检索结果-内蒙古大学图书馆

IEEE International Conference on Electronics, computing and Communication Technologies (CONECCT)

作者： Sumit Kumar Saurav Ashna S K Nitish Kumar Gupta Disinlung Kamei R Manavalan S Janakiraman Centre for Development of Advanced Computing Bangalore

ISBN: (数字)9798350385922

ISBN: (纸本)9798350385939

Urban modeling and simulation are critical for addressing urbanization challenges. Optimizing and scaling these simulations can significantly reduce simulation time and resource usage, enabling faster decision making and policy formulation. This paper investigates the performance optimization and scalability of the twin-building case. The study covers various optimization techniques, including compiler-level switches, MPI-specific binding flags, optimal decomposition strategies, and the utilization of vendor-specific compilers. Through extensive experimentation, a significant performance boost was achieved, increasing the performance by approximately 47 times and reducing the simulation time to 46 seconds. This was accomplished by scaling the prototype Twin Building 26.17M case across more than 1,000 CPU-only cores. These findings underscore the importance of performance optimization strategies in effectively harnessing computational resources for large-scale urban modeling simulations. The study improves performance and serves as a basis for future research on heterogeneous computing platforms to enhance simulation time.

关键词： Computational modeling Scalability Urban planning Decision making Buildings Prototypes Heterogeneous networks

来源：评论

学校读者我要写书评

暂无评论

Cross Site Scripting Attacks Classification using Convolutional Neural Network 12

Cross Site Scripting Attacks Classification using Convolutio...

引用

12th International Conference on Computer Communication and Informatics, ICCCI 2022

作者： Kumar, Jitendra Santhanavijayan, A. Rajendran, Balaji Centre for Development of Advanced Computing Nit Trichy Bengaluru India National Institute of Technology Trichy Trichy India Centre for Development of Advanced Computing Bengaluru India

ISBN: (纸本)9781665480352

The global nature of web applications puts them at a high risk of attacks from different locations and with various levels of severity and complexity. Cross-Site Scripting (XSS) is a code injection attack that happens at the client-side i.e., through the web browsers. The attacker's main strategy is to execute the malicious injected scripts in a legitimate web application through the victim's browser. XSS vulnerabilities can be a source of other security attacks such as the spread of malware, credential theft, credential phishing, social network worms, and website defacing. Plenty of research has been carried out on the detection and prevention of XSS using machine learning techniques that involved URL-based features, HTML features, and JavaScript features and achieved an accuracy of about 98%. XSS attacks can have different forms and evolve regularly, new patterns emerge daily, feature extraction can be challenging, so there is a high probability of being not exhaustive. A Convolutional Neural network can be useful for XSS classification tasks, as because of its architecture it requires less feature extraction pre-processing task. In this paper, we used almost all the characters of XSS Scripts during feature generation and used the Convolutional Neural Network (CNN) technique to classify and detect the XSS scripts as malicious or benign and achieved the accuracy of 98.62 and precision of 98.6 and recall 98.86. © 2022 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Web-based Manhole Overflow Prediction System Using Ultrasonic Level Sensors and Expert System

Web-based Manhole Overflow Prediction System Using Ultrasoni...

引用

2022 International Conference on Machine Learning, Big Data, Cloud and Parallel computing, COM-IT-CON 2022

作者： Jerry Daniel, J. Byju, C. Rakesh, G. Lekshmi, G. Control and Instrumentation Group Centre for Development of Advanced Computing Kerala Thiruvananthapuram India Strategic Electronics Group Centre for Development of Advanced Computing Kerala Thiruvananthapuram India

