Applied and Computational Engineering

- The Open Access Proceedings Series for Conferences

Volume Info.

  • Title

    Proceedings of the 2023 International Conference on Machine Learning and Automation

    Conference Date

    2023-10-18

    Website

    https://2023.confmla.org/

    Notes

     

    ISBN

    978-1-83558-295-4 (Print)

    978-1-83558-296-1 (Online)

    Published Date

    2024-02-04

    Editors

    Mustafa İSTANBULLU, Cukurova University

Articles

  • Open Access | Article 2024-02-04 Doi: 10.54254/2755-2721/35/20230350

    Review on natural language processing models

    Accessing information has grown simpler as a result of the internet's expanding use and the arrival of the big data era. Compared to traditional approaches, employing NLP for information condensation and amalgamation proves to be a highly effective method. This article focuses primarily on the sentiment analysis aspect of NLP, offering a comprehensive exploration of two deep learning models: BERT and CNN. It delves into the intricacies of their principles, analyzes their respective strengths and weaknesses, and proposes potential avenues for enhancement. By delving into these models, Researchers and practitioners can obtain a better understanding of sentiment analysis and its applications in diverse fields.

  • Open Access | Article 2024-02-04 Doi: 10.54254/2755-2721/35/20230351

    An overview of the emotional brain-computer interface

    This paper provides a comprehensive review of current research advances in emotional brain-computer interfaces. We introduce an approach to classifying emotions and highlight the two main datasets used for emotion recognition (DEAP and SEED). Subsequently, an extensive analysis of existing emotion recognition methods, both traditional and deep neural network methods, is presented. Finally, we explore the potential benefits of using transfer learning techniques to improve the performance of emotion recognition methods. Various deep neural network models exhibit redundant neural units and complexity, while facing challenges such as reduced computational power and reaction speed, increased storage requirements, and hardware dependency. The authors propose to integrate learned neural network pruning algorithms to simplify complex models, minimise hardware resource requirements without compromising accuracy, and improve operational capabilities with improved discriminants.

  • Open Access | Article 2024-02-04 Doi: 10.54254/2755-2721/35/20230353

    The application of artificial intelligence in aerospace engineering

    In recent years, there has been considerable interest in applying Artificial Intelligence (AI) in the field of aerospace engineering. However, the existing literature on this topic is not sufficiently comprehensive. This paper is purposed to solve this problem by providing a thorough analysis and overview of the current state of AI in aerospace engineering. The paper is divided into four sections. Firstly, the use of AI in autonomous navigation and flight control is explored, focusing on advanced algorithms and sensor technologies that enable highly autonomous and efficient aircraft navigation. Secondly, the application of AI in image recognition and computer vision is discussed, highlighting its significance in remote sensing and aerospace component quality inspection. The third section examines the integration of AI in unmanned aerial vehicles (UAV), covering the control system and the utilization of machine learning techniques for improved UAV capabilities. Lastly, the paper explores the impact of AI on data analysis and prediction in the aerospace industry, encompassing weather forecasting, resource allocation, and decision-making processes. Finally, this paper gives a general overview of the nowadays application of AI in aerospace engineering.

  • Open Access | Article 2024-02-04 Doi: 10.54254/2755-2721/35/20230354

    A research of the impact of ChatGPT on education

    The integration of AI language models, particularly ChatGPT, into higher education has sparked concerns about academic integrity and its impact on student learning experiences. This research aims to explore the applications, benefits, challenges, and future implications of ChatGPT in education, striving to achieve a balanced and beneficial integration of AI in higher education. The study reviews related works on ChatGPT, investigating its development, capabilities, and potential applications in education. Firstly, the paper emphasizes that ChatGPT changes teaching methods, enabling teachers to adopt more flexible and interactive approaches to education. Secondly, the paper highlights that ChatGPT can provide personalized learning experiences for students by generating customized teaching content based on their needs and offering real-time assistance and guidance, thereby enhancing learning effectiveness. However, the paper also acknowledges some potential challenges and issues, including concerns regarding plagiarism and privacy, as well as the possibility of biases and the generation of erroneous information. Addressing these issues requires technological improvements and the development of sound usage policies. The paper concludes by summarizing the findings and prospects of the research.

