检索结果-内蒙古大学图书馆

Braille–Latin conversion using memristive bidirectional associative memory neural network

Journal of Ambient Intelligence and Humanized Computing 2023年第9期14卷 12511-12534页

作者： Vaidyaraman, Jayasri Thyagarajan, Abitha K. Shruthi, S. Ravi, V. School of Electronics Engineering Vellore Institute of Technology Chennai India Department of Electrical Engineering and Computer Science University of Michigan Ann ArborMI United States

Artificial neural networks (ANNs) are finding increasing use as tools to model and solve problems in almost every discipline in today’s world. The successful implementation of ANNs in software—particularly in the fields of deep learning and machine learning—has spiked an interest in designing hardware architectures that are custom-made to implement ANNs. Several categories of ANNs exist. The two-layer bidirectional associative memory (BAM) is a particular class of hetero-associative memory networks that is extremely efficient and exhibits good performance for storing and retrieving pattern pairs. The memristor is a novel hardware element that is well-suited to modelling neural synapses because it exhibits tunable resistance. In this work, in order to create a device that can perform Braille–Latin conversion, we have implemented a circuit realization of a BAM neural network. The implemented hardware BAM uses a memristor crossbar array for modelling neural synapses and a neuron circuit comprising an I-to-V converter (resistor), voltage comparator, D flip-flop, and inverter. The efficiency of the implemented hardware BAM was tested initially using 2 × 2 and 3 × 3 patterns. Upon successfully verifying the ability of the implemented BAM to store and retrieve simple pattern pairs, it was trained for a pattern-recognition application, namely mapping Braille alphabets to their Latin counterparts and vice versa. The performance of the implemented BAM network is robust even on the introduction of noise. The application can recognize the input patterns with accuracies of 100% in either direction when tested with up to 30% noise. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Student Support with AI: A College Assistance Chatbot Using NLP and ANN 2

Enhancing Student Support with AI: A College Assistance Chat...

引用

2nd IEEE International Conference on Networks, Multimedia and Information technology, NMITCON 2024

作者： Abdul Razak, M.S. Manoj Kumar, M.V. Nirmala, C.R. Naseer, R. Prashanth, B.S. Sneha, H.R. Bapuji Institute of Engineering and Technology Department of Computer Science and Engineering Karnataka Davanagere577004 India Nitte Meenakshi Institute of Technology Department of Information Science and Engineering Karnataka Bengaluru560064 India

ISBN: (纸本)9798350372892

The rapid adoption of chatbots in various domains has revolutionized user support systems, particularly in educational institutions. This paper presents the development and implementation of a College Assistance Chatbot designed to aid university students in navigating academic and administrative queries. Leveraging Natural Language Processing (NLP) techniques and deep learning models, specifically an Artificial Neural Network (ANN), the chatbot efficiently understands and processes student inquiries. The system's architecture is meticulously crafted to manage communication effectively, ensuring timely and accurate responses. An extensive dataset was collected from college resources and pre-processed to train the neural network. The chatbot's performance was rigorously evaluated through a series of experimental campaigns, achieving an accuracy of 80.07% after 1000 epochs. The results indicate that the chatbot can reliably handle a wide range of student queries, providing a scalable solution for enhancing student support services. This innovative approach offers significant improvements over traditional methods, demonstrating high potential for broader application in educational settings. © 2024 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Robust Vehicle Detection Based on Improved You Look Only Once

引用

computers, Materials & Continua 2023年第2期74卷 3561-3577页

作者： Sunil Kumar Manisha Jailia Sudeep Varshney Nitish Pathak Shabana Urooj Nouf Abd Elmunim Department of Computer Science Banasthali VidyapithRajasthan304022India Department of Computer Science&Engineering School of Engineering&TechnologySharda UniversityGreater Noida201310India Department of Information Technology Bhagwan Parshuram Institute of Technology(BPIT)GGSIPUNew Delhi110078India Department of Electrical Engineering College of EngineeringPrincess Nourah bint Abdulrahman UniversityP.O.BOX 84428Riyadh11671Saudi Arabia