ISBN: (数字)9781665496025

ISBN: (纸本)9781665496025

The implementation of smart cities is becoming more evident with the continuous increase in the urban population. Difficulty in waste management, pollution, traffic congestions scarcity of resources, human health concerns, and inadequate, deteriorating and aging infrastructures are among the more basic technical, physical, and material problems. The integration of AI techniques in traditional real-time systems appears to be a promising approach to deal with the growing complexity of real-world applications. Real-time expert systems are online knowledge-based systems that are used to monitor the complex industrial process and combine analytical process models with conventional process control and heuristics to gauge and interpret sensory data, while reasoning about the past, present, and future to assess ongoing developments and plan appropriate actions in future. This paper describes the Real-Time Expert System Shell is an integrated software tool which can be used to monitor Sewer Network Monitoring System and prevent manhole overflow. The sewer level data measured by Ultrasonic level sensors is delivered wirelessly via GSM and in real-time to the citizens or the appropriate authorities. The expert system interfaces with the local SCADA System which acquires online sewer data from ultrasonic level sensors and identifies the possibility of manhole overflow in the future. A web-enabled, user-friendly GUI is designed to build the Knowledge Base for a particular domain as well as display overflow details. It also publishes the data to Cloud for taking necessary action by the appropriate authorities © 2022 IEEE.

关键词： SCADA systems

来源：评论

学校读者我要写书评

暂无评论

Digital Forensics Analysis of a Vehicle Tracking System

引用

SN Computer Science 2023年第6期4卷 835页

作者： Amala, R. Roy, K. Renin Aravind, G.S. Dija, S. Manohar, Krithi C-DAC (Centre for Development of Advanced Computing) Cyber Forensic Section Technopark Campus Kazhakkoottam Kerala Thiruvananthapuram 695581 India

Evolution of Internet of Things (IoT) has resulted in improved productivity and quality of life. But like any other technology, criminals are utilizing the vulnerabilities of these systems and exploiting them. In such cases, there is a need to collect forensic evidence from IoT systems that can be analyzed and then presented in court as evidence. The forensic investigation on these newer IoT systems is not supported by existing digital forensics tools and methods. Also, the variety of IoT platforms demands system-specific approaches. In this paper we are providing approaches to extract and analyze digital traces from vehicle tracking systems (VTS), which is an IoT ecosystem in transportation domain. Apart from the conventional uses of VTS systems, these systems create opportunities for extracting evidence that helps to investigate vehicle related incidents. This work includes the forensic data extraction and analysis of evidential artifacts from VTS IoT ecosystem. Also, a proof-of-concept tool, IoT Forensics Suite (IFS) which is developed as part of this research work is demonstrated. IFS tool can serve as a building block for performing forensic operations in other IoT domains such as power, healthcare, agriculture and infrastructure. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Bus pirate Database carving Flashrom Hardware acquisition IoT forensics Vehicle tracking systems

来源：评论

学校读者我要写书评

暂无评论

Long Short-Term Memory Auto-Encoder-Based Position Prediction Model for Fixed-Wing UAV during Communication Failure

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2023年第1期4卷 173-181页

作者： Kant, Ravi Saini, Poonam Kumari, Julee Defence Electronics Application Laboratory Defence Research and Development Organisation Dehradun248001 India Department of Computer Science and Engineering Punjab Engineering College Chandigarh148023 India Centre for Development of Advanced Computing Mohali160071 India

Unmanned aerial vehicles (UAV's) safe flight is one of the most important tasks of ground control stations (GCS). However, sometimes due to communication failure between ground data terminal (GDT) and UAV, GCS is not able to ensure a safe flight, which could be hazardous. In such conditions, the accurate UAV position finding prediction becomes essential to serve as sustenance for UAVs. Hence, this article proposes a UAV's position finding prediction model using a deep neural network application for successfully pointing the GDT toward UAV in real time. The proposed work consists of three components, namely data preprocessing, long short-term memory autoencoder (LSTM-AE)-based deep learning model, and mathematical formulation to calculate the ground radar look angle. First, we use different preprocessing techniques on a historical raw dataset for better visualization and generate patterns. To achieve this, Tensor flow along with Keras packages have been used. Next, an LSTM autoencoder deep learning model is applied to the same dataset in order to predict an accurate 4-D position of the UAV. Finally, the output from the LSTM autoencoder model is used in a mathematical model to calculate the GDT look-angles called Azimuth and Elevation. Both the parameters have been used to point the GDT toward the predicted point on the Airspace. We evaluate our proposed model against famous evaluation matrices, namely mean absolute error, mean square error, and root-mean-square error to validate the experimental results. © 2022 IEEE.

