, ICICACS 2024

作者： Aswini, K.R.N. Al-Fatlawy, Ramy Riad Jagadish, Sripelli Ramaswamy, Palanivel Deepak Kumar, B.P. KNS Institute of Technology Department of Artificial Intelligence and Machine Learning Bangalore India The Islamic University Najaf Iraq SR University School of Computer Science & Artificial Intelligence Warangal India Nitte Meenakshi Institute of Technology Department of AI and DS Bengaluru India CMR Technical Campus Hyderabad India

ISBN: (纸本)9798350317558

face authentication is one of the technique to prevent the loss of personal data, however the process is challenging due to variations in the patterns of the mouth, nose, eyes, and angles. A face authentication system that leverages an enhanced Deep Generative Adversarial Network (DGAN) is being developed as a solution to the problem. The process begins with preprocessing Histogram Equalization method to enhance the image quality for generator input. GAN generator to create synthetic image using data augmentation method to identify the true face, which is helpful for identifying fake one. Then AlexNet called discriminator to extract the feature of input image and compare the real and fake images to authenticate the person. The implemented DGAN model demonstrates superior performance, achieving Precision of (97.12%), recall of (97.31%) and F1-Score of (97.01%). When compared to previous models like AutoRegressive Biometric Authentication-Oriented Face Detection (ARBAOFD), deep steganography with Celebes (DSC) and Convolutional Neural Network (CNN) © 2024 IEEE.

关键词： AutoRegressive Celebes Convolutional Neural Network Generative Adversarial Network Steganography

来源：评论

学校读者我要写书评

暂无评论

Touchless Mouse Control Via Hand Gestures Using Resnet and Mediapipe

Touchless Mouse Control Via Hand Gestures Using Resnet and M...

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： Jagadeeswara Rao Palisetti Digumarthi Srilikhitha Karna Bhargava Basa Bhavana Devi Mettu Bharath Kumar Computer Science and Engineering(Artificial Intelligence and Machine Learning) Lakireddy Bali Reddy College of Engineering Mylavaram India

ISBN: (数字)9798331512248

ISBN: (纸本)9798331512255

Touchless control of systems using hand gestures is a trending technology in the field of Human-computer Interaction (HCI). One of the most common ways to interact with systems is through the mouse. In this paper, a touchless mouse is focus on, which can perform the same operations as a physical mouse using finger and hand gestures. All of these operations are carry out by the system without requiring any external devices. In the physical mouse, we hold and operate it using the index and middle fingers. Similarly, we use the same hand pose to control the touchless mouse system. Nowadays, every system has an inbuilt webcam. This system uses a low-resolution webcam as input to capture hand gestures with 21 landmarks using OpenCV and MediaPipe. Based on the movements of the landmarks in the hand, the cursor can navigate, and various actions such as right-click, left-click, double-click, zoom in and zoom out, drag and drop files, multiselect files, increase, and decrease volume, adjusting the brightness, are easily performed, ResNet18 is used to stop the cursor movement. Using different finger and hand gestures. The system has the potential to replace traditional HCI tools in the future and help optimize hu-man-computer communication.

关键词： Hands Human computer interaction Performance evaluation Webcams Tracking Navigation Hospitals Brightness Gesture recognition Indexes

来源：评论

学校读者我要写书评

暂无评论

AI -Driven Detection of Gastrointestinal Disease based on Advanced Deep learning Techniques 4

AI -Driven Detection of Gastrointestinal Disease based on Ad...

引用

4th International Conference on Sentiment Analysis and Deep learning, ICSADL 2025

作者： Izankar, Sakshi V. Puri, Chetan Burle, Rushikesh Computer Science and Design Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Maharashtra Wardha India Artificial Intelligence and Machine Learning Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Maharashtra Wardha India

ISBN: (纸本)9798331523923

Esophageal, gastric, and colorectal cancers (CRC) are some of the gastrointestinal (GI) cancers threatening global health with CRC being particularly concerning due to its high fatality rate. While early diagnosis is crucial in improving treatment efficiency, barriers such as image noise and visual subjective assessments during diagnostics such as colonoscopies often render it inconceivable. For better diagnostic accuracy in detecting gastrointestinal disease via endoscopic images, the research explores whether highly advanced artificial intelligence (AI) models such as Vision Transformers (ViTs) and pre-trained DenseNet201 can be effective. We compare these models to popular deep learning techniques such as Support Vector machines (SVM), ResNet50, VGG19, and GoogleNet. At a training accuracy of 99.9% and a validation accuracy of 98.8%, experiments on the KVASIR dataset indicate that Vision Transformer is superior to other models since it can learn long-range dependencies. The robustness of deep learning models for identifying GI disease is exemplified by the superior performance of DenseNet201, ResNet50, and InceptionV3, all of which possess high accuracy, precision, and recall values. The paper illustrates the potential of Vision Transformers, when combined with transfer learning and pre-trained CNN models, to revolutionize endoscopic diagnoses and provide a valuable resource to help physicians manage gastrointestinal conditions more effectively. © 2025 IEEE.

