检索结果-内蒙古大学图书馆

computer, Communication and Control (IC4), International Conference on

作者： M D Ashfaqul Hasan K. Balasubadra G. Vadivel N. Arunfred M.V Ishwarya S. Murugan Department of Computer Science and Engineering Malla Reddy Institute of Engineering and Technology Hyderabad Telangana India Department of Information Technology R.M.D. Engineering College Kavaraipettai Chennai Tamil Nadu India Department of Information Technology University of Technology and Applied Science Salalah Dhofar Oman Faculty of Management Studies SRM Institute of Science and Technology Kattankulathur Chennai Tamil Nadu India Artificial intelligence and Data science Department Agni College of Technology Thazhambur Tamil Nadu India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India

Microplastic pollution in water systems is growing, requiring novel detection and analysis methods. This research presents an Internet of Things (IoT)-driven image identification system using Convolutional Neural Networks (CNNs) to detect and quantify microplastics in water samples. The suggested method is more scalable and responsive due to IoT real-time data capture and remote monitoring of water infrastructure. An innovative CNN architecture for image processing allows the system to accurately identify micro plastics. The CNN model is trained and validated using a large dataset of micro plastic-containing water samples. The trained model can recognize various sizes, shapes, and colors of micro plastics, making it responsive to different environmental situations. The IoT architecture also allows image recognition modules in dispersed sensor nodes to cover water systems. Extensive studies prove the system can analyze vast amounts of image data quickly and reliably. Edge computing also minimizes latency and improves micro plastic analysis system responsiveness. The suggested IoT-driven image recognition method for continuous micro plastic pollution monitoring and evaluation in water systems seems promising. Scalability, realtime capabilities, and accuracy make it useful for environmental monitoring agencies and academics trying to reduce microplastics’ influence on aquatic ecosystems. This system advances IoT applications in environmental and pollution management.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enforcing Social Distancing with YOLO Algorithm Utilizing Object-to-Object Distance

Enforcing Social Distancing with YOLO Algorithm Utilizing Ob...

引用

information technology (ACIT)

作者： Muhamad Irsan Rosilah Hassan Taj-Aldeen Naser Abdali Mohamad Khairi Ishak School of Computing Telkom University Bandung Indonesia Department of Information Technology College of Engineering and Information Technology Ajman University U.A.E Faculty of Basic Education University of Misan Misan Iraq Department of Electrical and Computer Engineering Ajman University Ajman United Arab Emirates

Instances of COVID-19 transmission occur daily due to individuals failing to maintain distance or engaging in physical contact with others who may be contaminated with the virus. To mitigate this issue, this study has developed a system to detect human subjects practicing social distancing. The system utilizes a Raspberry Pi 4 Model B 8GB device in combination with a Logitech HD Webcam C270 camera. To detect human subjects, the Convolutional Neural Network is employed, utilizing the You Only Look Once (YOLO) method. In the testing phase of the tool, the system successfully identifies human subjects and assesses their proximity to others. It also detects instances of social distancing violations. The system achieved an average mean Average Precision (mAP) of 0.9792, a Precision of 0.9482, a Recall of 0.9819, and an f1 score of 0.9648.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A machine learning approach for text pattern diagnosis in mental health consultations

Decision Analytics Journal

引用

Decision Analytics Journal 2025年 15卷

作者： Juanita, Safitri Daeli, Anisah Hasratniwati Syafrullah, Mohammad Anggraeni, Wiwik Purnomo, Mauridhi Hery Faculty of Information Technology Universitas Budi Luhur Jakarta 12260 Indonesia Department of Information Systems Institut Teknologi Sepuluh Nopember Surabaya 60111 Indonesia Department of Computer Engineering Institut Teknologi Sepuluh Nopember Surabaya 60111 Indonesia

Online health consultation services are crucial for mental health support, particularly in densely populated areas. However, the heavy reliance on human expertise often leads to delays, necessitating more efficient and automated solutions. This study developed a machine learning framework to automate doctor response patterns for mental health questions — focusing on anxiety, depression, and stress — using clinically validated data from an Indonesian Online health consultation platform. We performed comprehensive text preprocessing, including duplicate removal, special character elimination, case folding, stopword removal, tokenization, lemmatization, and part-of-speech tagging, and evaluated four feature extraction methods: Word2Vec, Bag-of-Words, N-Gram, and Global Vectors for Word Representation. Five machine learning algorithms — Naïve Bayes, K-Nearest Neighbors, Random Forest, Neural Network, and Gradient Boosting — were tested, along with hybrid models combining Bagging Classifier or Genetic Algorithm. The results showed that Gradient Boosting achieved the highest accuracy (0.842) among standalone models, with high precision (0.858) and F1-score (0.864) for depression prediction, and recall (0.850) and F1-score (0.856) for stress prediction. The Gradient Boosting-Bagging Classifier hybrid matched this accuracy (0.842), while the Gradient Boosting-Genetic Algorithm hybrid showed superior performance for anxiety prediction (precision: 0.888, recall: 0.816). N-Gram and Bag-of-Words methods and the 90:10 and 70:30 train–test splits consistently produced optimal results. This work demonstrates that machine learning can automate mental health responses at scale, with Gradient Boosting balancing accuracy and efficiency. Future research will explore transformer-based models and multilingual validation to improve broader implementation. © 2025 The Authors

