检索结果-内蒙古大学图书馆

Electronics and Renewable systems (ICEARS), International Conference on

作者： V S Narayana Tinnaluri Manasi Vyankatesh Ghamande Shashank Singh Ramu Kuchipudi Minakshi Dattatraya Bhosale R Dharani Department of Computer Science Koneru Lakshmaiah Education Foundation Vijayawada Andhra Pradesh India Engineering and Applied Sciences Vishwakarma Institute of Information Technology Pune Department of Computer Science and Engineering Integral University Lucknow Uttar Pradesh India Department of Information Technology Chaitanya Bharathi Institute of Technology Hyderabad Telangana India Faculty of MCA Yashoda Technical Campus Satara Wadhe Maharashtra India Department of Computer Science and Business Systems M. Kumarasamy College of Engineering Karur Tamilnadu India

Mobile terminals' limited processing power and memory make it challenging to meet the needs of increasingly complex applications like autonomous vehicles and augmented reality. That’s why there’s been a rise in the demand for edge cloud computing power from endpoint gadgets. Due to its adaptability and proximity to the user, an unmanned aerial vehicle (UAV) may be used to support mobile edge computing (MEC) via job offloading, potentially relieving strain on edge clouds. Due to limitations in processing power and battery life, Unmanned Aerial Vehicles (UAV) devices face a huge issue with the rise of Applications and services for mobile devices that can't afford to be delayed and that need a lot of processing power. Task offloading is one way that mobile cloud computing may help you get around these restrictions. The biggest difficulties with this paradigm, however, are the significant latency and security concerns. The edge-cloud computing model was then proposed and has since seen widespread adoption as a means of dealing with these complications. However, the present task offloading models allow UAVs to perform their heavy jobs at the linked edge server, leading to unnecessary loads owing to the huge amount of UAVs and, in turn, increasing the latency. For this reason, this study has presented a delay-optimal task offloading strategy for multi-tier edge-cloud computing with many users. In this research, a system model has been proposed to assist an intelligent and perceptive agent in determining the best computational offloading strategy, minimizing both the time it takes to complete a job and the amount of power it needs to do so. The efficacy of an agent was shown, and simulation results revealed that its adoption may greatly cut delay and energy usage.

关键词： Cloud computing Computational modeling Autonomous aerial vehicles Software Numerical models Delays Servers

来源：评论

学校读者我要写书评

暂无评论

Generic Requirements for Inclusive Healthcare Software: Supporting Older Adults and People with Intellectual and Developmental Disability

Generic Requirements for Inclusive Healthcare Software: Supp...

引用

IEEE International Requirements Engineering Conference Workshops (REW)

作者： Ita Richardson Bilal Ahmad Shweta Premanandan Owen Doody Sarah Beecham Sofia Ouhbi Muneef Alsahmmari Åsa Cajander Dept of Computer Science and Information Systems Lero – the SFI Software Research Centre and Ageing Research Centre Health Research Institute University of Limerick Limerick Ireland Learnovate Centre Trinity College Dublin Dublin Ireland Dept of Informatics and Media Uppsala University Uppsala Sweden Dept of Nursing and Midwifery Health Implementation Science and Technology Cluster Health Research Institute University of Limerick Limerick Ireland Dept of Computer Science and Information Systems Lero – the SFI Software Research Centre University of Limerick Limerick Ireland Dept of Information Technology Uppsala University Uppsala Sweden Dept of Health Informatics College of Public Health and Health Informatics University of Hail Hail Saudi Arabia

As healthcare technology advances, it is important to ensure that everyone benefits from healthcare software, regardless of age or ability. That is why our research team has been working to identify and encapsulate the unique needs of two groups when developing software systems: older adults and people with mild intellectual and developmental disabilities. Through our research, we have developed design patterns that software engineers can use to create more usable healthcare software to support these groups. These patterns identify the generic requirements for usability including accessibility, crucial for creating software that meets the needs of marginalised populations. In this paper, we describe the steps we undertook to identify and develop these requirements. We discover many overlapping needs of these two cohorts. Our research aims to benefit older adults and people with mild intellectual and developmental disabilities and improve the lives of many others facing similar challenges. As we expand our research to other cohorts, we will be able to identify additional generic requirements that make healthcare software development more inclusive and effective.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Password-Sniffing Acoustic Keylogger Using Machine Learning

SSRN

引用

SSRN 2023年

作者： Akinbi, Alex Deniz, Erkan Ismael, Aras M. Rashid, Zryan N. Sengur, Abdulkadir School of Computer Science and Mathematics Liverpool John Moores University United Kingdom Firat University Technology Faculty Electrical-Electronics Engineering Department Elazig Turkey Sulaimani Polytechnic University College of Informatics Information Technology Department Sulaymaniyah Iraq

