检索结果-内蒙古大学图书馆

India Council International Subsections Conference (INDISCON), IEEE

作者： Sanjeev Kumar Yudhishthira Sapru Navdeep Singh Chahal Cyber Security Technology Division Centre for Development of Advanced Computing Mohali India Indian Computer Emergency Response Team CERT-In Delhi India

ISBN: (数字)9798350376753

ISBN: (纸本)9798350376760

Various prevalent malware detection methods employ static signature-based detection, dynamic analysis, and other techniques to identify malware. However, these traditional malware detection techniques have become less effective due to sophisticated evasion techniques employed by malware authors. In addition, malware analysis is a highly compute-intensive process. This research introduces a new malware detection architecture that deploys different textural features and transfer learning. In this approach, the entire binary executable program is first converted into a grayscale image before extracting the deep textural features by taking the whole image as input to the convolution neural network (CNN) model. Subsequently, a pre-trained InceptionV3 model is used to extract the textural characteristics of the visualized image. The dimension of feature maps is reduced by customizing the InceptionV3 model and adding fully connected (FC) dense layers. This study performs the feature correlation analysis to select only highly distinct textural features. Finally, the selected feature map trains a softmax classifier to predict unknown malware families. This study conducts the experiments using two well-known public benchmarked datasets-MalImg and Microsoft BIG. The proposed model reported a classification accuracy of $98.57 \%$ using the MalIng data set and an accuracy of $97.78 \%$ for the Microsoft data set. The proposed model is superior to similar approaches in the literature. The minimal computation cost of feature extraction makes it well-suited for malware threat detection in industrial environments. Index Terms-Cybersecurity, Deep learning, Image visualization, Malware detection, Transfer learning

关键词： Deep learning Accuracy Computational modeling Transfer learning Neural networks Gray-scale Feature extraction Malware Threat assessment Indexes

来源：评论

学校读者我要写书评

暂无评论

RankSum-An Unsupervised Extractive Text Summarization based on Rank Fusion

arXiv

引用

arXiv 2024年

作者： Joshi, Akanksha Fidalgo, Eduardo Alegre, Enrique Alaiz-Rodriguez, Rocio Department of Electrical Systems and Automation Universidad de León Spain León Spain Centre for Development of Advanced Computing Mumbai India

In this paper, we propose Ranksum, an approach for extractive text summarization of single documents based on the rank fusion of four multidimensional sentence features extracted for each sentence: topic information, semantic content, significant keywords, and position. The Ranksum obtains the sentence saliency rankings corresponding to each feature in an unsupervised way followed by the weighted fusion of the four scores to rank the sentences according to their significance. The scores are generated in completely unsupervised way, and a labeled document set is required to learn the fusion weights. Since we found that the fusion weights can generalize to other datasets, we consider the Ranksum as an unsupervised approach. To determine topic rank, we employ probabilistic topic models whereas semantic information is captured using sentence embeddings. To derive rankings using sentence embeddings, we utilize Siamese networks to produce abstractive sentence representation and then we formulate a novel strategy to arrange them in their order of importance. A graph-based strategy is applied to find the significant keywords and related sentence rankings in the document. We also formulate a sentence novelty measure based on bigrams, trigrams, and sentence embeddings to eliminate redundant sentences from the summary. The ranks of all the sentences -computed for each feature- are finally fused to get the final score for each sentence in the document. We evaluate our approach on publicly available summarization datasets- CNN/DailyMail and DUC 2002. Experimental results show that our approach outperforms other existing state-of-the-art summarization methods. © 2024, CC BY.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Augmented Reality localisation using 6 DoF phantom head Pose Estimation-based generalisable Deep Learning model

Augmented Reality localisation using 6 DoF phantom head Pose...

