检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Islam, Md Robiul Islam, Md Mahamodul Afrin, Suraiya Antara, Anika Tabassum, Nujhat Amin, Al Dept. of Computer Science and Engineering Uttara University Dhaka Bangladesh Dept. of Informatics University of Oslo Oslo Norway Khulna Bangladesh Dept. of Electrical and Electronics Engineering BRAC University Dhaka Bangladesh Dept. of Electrical and Computer Engineering North South University Dhaka Bangladesh Dhaka Bangladesh

Cybersecurity is one of the global issues because of the extensive dependence on cyber systems of individuals, industries, and organizations. Among the cyber attacks, phishing is increasing tremendously and affecting the global economy. Therefore, this phenomenon highlights the vital need for enhancing user awareness and robust support at both individual and organizational levels. Phishing URL identification is the best way to address the problem. Various machine learning and deep learning methods have been proposed to automate the detection of phishing URLs. However, these approaches often need more convincing accuracy and rely on datasets consisting of limited samples. Furthermore, these black-box intelligent models' decision to detect Suspicious URLs needs proper explanation to understand the features affecting the output. To address the issues, we propose a 1D Convolutional Neural Network (CNN) and trained the model with extensive features and a substantial amount of data. The proposed model outperforms existing works by attaining an accuracy of 99.85%. Additionally, our explainability analysis highlights certain features that significantly contribute to identifying the phishing URL. © 2024, CC BY.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Integrating Simulation and Optimization: A Case Study in Pamplona for Self-Collection Delivery Points Network Design 35

Integrating Simulation and Optimization: A Case Study in Pam...

引用

35th European Modeling and Simulation Symposium, EMSS 2023

作者： Izco, Irene Serrano-Hernandez, Adrian Sawik, Bartosz Faulin, Javier GILT-OR Group Institute of Smart Cities Dept. Statitistics Computer Science and Mathematics Public University of Navarra Campus Arrosadia s/n Pamplona31006 Spain Department of Business Informatics and Engineering Management AGH University of Science and Technology Mickiewicza 30 Kraków30059 Poland

ISBN: (纸本)9788885741881

The disruptions experienced by the processes in the last mile delivery during the SARS-CoV-2 pandemic raised the dilemma of up-to-date last mile approaches for Urban Logistics (UL) issues. Self-Collection Delivery Systems (SCDS) have been proved to be an improvement for all the players of the SC, providing flexibility of time-windows and reducing overall mileage, delivery time and, consequently, gas emissions. Differing from previous works involving hybrid modeling for automated parcel lockers (APL) network design, this paper brings a System Dynamics Simulation Model (SDSM) to forecast online shopping demand in the Spanish city of Pamplona. A bi-criteria Facility Location Problem (FLP) is solved by means of an e-constraint method, where e is defined as the level of coverage of the total demand. The experiment run considers 90% of demand coverage, in order to obtain the most complex network possible. The simulation and demand forecast was carried out using Anylogic simulation software and the optimization procedure makes use of the Java-based CPLEX API solver. © 2023 The Authors.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Leveraging Highly Approximated Multipliers in DNN Inference

arXiv

引用

arXiv 2024年

作者： Zervakis, Georgios Frustaci, Fabio Spantidi, Ourania Anagnostopoulos, Iraklis Amrouch, Hussam Henkel, Jörg The Computer Engineering & Informatics Dept. University of Patras Greece The DIMES University of Calabria Italy The Department of Computer Science Eastern Michigan University United States The School of Electrical Computer and Biomedical Engineering Southern Illinois University Carbondale United States Germany Karlsruhe Institute of Technology Germany

In this work, we present a control variate approximation technique that enables the exploitation of highly approximate multipliers in Deep Neural Network (DNN) accelerators. Our approach does not require retraining and significantly decreases the induced error due to approximate multiplications, improving the overall inference accuracy. As a result, our approach enables satisfying tight accuracy loss constraints while boosting the power savings. Our experimental evaluation, across six different DNNs and several approximate multipliers, demonstrates the versatility of our approach and shows that compared to the accurate design, our control variate approximation achieves the same performance, 45% power reduction, and less than 1% average accuracy loss. Compared to the corresponding approximate designs without using our technique, our approach improves the accuracy by 1.9x on average. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhance Undergraduate Research by Incorporating an Entrepreneurial Mindset 53

Enhance Undergraduate Research by Incorporating an Entrepren...