An acoustic keylogger is a form of side-channel attack where an attacker can extract and log what a victim typed on a keyboard by capturing the keystroke emanations and audio signals. Using a compromised smartphone microphone to capture keystroke audio recordings, this attack can be used to recognise confidential information such as passwords typed by a victim. In this paper, we demonstrate the training of a machine-learning model and develop a proof-of-concept password-sniffing acoustic keylogger. To this end, the input audio signals are initially converted to audio images by using the spectrogram representation of the Mel-Frequency Cepstral Coefficients (MFCC) method. MFCC applies the Fourier transform to yield the frequency content of the input signal. Then, a novel and less complex vision transformer-based approach namely ConvMixer is applied to the spectrogram images to detect the password according to its audio. In ConvMixer model group convolution and point convolution layers are located sequence for giving depth to the architecture. A novel key logger dataset is constructed by us and used in the experimental works. Various experiments are carried out and classification accuracy is applied for performance measurement tools. In the experimental works, an average 92.44% accuracy score is obtained with the proposed method. In addition, two pre-trained convolutional neural networks (CNN) models namely ResNet18 and VGG16 are used for comparison purposes. Comparisons show that the proposed approach has the potential for a compact acoustic keylogger system. © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

MF-MOS: A Motion-Focused Model for Moving Object Segmentation

arXiv

引用

arXiv 2024年

作者： Cheng, Jintao Zeng, Kang Huang, Zhuoxu Tang, Xiaoyu Wu, Jin Zhang, Chengxi Chen, Xieyuanli Fan, Rui The School of Electronic and Information Engineering South China Normal University Foshan528225 China The Department of Computer Science Aberystwyth University AberystwythSY23 3DB United Kingdom The Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong The School of Internet of Things Engineering Jiangnan University Wuxi China The College of Intelligence Science and Technology National University of Defense Technology Changsha China The College of Electronics & Information Engineering Shanghai Research Institute for Intelligent Autonomous Systems The State Key Laboratory of Intelligent Autonomous Systems Frontiers Science Center for Intelligent Autonomous Systems Tongji University Shanghai201804 China

Moving object segmentation (MOS) provides a reliable solution for detecting traffic participants and thus is of great interest in the autonomous driving field. Dynamic capture is always critical in the MOS problem. Previous methods capture motion features from the range images directly. Differently, we argue that the residual maps provide greater potential for motion information, while range images contain rich semantic guidance. Based on this intuition, we propose MF-MOS, a novel motion-focused model with a dual-branch structure for LiDAR moving object segmentation. Novelly, we decouple the spatial-temporal information by capturing the motion from residual maps and generating semantic features from range images, which are used as movable object guidance for the motion branch. Our straightforward yet distinctive solution can make the most use of both range images and residual maps, thus greatly improving the performance of the LiDAR-based MOS task. Remarkably, our MF-MOS achieved a leading IoU of 76.7% on the MOS leaderboard of the SemanticKITTI dataset upon submission, demonstrating the current state-of-the-art performance. The implementation of our MF-MOS has been released at https://***/SCNU-RISLAB/MF-MOS. © 2024, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

An Optimized Ensemble Model for Prediction the Bandwidth of Metamaterial Antenna

引用

computers, Materials & Continua 2022年第4期71卷 199-213页

作者： Abdelhameed Ibrahim Hattan F.Abutarboush Ali Wagdy Mohamed Mohamad Fouad El-Sayed M.El-kenawy Computer Engineering and Control Systems Department Faculty of EngineeringMansoura UniversityMansoura35516Egypt Electrical Engineering Department College of EngineeringTaibah UniversityMedina42353Saudi Arabia Operations Research Department Faculty of Graduate Studies for Statistical ResearchCairo UniversityGiza12613Egypt Wireless Intelligent Networks Center(WINC) School of Engineering and Applied SciencesNile UniversityGizaEgypt Department of Communications and Electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt Faculty of Artificial Intelligence Delta University for Science and TechnologyEgypt

Metamaterial Antenna is a special class of antennas that uses metamaterial to enhance their *** size affects the quality factor and the radiation loss of the *** antennas can overcome the limitation of bandwidth for small *** learning(ML)model is recently applied to predict antenna *** can be used as an alternative approach to the trial-and-error process of finding proper parameters of the simulated *** accuracy of the prediction depends mainly on the selected *** models combine two or more base models to produce a better-enhanced *** this paper,a weighted average ensemble model is proposed to predict the bandwidth of the Metamaterial *** base models are used namely:Multilayer Perceptron(MLP)and Support Vector Machines(SVM).To calculate the weights for each model,an optimization algorithm is used to find the optimal weights of the *** Group-Based Cooperative Optimizer(DGCO)is employed to search for optimal weight for the base *** proposed model is compared with three based models and the average ensemble *** results show that the proposed model is better than other models and can predict antenna bandwidth efficiently.