引用

International Conference on Image and Signal Processing and their Applications (ISPA)

作者： Kahina Amara Mohamed Amine Guerroudji Nadia Zenati Oussama Kerdjidj Shadi Atalla Wathiq Mansoor Naeem Ramzan Centre for Development of Advanced Technologies Algeria College of Engineering and IT University of Dubai Dubai UAE School of Computing Engineering and Physical Sciences UWS UK

ISBN: (数字)9798350309249

ISBN: (纸本)9798350309256

Localisation and the estimation of the six degrees of freedom (6 DoF) object’s position and orientation are essential tasks in numerous applications, such as augmented and virtual reality (AR and VR). It enables machines to gain a 3D understanding of their surroundings, empowering them to execute tasks like identifying objects, tracking their movement, interacting with them, and manipulating them. There is a growing trend in developing generalisable ’6DoF’ object pose estimators, which possess the ability to estimate the position and orientation of an unfamiliar object without the need for specific training or finetuning on that particular object during testing. By comparison, the previous 6 DoF object pose estimators focused primarily on specific categories of objects. This paper addresses the challenge of 6 DoF phantom head pose estimation from a single RGB image for augmented reality localisation. Using a local Magnetic Resonance Imaging (MRI) dataset, we reconstruct and print a 3D phantom head. This later is the target object for our AR localisation. Based on the comparison study including the accuracy and inference runtime scores, the Gen6D model achieves promising performance. Implementing 6 DoF pose estimation in deep learning stands to enhance and prove valuable in facilitating more effective interactions within the realm of augmented reality.

关键词： Solid modeling Head Three-dimensional displays Magnetic resonance imaging Pose estimation Phantoms 6-DOF

来源：评论

学校读者我要写书评

暂无评论

Questionnaire-Based Prediction of Hypertension Using Machine Learning

Questionnaire-Based Prediction of Hypertension Using Machine...

引用

International Conference on Evolving Technologies for computing, Communication and Smart World, ETCCS 2020

作者： Chaturvedi, Abhijat Srivastava, Siddharth Rai, Astha Cheema, A.S. Chelimela, Desham Aravindakshan, Rajeev Centre for Development of Advanced Computing Noida India All India Institute of Medical Sciences Mangalagiri India

ISBN: (纸本)9789811578038

Machine learning has proven its ability in health care as an assisting technology for health care providers either by saving precious time or timely alerts or vitals monitoring. However, their application in real world is limited by availability of data. In this paper, we show that simple machine learning algorithms especially neural networks, if designed carefully, are extremely effective even with limited amount of data. Specifically with exhaustive experiments on standard Modified National Institute of Standards and Technology database (MNIST) dataset, we analyse the impact of various parameters for effective performance. Further, on a custom data set collected at a tertiary care hospital for hypertension analysis, we apply these design considerations to achieve better performance as compared to competitive baselines. On a real-world dataset of only a few hundred patients, we show the effectiveness of these design choices and report an accuracy of 75% in determining whether a patient suffers from hypertension. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Health care

来源：评论

学校读者我要写书评

暂无评论

Extraction of Actionable Threat Intelligence from Dark Web Data

Extraction of Actionable Threat Intelligence from Dark Web D...

引用

International Conference on Control Communication & computing India (ICCC)

作者： Varsha Varghese Mahalakshmi S Senthilkumar Kb Cyber Forensics and Information Security Department of Computer Science & Engineering ER&DCI Institute of Technology Thiruvananthapuram Cyber Security Group Centre for Development of Advanced Computing Thiruvananthapuram Scientict_E Cyber Security Group Centre for Development of Advanced Computing Thiruvananthapuram

Darknet has emerged as an excellent platform for cybercriminals to conduct various illicit activities such as operating a fully functional crypto-currency-based marketplace or maintaining a highly anonymous communication channel. However, it also acts as a source of Cyber Threat Intelligence which is the information about the techniques, tactics, or motives of an emerging threat. The life cycle of a Darknet-based Cyber Threat Intelligence solution mainly consists of the Collection, Processing, Analysis, and Production of Data from the Darknet. The Collection and Processing stages deal with accumulating information from various dark web pages and transforming the data into some format using a big data system. The Analysis part is integral to the Threat Intelligence schema since it constitutes the extraction of named entities like Organization, Offensive Activity, Tools, etc., and the determination of relationships between these entities. The production stage is like data mining where some knowledge is extracted that can be relevant to an organization under consideration. Such knowledge can mitigate risks and disrupt any targeted cyber-attack campaigns, making Cyber Threat Intelligence actionable. In this research, an open-source-intelligence toolset is used to scan and collect data from the dark web forums through crawling and scrapping. The collected data is then ingested into a state-of-the-art NLP model that extracts actionable threat intelligence using Named Entity Recognition. The experimental results indicate that the model could identify HackerIds, tools, software, organizations, and other entities in the discussions of dark web forums with better efficiency and accuracy. This could be used to identify the source of a data leak, the release of new malware, evidence of a new exploit, and other offensive activities.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improving Design Accuracy of a Finite Impulse Response Fractional Order Digital Differentiator Filter Using Quantum-inspired Evolutionary Algorithm

