检索结果-内蒙古大学图书馆

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

作者： Dighe, Akshada Garg, Bindu Department of Computer Engineering BVDUCOE Pune India Department of Computer Science and Business System BVDUCOE Pune India

ISBN: (纸本)9798331541217

Intellectual disability (ID), a developmental condition often stemming from prenatal or postnatal factors, exerts a profound influence on individuals' lives and necessitates timely intervention. Conventional screening methods are resource-intensive and demand specialized medical expertise. This study introduces a novel, non-invasive approach to ID screening by meticulously analyzing facial features and vocal characteristics extracted from interview *** the extraction of facial measurements and speech patterns, we devised a Craniofacial Variability Index (CVI) to assess the likelihood of ID. Furthermore, advanced machine learning techniques were strategically employed to augment the predictive accuracy of this index. Our empirical findings unequivocally demonstrate promising results, with an accuracy rate reaching up to 80% when synergizing CVI scores and phonetic features. This research underscores the potential of a non-invasive, AI-powered screening instrument for ID, offering a more accessible and efficient alternative to prevailing practices. Future investigations will concentrate on refining the model and validating its efficacy across diverse populations. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence Integrated Rice Crop Disease Detection Using Drones for Smart Farming 7

Artificial Intelligence Integrated Rice Crop Disease Detecti...

引用

7th International Conference on Circuit Power and Computing Technologies, ICCPCT 2024

作者： Verma, Ayush Kumar Diksha Sharma, Sachin Graphic Era Deemed to Be University Department of Computer Science Engineering Dehradun India Graphic Era Hill Unniversity Department of Computer Science Engineering Dehradun India Graphic Era Deemed to Be University Graphic Era Hill University Department of Computer Science and Engineering Dehradun India

ISBN: (纸本)9798350372816

This investigate addresses the common challenge farmers confront when physically distinguishing crop infections. We propose a viable arrangement utilizing drone-based crop discovery frameworks, which incorporate a high-resolution camera and a YOLOv8 picture classification demonstrate. This innovation makes disease discovery in broad agricultural regions both productive and cost-effective. The proposed framework points to diminish financial misfortunes for agriculturists and improve the generally maintainability of crop yields. By giving convenient and precise infection distinguishing proof, our arrangement makes a difference minimize the hazard of illness spreading to adjacent crops. Also, our research highlights the broader suggestions of integrating advanced technologies into farming, emphasizing potential financial benefits for ranchers. The mechanized usefulness of the framework facilitates the manual workload on agriculturists, permitting them to center on key decision-making and asset optimization. In rundown, this examination marks a critical step in utilizing cutting-edge innovation to address significant challenges in farming, advancing financial versatility and maintainable practices. © 2024 IEEE.

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

Forecasting Geomagnetic Storms for Earth Using LSTM with Solar Wind and IMF Features

Forecasting Geomagnetic Storms for Earth Using LSTM with Sol...

引用

2024 International Conference on Innovations in science, engineering and Technology, ICISET 2024

作者： Shammi, Nusrat Jahan Ashraf, Taqia Ifty, Rashedul Arefin Rahman, Md. Ziaur International Islamic University Chittagong Kumira Department of Computer Science and Engineering Chattogram4318 Bangladesh Chittagong University of Engineering and Technology Department of Computer Science and Engineering Chittagong4349 Bangladesh

