Showing papers by "Shyan-Ming Yuan published in 2022"

Using Deep Learning with Thermal Imaging for Human Detection in Heavy Smoke Scenarios

Abstract: In this study, we propose using a thermal imaging camera (TIC) with a deep learning model as an intelligent human detection approach during emergency evacuations in a low-visibility smoky fire scenarios. We use low-wavelength infrared (LWIR) images taken by a TIC qualified with the National Fire Protection Association (NFPA) 1801 standards as input to the YOLOv4 model for real-time object detection. The model trained with a single Nvidia GeForce 2070 can achieve >95% precision for the location of people in a low-visibility smoky scenario with 30.1 frames per second (FPS). This real-time result can be reported to control centers as useful information to help provide timely rescue and provide protection to firefighters before entering dangerous smoky fire situations.

Enhancing Saga Pattern for Distributed Transactions within a Microservices Architecture

Abstract: The saga pattern manages transactions and maintains data consistency across distributed microservices via utilizing local sequential transactions that update each service and publish messages to trigger the next ones. Failure by one transaction causes the execution of compensating transactions that counteract the preceding one. However, saga lacks isolation, meaning that reading and writing data from an incomplete transaction is allowed. Therefore, this research proposes an enhanced saga pattern that resolves the lack of isolation issue via the use of the quota cache and the commit-sync service. Some transactions will be transferred from the database layer to the memory layer. Thus, no wrong commit to the main database will occur. If a microservice fails to be completed, the other microservices will run compensation transactions to rollback the changes that only affect the cache layer instead of the database layer. Database commit will be performed when all transactions are completed successfully. A lightweight microservices-based e-commerce system was implemented for comparison. Experiments were conducted for validation and evaluation. Results demonstrate that the proposal has the capability of resolving the lack of isolation. Results indicate that the proposal achieves better performance not only in typical cases but also in the scenario that needs to handle exceptions.

Hash-Chain Fog/Edge: A Mode-Based Hash-Chain for Secured Mutual Authentication Protocol Using Zero-Knowledge Proofs in Fog/Edge

Abstract: Authentication is essential for the prevention of various types of attacks in fog/edge computing. Therefore, a novel mode-based hash chain for secure mutual authentication is necessary to address the Internet of Things (IoT) devices’ vulnerability, as there have been several years of growing concerns regarding their security. Therefore, a novel model is designed that is stronger and effective against any kind of unauthorized attack, as IoT devices’ vulnerability is on the rise due to the mass production of IoT devices (embedded processors, camera, sensors, etc.), which ignore the basic security requirements (passwords, secure communication), making them vulnerable and easily accessible. Furthermore, crackable passwords indicate that the security measures taken are insufficient. As per the recent studies, several applications regarding its requirements are the IoT distributed denial of service attack (IDDOS), micro-cloud, secure university, Secure Industry 4.0, secure government, secure country, etc. The problem statement is formulated as the “design and implementation of dynamically interconnecting fog servers and edge devices using the mode-based hash chain for secure mutual authentication protocol”, which is stated to be an NP-complete problem. The hash-chain fog/edge implementation using timestamps, mode-based hash chaining, the zero-knowledge proof property, a distributed database/blockchain, and cryptography techniques can be utilized to establish the connection of smart devices in large numbers securely. The hash-chain fog/edge uses blockchain for identity management only, which is used to store the public keys in distributed ledger form, and all these keys are immutable. In addition, it has no overhead and is highly secure as it performs fewer calculations and requires minimum infrastructure. Therefore, we designed the hash-chain fog/edge (HCFE) protocol, which provides a novel mutual authentication scheme for effective session key agreement (using ZKP properties) with secure protocol communications. The experiment outcomes proved that the hash-chain fog/edge is more efficient at interconnecting various devices and competed favorably in the benchmark comparison.

Intent-Controllable Citation Text Generation

Abstract: We study the problem of controllable citation text generation by introducing a new concept to generate citation texts. Citation text generation, as an assistive writing approach, has drawn a number of researchers’ attention. However, current research related to citation text generation rarely addresses how to generate the citation texts that satisfy the specified citation intents by the paper’s authors, especially at the beginning of paper writing. We propose a controllable citation text generation model that extends a pre-trained sequence to sequence models, namely, BART and T5, by using the citation intent as the control code to generate the citation text, meeting the paper authors’ citation intent. Experimental results demonstrate that our model can generate citation texts semantically similar to the reference citation texts and satisfy the given citation intent. Additionally, the results from human evaluation also indicate that incorporating the citation intent may enable the models to generate relevant citation texts almost as scientific paper authors do, even when only a little information from the citing paper is available.

Modify, Decompose and Reassemble: Learner-Centered Constructive Teaching Strategy for Introductory Programming Course in College

Abstract: C/C++ is one of the most common programming languages in introductory computer science courses. For students with varying levels of digital literacy, traditional teaching strategies that begin with C/C++ syntax and concepts appear inappropriate. Moreover, different programming languages are required for specific industrial purposes. To complement traditional teaching methods, we design a learner-centered constrictive strategy. Other than C/C++, students begin with two programming languages. Rather than conventional lectures, students learn to program by modifying, decomposing, and reassembling example codes. The midterm assesses their learning effectiveness. After the midterm, they can choose to take the collegiate programming examination (CPE) or not. If they pass CPE, they can pick between 1) regular class and final exam, or 2) no class after midterm, find a topic for a final project, finish it and present it in the last class. We invited 21 students from a class of 90. Eight students had no prior coding experience. Even though these eight students obtained lower scores in the midterm, they all had significant improvements in the final exams. Among sixteen students, six of whom had no prior coding experience, acknowledged that they learned useful skills in the class. Our results show that students with varying coding backgrounds can benefit from our proposed teaching strategy.