Improving Design Accuracy of a Finite Impulse Response Fract...

引用

International Conference on Confluence The Next Generation Information Technology Summit (Confluence)

作者： Lubna Siddiqui Ashish Mani Jaspal Singh Amity School of Engineering and Technology Amity University Noida India Amity Innovation and Design Centre Amity University Noida India Centre for Development of Advanced Computing Chandigarh India

In this paper, a quantum-inspired evolutionary algorithm (QiEA) is applied to determine the optimal coefficients of a finite impulse response fractional-order digital differentiator filter. QiEA brings the power of quantum-inspired methods to the principles of natural evolution, which uses operators to gradually improve solutions over time. The design accuracy in terms of absolute magnitude error (AME) and phase error achieved in QiEA was compared with the AME achieved by the genetic algorithm (GA) and cuckoo search algorithm (CSA). In addition, we investigated the impact of increasing population sizes on these design parameters of the fractional order (FOD) digital differentiator filter. The simulation results demonstrate conclusively that the FOD digital differentiator's design accuracy using QiEA beats both CSA and GA in terms of accuracy, error function reduction, and identifying optimal filter coefficients.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Quantum-inspired Evolutionary Algorithms for Denoising PCG Signals

Towards Quantum-inspired Evolutionary Algorithms for Denoisi...

引用

International Conference on Signal Processing and Information Security (ICSPIS)

ISBN: (数字)9798350368673

ISBN: (纸本)9798350368680

This document aims to reaffirm the superiority of quantum-inspired evolutionary algorithms(QiEA) over conventional algorithms. The study proposes a novel QiEA with sorted mutation and greedy local restart (SMGLR) algorithm for finding the optimal coefficients of a filter using a multi-objective optimization function. PCG signals sourced from the Washington Hearts Sounds and Murmurs database and the Michigan Heart Sounds database were filtered using this enhanced filter. Comparative analysis was conducted against the proposed algorithm and established techniques such as Wavelet-based denoising and Variable Mode decomposition. Results: The results revealed that the filter designed using QiEA-SMGLR exhibited superior performance in terms of improved Signal-to-Noise Ratio (SNR) in both comparisons. A comprehensive statistical analysis yielded a correlation coefficient of close to 0.99 indicating strong signal integrity. The QiEA-SMGLR algorithm outperforms Wavelet-based and VMD methods by improving the output SNR by 20% to 100%. This variance can be attributed to the intensity of noise introduced. The result reaffirms the hypothesis that the QiEA-SMGLR algorithm is superior in improving signal clarity and precision over traditionally popular techniques. The improvement in the analysis of Phonocardiogram (PCG) signals could help improve patient diagnostics, amidst the fight against global cardiac problems.

关键词： Heart Noise reduction Signal processing algorithms Evolutionary computation Filtering algorithms Wavelet analysis Phonocardiography Signal integrity Optimization Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Meta-Heuristic with Machine Learning-Based Smart e-Health System for Ambient Air Quality Monitoring 4th

Meta-Heuristic with Machine Learning-Based Smart e-Health Sy...