关键词： Metamaterial antenna machine learning ensemble model multilayer perceptron support vector machines

来源：评论

学校读者我要写书评

暂无评论

xIDS-EnsembleGuard: An Explainable Ensemble Learning-based Intrusion Detection System

arXiv

引用

arXiv 2025年

作者： Adil, Muhammad Jan, Mian Ahmad Hakim, Safayat Bin Song, Houbing Herbert Jin, Zhanpeng Deptartment of Computer Science University at Buffalo Buffalo United States College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates School of Information Systems University of Maryland Baltimore County United States School of Future Technology South China University of Technology Guangdong China University at Buffalo Buffalo United States

In this paper, we focus on addressing the challenges of detecting malicious attacks in networks by designing an advanced Explainable Intrusion Detection System (xIDS). The existing machine learning and deep learning approaches have invisible limitations, such as potential biases in predictions, a lack of interpretability, and the risk of overfitting to training data. These issues can create doubt about their usefulness, and transparency, and decrease the trust of involved stakeholders. To overcome these challenges, we propose an ensemble learning technique called the"EnsembleGuard". This approach uses the predicted outputs of multiple models, including tree-based (LightGBM, GBM, Bagging, XGBoost, CatBoost) and deep learning models such as neural network (LSTM (long short-term memory networks) and GRU (gated recurrent unit), to maintain a balance and achieve trustworthy results. Our work is unique because it combines both tree-based and deep learning models to design an interpretable and explainable meta-model through model distillation. By considering the predictions of all individual models, our neta-model effectively addresses key challenges, and ensures both explainable and reliable results. We evaluate our model using well-known datasets, including UNSWNB15, NSL-KDD, and CIC-IDS-2017, to assess its reliability against various types of attacks. During analysis, we found that our model outperforms both tree-based models and other comparative approaches when it comes to different kinds of attack scenarios. © 2025, CC BY-NC-ND.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

WIP: Technical Interview Preparation Initiative: Promoting Faculty Awareness and Intervention with Computing Majors

WIP: Technical Interview Preparation Initiative: Promoting F...

引用

Frontiers in Education (FIE) Conference

作者： Edward Dillon Kinnis Gosha Krystal L. Williams John J. Porter Portia Smith Department of Information Systems University of Maryland Baltimore County Baltimore USA Department of Computer Science Morehouse College Atlanta USA Department of Educational Leadership and Policy Analysis University of Wisconsin-Madison Madison USA Executive Recruiter & Director of Programs and Partnerships KARAT Overland Park USA

ISBN: (数字)9798350351507

ISBN: (纸本)9798350363067

This innovative practice WIP paper describes an initiative that seeks to promote faculty awareness and interventions towards student-based technical interview preparations. In the field of Computing, there is a trend for having a high demand of jobs in industry and a low supply of candidates to fill them. Literature indicates notable challenges that could pose as influential factors for this job/candidate ratio discrepancy in the field: 1) student retention challenges in computing areas at the collegiate level; 2) fostering stronger K-12 student interests and engagement towards computing fields as a career choice; and 3) representation barriers that exist within marginalized groups in computing. Yet, computing majors' inability to showcase their developed computational skills as prospective candidates to tech employers and hiring managers can persist as another barrier. Candidates are typically expected to demonstrate their computational skills and abilities practically. A candidate's inability to demonstrate such skills and abilities effectively could lead to missed job opportunities and even lucrative career pursuits in tech. One notable approach used by tech industry companies to examine the skillset compositions of their candidates is through technical interviews. This interview-based examination allows a hiring manager(s) to observe a candidate's ability to solve problems computationally in a think-aloud format, which also enables these professionals to gauge the candidate's verbal and communication skills during this interaction. When cross referencing the practice of technical interview examination in industry with the styles of learning and application fostered in computing classrooms in the academy, there exists a potential contrast between this expectation imposed by tech industry companies and professional preparation protocols fostered at academic institutions. There are computing-focused departments/schools and institutions at large that have identified

关键词： Industries Surveys Protocols Engineering profession Conferences Refining Stars Companies Market research Interviews

来源：评论

学校读者我要写书评

暂无评论

Comparison of Seventeen Missing Value Imputation Techniques

引用

Hunan Daxue Xuebao/Journal of Hunan University Natural sciences 2022年第7期49卷 26-36页

作者： Hameed, Wafaa Mustafa Ali, Nzar A. Technical College of Informatics Sulaimani Polytechnic University Kurdistan Region Sulaimani46001 Iraq Department of Computer Science Cihan University Sulaimaniya Kurdistan Region Sulaimaniya46001 Iraq Department of Statistics and informatics University of Sulaimani Kurdistan Region Sulaimani46001 Iraq

