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






    978-1-83558-309-8 (Print)

    978-1-83558-310-4 (Online)

    Published Date



    Mustafa İSTANBULLU, Cukurova University


  • Open Access | Article 2024-02-23 Doi: 10.54254/2755-2721/42/20230670

    An analysis of various deep learning-based target detection algorithms in the field of autonomous driving

    Target detection is a crucial research objective within the domain of computer vision, finding extensive applications in areas such as robotics, autonomous driving, industrial inspections, and various other fields. Based on the foundation of deep learning theory, this paper systematically summarizes the application and prospect of each type of target detection algorithm (based on regression and based on candidate region) on automatic driving, compares the advantages and disadvantages of the two types of algorithms, as well as the results of detecting traffic signals, traffic vehicles, and pedestrians, and focuses on the application scenarios as well as the comparison of advantages and disadvantages of each method. A systematic summary of the current development results is made. Among them, the most prominent target detection in the field of transportation is undoubtedly the algorithms of various branches of the YOLO series.

  • Open Access | Article 2024-02-23 Doi: 10.54254/2755-2721/42/20230671

    Research on the technology of intelligent vehicle sensor positioning system in autonomous driving

    In this comprehensive exploration of positioning and navigation technologies, we have delved into the intricacies of GPS (Global Positioning System), IMU (Inertial Measurement Unit), and VPS (Visual Positioning Systems) systems, shedding light on their unique attributes and applications. GPS, a global satellite-based system, offers precise positioning on a worldwide scale, although it encounters challenges in complex urban and environmental conditions. Its role in navigation and tracking is undeniable. IMU, characterized by accelerometers and gyroscopes, excels in delivering high-precision positioning over short durations, making it invaluable for applications in aviation, robotics, and virtual reality. However, it is susceptible to drift over time. Visual Positioning Systems (VPS), harnessing computer vision and visual sensors, provide remarkable sub-meter to centimeter-level accuracy when conditions are optimal. Their significance is particularly pronounced in indoor navigation, augmented reality, and robotics, although they may face challenges in less favorable environments. These technologies are not isolated but can synergize to enhance accuracy and reliability. GPS and IMU collaborate to compensate for signal disruptions, while GPS and VPS join forces to tackle urban complexities. IMU and VPS integration offer precise indoor navigation and augmented reality experiences, delivering impeccable positioning and orientation data. Ultimately, the choice of technology hinges on specific application requirements, encompassing accuracy, environmental considerations, cost factors, and the need for complementary systems. As these technologies advance, they hold the promise of revolutionizing navigation across various domains, from autonomous vehicles to immersive augmented reality environments.

  • Open Access | Article 2024-02-23 Doi: 10.54254/2755-2721/42/20230673

    The comprehensive performance analysis and improvement of flexible screen with its reality applications

    Flexible display technology and flexible screens are one of the key research topics today. The research focus of this paper is to study the basic concept of flexible screen, analyze the development and research process of it, explore the reasons why it can lead the display technology revolution, and the challenges and problems it is currently facing for further development. On this basis, the paper also makes a reliable prediction of the future development direction of the flexible screen, explores the solution ideas to deal with its shortcomings, and looks forward. Through the analysis of this study, the main advantages of flexible display technology are lightweight, portable, wearable. However, the mechanical strength of the flexible screen is also a big challenge, and it is the main solution point for its performance to be improved in the future. Flexible screens have been initially applied in smart phones, folding computers and other electronic devices, and more smart products with flexible display technology will be born in the future, deeply integrated with people’s lives. In this paper, the current situation and future of flexible screens are comprehensively explained.

  • Open Access | Article 2024-02-23 Doi: 10.54254/2755-2721/42/20230677

    Challenges and countermeasures in planning, building, and managing electric vehicle charging piles

    The widespread adoption of new energy vehicles, particularly electric vehicles (EVs), has created a significant demand for charging infrastructure globally. China, a key player in the EV market, has made substantial advancements in charging pile technology and infrastructure development. However, several critical challenges threaten the sustainability and efficiency of the EV charging ecosystem. This paper identifies and analyzes these challenges, including insufficient planning and construction of charging piles, increased demand for electric energy affecting power grids, high construction costs of fast-charging infrastructure, regional disparities in investment returns, and operational management issues. Moreover, it explores potential strategies to address these challenges. Proposed strategies include optimized planning for charging pile construction, the creation of integrated vehicle-charging-pile platforms, the development of distributed energy systems using blockchain technology, promoting recycling and reutilization of waste charging infrastructure, continuous financial subsidies, and enhanced follow-up operation supervision. Addressing these challenges through comprehensive strategies is essential for China and other nations to establish robust and sustainable EV charging infrastructure, ensuring it meets the growing demand for new energy vehicles in the years ahead. This effort will contribute to a cleaner and more sustainable future for the transportation sector.