关键词： Endoscopy

来源：评论

学校读者我要写书评

暂无评论

IoT And IIoT Integrated Spruce Grid System

IoT And IIoT Integrated Spruce Grid System

引用

2023 International Conference on Power Energy, Environment and Intelligent Control, PEEIC 2023

作者： Gupta, Anand Kumar Raghavendra, R. Sikri, Alisha Tula's Institute Department of Computer Science and Engineering Dehradun India Department of Computer Bangalore India Noida Institute of Engineering and Technology Department of Artificial Intelligence & Machine Learning Uttar Pradesh Greater Noida India

ISBN: (纸本)9798350357769

The Network of Things is a rapidly developing field of technology that provides creative solutions in many different areas, most notably essential infrastructures. Its revolutionary effect is especially seen in the field of standard electricity systems, where it makes the transition to a more intelligent and efficient energy grid easier. This analysis explores the architecture and features of Internet of Things (IoT)-enabled intelligent energy grid systems, with an emphasis on several IoT technologies (sensing, communication, and computation) and their respective standards within the smart energy grid context. This page also offers a thorough summary of previous studies on the use of IoT in systems with smart grids. A review of current studies and literature indicates a significant worry about the security flaws that IoT technologies and energy systems are known to have. As a result, we examine popular threat as attack models that are unique to IoT-enabled power plants and compile mitigation strategies designed to deal with these security issues. The article's conclusion highlights the use of cutting-edge technology, such as blockchain, artificial intelligence, and machine learning, to improve the security and resilience of IoT-enabled energy networks. These cutting-edge solutions help to improve the efficacy, stability, and dependability of smart energy systems by tackling contemporary issues including security flaws. This comprehensive investigation offers insightful information on the architecture of IoT-enabled clever energy systems, the security issues they raise, and how cutting-edge technology might improve their overall efficacy systems. © 2023 IEEE.

关键词： Advanced Metering Infrastructure (AMI) cybersecurity energy system optimization fog computing and SCADA technologies Internet of Things (IoT) technologies IoT-enabled smart energy grid renewable energy integration self-healing mechanisms smart grid architecture smart meters

来源：评论

学校读者我要写书评

暂无评论

Optimized Constrained Application Protocol for IoT Smart Home Data Security: A Novel Lightweight Approach

Optimized Constrained Application Protocol for IoT Smart Hom...

引用

2024 IEEE International Conference on Recent Advances in Science and engineering Technology, ICRASET 2024

作者： Subhashini, R. Jyothi, D.G. Bangalore Institute of Technology Affiliated to Visvesvaraya Technological University Department of Computer Science and Engineering Karnataka India Bangalore Institute of Technology Affiliated to Visvesvaraya Technological University Department of Artificial Intelligence and Machine Learning Karnataka India

ISBN: (纸本)9798350388602

By increasing simplicity and efficiency, a smart environment aims to enhance human existence. The IoT paradigm has evolved into a crucial technology for creating smart buildings, and the majority of computer networks now have IoT technologies. Nevertheless, during this shift, IoT devices are susceptible to cyberattacks. Thus, in practical smart home applications, security and privacy are key issues. In order to improve data security in smart home settings while lowering computing costs, this publication proposes the Broken-Stick Regressive Lightweight Speck Ephemeral Cryptography-based Constrained Application Protocol (BRLSC-CoAP). Real-time data is gathered by IoT devices and sent to authorized users. BRLSC-CoAP includes processes for authentication, encryption, decryption, and registration to safeguard this process. Forbes indexive Broken-stick regression is used to verify user authentication, and a lightweight Speck ephemeral cryptography technique is utilized for encryption. The experimental findings demonstrate that BRLSC-CoAP performs better than traditional techniques by increasing confidentiality, accuracy, and precision in authentication while lowering computing overhead, delay, and cost.. © 2024 IEEE.

关键词： Smart homes

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：