关键词： Health consultation Machine learning Online health consultation Pattern recognition Predictive modeling Text analytics

来源：评论

学校读者我要写书评

暂无评论

Design of an Optimized Asymmetric Multilevel Inverter with Reduced Components Using Newton-Raphson Method and Particle Swarm Optimization

引用

Mathematical Problems in engineering 2023年第1期2023卷

作者： Gireesh Kumar, Devineni Venkata Sireesha, Nagineni Ganesh, Aman Kotb, Hossam Aboras, Kareem M. Zeinoddini-Meymand, Hamed Kamel, Salah Department of Electrical and Electronics Engineering B v Raju Institute of Technology Telangana Narsapur502313 India Department of Information Technology Institute of Aeronautical Engineering Hyderabad Telangana Dundigal500043 India Ambala Mullana133203 India Department of Electrical Power and Machines Faculty of Engineering Alexandria University Alexandria21544 Egypt Department of Electrical and Computer Engineering Graduate University of Advanced Technology Kerman Iran Electrical Engineering Department Faculty of Engineering Aswan University Aswan81542 Egypt

Multilevel inverters have great scope in current developments of grid-connected solar PV systems. Two-level inverters are the simplest kind of multilevel inverter available (MLI). As the number of output levels is raised, the total harmonic distortion decreases. In classic MLI topologies, more electronic components are utilized to get higher-level outputs, which raise the cost, complexity, and volume of typical MLI installations. By reducing the design components, the cost of the system will be reduced. Furthermore, the two- and three-level inverters produce constant dv/dt output, which increases the stress on the power switches. This research proposes an asymmetric MLI topology that is suitable for PV applications and utilizes less number of DC sources and switches. The proposed inverter is controlled by selective harmonic elimination-based pulse width modulation (SHEPWM) to eliminate the lower-order dominant harmonics. The nonlinear equations produced by the SHEPWM are solved for the switching angles of the proposed inverter using the Newton-Raphson (NR) method and particle swarm optimization (PSO) method for various modulation indexes. The performance of the proposed inverter is analyzed based on the total harmonic distortion (THD) of the output for different operating levels of the inverter by comparing similar topologies in the literature. The THD obtained by the NR method is 7.3% and by using PSO is 4.23% at 0.9 modulation index. © 2023 Devineni Gireesh Kumar et al.

关键词： Newton-Raphson method

来源：评论

学校读者我要写书评

暂无评论

Adaptive Temporal Frame Interpolation Algorithm for Frame Rate Up-Conversion

Adaptive Temporal Frame Interpolation Algorithm for Frame Ra...

引用

作者： Vranjes, Denis Rimac-Drlje, Snjezana Vranjes, Mario Faculty of Electrical Engineering Computer Science and Information Technology Osijek Croatia

This article presents a novel adaptive temporal frame interpolation (FI) algorithm for frame rate up-conversion with reduced complexity. According to the adaptability criteria in the proposed algorithm, frames with a low temporal activity are interpolated using frame averaging, which significantly decreases the algorithm complexity. In the case of a high temporal activity, motion compensated FI is used and the high quality of interpolated frames is achieved. Compared to well-known frame rate up-conversion algorithms, the proposed approach is of significantly lower computational complexity, while maintaining the high quality of the interpolated frames. © 2019 IEEE.

关键词： Interpolation

来源：评论

学校读者我要写书评

暂无评论

Hybrid BWO-IACO Algorithm for Cluster Based Routing in Wireless Sensor Networks

引用

computers, Materials & Continua 2021年第10期69卷 433-449页

作者： R.Punithavathi Chinnarao Kurangi S.P.Balamurugan Irina V.Pustokhina Denis A.Pustokhin K.Shankar Department of Information Technology M.Kumarasamy College of EngineeringKarur639113India Department of Computer Science Pondicherry UniversityPuducherry605014India Department of Computer and Information Science Faculty of ScienceAnnamalai UniversityChidambaram608002India Department of Entrepreneurship and Logistics Plekhanov Russian University of EconomicsMoscow117997Russia Department of Logistics State University of ManagementMoscow109542Russia Department of Computer Applications Alagappa UniversityKaraikudi630001India