Vehicle detection is still challenging for intelligent transportation systems(ITS)to achieve satisfactory *** existing methods based on one stage and two-stage have intrinsic weakness in obtaining high vehicle detection *** to advancements in detection technology,deep learning-based methods for vehicle detection have become more popular because of their higher detection accuracy and speed than the existing *** paper presents a robust vehicle detection technique based on Improved You Look Only Once(RVD-YOLOv5)to enhance vehicle detection *** proposed method works in three phases;in the first phase,the K-means algorithm performs data clustering on datasets to generate the classes of the ***,in the second phase,the YOLOv5 is applied to create the bounding box,and the Non-Maximum Suppression(NMS)technique is used to eliminate the overlapping of the bounding boxes of the ***,the loss function CIoU is employed to obtain the accurate regression bounding box of the vehicle in the third *** simulation results show that the proposed method achieves better results when compared with other state-of-art techniques,namely LightweightDilated Convolutional Neural Network(LD-CNN),Single Shot Detector(SSD),YOLOv3 and YOLOv4 on the performance metric like precision,recall,mAP and *** simulation and analysis are carried out on PASCAL VOC 2007,2012 and MS COCO 2017 datasets to obtain better performance for vehicle ***,the RVD-YOLOv5 obtains the results with an mAP of 98.6%and Precision,Recall,and F1-Score are 98%,96.2%and 97.09%,respectively.

关键词： Image-processing K-means clustering CNN YOLOv5 loss function deep-learning

来源：评论

学校读者我要写书评

暂无评论

Mitigating Denial Based Service Attacks in Heterogeneous Sensor Networks: Strategies and Solutions 11

Mitigating Denial Based Service Attacks in Heterogeneous Sen...

引用

11th International Conference on Reliability, Infocom Technologies and Optimization, ICRITO 2024

作者： Desai, Jaynesh H Bagle, Neha S Rami, Khyati Verma, Shanti Bhagwan Mahavir University Department of Computer Applications Gujarat Surat India Sal Institute of Technology & Engineering Research Department of Computer Science Gujarat India L J University Department of Computer Applications Gujarat Ahmedabad India

ISBN: (纸本)9798350350357

With the development of heterogeneous sensory networks in various applications of domains for ensuring the security against denial based service (DoS) attacks will become a paramount. In this research study, a proposal of a novel system named SecureSenseGuard(SSG) for effectively detecting DoS attacks in heterogeneous sensor networks. SecureSenseGuard(SSG) leveraging the Decision Tree (DT) algorithm augmented with Recursive type Features Elimination (RFE) for achievinga robust and efficient attack detection. The proposed system may operate by first Collection of data from diverged sensors within the network. The data, representing various network attributes, are then preprocessed and fed into the DT algorithm for classifications process. RFE will be employed as a feature selection techniques to enhance the performance of DT algorithm by iterative process for removing less relevant features, thus improving in detection accuracy and reducing computational overhead. The proposed system SecureSenseGuard(SSG) will offer several advantages over existing approaches. By employing DT, it will provide interpretable and transparent decision rules for facilitating understanding and trust in the detection process. Moreover, the integration of RFE will enhance the system's scalability and adaptability for dynamic network environments. To evaluate the effectiveness of SecureSenseGuard(SSG) an extensive experiment may be conducted by using various ranges of datasets and synthetic attack scenarios. The Results demonstrate that SecureSenseGuard(SSG) achieved high detection rates. while maintaining a low false alarm rate, outperforming traditional approaches. Overall, SecureSenseGuard(SSG) may present a promising solution in mitigating DoS attacks in heterogeneous sensory networks by offering a balance between detection accuracy, interpretability, and computational efficiency. © 2024 IEEE.

关键词： Heterogeneous networks

来源：评论

学校读者我要写书评

暂无评论

Leveraging Machine Learning for Early Detection of Cardiovascular Diseases

Leveraging Machine Learning for Early Detection of Cardiovas...

引用

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

作者： Shrivastava, Anurag Maindola, Meenakshi Kumar, Rakesh Thethi, H. Pal Sreeja, S.P. Sirisha, N. Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamilnadu Chennai India Graphic Era Deemed to Be University Department of Computer Science & Engineering Dehradun India GLA University Department of Computer Engineering & Applications Mathura India Lovely Professional University Phagwara India New Horizon College of Engineering Master of Computer Application Bangalore India MLR Institute of Technology Department of Computer Science & Engineering Telangana Hyderabad India

