检索结果-内蒙古大学图书馆

International Conference on Information and Communication Technology Convergence (ICTC)

作者： Chanwoo Lee Hyunjeong Lee Minsang Kim Hyun Kim Haneol Jang Cheoneum Park Dept. of Software Convergence Seoul Woman's University Seoul South Korea Dept. of Computer Engineering Hanbat National University Daejeon South Korea Dept. of Computer Science and Engineering Korea University Seoul South Korea Superintelligence Creative Research Lab. Electronics and Telecommunications Research Institute Daejeon South Korea

ISBN: (数字)9798350364637

ISBN: (纸本)9798350364644

In the field of NLP, Large Language Models (LLMs) have recently achieved significant advancements, leading to the development of various benchmarks for their evaluation. Along-side NLP, Vision Language Models (VLMs) have also VLM have also significantly progressed, similar to LLMs. However, benchmarks for VLMs are still relatively underdeveloped compared to those for NLP, and their construction is often costly. In this work, we propose an automatically generated benchmark for evaluating VLMs based on LLMs and conduct a visual question answering task to assess this benchmark. The benchmark includes multiple-choice questions that not only distinguish between animate and inanimate objects but also generate these distinctions automatically, along with entity and object information within images. We evaluate the performance of open VLM using the generated multiple-choice questions, demonstrating the model's capabilities and the significance of the automatically generated benchmark. Finally, we discuss the necessity and future directions for benchmark research in this area.

关键词： Visualization Annotations Large language models Natural languages Benchmark testing Information filters Question answering (information retrieval) Cognition Information and communication technology Convergence

来源：评论

学校读者我要写书评

暂无评论

E-commerce platform based on Machine Learning Recommendation System 6

E-commerce platform based on Machine Learning Recommendation...

引用

6th International Multi-Topic ICT Conference, IMTIC 2021

作者： Tahir, Muhammad Enam, Rabia Noor Mustafa, Syed Muhammad Nabeel Sir Syed University of Engineering and Technology Dept. of Software Engineering Karachi Pakistan NED University of Engineering and Technology Dept. of Computer Science I.T Karachi Pakistan

ISBN: (纸本)9781665482943

Information overload is one of the potential setbacks to many e-commerce platform users. It is very important to filter the media and the choices that are overwhelming for internet users while making buying decisions using online stores. To solve this problem, recommendation systems are used widely. A recommender system helps users find a product of their own choice by filtering and prioritizing and effectively generating the relevant information to its users. The purpose of a recommender system is to save time and hassle of searching through the World Wide Web, instead it generates specific and relevant content that promotes online transaction and bring satisfaction to the users of e-commerce platforms. The proposed system is an e-commerce platform based on an apparel recommendation system that recommends products on the foundation of the user's preferences. © 2021 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Enhanced Framework for Secure Third-Party Vendor Risk Management and Vigilant Security Controls

arXiv

引用

arXiv 2024年

作者： Gupta, Deepti Elluri, Lavanya Jain, Avi Moni, Shafika Showkat Aslan, Omer Dept. of Computer Information Systems Texas A&M University - Central Texas TX United States College of Business University of Tampa Florida United States Dept. of Electrical Engineering and Computer Science Embry-Riddle Aeronautical University Florida United States Department of Software Engineering Bandırma Onyedi Eylül University Bandırma Turkey

