检索结果-内蒙古大学图书馆

16th International Conference on COMmunication Systems and NETworkS, COMSNETS 2024

作者： Pandeeti, Guru Satya Dattatreya Dixit, Janhvi Hussain, Asif Behera, Dibya Prakash Dubey, Umang Banerjee, Anindita Maity, Samrit Kumar Modani, Manish Centre for Development of Advanced Computing C-DAC Innovation Park Maharashtra Pune India Nvidia Commerce Zone IT Park Pune Maharashtra Pune India

ISBN: (纸本)9798350383119

Toeplitz Hashing is a class of functions in the 2-universal hash function family, that is widely adopted in quantum secure applications, particularly for the privacy amplification in quantum key distribution to generate secret keys, and as a strong randomness extractor for the quantum random number generators. In this work, we have investigated the preliminary implementation of Toepltiz hashing on processors, co-processors, and system-on-chip (SoC). We have implemented the fast-Fourier transform (FFT)-based Toepltiz hashing on Intel Xeon Cascade-lake 8268 processor and NVIDIA Tesla V100 GPU compute hardware. We have also implemented the binary multiplication-based Toeplitz hashing on the AMD Xilinx ZCU102 FPGA evaluation kit. Further, we present an example of heterogenous computing, by combining an Intel Core i7 CPU with the VEGA ET1031-based Aries v2.0 development board. Finally, we report, for the first time, an implementation of convolution of two matrices on an indigenously designed RISC-V VEGA SoC. Further, we have compared the implementation results following two approaches, i.e. normal matrix multiplication and the number theoretic transform (NTT) method. We report that there is a tenfold reduction in the computational time using the NTT method over the conventional method. © 2024 IEEE.

关键词： Cryptography Field Programmable Gate Array Graphics Processing Unit Number Theoretic Transform Quantum Key Distribution Quantum Random Number Generator RISC-V-based processor Toeplitz Hashing

来源：评论

学校读者我要写书评

暂无评论

A Simple Fall Detection Scheme for Early Detection of Falls in Elderly People

A Simple Fall Detection Scheme for Early Detection of Falls ...

引用

2023 International Conference on Evolutionary Algorithms and Soft computing Techniques, EASCT 2023

作者： Ghatak, Srijita Mitra, Rishita Ahmed, Washef Chanda, Kunal Techno Main Salt Lake Department of Information Technology Kolkata India Centre for Development of Advanced Computing Kolkata India

ISBN: (纸本)9798350313413

Human fall is considered to be a prominent risk especially among the elderly population and for disabled people. Fall detection systems often rely on video surveillance, capturing frames and utilizing various algorithms to identify instances of fall. The continued development of such systems is one of the goals of AI technology, which aims to improve quality of life and reduce fall risks. The field of computer vision still faces significant difficulties with the estimate of human postures. Recognizing the poses of multiple individuals in real-world scenarios presents greater challenges compared to recognizing the pose of a single person in an image. An automated camera-based system that can recognize abnormal human postures is presented in this work. To identify people in frames and extract their body key points, a pre-trained pose estimation algorithms like PoseNet and OpenPose is used. The human body geometry that was recorded at various frames of the video series is used in this paper's proposal of a fall detection method. To generate the active energy image, the average of the difference frames obtained from the silhouette sequence is calculated. The resulting image is then divided into multiple segments. For each section, affine moment invariants as gait features are computed. This paper will provide a detailed description of the fall detection technique. Results show an accuracy of more than 90%. On the test set, this method had an F1 score of 92.5%, accuracy of 92.5%, precision of 91.2%, recall of 93.8%. © 2023 IEEE.

关键词： elderly fall Frame-extraction Gait Analysis Image Segmentation OpenPose person-detection pose-estimation

来源：评论

学校读者我要写书评

暂无评论

Cocoa-Net: Performance Analysis on Classification of Cocoa Beans Using Structural Image Feature

Informatica (Slovenia)

引用

Informatica (Slovenia) 2024年第12期48卷 41-54页

作者： Pal, Chandrajit Das, Samikshan Akuli, Amitava Adhikari, Sudip Kumar Dey, Aniruddha Department of Electrical Engineering IIT Hyderabad India Capgemini India Centre for Development of Advanced Computing Kolkata India Department of Computer Science & Engineering CGEC Cooch Behar India Department of Computer Science & Engineering MSIT Kolkata India