  • Open Access | Article 2024-02-04 Doi: 10.54254/2755-2721/35/20230355

    Application and existing problems of artificial intelligence technology in the agricultural field

    In recent years, the application of artificial intelligence technology in the field of agriculture has been rapidly developed. This paper summarizes the application of artificial intelligence in agriculture and divides it into two main directions: monitoring system and expert system. This paper analyzes the soil monitoring, pest monitoring, and plant growth detection of the monitoring system, the simple decision chain of the expert system, and the complex expert system combined with artificial intelligence technology. Utilizing sensor networks, image processing, and machine learning techniques, artificial intelligence enables real-time monitoring of soil parameters, automatic identification of pest and disease, analysis of plant growth status, and provision of tailored management recommendations. By employing rule-based expert systems, artificial intelligence assists farmers in making informed decisions. These applications have significantly advanced resource management optimization, pest control, precise growth monitoring, and intelligent decision-making in agriculture. At the end of the article, this paper summarizes the full text and looks forward to the future trend.

  • Open Access | Article 2024-02-04 Doi: 10.54254/2755-2721/35/20230358

    Application of matrix in signal processing

    Signal processing, a foundational discipline in modern technology, encompasses a diverse array of applications, ranging from audio and image processing to communication systems and medical imaging. This review investigates how matrix-based techniques are widely used to advance signal processing methodologies. In order to discretize continuous-time signals for digital processing, which occurs in the first section of the paper, matrices play a crucial role in signal sampling. A key principle, the Nyquist-Shannon Sampling Theorem, directs appropriate sampling rates to prevent aliasing, with matrices permitting effective signal representation. The effectiveness of matrix-based filtering methods for frequency modulation and noise reduction, such as convolution and correlation, is then investigated. By utilising matrix operations, these methods enable real-time signal processing. The Fourier Transform and Wavelet Transform are also featured in matrix-driven signal transformation, providing insights into frequency analysis and non-stationary signal characterization. By reducing noise components, matrix-based approaches, particularly Singular Value Decomposition (SVD) denoising, are essential for improving signal quality. Additionally, image compression employs SVD. Matrix-based compressive sensing revolutionises signal recovery from sparse data and results in data-efficient reconstruction. Signal processing has been transformed by matrix-based approaches, which have enabled previously unheard-of levels of efficiency, accuracy, and adaptability. The review highlights their significant influence on several signal processing fields.

  • Open Access | Article 2024-02-04 Doi: 10.54254/2755-2721/35/20230359

    An overview of 6G wireless systems

    With the demand of low latency communication explodes, the inherent limitations of the fifth generation communication is constantly exposed to the public. Such 5G shortcomings are spurring worldwide activities focused on defining the next-generation 6G wireless communication system. So the paper offers an overview of 6G wireless systems based on existing literature and statistical data. The paper concentrate on the driving forces in the development of 6G. In the meanwhile, the paper presents some potential application scenarios in the future. In the last section, the paper points out some challenges that are most likely to encounter in the coming development of 6G. Based on current prospect of 6G, it is likely that 6G features low latency and high efficiency and has 100 times better transmission capacity than 5G. The future applications are holographic telecommunications, mutual interaction of emotional thinking, and digital twinning. In conclusion, integrated with different technologies like AI,Terahertz Communications, and blockchain, 6G features many advantages and will permeate into people’s daily lives.

  • Open Access | Article 2024-02-04 Doi: 10.54254/2755-2721/35/20230361

    Deep learning for sentiment analysis on IMDB movie reviews using N-gram features

    In the rapidly evolving digital landscape, the synergy of deep learning techniques and abundant datasets has opened new frontiers in various domains. This research delves into the film industry, specifically harnessing the potential of the International Movie DataBase (IMDB) dataset for sentiment analysis. Through a deep learning paradigm, we embark on sentiment classification of movie reviews, discerning between positive and negative sentiments. By navigating data preprocessing and N-gram feature extraction, we engineer a deep learning model comprising embedding, global average pooling, and multi-layer dense architectures. The experimental results underscore the model's prowess in sentiment analysis, emphasizing its capacity to empower informed decision-making within the film industry.