In an era of heightened digital interconnectedness, businesses increasingly rely on third-party vendors to enhance their operational capabilities. However, this growing dependency introduces significant security risks, making it crucial to develop a robust framework to mitigate potential vulnerabilities. This paper proposes a comprehensive secure framework for managing third-party vendor risk, integrating blockchain technology to ensure transparency, traceability, and immutability in vendor assessments and interactions. By leveraging blockchain, the framework enhances the integrity of vendor security audits, ensuring that vendor assessments remain up-to-date and tamper-proof. This proposed framework leverages smart contracts to reduce human error while ensuring real-time monitoring of compliance and security controls. By evaluating critical security controls—such as data encryption, access control mechanisms, multi-factor authentication, and zero-trust architecture—this approach strengthens an organization’s defense against emerging cyber threats. Additionally, continuous monitoring enabled by blockchain ensures the immutability and transparency of vendor compliance processes. In this paper, a case study on iHealth’s transition to AWS Cloud demonstrates the practical implementation of the framework, showing a significant reduction in vulnerabilities and marked improvement in incident response times. Through the adoption of this blockchain-enabled approach, organizations can mitigate vendor risks, streamline compliance, and enhance their overall security posture. Our findings highlight the importance of employing blockchain to enforce security controls and maintain compliance with healthcare regulations such as HIPAA. In this paper, we present a comprehensive set of security controls and demonstrate how blockchain technology enhances their effectiveness, ensuring greater transparency, accountability, and automation in vendor assessments. By reducing human error, enab

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Prediction of Continuous Targets by Explainable Imbalanced Regression from Omics Data in Childhood Obesity 1

Prediction of Continuous Targets by Explainable Imbalanced R...

引用

1st Workshop on Explainable Artificial Intelligence for the Medical Domain, EXPLIMED 2024

作者： Arteaga, María Torres-Martos, Álvaro Anguita-Ruiz, Augusto Alcalá-Fdez, Jesús Alcalá, Rafael Gacto, María José Dept. of Computer Science and Artificial Intelligence Univ. of Granada Granada Spain Center of Biomedical Research Univ. of Granada Inst. de investigación Biosanitaria ibs.GRANADA Granada Spain Inst. de Salud Carlos III Madrid Spain Barcelona Spain Univ. of Granada Granada Spain Dept. of Software Engineering Univ. of Granada Granada Spain

Childhood obesity is a persistent challenge for society since it is highly related to insulin resistance and a wide range of other chronic diseases, which impair not only the health of the people, but also the health system itself due to extra costs of treating them. In this context, it is imperative to consider innovative approaches, like eXplainable Artificial Intelligence, to understand the factors underlying childhood obesity. Data imbalance has been thoroughly studied in classification, but scarcely studied in regression since classes do not exist. However, extreme values in continuous domains, which are usually minority are often the most clinically relevant. Facing the imbalance in regression while obtaining explainable models has never been studied. In this application work, we adopt a Machine Learning approach to obtain explainable regression models for imbalanced continuous targets in childhood obesity, as HOMA-IR and Waist Circumference. We consider 79 variables, including targeted metabolomics, targeted proteomics, exposomic data (e.g., the physical activity subdomain), hematological parameters and anthropometry of Spanish children from 3 to 18 years with significant imbalance ratios around 12% in HOMA-IR and Waist Circumference. Even though we mainly focus on extensions of linguistic fuzzy rule-based systems, particularly designed for explainability, we also consider highly accurate complementary approaches as Random Forest that could additionally provide contrast interesting information by post-hoc SHAP. The models so obtained are better considering the relevant minority information (17% improvements in F1). Moreover, they seem to properly explain biologically meaningful relations, as in the case of physical activity data or the one with the follicle stimulating hormone, among others. © 2024 Copyright for this paper by its authors.

关键词： Nutrition

来源：评论

学校读者我要写书评

暂无评论

Visual object detection using audio data 5

Visual object detection using audio data

引用

5th International Conference on Computing and Data Science, CONF-CDS 2023

作者： Chaturvedi, Rajnish Kumar Sahu, Dinesh Prasad Tyagi, Manoj Kumar Diwakar, Manoj Singh, Prabhishek Shankar, Achyut Sathishkumar, V.E. Schoolof Computer Science Engineering and Technology Bennett University Greater Noida India Galgotias University India CSE Dept. Graphic Era Deemed to Be University Dehradun India University of Warwick United Kingdom Department of Software Engineering Jeonbuk National University Jeonju-si Jeollabuk-do Korea Republic of