引用

53rd IEEE ASEE Frontiers in Education International Conference, FIE 2023

作者： Nezafati, Maysam Reizman, Irene Benton, Mary Lauren Peponis, John Payne, Michelle Marincel Johnson, Blake E. Van Treuren, Kenneth Liu, Liping Georgia Tech Emory Uni. Dept. of Biomedical Eng. AtlantaGA United States Rose-Hulman Inst. of Technology Dept. of Chemical Eng. Terre HauteIN United States Baylor University Dept. of Computer Science WacoTX United States Lawrence Technological University Dept. of Biomedical Eng. SouthfieldMI United States Rose-Hulman Inst. of Technology Dept. of Civil & Env. Eng. Terre HauteIN United States Uni. of Illinois Urbana-Champaign Dept. of Mechanical Eng. UrbanaIL United States Baylor University Dept. of Mechanical Eng. WacoTX United States

ISBN: (纸本)9798350336429

Undergraduate (UG) Undergraduate (UG) research is a high-impact practice that has been shown to benefit students' development and has the potential to contribute to faculty research output. However, UG research does not attain the impact that it could have on student development or faculty research productivity. Faculty doing UG research face two main challenges: continuity and efficiency. Continuity is important for faculty to achieve research goals. However, onboarding, training, and mentoring UG researchers can be an inefficient, time-consuming process due to a lack of formal mentorship processes. From a student perspective, UG research has two main challenges: lack of autonomy and understanding of relevance relative to other co-curricular activities. In some research groups, UG students may not feel that they have ownership of their work, which results in the decay of intrinsic motivation. We are developing an Entrepreneurial Mindset (EM)-focused framework to enhance the research experience both for faculty and students. This framework provides faculty with access to resources and collaborators to support their efforts in engaging students in UG research and developing continuity in their laboratories. Students, on the other hand, will benefit from training opportunities designed to spark their curiosity, help them establish connections between their learnings, and enhance the value they create through their work. EM principles can transform UG research experiences by improving students' understanding of the relevance of their research and how it creates value for society. Our goal is to infuse EM into students' understanding of the UG research process, with the objective of broadening their participation, addressing institutional challenges, and enhancing research productivity to benefit society. We seek to understand what benefits students perceive they will gain through the UG research experience so that we can understand how entrepreneurially-minded learning

关键词： curriculum development entrepreneurial mindset intrinsic motivation undergraduate research

来源：评论

学校读者我要写书评

暂无评论

Design of efficient single-etch grating couplers for silicon nitride photonics at 1550 nm

Design of efficient single-etch grating couplers for silicon...

引用

2024 Photonics North, PN 2024

作者： Fraser, William Benedikovic, Daniel Korcek, Radovan Milanizadeh, Maziyar Bucio, Thalía Domínguez Vitali, Valerio Gardes, Frederic Y. Schmid, Jens H. Cheben, Pavel Ye, Winnie N. Dept. Electronics Carleton University Ottawa Canada Dept. Multimedia and Information-Communication Technologies University of Zilina Zilina Slovakia University Science Park University of Zilina Zilina Slovakia National Research Council Ottawa Canada Optoelectronics Research Centre University of Southampton Highfield Campus Southampton United Kingdom Electrical Computer and Biomedical Engineering Department University of Pavia Pavia27100 Italy

ISBN: (纸本)9798350366365

We present the design of single-etch grating couplers implemented on native and a hybrid silicon nitride (SiN) photonic platform with amorphous silicon (α-Si) overlays, operating in the telecom waveband. The SiN-only grating coupler has a coupling loss of -3.6 dB and a 1-dB bandwidth of 37 nm. A hybrid α-Si-on-SiN platform yields improved coupling loss of -1.4 dB and -1 dB for uniform and subwavelength grating apodized designs, respectively. © 2024 IEEE.