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

A Parsing Tool for Short Linguistic Constructions: A Case Study for Indian Languages 1st

A Parsing Tool for Short Linguistic Constructions: A Case St...

引用

1st International Conference on Speech and Language Technologies for Low-resource Languages, SPELLL 2022

作者： Jain, Priyanka Jain, N.K. Darbari, Hemant Bhavsar, Virendrakumar C. Centre for Development of Advanced Computing Delhi India Faculty of Computer Science University of New Brunswick Fredericton Canada

ISBN: (纸本)9783031332302

In the current trend of unstructured language usage in simpler and shorter conversations, we identified a need of language analysis tool (a language parser) to find semantic relations within the sentence constituents. Earley’s algorithm is used in this paper to propose a parsing approach based on the Tree Adjoining Grammar (TAG) formalism. It is able to extract dependency relations in the derivation tree form. A generalized TAG tree-grammar pertaining to Subject-Object-Verb (SOV) syntactic pattern is also presented corresponding to the proposed algorithm. This grammar is targeted to be suitable for short dialogues in low resource languages which have scarcity of enough data for ML/DL based approaches. The process flow is presented using the combinatory tree-set formation and parsing. Two implementations are carried out using XML and LISP notation data structure. Examples from an Indian language are presented in a step-by-step manner that illustrates parsing in a controlled grammar environment for linguistically not-very complex syntactic constructions. Results along with findings are presented for execution time and memory consumption. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

Large Vocabulary Continuous Speech Recognition System for Marathi 1

Large Vocabulary Continuous Speech Recognition System for Ma...

引用

1st IEEE International Conference on Advances in Electronics, Communication, computing and Intelligent Information Systems, ICAECIS 2023

作者： Bajaj, Snehal Chandulal Kant, Kamal Bole, Amol V Kumar, Pranaw Sanjivani College of Engineering Dept. of Electronics and Telecommunication Kopargaon India Centre for Development of Advanced Computing Language Computing Group Mumbai India

ISBN: (纸本)9798350348057

Lots of efforts have been made in the development of Automatic Speech Recognition systems for Indian languages, and good progress has been made for Hindi, Tamil, Telugu & Bengali, and Indian English. However, practically usable robust systems are still not available for many regional Indian languages including Marathi. This paper presents an effort toward the development of a large vocabulary continuous speech recognition system for Marathi and its integration into practical application, such as Speech-based typing system. This speech recognition system has been developed using the Kaldi toolkit. The Kaldi toolkit facilitates the exploration of different acoustic models such as Gaussian Mixture Model with Hidden Markov Model (GMM-HMM) and Deep Neural Networks with Hidden Markov Model (DNN-HMM). In this paper we have developed Marathi Speech Recognition system which is trained around 95 hours of audio data. We have used the trigram language model which is having 29 lakhs of words and 3 lakhs of vocabulary size. This system gives average word error rate of 19%. © 2023 IEEE.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Matched Filtering and Timing Recovery Algorithm for IEEE 802.15.4 Digital Baseband Front End 5th

Design and Implementation of Matched Filtering and Timing Re...