The process of cocoa hybridization produces new types that have unique chemical properties impacting the manufacturing of chocolate yet are resistant to a number of plant illnesses. Image analysis is a valuable tool for visually differentiating cocoa beans where deep neural networks (DNN) play a pivotal role in implementing them. In this manuscript, we compare machine learning and deep learning models because it takes into consideration multiple images covering a wide range of agricultural products. Specifically, we extract features from images using a series of image processing techniques, following which we use both traditional machine learning methods (KNN, Decision tree, SVM, and Random Forest) and Convolutional Neural Networks (proposed Cocoa-Net and RESNET 50) to classify the cocoa beans into four categories: large, medium, small, and rejected. Since each methodology offers strong classification performance and has potential for use in the classification of food, they were all chosen. To test these methods, a dataset including 200 samples of fragmented images was utilized. Studies that compare various similar approaches are also carried out. Two optimization techniques: Univariate Selection and Feature Importance have been leveraged to optimize the retrieved features before the learning models are trained. The Adam optimizer is used to optimize the proposed Cocoa-Net model. K-fold cross validation is utilized to assess trained models, and mean cross validation scores are then computed for performance analysis. The empirical result shows that, the proposed Cocoa-Net model predicts with the highest classification accuracy score of 0.85. © 2024 Slovene Society Informatika. All rights reserved.

关键词： cocoa beans Cocoa-Net decision tree KNN random Forest SVM

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Application for Classification of Brain Tumors Through MR Images to Detect Malignancy 4

Machine Learning Application for Classification of Brain Tum...

引用

4th IEEE International Conference on computing, Communication, and Intelligent Systems, ICCCIS 2023

作者： Chanda, Kunal Tiwari, Jay Verdhan Banik, Souvik Ahmed, Washef Advanced Signal Processing Group Centre for Development of Advanced Computing Kolkata India Medical Electronics Ministry of Electronics and Information Technology New Delhi India

ISBN: (纸本)9798350306118

In the present paper classification of Brain Tumours through MRI imaging as Fine, Medium and Coarse textures is proposed. The other methods of classification of brain tumours that are frequently used are based on size, shape and spread of the tumour. The importance of classifying tumours based on texture is that there is correlation between malignancy of the tumour and the texture of the tumour. The other methods normally don't give this information. In this paper relation between texture of the tumour and it's malignancy has been explored. Four methods of feature extraction have been used, in order to obtain texture information of the tumour. They are, Gray Level Co-occurrence Matrix (GLCM), Gradient Matrix (GM), Laplacian Of Gaussian (LoG) and the Run-Length Matrix (RLM). Once the features are extracted, they are passed to Decision Tree classification algorithm. The classification algorithms classified the extracted features as having Fine, Medium or Coarse textures. The result obtained showed correlation between texture of the tumour and its malignancy. If the texture is predicted as Fine, then it is most likely a non-malignant, or benign tumour, and its diagnosis is most likely going to give a Complete response. A Medium texture would most likely give a Partial response, and is not very malignant. This is important, since knowing this information can benefit the patient and clinicians. This improves the diagnostic confidence of the clinicians and allows them to diagnose and report multiple patients that results in lower cost of the examination as well as access to diagnostics to people living in remote areas. © 2023 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence (AI)-Deep Neural Network (DNN) based Classification model to find BI-RADS score from Mammogram Images

Artificial Intelligence (AI)-Deep Neural Network (DNN) based...

引用

Global Conference for Advancement in Technology (GCAT)

作者： Snehal C. Sapkale Swapna Yenishetti Lakshmi Panat AIQT Centre for Development of Advanced Computing Pune India

ISBN: (数字)9798350376685

ISBN: (纸本)9798350376692

Breast cancer is the leading cancer among women globally. It is reported that with every four minutes, an Indian woman is diagnosed with breast cancer. To describe cancer, concept of staging is used. The cancer's stage tells us how far it has grown into nearby tissues. In breast cancer, there are total five stages from 0 (zero) to 4. If breast cancer is detected early between the stage 0-2, then its five-year survival rate exceeds 90% [1]. Survival becomes more difficult in higher stages of cancer. The low survival rates of breast cancer in India is due to delay in detection. Breast imaging tests - such as mammograms, magnetic resonance imaging (MRI) and ultrasounds, help doctors assess breast tissue for the early detection of breast cancer. The results of these tests are scored as BI-RADS (Breast Imaging Reporting and Data System) categories. These categories ranges from category 0 to category 6 (high likelihood of cancer). Radiologists determine the BI-RADS category by applying specific criteria and assessing the imaging tests. There is a need of an efficient and reliable tool that would help in automatic reading of mammogram characteristics and also assist radiologists in mammographic image interpretation. This paper describes a deep neural network (DNN)-based classification model that would efficiently detect mammogram characteristics and categorise it into a relevant BI-RADS category with an accuracy of 71.78%.

