Welcome to COIT 2022

2nd International Conference on Computing and Information Technology (COIT 2022)

February 19 ~ 20, 2022, Dubai, UAE



Accepted Papers
Application of Heuristic Algorithms to a Neural Network Inference Execution Scheduler for Shared Memory Systems (HANNES)

Mikhail Zhelezin1,2, Stanislav Pavlov1,2,3, PhD Valeria Lakshina1,2, Dr. Prof. Yury Fedosenko3, 1Huawei Research Center, Nizhny Novgorod, Russia, 2National Research University Higher School of Economics" Nizhny Novgorod, Russia, 3Volga State University of Water Transport, Nizhny Novgorod, Russia

ABSTRACT

We are conducting research aimed at accelerating neural networks on a CPU. This acceleration will be associated with the solution of the computational graph planning problem. In the modern world, large neural networks are computed on accelerators (GPU, NPU, TPU), since their architecture is designed for numerous calculations of matrix multiplications and vector operations. Many modern approaches do not take into account factors that can speed up the inference of neural networks, such as the number of cores, cache size, bus bandwidth, etc. Also, many researchers underestimate simple heuristics that can significantly speed up the computation of neural networks. In this article, we show how simple heuristics can efficiently solve the scheduling problem and apply it to compute neural networks.

KEYWORDS

Deep Learning, Scheduling, Parallel Programming, Inference, Performance Optimization, Heuristic Algorithm.


Firebot - An Autonomous Surveillance Robot for Fire Prevention, Early Detection and Extinguishing

Josip Balen, Davor Damjanovic, Petar Maric, Kresimir Vdovjak, Matej Arlovic, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek Josip Juraj Strossmayer University of Osijek Kneza Trpimira 2b, 31000 Osijek, Croatia

ABSTRACT

Every year, fire is responsible for numerous deaths, as well as huge material losses. Therefore, prevention and early detection of fire have become a priority for society, as well as the main research and development issue for many scientists and various industries. This paper describes our work in the development of FireBot, an autonomous surveillance robot. The Firebot is equipped with modern technologies and state-of-the-art navigational and computer vision methods that enable autonomous navigation, obstacle avoidance, video surveillance, fire prevention and detection, and fire extinguishing. It utilizes both infrared thermal (IRT) and RGB cameras paired with a modern convolutional neural network (CNN) for fault and fire detection, as well as various other sensors for analyzing air composition, processing of surrounding sounds, and detecting irregularities in its environment in general. The best performing CNN was implemented and tested in real-world environments for fire detection purposes, the results of which are presented in this paper. A state-of-the-art SLAM algorithm paired with LiDAR and a depth camera is used for mapping and navigation. The architecture presented in this paper, along with all functionalities planned for future work, represents an innovative autonomous surveillance system that will make a great contribution in the field of fire prevention and detection.

KEYWORDS

convolutional neural network, fire detection, fire prevention, infrared thermography, SLAM.


Assisting Blind People using Object Detection with Vocal Feedback

Heba Najm, Khirallah Elferjani and Alhaam Alariyibi, Department of Computer Science, Benghazi University, Benghazi, Libya

ABSTRACT

Blind and visually impaired people face difficulties in safe and independent movement which prevent them from regular professional and social activities in both indoors and outdoors. Similarly, they have problem perceiving objects of surrounding environment that may pose a risk to them. The proposed approach suggests detection of objects in real-time video by using a web camera, for the object identification, process CNN-based real-time object detection technique called You Look Only Once (YOLO). The software is implemented by using OpenCV libraries of Python as well as implementing deep learning process. Image recognition results are transferred to the visually impaired users in audible form by means of Google text-to-speech library and determine object location relative to its position in the screen. The result was evaluated by using the mean Average Precision (mAP), and it was found that the proposed approach achieves excellent results when it compared to previous approaches.

KEYWORDS

Visually Impaired, Computer Vision, Deep Learning, Object Detection, YOLO Algorithm, OpenCV, Real-time.


Mitigating the Impact of a Change Request Risks for Large Software Development

Hassan Osman Ali and Osama Rahmeh, Department of Information Security, Faculty of Computer Information Science (CIS), Higher Collages of Technology (HCT), Fujairah, UAE

ABSTRACT

As usually in every software project have to deal with change. Being able to effectively control and handle the proposed changes is crucial for allowing continued development of a software project to occur. To mitigate and control the change, developers must assess the risks related in doing the change. To understand the risk, the project manager must identify where the change will effect and the impact of the change entire the project. As usual, each change has its own risk, in smaller project will have fewer and manageable risk, but, larger project has higher level of risks. However, it can inundate yourself with too many changes request if you don’t take a focused approach that you can handle the risk. Some project managers are extremely slow moving, analytical types of project in which all requirements must be collected and assessed. On the other hand, some recent surveys reported that the project success rate has slightly better and increased over the last decade. This success is the outcome of describing a process and use of some available tools like requirements management tools. But, these tools are not mostly enough to handle and control the risks involve with the proposed change. Therefore, this paper focuses more on the factors that have high impact with the assessment and evaluation of the risks involve to the requested change.

KEYWORDS

Risks involve software changes, Software Change requirements, Risk management.