Wireless Sensor Network(WSN)comprises a massive number of arbitrarily placed sensor nodes that are linked wirelessly to monitor the physical parameters from the target *** the nodes in WSN operate on inbuilt batteries,the energy depletion occurs after certain rounds of operation and thereby results in reduced network *** enhance energy efficiency and network longevity,clustering and routing techniques are commonly employed in *** paper presents a novel black widow optimization(BWO)with improved ant colony optimization(IACO)algorithm(BWO-IACO)for cluster based routing in *** proposed BWO-IACO algorithm involves BWO based clustering process to elect an optimal set of cluster heads(CHs).The BWO algorithm derives a fitness function(FF)using five input parameters like residual energy(RE),inter-cluster distance,intra-cluster distance,node degree(ND),and node *** addition,IACO based routing process is involved for route selection in inter-cluster *** IACO algorithm incorporates the concepts of traditional ACO algorithm with krill herd algorithm(KHA).The IACO algorithm utilizes the energy factor to elect an optimal set of routes to BS in the *** integration of BWO based clustering and IACO based routing techniques considerably helps to improve energy efficiency and network *** presented BWO-IACO algorithm has been simulated using MATLAB and the results are examined under varying aspects.A wide range of comparative analysis makes sure the betterment of the BWO-IACO algorithm over all the other compared techniques.

关键词： Clustering routing wireless sensor network energy efficiency black widow optimization

来源：评论

学校读者我要写书评

暂无评论

Exploring the Effectiveness of Deep Learning in Audio Compression and Restoration

Exploring the Effectiveness of Deep Learning in Audio Compre...

引用

Trends in Quantum Computing and Emerging Business Technologies (TQCEBT), International Conference on

作者： S. Pushparani K. Sashi Rekha V. M. Sivagami R. Usharani M. Jothi Department of Computer Science and Engineering Meenakshi College of Engineering Chennai Tamil Nadu Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai Tamil Nadu India Department of Information Technology Sri Venkateswara College of Engineering Sriperumbudur Chennai Tamil Nadu Department of Computational Intelligence School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamil Nadu Department of Artificial Intelligence & Data Science CARE College of Engineering Trichy Tamil Nadu

ISBN: (数字)9798350384277

ISBN: (纸本)9798350384284

Modern audio processing requires compression and restoration for streaming services and data storage and transmission. This study examines how deep learning can address these difficulties and includes an architecture flow diagram. The suggested complex design has numerous integral stages optimized for audio compression and restoration. The input layer contains raw audio data. The pre-processing module normalizes and extracts features from raw data, frequently using Mel-frequency cepstral coefficients (MFCC) to capture audio characteristics. This module improves data quality by reducing noise and filtering. The architecture's heart is the compression module, where deep learning is used. This module compresses audio data using neural networks, maybe CNNs or RNNs. This compression is quantified by compression ratio and bitrate, with hypothetical values representing audio quality trade-offs. The compression module compacts audio data for storage or transmission. To minimize data size, quantization and encoding are common here. To accurately decompress audio, the decompression module mimics the compression module's architecture. Depending on needs, error correction or quality enhancement layers may be added. Filtering, equalization, and dynamic range compression may be used in the post-processing module to improve audio quality. If needed, a restoration module uses deep learning models to minimize noise and artifacts. This study presents four hypothetical scenarios to demonstrate different results. The scenarios emphasize high compression, balanced approaches, quality prioritization, and low resource utilization. Deep learning approaches can adapt to varied audio processing needs by balancing compression ratio, bitrate, audio quality (measured by PSNR), and restoration accuracy in each case.

关键词： Deep learning Training Filtering Bit rate Noise computer architecture Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Intrusion Detection in Networks using Honey Badger Algorithm with improved Adaptive Neuro-Fuzzy Inference System

Intrusion Detection in Networks using Honey Badger Algorithm...

引用

Communication and information technology (AICCIT), Al-Sadiq International Conference on

作者： Ibrahim Riyadh Alrikabi Murtadha A. Alazzawi Ahmed Al-Khaleefa Buraq T. Sh. Al-Mosawi Hassanain Raheem Kareem Ali Alsalamy Department of Computer Engineering Faculty of Engineering Shahid Chamran University of Ahvaz Ahvaz Iran Department of Computer Techniques Engineering Imam Al-Kadhum College (IKC) Baghdad Iraq Department of Physics Faculty of Education University of Misan Maysan Iraq Department of Computer Technical Engineering College of Information Technology Imam Ja’afar Al-Sadiq University Al-Muthanna Iraq