关键词： Accuracy Ultrasonic imaging Magnetic resonance imaging Biological system modeling Transfer learning Artificial neural networks Breast cancer Mammography Reliability Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Accident Detection and Reporting System for Powered Two-Wheelers Using Internet of Things and Edge AI augmented with MCUSUM features

Accident Detection and Reporting System for Powered Two-Whee...

引用

Intelligent Systems (ETIS), Emerging Technologies for

作者： Vijay Viswanath Unnikrishnan S Saeed S Dhanya V S Deepa P P Kalai Selvan Emerging Technologies Group Centre for Development of Advanced Computing Thiruvananthapuram

ISBN: (数字)9798331507541

ISBN: (纸本)9798331507558

According to data provided by the Ministry of Road Transport and Highways (MORTH), Government of India, about 1.68 lakh people have lost their lives in accidents and nearly 4.4 lakh people have suffered injuries [1]. The number of accidents has increased by approximately 12% year on year. The data also show that people affected by accidents are likely to be in the age group of 15 to 49 years. This age group is virtually the pillar that supports the nation's development. Therefore, road fatalities can indirectly influence the nations development. In this work, we have implemented a system aimed towards powered two-wheelers (PTWs) that detects accidents and sends an SOS signal to a preconfigured contact. The system, upon detecting an accident/critical event, can attempt to convey the SOS signal in multiple modalities for redundancy. The SOS signal includes the last known GNSS coordinates of the vehicle to be able to pinpoint the location of the incident. The system also has a manual SOS trigger option that can be used as a panic button. Detection is performed by a Convolutional Neural Network (CNN) based classifier running on the system using Edge AI capability that uses sensory output from an inertial measurement unit (IMU) and its derivative data for input features. In this work, we have experimented with the possibility of improving the classification performance of the classifier by augmenting the input feature set with Multivariate Cumulative Summation (MCUSUM) [2] control chart statistic of the IMU data. The results show that this technique can give marked improvements in the overall accuracy of the classification system.

关键词： Accuracy Sensitivity Roads Edge AI Manuals Feature extraction Vectors Internet of Things Convolutional neural networks Accidents

来源：评论

学校读者我要写书评

暂无评论

Bits to Qubits: An Overview of Quantum computing

Bits to Qubits: An Overview of Quantum Computing

引用

Intelligent Control, computing and Communications (IC3), International Conference on

作者： Kendre Saraswati Vasantrao Amit Saxena AIQT Centre for Development of Advanced Computing – Panchvati Pune India

ISBN: (数字)9798331527495

ISBN: (纸本)9798331527501

The advent of computers has significantly diminished the need for manual computation. As technology has evolved, it has led to the creation of classical computers with high performance, throughput, and memory capacity. Classical computers store data in binary format, using bits that can either be 0 or 1, typically represented by low and high voltage levels, respectively. While effective, this method sometimes demands considerable resources for certain computations. In contrast, quantum computers represent the cutting edge of computing technology. They utilize quantum bits or qubits, which exploit quantum mechanical phenomena like superposition and entanglement, allowing for more efficient problem-solving. This paper presents a simplified overview of the core concepts of quantum computing.

关键词： Computers Quantum computing Quantum algorithm Quantum entanglement Qubit Logic gates Programming Throughput Proposals Quantum circuit

来源：评论

学校读者我要写书评

暂无评论

development of Python-Based Applications for Virtual Instrument Control Using PyQt5, PyVISA, and SCPI Protocol 2

Development of Python-Based Applications for Virtual Instrum...