Nowadays Internet of Things (IoT) and Machine Learning (ML) are growing fields. One application of these two fields is object detection, which detects semantic objects using digital images and videos of classes like humans, vehicles, buildings, etc. Visual object detection systems are very effective and accurate due to the appearance information obtained from the cameras. But they face the problem of a limited Field of View. This paper aims to tackle this issue by using audio data to localize the object. A microphone is used to estimate the angular position of the object emitting the sound. Objects currently in the Field of View of a camera are detected and tracked using optical flow, but when they go out of the Field of View, the sound emitted by the object is used by the microphone to calculate the object's angular position. Once the angle is calculated, the camera is rotated in that direction. This thus ensures that the object can be located even if it goes out of frame. Once the object is located through IoT devices, we use ML to identify the person's face. © Published under licence by IOP Publishing Ltd.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Exploring Loss Scenarios of STPA with Reinforcement Learning: A Case Study of Platform Screen Door

Exploring Loss Scenarios of STPA with Reinforcement Learning...

引用

Asia-Pacific Conference on software engineering

作者： Jiyoung Chang Ryeonggu Kwon Gihwon Kwon Dept. of Software Safety and Cyber Security University of Kyonggi Suwon Republic of Korea Dept. of Computer Science University of Kyonggi Suwon Republic of Korea Dept. of AI Computer Engineering University of Kyonggi Suwon Republic of Korea

System-Theoretic Process Analysis (STPA) is performing a potential hazard analysis in the interactions of components within a system. Among STPA's process, deriving loss scenarios by identifying causes of the hazard has become increasingly important due to the complexity of modern systems. In this study, we utilize reinforcement learning to derive state transition paths that lead to hazard as loss scenarios, and extract the frequency of risk frequencies to demonstrate the necessity of safety measures for the respective loss scenarios. It is anticipated that this efficient approach will aid in simulating the system design process and enhancing safety.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SES: Smart Education System

SES: Smart Education System

引用

International Conference on computer and Applications (ICCA)

作者： Wadha Alyammahi Saed Alrabaee Dept. of Computer and Network Engineering Dept. of Information Systems and Security College of Information Technology United Arab Emirates University AlAin UAE

Responding to inefficiencies in traditional classroom management methods, this paper proposes an innovative, technology-driven approach to enhance educational processes. Central to our proposal is the development of a facial recognition system designed for efficient student attendance tracking, thus eliminating time-consuming roll calls. Additionally, we plan to introduce interactive whiteboard features to enrich classroom dynamics between students and faculty. However, our approach extends beyond mere attendance tracking and interactive learning. We aim to launch a Program Learning Outcomes (PLO) and Course Learning Outcomes (CLO) mapper. Leveraging Natural Language Processing (NLP) techniques, this tool will auto-align CLOs with PLOs, facilitating a more efficient curriculum development process. We also suggest implementing a feature powered by YOLOv5 to monitor and assess student attention in the classroom. Our comprehensive suite of tools is designed to equip educators with resources to refine their teaching strategies and boost student learning outcomes. By integrating facial recognition for attendance, interactive whiteboard features, NLP-based CLO/PLO mapping, and attention monitoring, we aspire to provide a robust solution enabling educators to adapt their teaching methods to students’ unique needs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Moving Robots in Unknown Environments Using Potential Field Graphs 2

Moving Robots in Unknown Environments Using Potential Field ...

引用

2nd International Conference on Advanced Research in Computing, ICARC 2022

作者： Panagoda, Mithila Lokuliyanage, Minuli Senarath, Amadi Nisansala, N.K.V.M. Nethmini Rajapakshe, R.W.A.D.U. Rajapaksha, U.U. Samantha Jayawardena, Chandimal Sri Lanka Institute of Information Technology Dept. of Software Engineering Malabe Sri Lanka Sri Lanka Institute of Information Technology Dept. of Information Technology Malabe Sri Lanka Sri Lanka Institute of Information Technology Deprt. of Computer System and Engineering Malabe Sri Lanka