An Intrusion detection system IDS is a key component of the security management infrastructure. The goal of IDS is to monitor the processes prevailing in a network and to analyze them for signs of any possible deviations. Because of the large volume of data, the network gets expansion with a false alarm rate of intrusion, and detection accuracy decreased. It is one of the main problems in unknown attacks on network experiences. The basic aim was to develop accuracy also reduce the false alarm rate (FAR). We will design an Adaptive Neuro-Fuzzy based system to identify the intrusion activities within a network effectively. The Honey Badger Algorithm with an improved Adaptive Neuro-Fuzzy Inference System (HBA-IANFIS) is used to address the problems presented. The IANFIS combines an artificial neural network and a fuzzy interference system. To enhance the performance of the IANFIS model, the Honey Badger Algorithm is used to optimize the IANFIS. The intrusion detection results based on the NSL-KDD dataset were better and more efficient than those models because the detection rate was 96.68%, and the FAR result was 0.438%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Using Machine Learning for Industry 5.0 Efficiency Prediction Based on Security and Proposing Models to Enhance Efficiency 11

Using Machine Learning for Industry 5.0 Efficiency Predictio...

引用

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

作者： Pant, Piyush Rajawat, Anand Singh Goyal, S.B. Singh, Deepmala Constantin, Neagu Bogdan Raboaca, Maria Simona Verma, Chaman School of Computer Sciences and Engineering Sandip University Nashik India School of Computer Science and Engineering Sandip University Nashik India City University Faculty of Information Technology Petaling Jaya Malaysia India Gheorghe Asachi Technical University of Iasi Department of Power Engineering Iasi Romania National Research and Development Institute for Cryogenics and Isotopic Technologies Icsi Energy Department Ramnicu Valcea Romania University of Eötvös Loránd Faculty of Informatics Budapest1053 Hungary

ISBN: (纸本)9781665487320

Machine learning, with its huge untapped potential, is being researched all over the world to develop truly intelligent systems. Its applications are not enclosed in just one domain but in almost everything, from prediction models, recommender systems, and anomaly detection to automation and teaching a computer how to fly a helicopter. In this research, Multivariate Linear regression of supervised machine learning is studied to predict the efficiency of Industry 5.0, however, the efficiency of the model would be dependent on many factors and components such as security protocols and models, Industrial IoT - performance, connectivity, reachability, availability and many more. These factors and components would be categorized as the features of the algorithm which would be assigned weight 'w' and bias 'b'. To improve the efficiency of the model, these components could be changed and updated in order to enhance the overall model. Previous research papers discussed the integration of 'hot' technologies like 5G, Blockchain, AI, and IIoT in the industry 5.0 model, but this research is presented as their future work as it proposes to determine the efficiency of the model based on the features provided so that ultimate and optimal model could be determined. Later it proposes security and IIoT models that could improve the overall Industry 5.0. Quorum blockchain is proposed by the research in order to implement the ultimate security in the Industry 5.0. © 2022 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Optimizing Resource Utilization Using Vector Databases in Green Internet of Things

Optimizing Resource Utilization Using Vector Databases in Gr...

引用

IEEE Globecom Workshops

作者： Rani Kumari Dinesh Kumar Sah Korhan Cengiz Ali Nauman Nikola Ivkovi Ivan Mihaljevi Department of Computer Science and Engineering Birla Institutue of technology Ranchi India Department of Computer Science and Engineering Siksha ‘O’ Anusandhan Bhuwanswar India Department of Computer Engineering Istinye University Istanbul Turkey Department of Information Technologies Faculty of Informatics and Management University of Hradec Kralove Kralove Czech Republic Department of Information and Communication Engineering Yeungnam University Gyeongbuk Republic of Korea Faculty of Organization and Informatics University of Zagreb Varaždin Croatia

With the rapid proliferation of Internet of Things (IoT) devices and the ever-increasing volume of sensor data, optimizing resource utilization has become crucial for building sustainable and efficient IoT systems. In this study, we propose a novel approach for optimizing resource utilization in Green IoT through efficient storage and retrieval in vector databases. Our approach leverages specialized data structures, including k-d trees and ball trees, to achieve improved storage efficiency and accelerated retrieval performance for high-dimensional sensor data. We conducted extensive experiments to evaluate the effectiveness of our proposal, comparing it with traditional database approaches. The results demonstrate significant improvements in storage efficiency, with vector databases requiring considerably less storage space compared to traditional databases. Moreover, our approach enables fast and accurate retrieval of high-dimensional sensor data, reducing query times and enhancing real-time data analysis and decision-making capabilities. The technical achievements of our proposal offer promising prospects for the development of sustainable and efficient IoT systems in various domains, such as environmental monitoring, healthcare, and smart cities. Our work contributes to advancing the field of Green IoT by addressing the challenges of resource utilization and query performance through efficient storage and retrieval in vector databases.

关键词：

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：