ISBN: (纸本)9798350355499

When the solar wind interacts with Earth's field, it can cause geomagnetic storms, which pose serious risks to vital infrastructure such as satellite communication, GPS systems, and electric power transmission. We presented a novel method for forecasting the Disturbance Storm-Time Index (Dst) using a long-short-term memory (LSTM) neural network in order to meet the urgent requirement for precise predictions. Our model employs sensing data from NASA's ACE and NOAA's DSCOVR satellites to analyze the complex relationship between interplanetary magnetic field & plasma from solar wind & sunspot activity. These factors are crucial to understanding geomagnetic disturbances. The LSTM model accumulates complex patterns and temporal relationships within the space weather data by including real-time data assimilation, resulting in enhanced weather prediction capabilities. Evaluation metrics like the root mean square error (RMSE) and coefficient of determination (R2) are used to assess the model's performance and reliability. The outcomes indicate that the LSTM model is highly effective in accurately predicting geomagnetic storms. The predicted values offer vital information for operators of satellites, power grids and magnetic navigation systems, enabling them to implement preemptive actions to mitigate the effects of any disruptions caused by geomagnetic storms. The research we accomplished helps to improve the approaches employed for forecasting space weather. This provides decision-makers with a useful and timely tool to strengthen vital systems and prepare for geomagnetic disturbances. © 2024 IEEE.

关键词： NASA

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Survey on Traffic Light Detection Sensors for Vehicle Safety and Automatic Emergency Braking Systems Using Deep Learning Techniques 3rd

A Comprehensive Survey on Traffic Light Detection Sensors fo...

引用

3rd International Conference on Intelligent Systems and Sustainable Computing, ICISSC 2023

作者： Gowri, B. Shyamala Priya, G. Vishnu Anjana, S. Arjun, V. Kodal, Devendraa Department of Computer Science and Engineering Easwari Engineering College Tamil Nadu Chennai India

ISBN: (纸本)9789819783540

The integration of Traffic Light Detection (TLD) systems with Advanced Emergency Braking Systems (AEBS) marks a critical milestone in enhancing road safety and paving the way for advanced autonomous driving. This survey paper provides a panoramic and extensive overview of the state-of-the-art TLD solutions leveraging sensors and deep learning techniques. With an increasing emphasis on accident prevention and traffic management, the intersection of TLD and AEBS has become a focal point of research and development. This survey begins by elucidating the fundamental challenges associated with TLD, including varying environmental conditions, occlusions, and complex traffic scenarios. We explore the pivotal role of sensors such as cameras, LiDAR, and radar in providing the requisite data for TLD, and delve into the intricacies of sensor fusion techniques for enhanced perception. Deep Learning has emerged as a cornerstone technology in TLD, enabling robust object detection, classification, and real-time decision-making. We meticulously analyze a spectrum of deep learning architectures including Single-Shot Detectors (SSD), Faster R-CNN, YOLO, and custom-designed networks tailored for TLD applications. Furthermore, the survey examines critical components of the TLD pipeline, encompassing data collection, preprocessing, model training, real-time inference, and integration with AEBS. Emphasis is placed on real-time constraints, multi-modal sensor fusion, and adaptability to diverse traffic light configurations. The paper also delves into the significance of accurate traffic light state prediction, going beyond mere detection to anticipate traffic light changes and optimize vehicle control actions. Human-centric interaction and privacy concerns are addressed, encompassing driver warnings, user interfaces, and data anonymization strategies. Moreover, the survey discusses the importance of safety, validation, and collaboration within the TLD and AEBS ecosystem, emphasizing compl

关键词： Road and street markings

来源：评论

学校读者我要写书评

暂无评论

High Degree Dependency Study of Ensemble Models in Credit Card Fraud Analysis 2

High Degree Dependency Study of Ensemble Models in Credit Ca...

引用

2nd International Conference on Computational Intelligence, Communication Technology and Networking, CICTN 2025

作者： Rani, Shalini Tiwari, Mayank Tyagi, Shiva Department of Computer Science and Engineering Ajay Kumar Garg Engineering College Ghaziabad India

ISBN: (纸本)9798331530389

Credit card fraud detection is an increasingly critical issue due to the growth of digital transactions and the sophistication of fraudulent activities. This study proposes a hybrid framework combining Graph Neural Networks (GNNs), ensemble methods (e.g., XGBoost, Random Forest), and polynomial feature engineering to address key challenges, including class imbalance, non-linear data relationships, and real-time applicability. The system achieved a detection accuracy of 96.7%, precision of 96.9%, recall of 96.4%, and a false-negative rate of 3.6% on benchmark datasets. These improvements are attributed to the integration of advanced sampling techniques, polynomial feature transformations, and the hybrid architecture. The findings demonstrate the effectiveness of the proposed approach in enhancing fraud detection systems and provide a scalable solution for real-world applications. © 2025 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Optimized Hybrid Deep Learning Approach for Detecting DoS Attacks Using Feature Selection in Wireless Sensor Networks

Optimized Hybrid Deep Learning Approach for Detecting DoS At...