引用

4th International Conference on Recent Innovations in computing, ICRIC 2021

作者： Rahi, Pankaj Sood, Sanjay P. Bajaj, Rohit University Institute of Computing Chandigarh University Punjab Gharuan Mohali India Health Informatics Division Centre for Development of Advanced Computing Punjab Mohali India Department of Computer Science and Engineering Chandigarh University Punjab Gharuan Mohali India

ISBN: (纸本)9789811688911

Health issues caused by air pollution are the primary concern nowadays. The air quality monitoring system aids in monitoring the level of air pollutants by measuring the concentration of a particular pollutant in the environment. A systematic study of the existing systems has been done to analyze the limitations in the current scenario of these systems. This paper proposes a smart e-health air quality monitoring system that utilizes a meta-heuristic Firefly algorithm as well as a Cat Swarm Optimization algorithm to efficiently optimize the selected features to give better results in the feature selection process. Further, these features are classified by using a Support Vector Machine which predicts the index level of the air quality and gives better precision and recall. The combination of all these algorithms has true positive and false positive rates as 99% and 88.4%, respectively while the recall rate is 89.6%. Also, the proposed work predicts a high air quality index based on the input dataset. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

CQFaRAD: Collaborative Query-Answering Framework for a Research Article Dataspace

引用

International Journal of Information Technology (Singapore) 2024年第3期16卷 1873-1886页

作者： Singh, Mrityunjay Pandey, Shivam Saxena, Rohaan Chaudhary, Maheep Lal, Niranjan Indian Institute of Information Technology Una Himachal Pradesh Una 177209 India C-DAC: Centre for Development of Advanced Computing Uttar Pradesh Noida 201010 India Navana Tech Karnataka Bengaluru 562130 India SoCSE Nanyang Technological University Singapore Singapore SRM Institute of Science and Technology Uttar Pradesh Modinagar 201204 India

Dataspace systems cope with the problem of integrating a variety of data based on its structures and semantics such as structured, semi-structured, and unstructured data, and returns the best-effort or approximate answers to their users. The existing works on query answering from a dataspace system are content-based and paid attention to return the best answers to the users without taking care of their preferences. This paper aims to consider not only the content-based information but also the users’ preferences while answering the users’ queries. Therefore, we present a framework, known as Collaborative Query-Answering Framework for a Research Article Dataspace, to answer the users’ queries in efficient manner and returns more prominent answers to the users. In this work, we present a collaborative approach that adopts the advantages of the existing content-based and users’ preferences-based approaches. To achieve the objectives, we use the Bidirectional Encoder Representations from Transformers model to represent our dataspace and users’ query. We have validated our proposed approach on the research papers dataset available on Kaggle. The experimental results show that our approach works fairly well to return relevant information to the users. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of Computer Applications and Management.

关键词： BERT model Pay-as-you-go data integration Query-Answering model Recommendation system Research Article Dataspace Similarity measure Vector space model

来源：评论

学校读者我要写书评

暂无评论

Modeling and Analysis for Drain Source Voltage Overshoot in the Synchronous Rectifier of SiC based PSFB converter and Passive Snubber Design

Modeling and Analysis for Drain Source Voltage Overshoot in ...

引用

International Conference on Power Electronic Drives

作者： Anoop Kumar N K Neeraja Udaya Sagar V P Ganesan V Chandrasekar Power Electronics Group Centre for Development of Advanced Computing Thiruvananthapuram India

A frequency domain approach for snubber design, for the secondary side of High Frequency Switched Isolated Phase Shifted Full Bridge (PSFB) converter with synchronous rectification, is presented in this paper. At the rectifier side of the converter, the synchronous MOSFETs witness huge overshoots in the drain-source voltage reaching more than twice its rated values with very poor damping of the subsequent oscillations during turn-off. In order to investigate and identify the significant elements in the converter that contributes to such large over-shoots with nearly sustained ringing, a study is presented in this paper with the help of converter modeling and frequency domain analysis. The drain-source voltage characteristics obtained using the model are verified through simulations by comparing the results with the experimental values. For the analytical study, the rectifier side of the PSFB is modeled using an equivalent circuit and a frequency domain approach is adopted to design a passive RC snubber for suppressing the voltage overshoot and ringing. Its performance is validated through simulation and experimental results.

关键词： Analytical models Silicon carbide Frequency-domain analysis Snubbers Rectifiers Transfer functions Voltage

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：