Investigation of Optimization Techniques on the Elevator Dispatching Problem

Shaher Ahmed, Mohamed Shekha, Suhaila Skran and Abdelrahman Bassyouny, Department of Mechatronics Engineering, Faculty of Engineering and Materials Science, The German University in Cairo, Egypt

ABSTRACT

The reduction of passenger journey time in an elevator system is an important goal in the lift industry. The major obstacle that prevents the optimization of the elevator dispatching is the uncertain traffic flow of passengers. In this paper, a comparison between the use of multiple Optimization Techniques such as Simulated Annealing (SA), Genetic Algorithm (GA), Particle Swarm Optimization Algorithm (PSO), and Whale Optimization Algorithm (WOA), are presented. A case study has been designed to analyze the functionality of the algorithms and to obtain a reasonable solution. To compare the results of the algorithms, performance indices are computed such as average and optimal fitness value in 5 runs in order to find the best algorithm for the elevator dispatching problem. The objective of this study is to reduce the average journey time for all passengers by computing a dispatching scheme; which is the output of the algorithms. The proposed technology would improve lift efficiency and provide a better user experience.

KEYWORDS

Stochastic Optimization, Elevator Dispatching Systems, Meta-Heuristics Optimization Techniques.


W&G-BERT: A Concept for a Pre-Trained Automotive Warranty and Goodwill Language Representation Model for Warranty and Goodwill Text Mining

Lukas Jonathan Weber1, Alice Kirchheim2, Axel Zimmermann3, 1Department Mechanical Engineering, Helmut-Schmidt-University, Hamburg, Germany, 2Department Mechanical Engineering, Helmut-Schmidt-University, Hamburg, Germany, 3esz-partner Eber, Schwarzer, Zimmermann GbR, Kirchheim, Baden-Württemberg, Germany

ABSTRACT

The demand for accurate text mining tools to extract information of company based automotive warranty and goodwill (W&G) data is steadily increasing. The progress of the analytical competence of text mining methods for information extraction is among others based on the developments and insights of deep learning techniques applied in natural language processing (NLP). Directly applying NLP based architectures to automotive W&G text mining would wage to a significant performance loss due to different word distributions of general domain and W&G specific corpora. Therefore, labelled W&G training datasets are necessary to transform a general-domain language model in a specific-domain one to increase the performance in W&G text mining tasks. In this article, we describe a concept for adapting the generally pre-trained language model BERT [1] with the popular two-stage language model training approach in the automotive W&G context. For performance evaluation, we plan to use the common metrics recall, precision and F1-score.

KEYWORDS

Natural language processing, Domain-specific language models, BERT, Labelled domain-specific datasets, Automotive warranty and goodwill.


Analyzing and Personalizing the Learning Performance forSpecial Needs Students using Machine Learning and Data Analytics

Aaron Fei1 and Yu Sun2, 1St. Margaret’s Episcopal High School, 31641 La Novia Ave, San Juan Capistrano, CA 92675, 2California State Polytechnic University, Pomona, CA, 91768, Irvine, CA 92620

ABSTRACT

Recognizing the fact that autistic kids usually have troubles socially and focusing on academic studies, this research attempts to give a more insightful perspective on the ethnic way of helping autistic kids through technologies [4]. The core idea of this paper is to find a way of helping the autistic kids to maximize their potential instead of accommodating this society using assistive tools. Holding the responsibility of sharing the advantages in this society, this application is built to the end of using a general value to connect level of focus to level of reward. This solution is achieved by three steps: Designing a text box with different variables that evaluates focus level, calculating the level of reward based on achievements on the variables, and the game begins with different hardness according to the level of reward. The results show that the designed application increases the focus level of the kids and their willingness to communicate surprisingly.

KEYWORDS

Python, Computer Science, Autism.


An Application to Provide Translated Subtitles and Pictures for Youth English Learners using Speech-to-Text and NLP Techniques

Harry Cao1, Yu Sun2 and Ariel Jiang3, 1SuZou Industry Park Foreign Language School, Jiangsu, China, 2California State Polytechnic University, CA, 91768, 3Cornell Tech, Pomona, New York, NY

ABSTRACT

Currently, thousands of free K-12 educational videos exist online with the aim of trying to help young students learn outside of the typical scholastic environment. However, most of these videos are in English, so without subtitles it may be difficult for non-native English-speaking students to fully understand them. These students may need to spend time searching for translations and understanding content, which can distract them from grasping the important concepts within the videos. The state-ofthe- art of speech-to-text and NLP techniques might help this group digest the content of instructional videos more effectively. This paper proposes an application that uses speech-to-text, machine translation, and NLP techniques to generate translated subtitles and visual learning aids for viewers of instructional videos. This video application supports more than 20 languages. We applied our application to some popular online educational videos and conducted a qualitative evaluation of its approach and effectiveness. The results demonstrated that the application could successfully translate the English of the videos into the viewers’ native language(s), detect keywords, and display relevant images to further facilitate contextual understanding.

KEYWORDS

Educational videos, mobile applications, language translation applications.


The Challenges and Viability of using Blockchain for WSN Security

Muhammad R. Ahmed , Thirein Myo and Badar Al Baroomi, Military Technological College, Muscat, Oman

ABSTRACT

Wireless Sensor Network (WSN) comprises of cheap and multifunctional resources constrain nodes that communicate at a fair distances through wireless connections. It is open media and underpinned by an application scenario for data collecting and processing. It can be used for many exclusive applications range from military implementation inside the battlefield, environmental tracking, fitness quarter as well as emergency response of surveillance. With its nature and application scenario, protection of WSN had drawn an attention. It is understood that the sensor nodes are valuable to the attacks because of the construction nature of the sensor nodes and distributed network infrastructure. In order to ensure its capability especially in malicious environments, security mechanisms are essential. In this paper, we have discussed the challenges and the viability of the blockchain to implement in the WSN in order to protect WSN from the attacks.

KEYWORDS

Wireless Sensor Network, Security, challenges, blockchain.