引用

2025 IEEE International Conference on Computational, Communication and Information Technology, ICCCIT 2025

作者： Sasson Taffwin Moses, S. Abraham David, L. Emil Selvan, G.S.R. Ramkumar, M.P. Thiagarajar College of Engineering Department of Computer Science and Engineering Tamil Nadu Madurai India

ISBN: (纸本)9798331512965

The rapid growth of smart cities, healthcare monitoring, and environmental sensing relies heavily on the real-time data processing capabilities of Wireless Sensor Networks (WSNs). However, these networks face significant security challenges, particularly from malicious activities like Denial of Service(DoS) attacks, which can disrupt critical operations. A hybrid intrusion detection model that combines Convolutional Neural Networks (CNN) and Deep Neural Networks (DNN) to improve the detection of such threats has been proposed. The preprocessing phase includes the Synthetic Minority Over-sampling Technique (SMOTE) which mitigates class imbalances ensuring robust performance across diverse attack scenarios. The model incorporates advanced feature selection techniques including SelectKBest and Grey Wolf Optimization (GWO) to identify the most critical features for enhanced detection accuracy. The CNN component effectively captures local traffic patterns, which are then refined by the DNN for accurate classification. This hybrid model's effectiveness in detecting diverse DoS attack scenarios is evaluated using WSN-DS dataset, ensuring robust security for WSNs. By achieving an impressive 98% detection accuracy, this hybrid model proves to be effective in intrusion detection. Its applications can significantly strengthen the security and reliability of WSNs, ensuring uninterrupted operations in key sectors such as smart cities, healthcare, and environmental monitoring. © 2025 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Optimized Deep Learning for the Classification of Parkinson’s Disease Based on Voice Features

引用

Critical Reviews in Biomedical engineering 2022年第5期50卷 1-28页

作者： Sharanyaa, S. Sambath, M. Renjith, P.N. Computer Science and Engineering Hindustan Institute of Technology and Science Tamil Nadu India Department of Computer Science and Engineering Hindustan Institute of Technology and Science Tamil Nadu India

Parkinson’s disease (PD) is a neurodegenerative disorder. Hence, there is a tremendous demand for adapt-ing vocal features to determine PD in an earlier stage. This paper devises a technique to diagnose PD using voice signals. Initially, the voice signals are considered an input. The signal is fed to pre-processing wherein the filtering is adapted to remove noise. Thereafter, feature extraction is done that includes fluctuation index, spectral flux, spectral centroid, Mel frequency Cepstral coefficient (MFCC), spectral spread, tonal power ratio, spectral kurtosis and the proposed Exponential delta-Amplitude modulation signal (delta-AMS). Here, exponential delta-amplitude modulation spectrogram (Ex-ponential-delta AMS) is devised by combining delta-amplitude modulation spectrogram (delta-AMS) and exponential weighted moving average (EWMA). The feature selection is done considering the extracted features using the proposed squirrel search water algorithm (SSWA), which is devised by combining Squirrel search algorithm (SSA) and water cycle algorithm (WCA). The fitness is newly devised considering Canberra distance. Finally, selected features are fed to atten-tion-based long short-term memory (attention-based LSTM) in order to identify the existence of PD. Here, the training of attention-based LSTM is performed with developed SSWA. The proposed SSWA-based attention-based LSTM offered enhanced performance with 92.5% accuracy, 95.4% sensitivity and 91.4% specificity. © 2022 by Begell House, Inc.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Analytical Modeling and Performance Evaluation of Beam-Based Random Access Protocol for 5G Beamforming Networks