  • Open Access | Article 2024-02-04 Doi: 10.54254/2755-2721/35/20230362

    A review of 3D reconstruction methods based on deep learning

    In computer vision, an important research area is three-dimensional reconstruction. Using computer technology to reconstruct three-dimensional models of objects has become an indispensable part of in-depth research in many fields. This thesis presents the development process of 3D reconstruction methods that use deep learning. Compared with traditional methods, the 3D reconstruction method based on deep learning has more flexible input and output and higher efficiency. This thesis classifies the methods by the type of 3D model representation and discusses different frameworks for 3D reconstruction based on deep learning. With the introduction of the method NeRF (Neural Radiance Field), the three-dimensional reconstruction work based on deep learning has got a great development. NeRF can achieve good results in a very short period of time in the face of various complex scenes. With the continuous improvement of NeRF by researchers, this method has achieved more amazing results. Finally, the existing problems in the field of 3D reconstruction, the causes of problems and possible solutions are analyzed. Finally, the future development trend and direction of this field are hypothesized and discussed.

  • Open Access | Article 2024-02-04 Doi: 10.54254/2755-2721/35/20230364

    Surgical robot navigation based on SLAM technology

    With the widespread application of surgical robots and the development of computer vision, SLAM-applicated surgery is receiving increasing attention. However, due to the unique surgical environment, SLAM faces some challenges. Two key issues will be discussed in this article: dynamic object detection and image segmentation, as well as scene reconstruction under data scarcity. Firstly, dynamic object detection and image segmentation is an important issue in SLAM applications. During the surgical process, doctors often use surgical instruments, which may partially or completely obscure the object, making it difficult to detect the target. Methods based on traditional feature matching may not be able to accurately detect dynamic targets perform image segmentation. Therefore, this article will combine semantic networks for analysis to improve the performance. In addition, scene reconstruction under data scarcity is another challenge in SLAM applications. Traditional SLAM methods typically rely on a large amount of feature points or map data. But in surgery, due to the complexity of occlusion and geometric structure, reliable data may not be easily obtained. This article will develop with the steps of reconstruction and analyze feasible methods that can improve the accuracy and stability of reconstruction. To conclude, this article will concentrate on these two issues, analyze recent papers, and ultimately summarize some feasible solutions, providing ideas and references for other researchers in this field.

  • Open Access | Article 2024-02-04 Doi: 10.54254/2755-2721/35/20230367

    Current study on multi-robot collaborative vision SLAM

    Simultaneous Localization and Mapping (SLAM) stands as a vital technology for automatic control of robots. The significance of vision-based multi-robot collaborative SLAM technology is noteworthy in this domain, because visual SLAM uses cameras as the main sensor, which offers the benefits of easy access to environmental information and convenient installation. And the multi-robot system has the advantages of high efficiency, high fault tolerance, and high precision, so the multi-robot system can work in a complex environment and ensure its mapping efficiency, these may be a challenge for a single robot. This paper introduces the principles and common methods of visual SLAM, as well as the main algorithms of multi-robot collaborative SLAM. This paper analyzed the main problems existing in the current multi-robot collaborative visual SLAM technology: multi-robot SLAM task allocation, map fusion and back-end optimization. Then this paper listed different solutions, and analyzed their advantages and disadvantages. In addition, this paper also introduces some future research prospects of multi-robot collaborative visual SLAM technology, aiming to provide a reference direction for subsequent research in related fields.

  • Open Access | Article 2024-02-04 Doi: 10.54254/2755-2721/35/20230368

    Current status and future prospects of SLAM technology in the field of blind navigation

    This comprehensive review paper explores the progressive integration of Simultaneous Localization and Mapping (SLAM) technology within the realm of blind navigation. The study delves into the current landscape of research and practical implementations where SLAM techniques are harnessed to empower visually impaired individuals in navigating their surroundings. The paper takes a focused approach by elucidating the advancements achieved through RGB-D-based SLAM navigation systems and the intriguing developments within the realm of LSD-SLAM-based navigation. A paramount facet of this exploration involves the design and deployment of interactive devices that bridge the gap between blind individuals and navigation systems. Notably, the paper examines the intricacies of these interaction interfaces, highlighting their pivotal role in enhancing the efficacy and user-friendliness of SLAM-driven navigation. Furthermore, this review critically assesses the existing limitations that persist within the current application of SLAM technology for blind navigation. The discussion encompasses challenges related to environmental diversity, real-time processing constraints, and the need for robustness in complex scenarios. By acknowledging these limitations, the paper paves the way for a comprehensive examination of potential avenues for refinement and enhancement. In conclusion, this paper serves as a comprehensive guide to the progressive incorporation of SLAM technology into blind navigation. It underscores the transformative potential of RGB-D and LSD-SLAM systems, underscores the significance of interaction interfaces, and underscores the evolving trajectory towards a more inclusive and efficient navigation solution for the visually impaired.