引用

5th International Conference on VLSI, Communication and Signal Processing, VCAS 2022

作者： Shukla, Preeti Tiwari, Manish Mohanasundaram Haribabu, P. Motilal Nehru National Institute of Technology Allahabad Prayagraj India Centre for Development of Advanced Computing Bangalore India

ISBN: (纸本)9789819909728

IEEE 802.15.4 is a technical standard for low-rate wireless personal area network for long range communication. This standard provides a framework for the lower layers (PHY and MAC) in the OSI model for wireless connectivity network which is used in IoT applications. In a communication network, channel noise and timing mismatch are common problems. In order to recover the received signal successfully, a receiver should be able to overcome these problems. Demodulation and demapping alone would not be able to serve the purpose. This paper proposes modeling, design, and simulation of signal conditioning blocks in the receiver for O-QPSK PHY and SUN O-QPSK PHY mentioned in the standard. These blocks process the signal available at the digital baseband front end of the receiver which is available after RF to analog baseband down conversion and analog baseband to digital baseband conversion. Signal conditioning introduced in this work involves the design of matched filter and timing recovery to overcome the noise and sampling time mismatch. These blocks along with the O-QPSK transceiver have been first modeled in MATLAB/Simulink. Logic design for the modules introduced in the receiver chain has been implemented using Verilog RTL and verified through simulation. For FPGA implementation, RTL modules of matched filter and timing recovery have been integrated at the output of ADC, and output of timing recovery goes for inverse pulse shaping and is fed to O-QPSK and smart utility network (SUN) O-QPSK demodulator of receiver chain. All the modules are implemented on the FPGA Board Xilinx UltraScale + VCU118. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

Survey Paper on Detection of Water Bodies in Satellite Imagery 3rd

Survey Paper on Detection of Water Bodies in Satellite Image...

引用

3rd International Conference on "Emerging Trends and Technologies on Intelligent Systems" (ETTIS-2023)

作者： Dhore, Disha Dixit, Sakshi Mulik, Akanksha Ghogale, Kedar Nagnathrao Karamtoth, Shankar Naik Rathod Kumar, Binay Khare, Manoj SKN College of Engineering SPPU Pune India C-DAC: Centre for Development of Advanced Computing Pune India

ISBN: (纸本)9789819939626

Water body extraction from satellite images helps us to study water resources. Due to constant changes in weather and increase of global warming, it is necessary to track changes in water resources to study their impact on environment. From agriculture to industries, water bodies play a significant role in production. Water bodies play vital role in keeping environmental balance. To study water bodies, acquiring high-resolution satellite images is an important step. But even after receiving high-resolution images, there are some issues which are faced during extraction of water bodies from images taken through satellite. One of the most difficult tasks to overcome is to distinguish between water bodies and its surroundings shadows which are casted on the water. Detection of narrow water bodies is also challenging. Studying water bodies helps us in detection of floods, drought detection, and resource study and also how these water bodies can be used for developing water transport. Apart from these advantages, studying water bodies can become useful in defense. Using detection, it is possible to extract water bodies which can become a water source, electricity generation source, or even a place around which the army can set up their camps. In this paper, various approaches are studied which are used for detecting images taken through satellite. The objective of this paper is to discuss the approaches, algorithms, and methodologies used for detection of water bodies from the images taken by satellite. Accuracy of the various models used is compared and presented. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

MNIST Fashion Classification Using Quantum Convolutional Neural Networks

MNIST Fashion Classification Using Quantum Convolutional Neu...

引用

2024 IEEE International Conference on Computer Vision and Machine Intelligence, CVMI 2024

作者： Ali, Nasir Tiwari, Abhishek Neiwal, Rahul Kumar Centre for Development of Advanced Computing Embedded Systems Division Noida India Ministry of Electronics and Information Technology Electronics Division New Delhi India

ISBN: (纸本)9798350376876

This paper explores the innovative application of Quantum Convolutional Neural Networks (QCNN) in the classification of the MNIST fashion dataset. Quantum computing presents novel opportunities for enhancing machine learning algorithms, particularly in handling complex datasets. The MNIST fashion dataset is a large collection of Zalando's article images, serves as an ideal candidate for demonstrating the efficacy of QCNN. This paper dives into the implementation of QCNN, compares QCNN's performance with traditional neural networks, and further evaluates QCNN's potential in revolutionizing image classification tasks in the realm of Quantum Machine Learning. © 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

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：