ISBN: (纸本)9798331512965

In order to enhance patient outcomes, rapid and precise detection approaches are needed for cardiovascular diseases (CVDs), which are among the top causes of death globally. By examining a wide range of demographic and clinical data, this study investigates how machine learning approaches could improve the early diagnosis of CVDs. We explore how many different machine learning methods could identify different heart diseases. Decision trees, support vector machines and more, are included in these algorithms. By using feature selection and optimization methods we want to strengthen these models' prediction abilities and make them more resilient. The dataset used by this research includes all of the medical information of patients as they include all the pertinent biomarkers such as age, blood pressure, cholesterol levels and etc. The results suggest that machine learning models, especially ensemble methods like Random Forest and gradient boosting, are indeed able to predict the risk of CVD better than conventional diagnostic strategies. Results suggest that early risk assessment using machine learning embedded within healthcare processes is a reliable and non-invasive approach. This study has found machine learning to have promise for change and further research into the practical use of these models to revolutionize treatment of cardiovascular diseases. © 2025 IEEE.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Depth-Integrated CNN Approach for Effective Face Spoof Detection 1

Depth-Integrated CNN Approach for Effective Face Spoof Detec...

引用

1st International Conference on Cognitive, Green and Ubiquitous Computing, IC-CGU 2024

作者： Singh, Ravi Pratap Singh, Siddhartha Shekhar Dash, Ratnakar Mishra, Vinita Debayani Gochhayat, Sudeep Kumar Muduli, Debendra National Institute of Technology Rourkela Department of Computer Science and Engineering Rourkela India NIIS Institute of Business Administration Department of MCA Bhubaneswar India CV Raman Global University Bhubaneswar Department of Computer Science and Engineering Bhubaneswar India

ISBN: (纸本)9798350361780

Facial recognition systems present certain benefits, notably their relative convenience, contactless nature, and nonintrusiveness compared to alternative biometric methods like voice recognition and fingerprint technology. These characteristics enhance their applicability, popularity, and overall adoption. However, the susceptibility of facial recognition to spoofing attacks poses a significant challenge. This vulnerability arises from the ease with which photos and videos of registered users can be obtained online or captured without their knowledge or consent. This article introduces a method based on convolutional neural networks (CNN) to enhance the security of facial recognition systems against presentation attacks (PA). By employing both RGB and monocular depth data, the method distinguishes between authentic and fake facial images. The initial step involves preprocessing the images to minimize background interference and improve feature extraction. Following this, the CNN analyzes the preprocessed images to extract color features from both RGB and depth data. This approach not only lowers the expenses associated with depth cameras but also improves the accuracy of classification. The efficiency of this new model has been confirmed through its training and testing on the NUAA and MSU-MFSD datasets. Quantization is implemented for model optimization to make it memory-efficient and faster to execute. © 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

Real-Time Bus Driver Monitoring System Using Machine Learning 2

Real-Time Bus Driver Monitoring System Using Machine Learnin...

引用

2nd International Conference on Advanced Computing and Communication Technologies, ICACCTech 2024

作者： Kadu, Anil Dharashive, Rajnandini Nimje, Rachit Rajvaidya, Arya Palkar, Sanket Gaikwad, Vijay Vishwakarma Institute of Technology Department of Instrumentation and Control Pune India Vishwakarma Institute of Technology Department of Computer Engineering Pune India Vishwakarma Institute of Technology Department of Electronics and Telecommunication Pune India

ISBN: (纸本)9798331519056

In recent years, the importance of ensuring road safety has intensified, prompting the development of advanced driver monitoring systems. This paper presents a real-time bus driver monitoring system utilizing a Raspberry Pi, OpenCV, a RaspiCam and machine learning techniques. The system aims to enhance passenger safety by detecting driver fatigue and distraction, which are major contributors to road accidents. The proposed solution leverages the Raspberry Pi's processing capabilities and the RaspiCam's imaging features to continuously capture and analyze the driver's facial expressions and eye movements. OpenCV's robust image processing algorithms are employed to identify signs of drowsiness and inattentiveness. The innovative aspects of the proposed solution include the use of Eye Aspect Ratio (EAR) for drowsiness detection and Mouth Aspect Ratio (MAR) for detecting yawning. Both the EAR and MAR are calculated through real-time facial landmark analysis. The system issues alerts when unsafe driving behavior is detected, thereby allowing for timely intervention. The proposed monitoring system is cost-effective and scalable. It offers a promising approach to improving public transportation safety by mitigating the risks associated with driver fatigue and distraction. Experimental results showed an accuracy of 92% for fatigue detection and 88% for distraction detection. This demonstrates the system's effectiveness in real-time detection and its potential for deployment in commercial bus fleets. © 2024 IEEE.

关键词： Bus drivers

来源：评论

学校读者我要写书评

暂无评论

Advancing Stress Detection through Deep Learning in Human-Machine Interactions with Speech Signals Analysis 15

Advancing Stress Detection through Deep Learning in Human-Ma...