  • Open Access | Article 2024-02-04 Doi: 10.54254/2755-2721/35/20230370

    A game production based on “Angry Birds”

    In the past few years, the game industry has undergone many changes, and now it has improved from single player games to the era of online mobile games. Games that used to only run on computers now can also be used on smart phones. This time we improve the once popular game "Angry Birds", with the aim of making the content of the game more comprehensive and better attracting players. For example, we have added more kinds of birds to the game and optimized animation effects such as the injuries of pigs and the deaths of birds. In the programme and improvement of making game, we also referenced a lot of literature and videos on the internet, and the experimental results showed that it’s a success of game making because most people who experienced our “Angry Birds”gave it a positive review and high points.

  • Open Access | Article 2024-02-04 Doi: 10.54254/2755-2721/35/20230375

    The applications and prospects of intelligent services robots in medicine

    With the rapid growth of the ageing population and the increasing demand for medical services, the medical market is facing great challenges and opportunities. Intelligent service robots can provide various medical services, such as patient monitoring, drug distribution, medical record management, etc., which can improve medical efficiency, reduce the burden of medical staff, and have the advantage of 24-hour uninterrupted service. However, the application of intelligent service robots in the medical field still faces some challenges, such as technical limitations, legal and ethical issues. In addition, there are also differences in patient acceptance and demand for intelligent service robots. Based on the summary of intelligent medical treatment, this paper will introduce the application of intelligent service robots, study the application and prospect of intelligent service robots in medical treatment and the innovation of intelligent service robots in business models. Through literature review, SWOT analysis and data, the paper explains the wide application of intelligent service robots and their future opportunities and challenges.

  • Open Access | Article 2024-02-04 Doi: 10.54254/2755-2721/35/20230376

    The investigation of application related to ChatGPT in foreign language learning

    The integration of Chat Generative Pre-trained Transformer (ChatGPT) into the realm of education has garnered significant attention recently. Due to its capability of providing answers to inquiries, the feasibility of ChatGPT’s implementation in education has been examined. This review explores the potential benefits of ChatGPT in foreign language learning. Initially, different methods used to research the ChatGPT’s plausibility of improving language skills are shown. Furthermore, this review discusses some different application scenarios of ChatGPT, also presenting its drawbacks and limitations. Despite recognized concerns, the viability of ChatGPT as a valuable instrument for foreign language education remains substantiated. The technology exhibits promise in offering personalized and interactive language practice. While acknowledging potential pitfalls, the study underscores the need for further investigation to harness ChatGPT's potential optimally. By emphasizing ongoing research and development, this review envisions a future where ChatGPT contributes significantly to language education, underscoring the necessity for careful exploration of its evolving capabilities.

  • Open Access | Article 2024-02-04 Doi: 10.54254/2755-2721/35/20230377

    A comprehensive investigation for ChatGPT’s applications in education

    With the surge in popularity of Chat Generative Pre-trained Transformer (ChatGPT), an artificial intelligence technology, on a global scale, numerous industries have started to take notice of its potential applications in their specific sectors, including the field of education. This document presents a thorough examination of how ChatGPT is being used in the realm of education. The following piece outlines the approaches to integrating ChatGPT into education, viewed from three angles: Educational Assessment, Exercise Generation, and Personalized Learning. It also provides comprehensive guidelines aimed at both teachers and students. Utilizing ChatGPT in education allows for personalized one-on-one assistance to students, addressing challenges posed by uneven distribution of educational resources and individual differences among students. Current research on applying ChatGPT in education mostly revolves around designing prompts to elicit specific responses or using generated content for evaluating its subject-specific capabilities. Given that ChatGPT is a more versatile form of artificial intelligence not limited to any particular domain, the article suggests that future research should focus more on integrating ChatGPT into existing educational systems, ensuring its consistent performance in specific tasks. Furthermore, considering ChatGPT's possibility of generating imprecise information, it is necessary to explore how to fine-tune ChatGPT using specialized databases, enabling it to generate reliable content in professional subject areas.