Copious data are collected and put away each day. That information can be utilized to extricate curiously designs. However, the information that we collect is ordinarily inadequate. Presently, utilizing that information to extricate any data may allow deceiving comes about. Utilizing that, we pre-process the information to exterminate the variations from the norm. In case of a low rate of lost values, those occurrences can be overlooked, but, in the case of huge sums, overlooking them will not allow wanted results. Many lost spaces in a dataset could be a huge issue confronted by analysts because it can lead to numerous issues in quantitative investigations. So, performing any information mining procedures to extricate a little good data out of a dataset, a few pre-processings of information can be done to dodge such paradoxes and, in this manner, move forward the quality of information. For handling such lost values, numerous methods have been proposed since 1980. The best procedure is to disregard the records containing lost values. Another method is ascription, which includes supplanting those lost spaces with a few gauges by doing certain computations. This would increment the quality of information and would extemporize forecast comes about. This paper gives an audit on methods for handling lost information like median imputation (MDI), hot (cold) deck imputation, regression imputation, expectation maximization (EM), support vector machine imputation (SVMI), multivariate imputation by chained equation (MICE), SICE technique, reinforcement programming, nonparametric iterative imputation algorithms (NIIA), and multilayer perceptrons. This paper also explores some good options of methods to estimate missing values to be used by other researchers in this field of study. Also, it aims to help them to figure out what method is commonly used now. The overview may also provide insight into each method and its advantages and limitations to consider for future research i

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Prediction of groundwater table for Chennai Region using soft computing techniques

引用

Arabian Journal of Geosciences 2022年第9期15卷 1-19页

作者： Ramasamy, Viswanathan Alotaibi, Youseef Khalaf, Osamah Ibrahim Samui, Pijush Jayabalan, Jagan Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram India Department of Computer Science College of Computer and Information Systems Umm Al-Qura University Makkah Saudi Arabia Al-Nahrain University Al-Nahrain Nano-renewable Energy Research Center Baghdad Iraq Department of Civil Engineering National Institute of Technology Patna Patna India Department of Civil Engineering Galgotias University Greater Noida India

Groundwater is one of the fundamental sources for the people in Chennai Region; also, determination of groundwater depth will be utilized for prior planning on excavation and construction purposes. This research article determines the depth of groundwater table by adopting various soft computing techniques like support vector machine (SVM), adaptive neuro-fuzzy inference system (ANFIS), and backpropagation (BP). The dataset was collected from the Tamil Nadu Water Supply and Drainage Board (TWAD), Chennai. It consists of input latitude (Lx), longitude (Ly), and the depth of groundwater (dw). The data were processed, and it was incorporated in the above-stated predicting models. The color map was the yield from the developed models. The performance of the developed model was assessed by various statistical parameters, and it was found that all the adopted models yield better performance for predicting the groundwater table. The comparison between the models depicted that support vector machine gave the promising result in determining the groundwater table with an equation for the futuristic purposes. Multifarious statistical analysis was computed in order to justify the attainment of the adopted models. The Taylor diagram and William’s plot were also included in order to substantiate the capability of the developed soft computing models to foretell the groundwater depth for the Chennai City.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Synthesis of a Finite State Machine With Elementary Chains of States

Synthesis of a Finite State Machine With Elementary Chains o...

引用

International Scientific-Practical Conference Problems of Infocommunications science and Technology

作者： Alexander Barkalov Larysa Titarenko Irina Zeleneva Svitlana Hrushko Tetiana Holub Mykhailo Shadrin Departament of Computer Science Electrotechnics and Informatics University of Zielona Góra Zielona Góra Poland Institute of Metrology Electrotechnics and Informatics University of Zielona Góra Zielona Góra Poland Department of Computer Systems and Networks National University "Zaporizhzhya Polytechnic" Zaporizhzhya Ukraine

Modified structure and method are proposed for synthesis of a combined finite state machine (CFSM) which forms the output functions of both types FSM – Mealy and Moore. Similar algorithms are used mainly for controlling the blocks of in-built systems in cases when the sensors that describe the system are not numerous, but it is necessary to perform certain sequences of microoperations. We consider a case when initial control algorithm is represented with a linear flowchart. Such flowcharts have a significant number of operator vertices, exceeding 75% of the total number of vertices. In the case of linear flowchart we propose to replace the register RG with a counter of states CT. It allows simplification of Boolean functions representing a combined FSM logic circuit. Also this allows to simplify the system of memory-excitation functions. The method uses existence of elementary linear chains of states in the initial flowchart. There is an example of synthesis and results of experimental study given in the article. The study of the proposed method based on the real control algorithm of the onboard computing device. Experiments and testing performed for various Intel (Altera) microchips. The studies carried out for different families of FPGAs, in different price ranges. A comparative analysis of time characteristics for the basic and proposed structures allows us to notice a tendency to some acceleration of the operation. In general, research results have shown that proposed structures of combined FSM can be useful for design of embedded systems.

关键词：

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：