关键词： Silicon nitride

来源：评论

学校读者我要写书评

暂无评论

Monolithic 3D Printed Micro-Optofluidic Device for Two-phase Flow Monitoring and Bioapplications

Monolithic 3D Printed Micro-Optofluidic Device for Two-phase...

引用

Electric And Power Engineering (EPEi), IEEE International Conference And Exposition On

作者： Lorena Saitta Emanuela Cutuli Giovanni Celano G Claudio Tosto Francesca Guarino Gianluca Cicala Maide Bucolo dept.of Civil Engineering and Architecture University of Catania Catania Italy dept. of Electrical Electronic and Computer Science Engineering University of Catania Catania Italy dept. of Biomedical and Biotechnological Science University of Catania Catania Italy

ISBN: (数字)9798350356199

ISBN: (纸本)9798350356205

In this work, a biocompatible 3D printed micro-optofluidic (MoF) device designed for monitoring two-phase flows is presented. It was manufactured using the Projection Micro-Stereolithography (PμSL) 3D printing technique combined with a biocompatible resin. This device successfully monitored both an air-water slug-flow and a two-phase mixture of micrometric eukaryotic yeast cells (Saccharomyces cerevisiae) suspended in a phosphate-buffered saline (PBS) solution. Its working principle relies on the absorption phenomenon, since different light transmissions are correlated to either the fluid or the cells interfering with a laser beam in a microchannel section. To accomplish this, the MoF device was designed with two micrometric slots for the insertion of optical fibers to capture the light signal. Both the micro-optical and microfluidic components, each 200 μm in size, were integrated into the MoF device as a monolithic structure. A wide experimental campaign was performed on the MoF device investigating different flow rates and cells concentrations. The optimal operative condition for achieving the most robust working ability were determined using a Design of Experiments (DoE) approach.

关键词： Performance evaluation Fluids biomedical optical imaging Voltage measurement Cells (biology) Three-dimensional printing Stability analysis Real-time systems biomedical monitoring Monitoring

来源：评论

学校读者我要写书评

暂无评论

Primary school teachers' attitudes towards digital educational games: Preliminary findings from the Multiplication Game evaluation 12

Primary school teachers' attitudes towards digital education...

引用

12th International Conference on Information, Intelligence, Systems and Applications, IISA 2021

作者： Leonardou, Angeliki Rigou, Maria Garofalakis, John University of Patras Dept. of Computer Engineering and Informatics Patra Greece University of Patras Dept. of Management Science and Technology Patra Greece

ISBN: (纸本)9781665400329

The COVID-19 pandemic among other radical changes it imposed onto our typical way of living, working, and interacting, established online education in both synchronous and asynchronous forms. This in many cases has given alternative forms of education like digital games, more practical potential. Teachers during this period have proposed digital games as a part of the teaching and learning procedure more often. The digital games that managed to prove their value in more effective learning will probably gain a place in the classroom and teachers' role is significant towards this change. This study presents the results of an online survey with the participation of 184 primary school teachers in Greece. The purpose of the survey is to investigate teachers' attitudes towards digital games in general and the Multiplication Game (MG) in particular and the findings are positive as teachers' opinion for both MG and digital games is high. © 2021 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Enhancing Drug Detection Strategies for Post-Rehabilitated Juveniles: A Comprehensive Review and Empirical Study

Enhancing Drug Detection Strategies for Post-Rehabilitated J...