  • Open Access | Article 2024-02-04 Doi: 10.54254/2755-2721/35/20230379

    Exploring the impact of artificial intelligence-based assistants in modern education: The case of ChatGPT

    The rapidly evolving digital landscape of the 21st century has marked the ascendancy of Artificial Intelligence (AI) as a potent transformative element across multifarious sectors, especially within the educational realm. This research undertakes a meticulous exploration of AI-integrated conversational models, emphasizing the pivotal role of ChatGPT, a brainchild of OpenAI. Delving into its developmental trajectory, this study maps the intricate transitions from ChatGPT's version 3.5 to its superior successor, version 4.0. This journey reveals marked enhancements, such as the model's adeptness at handling extensive textual data, and its uncanny ability to produce nuanced, human-like interactive responses. From empirical and qualitative evaluations, it was found that ChatGPT has demonstrated a profound impact in two main areas: expanding student engagement and advocating for a hyper-personalized learning paradigm. Findings suggest a compelling correlation between ChatGPT-integrated pedagogical methods and augmented student motivation, proactive engagement, and enriched academic achievements. Moreover, detailed case studies within specialized fields, notably medical education and legal studies, underscore ChatGPT's versatility in tailoring instructional content to niche disciplinary requirements. In synthesizing these insights, this research postulates an imminent educational future characterized by deep personalization, dynamic interactivity, and an enhanced learner-centric ethos. Such a vision places this study at the forefront of educational discourse, proffering invaluable guidance for educators, technologists, and policymakers endeavoring to maximize the benefits of AI-infused pedagogy.

  • Open Access | Article 2024-02-04 Doi: 10.54254/2755-2721/35/20230380

    ChatGPT - A new milestone in the field of education

    With the rapid development of artificial intelligence, natural language processing models like ChatGPT hold creative potential for applications in education. This study focuses on ChatGPT and explores its applications in the field of education. This research employs literature review and case analysis methods to systematically investigate the applications of ChatGPT in instructional assistance, personalized education, and writing support. By analyzing three cases involving ChatGPT's professional competence in medical exams, the construction of personalized learning systems, and writing support, the paper emphasizes ChatGPT's advantages in education, future development directions, as well as ethical and privacy concerns. The study finds that ChatGPT possesses strong semantic understanding and analytical capabilities. Within the context of general applicability, it can provide accurate answers to questions posed by users with certain specialized backgrounds. The paper not only addresses ChatGPT's role as a student's auxiliary tool but also explores collaborative models between ChatGPT and teachers. However, it's important to note that ChatGPT currently has limitations in terms of limited knowledge and inadequate emotional understanding. Additionally, in terms of ethics and privacy, considerations regarding information protection and moral aspects within the educational application of ChatGPT are crucial. In the future, it's worth further exploring specialized models for ChatGPT's tasks in both teacher and student roles, along with enhancing ChatGPT's emotional support capabilities.

  • Open Access | Article 2024-02-04 Doi: 10.54254/2755-2721/35/20230382

    Control of an intelligent car based on OpenMV perception

    This project presents an intelligent car system based on machine vision, which enables the car to perform a series of tasks through visual perception. The project utilizes an OpenMV camera and an Arduino microcontroller board, where the OpenMV camera captures and preprocesses images, and the processed data is then transmitted to the Arduino for further processing and recognition. In addition, the project incorporates the GoogleNet network for training and classifying the preprocessed images. The network is used to recognize common objects, and the model is optimized and tested accordingly. The results demonstrate a high accuracy in image recognition, making it applicable to visual perception in vehicles.

  • Open Access | Article 2024-02-04 Doi: 10.54254/2755-2721/35/20230384

    The application of optical fiber in network communication

    In recent years, optical fiber communication has gained widespread use in daily life due to its robust communication and transmission capabilities, strong confidentiality, anti-interference properties, and the availability of convenient and accessible materials. This technology has made remarkable strides in network communication and integrated device design, among other areas. This article will commence by discussing the fundamental structure of optical fibers and illustrating the propagation of optical signals within them. It will then analyze the benefits, such as higher transmission rates, wider frequency bands, and the low loss characteristics of optical fibers. Subsequently, the article will enumerate two of the most commonly utilized Optical Fiber Communication (OFC) technologies: Wavelength Division Multiplexing (WDM) technology and optical amplifier technology. It will summarize their principles and strengths. Finally, the article will showcase the practical applications of optical fiber communication, particularly focusing on its role in 5G mobile communication, military operations, and radio and television communication.

Copyright © 2023 EWA Publishing. Unless Otherwise Stated