引用

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

作者： Santhiya, S. Jayadharshini, P. Abinaya, N. Sruthi, K. Vishnu, N. Kavin Suganth, V. Department of Artificial Intelligence Kongu Engineering College Erode India Department of Computer Science and Engineering Hindustan Institute of Technology Coimbatore India

ISBN: (纸本)9798350370249

In the modern world, where stress is a major issue that negatively impacts people's general well-being, it is essential to create a strong audio-based stress sensor. By developing an Acoustic Features Stress Perception model, this research seeks to facilitate early identification of stress-related problems, thereby supporting preventive health measures. The research makes use of RAVDESS and CREMA-D audio datasets, which span a wide range of emotional expressions like stress and relaxation, and applies sophisticated signal processing techniques and machine learning to them. With 7,882 audio files in it, the large dataset offers a strong basis for training and evaluating the stress detection *** such as Librosa (feature extraction), WavePlot(waveform visualization), Spectrogram (frequency-time representation), and Mel-Frequency Cepstral Coefficients (the spectrum characteristic capture) are used in this research. The model seeks to precisely identify and categorize stress levels in audio recordings by incorporating these features. Using the extracted acoustic features, deep neural networks are used to train the system to distinguish between stressed and relaxed states. The results obtained demonstrate that the suggested model can accurately identify stress, which qualifies it for incorporation into a range of applications, such as workplace settings, personal wellbeing applications, and healthcare monitoring equipment. The results of the model is about 97% and 99%which demonstrate how audio-based stress detection systems can be used to improve general well-being and preventive health measures. In order to produce accurate and dependable results, this study offers a novel method of stress detection by fusing deep learning algorithms with sophisticated signal processing techniques. © 2024 IEEE.

关键词： Audio recordings

来源：评论

学校读者我要写书评

暂无评论

EEG Based Identification of Learning Disabilities using Deep Learning Algorithms 15

EEG Based Identification of Learning Disabilities using Deep...

引用

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

作者： Santhiya, S. Abinaya, N. Jayadharshini, P. Dharshini, M.N. Dinesh Kumar, B. Sandeep, K. Kongu Engineering College Department of Artificial Intelligence Erode India Hindustan Institute of Technology Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350370249

A learning disability (LD) encompasses various learning challenges, characterized by difficulties in understanding words and poor reading skills. It affects many school-Aged children, especially boys, often leading to poor academic performance and low self-esteem. Early detection and intervention are crucial in mitigating these adverse effects. Our research aims to develop a deep learning model to analyze EEG signals from individuals with learning difficulties, providing highly accurate results quickly. We employed Principal Component Analysis (PCA), Independent Component Analysis (ICA), and Linear Discriminant Analysis (LDA) for component analysis of the dataset and used deep learning algorithms such as Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM) networks, Recurrent Neural Networks (RNN), and Graph Neural Networks (GNN) for classification. The goal is to determine the most effective combination of data preprocessing techniques and deep learning algorithms for detecting learning disabilities. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

The Firstever LTE Network on the Moon: Challenges and Prospects 5

The Firstever LTE Network on the Moon: Challenges and Prospe...

引用

5th IEEE International Conference on Recent Trends in computer Science and technology, ICRTCST 2024

作者： Routray, Sudhir K. Pappa, M. Singh, Monika Javali, Abhishek Sharmila, K.P. Tengshe, Richa CMR University Department of Computer Science and Engineering Bangalore India CMR Institute of Technology Department of Electronics and Communication Engineering Bangalore India

ISBN: (纸本)9798350351378

Mobile cellular networks are very popular across the globe, and they are found at all places where human settlements are present. Long term evolution (LTE) is a popular standard for mobile wireless communications. It has been deployed in almost all the countries. These networks are deployed to support various services, such as voice, image, video, text, and data transmission. In 2024, NASA and Nokia together get ready to deploy an LTE network on the moon. This project was planned in 2020, and NASA selected Nokia as the vendor for this lunar LTE network deployment mission. The LTE network on the moon would help in the enhancement of lunar exploration. The common services of LTE are planned to be deployed on the lunar surface. In addition to that, some moon specific valueadded services will also be deployed to support the exploration tasks. The deployed network would send the pictures, videos, and other sensor measured data from the lunar surface back to earth. This lunar network will be supported by the orbiting satellites and other peripheral networks. In this paper, the basic features and characteristics of the first lunar LTE network and its utilities have been studied. © 2024 IEEE.

关键词： NASA

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：