引用

Advances in Computing, Communication and Networking (ICAC2N), International Conference on

作者： Priyanka Kaushik Prabha Gour Lovish Bir Lubna Ansari Rojalini Samnata R. Soundarya Dept. of Computer Science Engineering Chandigarh University Chandigarh India Dept. of Humanities & S.Science Madhav University Pindwara India Dept. of of Com. Science Engineering Chandigarh University Chandigarh India Dept. of Computer Eng. & Applications Mangalayatan University Aligarh India Dept. of Pharamcy Usha Martin University Jharkhand India Dept. of Biomedical Engineering Dhanalakshmi Srinivasan College Coimbatore India

ISBN: (数字)9798350356816

ISBN: (纸本)9798350356823

Drug addiction is a complex problem that will affect individuals of all ages, including juveniles. It is a chronic and often relapsing disease that requires continued care and support to help individuals achieve and maintain long-term recovery. While rehabilitation programs are designed to help individuals overcome addiction, relapse rates remain high, making post-rehabilitation drug detection an important component of continued care. This study aims to investigate the efficacy of various drug detection techniques for juveniles who have completed their rehabilitation. The success of rehabilitation program for young drug addicts depends on the creation of efficient drug detection rules and procedures that can assist avoid relapse and increase program effectiveness overall. The research technique comprises both an empirical investigation of post-rehabilitated juvenile participants and a thorough evaluation of the literature of past studies on drug detection for young people. The results of this study will have a big impact on how well drug detection policies and practises for young people who have completed their rehabilitation are developed.

关键词： Drugs Technological innovation Accuracy Reviews Computational modeling Addiction Machine learning Predictive models Security Diseases

来源：评论

学校读者我要写书评

暂无评论

Doppler Image-Based Weakly-Supervised Vascular Ultrasound Segmentation with Transformer

Doppler Image-Based Weakly-Supervised Vascular Ultrasound Se...

引用

IEEE International Symposium on biomedical Imaging

作者： Guochen Ning Hanying Liang Fang Chen Xinran Zhang Hongen Liao Dept. of Biomedical Engineering Tsinghua University Beijing China Dept. of Computer Science and Engineering Nanjing University of Aeronautics and Astronautics Nanjing China

Vascular segmentation in ultrasound (US) images faces labor-intensive labeling procedures and performance degradation due to unsatisfied image quality. Herein, we propose to use the Doppler image for vascular segmentation with an incremental Transformer structure. First, local features within the image patch are extracted by a convolutional neural network (CNN) patch embedding layer and further encoded by a multi-level Transformer to enhance the global dependencies from coarse to fine. A multi-level CNN decoder is introduced to decode corresponding features. Doppler imaging is capable of blood visualization and indicating the positional and structural information used as the pseudo label. A conditional random field (CRF) module and shape similarity loss function are introduced to improve the effectiveness of the Doppler images. The segmentation accuracy of the radial artery and carotid artery datasets can achieve 78.8% and 81.9% in Dice, with 63.5% and 53.7% accuracy in noisy labels. In addition, the framework can be generalized to unseen data without related Doppler images.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Reconfiguration Cost for Reconfigurable Computing Architectures

Reconfiguration Cost for Reconfigurable Computing Architectu...

引用

Summer Virtual Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD-Summer), ACIS International

作者： Shigeyuki Takano Hideharu Amano Dept. of Informatics and Computer Science Keio University Kanagawa Japan

ISBN: (纸本)9798350396386

Reconfigurable computing systems show the advantage of high flexibility and high-performance or low-power relative to traditional computing systems. Reconfiguration can change user logic statically or dynamically. The reconfiguration is a key feature in the reconfigurable computing system, however, the reconfiguration techniques are not considered enough. One of the reconfiguration techniques must be chosen for usage target characteristics of reconfiguration. This article shows the cost of typical reconfiguration techniques which can be applied to not only field-programmable gate arrays (FPGAs) but also coarse-grained reconfigurable arrays (CGRAs). We call these microarchitectures, field-programmable logic (FPL). We focus on three device classes; traditional configurable FPL (ex. FPGA), a partially reconfigurable FPL and a multi-context FPL. We investigate how the size and frequency of reconfiguration can be taken care of and how much speed-up is theoretically expected from a perspective of reconfiguration cost. In addition, the investigation introduces temporal and spatial configuration cache techniques.

关键词： Costs Microarchitecture Reconfigurable architectures Artificial intelligence Field programmable gate arrays Software engineering

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：