引用

IEEE Internet of Things Journal 2023年第24期10卷 22246-22255页

作者： Lin, Ting-An Cheng, Ray-Guang National Taiwan University of Science and Technology Department of Electronic and Computer Engineering Taipei106335 Taiwan

Access parameters, user equipment (UE) density, system load, and channel conditions significantly impact the performance of random-access (RA) protocols, influencing network capacity, latency, and robustness. In 3GPP standard, the prach-ConfigurationIndex access parameter is used to designate reserved RA channel occasions (ROs) for each beam, enabling UEs to derive beam mapping patterns and select desired beams through a beam-based RA protocol. This article addresses the challenge of bursty arrivals from massive Internet of Things (IoT) devices with sporadic traffic patterns in 5G beamforming networks. We propose an analytical model to evaluate the performance of the beam-based RA protocol for any beam mapping pattern. Extensive computer simulations are conducted to validate the accuracy and effectiveness of our model across various scenarios. The results demonstrate that our model provides valuable insights into the behavior and performance of the beam-based RA protocol and offers a reliable tool to evaluate and optimize beam mapping patterns in practical 5G network deployments. © 2014 IEEE.

关键词： Analytical models

来源：评论

学校读者我要写书评

暂无评论

Detection and Prevention of Black Hole Attack using Tree Hierarchical Deep Convolutional Neural Network and Enhanced Identity-based Encryption in Vehicular Ad Hoc Network

引用

IEIE Transactions on Smart Processing and Computing 2024年第1期13卷 41-50页

作者： Narayanan, K. Lakshmi Naresh, R. Department of Computer Science and Engineering SRM Institute of Science and Technology Kattankulathur Chengalpattu Tamilnadu Chennai603203 India Department of Networking and Communications SRM Institute of Science and Technology Kattankulathur Chengalpattu Tamilnadu Chennai603203 India

A method for the recognition and prevention of a black hole attack is proposed using a tree hierarchical deep convolutional neural network (THDCNN)and enhanced identity based encryption in a vehicular ad hoc network (VANET). Automobiles are organized with a cluster formula using an improved k-means clustering algorithm. Following the cluster formation, cluster head (CH) selection is done using a balancing composite motion optimization (BCMO) algorithm. After selecting the cluster head, the entrance of a spiteful node occurs in the cluster. The THDCNN is proposed for classifying a cluster node as i) a black hole attack node or ii) a normal node. If a black hole attack node is found, the attack node information is communicated to an individual CH, which makes a final decision. Otherwise, the standard node data is encrypted with the enhanced identity-based encryption algorithm. Finally, the proposed method prevents the normal node data from the attacker. Thus, the proposed method attains higher accuracy and lower computational time than other methods. Copyrights © 2024 The Institute of Electronics and Information Engineers.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Identity Preservability and Detectability of IDInvert GAN Model 20

Identity Preservability and Detectability of IDInvert GAN Mo...

引用

20th International Conference on Electrical engineering/Electronics, computer, Telecommunications and Information Technology, ECTI-CON 2023

作者： Chaengsrisuk, Pattanadej Sae-Bae, Napa Srinakharinwirot University Faculty of Science Department of Computer Science Bangkok Thailand

ISBN: (纸本)9798350310467

GAN inversion is a type of generative adversarial networks (GAN) models that can regenerate realistic images from real face photos and further perform image manipulation. While GAN inversion models can be useful for many purposes, it can be abused to generate harmfully fake contents also. This paper evaluates the performance of the recent In-domain GAN inversion model (IDInvert) regarding identity preservability and detectability of its generated face images. The experiments are conducted to answer the two main questions;how well IDInvert can imitate real face photos and how well existing image classification techniques can distinguish its generated images from the real ones. The results show that generated images do not preserve personal identity and thus significantly loss similarity to their reference photos. In addition, common machine learning classifiers can modestly distinguish these generated images from real photos with 0.87 accuracy. This indicates that the recent IDInvert model's ability to imitate real faces is not yet perfect and hazardous, and its generated images are still simply detected. © 2023 IEEE.

关键词： Face recognition

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：