ISBN: (纸本)9781665407410

The purpose of this research paper is to introduce a new navigation algorithm for Robot Operating System (ROS) based robots which will allow complete autonomous traversal in any given indoor environment. Turtle bot3 burger bot is the sample robot chosen for this project. This will be equipped with a Light Detection and Ranging (LIDAR) scanner with the default settings, ultrasound, Intel Real Sense camera, etc. Environment information gathered via these sensors will be sent into a remote computer for processing since the raspberry pie micro-controller with the turtle bot burger is not enough to carry out a high computation-intensive task. Once the information is received series of tasks will be carried out by the remote personal computer before executing the newly developed navigation algorithm. The data from the LIDAR scanner help to generate a 2-dimensional(2D) potential field graph. Then it will later be used for path planning by navigation algorithm. Furthermore, the Real sense camera is used for object boundary detection to produce more accurate data for the navigation algorithm. Once all the data proceed, data will return to the robot, where the navigation algorithm will start execution in parallel with a recovery behavior algorithm and scan algorithm. The recovery behavior algorithm is responsible for guiding the robot to face away from an obstacle in an event where the predetermined path is obstructed. Furthermore, it is responsible for maintaining accurate data in the cost map. Subsequently, the scanning algorithm will be used to generate maps. © 2022 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Adaptation of PAM4 Serial Link Transceiver Equalizers using Eye Diagram Monitoring

Adaptation of PAM4 Serial Link Transceiver Equalizers using ...

引用

2021 International Conference on Microelectronics, ICM 2021

作者： Mubarak, Hisham M. Elkhweski, Mohsen F. Yehia, Yehia Hamdy El-Kharashi, M. Watheq Zaki, Ahmed M. Ain Shams University Dept. of Computer and Systems Engineering Cairo Egypt Ain Shams University Dept. of Electronics and Communications Engineering Cairo Egypt

ISBN: (纸本)9781665408394

This paper studies the possible gains from using a single adaptation algorithm in tuning multiple equalizers in a Pulse Amplitude Modulation 4-level (PAM4) serial link transceiver. A comparison with the typical approach of using an algorithm for tuning one of the many equalizers used in transceivers from the perspective of bit error rate (BER) is carried out. This work also presents a method of measuring the eye diagram using an Eye Diagram Monitor (EDM) to continuously feed a Figure of Merit (FOM) to the adaptation algorithm to update equalizers' settings. A demonstration on deploying our algorithm in adapting three major building blocks of a typical PAM4 transceiver is presented, showing its effectiveness in comparison with adapting only one equalizer at receiver (Rx) side. Simulation results show improvement in eye diagram measures in terms of achieving an eye height of 326 mV and a width of 97 ps compared to 67 mV and 12 ps respectively in case of adapting only one equalizer in Rx. © 2021 IEEE.

关键词： Pulse amplitude modulation

来源：评论

学校读者我要写书评

暂无评论

Effect of climatological variations on Eco-efficiency of Wastewater Treatment Plants operation

Effect of climatological variations on Eco-efficiency of Was...

引用

International Conference on Emerging Technologies and Factory Automation (ETFA)

作者： Silvana Revollar Montse Meneses Mario Francico Pastora Vega Ramón Vilanova Dept. Computer Science and Automation University of Salamanca Salamanca Spain Dept. Telecommunications and Systems Engineering Universitat Autonoma Barcelona Barcelona Spain

This study addresses the effect of climate conditions on treatment effectiveness and energy consumption in a conventional Wastewater Treatment Plant (WWTP). It has been observed that winter temperatures below 12°C produce a deterioration of pollutants elimination and energy efficiency in the activated sludge process (ASP). Then, in this work, variations of climatological conditions are considered, and ASP control parameters are modified, to evaluate their effect into the eco-efficiency of the WWTP operation. The eco-efficiency of the operation is analyzed from a plant-wide perspective considering the effects on different units of the plant. The Benchmark Simulation Model 2 (BSM2), that represents a typical WWTP, is selected for simulations. Introduction of seasonal temperature effects on ASP control strategy are contemplated for future work.

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：