引用

2nd International Conference on Emerging Trends in Information Technology and Engineering, ic-ETITE 2024

作者： Rao, Abhishek Singh Sai, Deepak Mahajan, Anita Taterao Singh, Vaibhav Pratap Neiwal, Rahul Pasupuleti, Haribabu Sudarsan, S.D. Group Bengaluru India Ministry of Electronics and Information Technology R&d in It Group Delhi India Centre for Development of Advanced Computing Bangalore Bengaluru India

ISBN: (纸本)9798350328202

This work aims to create desktop applications to enable virtual access and control to prominent lab equipment like signal generators, oscilloscopes, spectrum analyzers, etc. The developed applications utilize PyQt5 and PyVISA Python libraries, enabling the creation of Graphical User Interfaces (GUIs) and virtual instrument communication. The applications support USB and Ethernet connection between the PC and the instruments. We demonstrate Python-enabled applications to remotely access a Vector Signal Generator, an Oscilloscope and in conjugation, also use an OEM's Spectrum Analyzer PC application to complete a framework for remote signal generation, analysis, and acquisition which can be useful in various research and testing scenarios in the modern hybrid work culture. © 2024 IEEE.

关键词： Spectrum analyzers

来源：评论

学校读者我要写书评

暂无评论

Machine learning-based malware detection using stacking of opcodes and bytecode sequences 7

Machine learning-based malware detection using stacking of o...

引用

7th International Conference on Parallel, Distributed and Grid computing, PDGC 2022

作者： Sai, Manoj Tyagi, Aakansha Panda, Kajal Kumar, Sanjeev Centre for Development of Advanced Computing Cyber Security Technology Division Mohali India

ISBN: (纸本)9781665454018

Malware detection is a complex problem. The commonly used signature-based technique cannot detect unknown or zero-day malware. Traditional machine learning-based methods can identify unknown malicious programs but require high domain expertise for feature engineering. This research study presents a new method of malware detection using the stacking of static opcode and bytecode features. At first, bytecode and opcode sequences of executables files are extracted using a disassembler. After that, an NLP technique, TF-IDF, is employed to vectorize the extracted feature map. The extracted features as opcodes and bytecodes are concatenated to combine a single feature map, which serves as input to train machine learning classifiers: SVM, k-NN, and Random Forest (RF). The RF classifier obtained the best accuracy, precision, recall, and F-score results as 98.47%, 98.60%,98.46%, and 98.47% even using small data counts of bench-marked Microsoft BIG data set. The accuracy of the best model is comparatively better than the accuracy of using bytecodes and opcodes as individual feature vectors. The empirical results signify that the proposed method is helpful to the security industries with the benefit of being less dependent on manual feature engineering and can reduce the burden on virus databases by handling large-scale malware. © 2022 IEEE.

关键词： Viruses

来源：评论

学校读者我要写书评

暂无评论

Deep learning methods for malicious URL detection using embedding techniques as Logistic Regression with Lasso penalty and Random Forest 7

Deep learning methods for malicious URL detection using embe...

引用

7th International Conference on Parallel, Distributed and Grid computing, PDGC 2022

作者： Thakur, Isha Panda, Kajal Kumar, Sanjeev Centre for Development of Advanced Computing Cyber Security Technology Division Mohali India

ISBN: (纸本)9781665454018

In the Internet ecosystem, URLs (Uniform Resource Locators) are widely used to propagate malicious infections through spam, spear-phishing, drive-by-download exploitation, malware embedding, etc. The blacklisting, pattern analysis, and signature-matching approaches are widely used to detect such threats. However, these techniques are very effective in detecting known types of malicious URLs but unable to detect new types of attacks launched by the malicious URLs. Moreover, traditional machine learning-based malicious URL detection is highly dependent upon manual feature engineering, which is a costly approach. , This research study proposes deep learning-based malicious URL detection with less dependent on manual feature engineering to overcome the above-mentioned challenges. The Natural Language Processing (NLP) technique, i.e., Term Frequency-Inverse Document Frequency (TF-IDF) vectorizer, along with the N-gram parameter, is used for extracting the features. Afterward, two feature selection techniques as Embedded methods are used - Logistic Regression with L1 (Lasso) penalty and Random Forest Selection. Neural network models such as Deep Neural Networks (DNN), Long Short-Term Memory (LSTM), and Convolution Neural Networks (CNN) are constructed to detect malicious URLs. The experiment results demonstrate that the DNN model gives the best performance results as 96.95% accuracy, 99% precision, 100% recall, and 99% F1-score with logistic regression along with the L1 (Lasso) penalty as a feature selection method. Finally, this study compares state-of-art implemented deep learning methods for malicious URL detection. © 2022 IEEE.

关键词： Inverse problems

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：