  • Open Access | Article 2024-02-23 Doi: 10.54254/2755-2721/42/20230678

    The signal generator: A critical analysis of its basic principles, applications, and development

    The signal generator is a fundamental electronic device used in a wide range of applications, from communication systems to research fields. This paper provides a comprehensive overview of the basic principles, applications, and development of signal generators. Beginning with an introduction to the signal generator and its importance in various fields, the paper delves into its basic information, including the definition, types, basic components, and working principles. The applications of signal generators in communication, research, and software implementation are then discussed. The development of modern signal generators and their specifications are analyzed, followed by a comparison with previous technologies. The design of a signal generator based on FPGA is presented, including the working principles and advantages of FPGA, results and data, and the problems solved by FPGA. Finally, the paper concludes with key findings, limitations, and future issues.

  • Open Access | Article 2024-02-23 Doi: 10.54254/2755-2721/42/20230680

    Enhancing UAV safety with an innovative anti-collision cage: Design, testing, and future prospects

    The rapid evolution of Unmanned Aerial Vehicles (UAVs) or Unmanned Aircraft Systems (UAS) has revolutionized aviation across military and civilian domains with their pilotless flight capabilities. Despite their versatility, UAVs pose challenges in in-flight piloting precision, leading to potential mishaps. Addressing these concerns, this research introduces an innovative UAV Anti-Collision Cage designed to enhance drone safety. Constructed from C60-shaped carbon fiber rods and 3D-printed connectors, the cage resembles a football’s geometry, offering 360° protection. Experimental validations, including rolling, collision, and flying tests, were conducted to assess the cage’s performance. While the cage demonstrated resilience against minor impacts, significant impacts posed challenges. The study concludes with recommendations for future improvements, emphasizing geometric refinements, material choices, enhanced rolling abilities, sensor integration, and payload capacity. This research underscores the importance of safety mechanisms in UAV operations, paving the way for safer and more efficient drone operation in confined and complex environments.

  • Open Access | Article 2024-02-23 Doi: 10.54254/2755-2721/42/20230682

    Advancements and comparative analysis of high-voltage direct current transmission technologies

    This paper outlines the fundamental principles of high-voltage direct current (HVDC) transmission, elucidating its two primary variants: current-source converter (CSC) HVDC and voltage-source converter (VSC) HVDC. It also undertakes a comparative analysis with high-voltage alternating current (HVAC) technologies, focusing on aspects such as power transmission efficiency and cost-effectiveness, drawing upon prior research findings. Additionally, the paper underscores the critical role of circuit-breakers (CB) as essential components for controlling HVDC systems. HVDC technology plays a pivotal role in augmenting AC transmission systems, facilitating the integration of large-scale renewable energy sources, and enhancing the efficiency of expansive power grids over considerable distances. Its continued evolution and refinement are highly probable, given its indispensable role in the energy landscape.

  • Open Access | Article 2024-02-23 Doi: 10.54254/2755-2721/42/20230683

    Adverse Drug Reactions prediction by combining wide & deep learning and POLY2

    Accurate prediction of Adverse Drug Reactions (ADRs) holds immense importance in the field of clinical medicine and drug development. The requirement of accurate prediction spans various stages, ranging from drug design and clinical trials to marketing monitoring. The traditional ADR forecasting method has the disadvantage that it requires a lot of computing resources and is not suitable for large-scale forecasting. To address this issue, this study introduces the Wide & Deep model. This model combines the abilities of memorization and generalization to enhance the accuracy of ADR predictions. Additionally, we identify a shortcoming in the wide component of the traditional Wide & Deep model – the lack of nonlinear transformation. Therefore, we propose the inclusion of POLY2 in the Wide & Deep model to rectify this shortcoming. By incorporating POLY2, our aim is to retain the model’s memorization and generalization abilities, leverage the nonlinear relationship between features, and capture the interaction effect between drug chemical substructures for better model performance. To validate our proposed method, we conduct experiments on two datasets: the FDA Adverse Event Reporting System (FAERS) and PubChem. The evaluation metric utilized is the Area Under the Curve (AUC) score, which demonstrates that our method outperforms the original model. The results indicate that by combining POLY2 feature crosses with the Wide & Deep model, we have achieved significant improvements in the prediction of ADRs.

  • Open Access | Article 2024-02-23 Doi: 10.54254/2755-2721/42/20230684

    The research on the solutions of the energy consumption problem in WSN in medical field

    In the last few years, the Wireless Sensor Networks technology has been a hot topic, and depending on its self-organization feature, it has been utilized in many fields. The WSN is a technology that collects different kinds of data from different sensor nodes and processes them to a database center which will provide information to the users. But, because the main tool to collect data is the sensor nodes, the problem of energy consumption will be caused. The article will mainly give the exact reason why the energy consumption problem shows up and pay attention to different solutions to this problem. The solutions are very effective in solving these problems and can be gradually applied in many fields, especially in the medical field, which the article focuses on.

  • Open Access | Article 2024-02-23 Doi: 10.54254/2755-2721/42/20230685

    Research on the intersection of natural language processing and deep learning

    In the past ten years, Natural Language Processing (NLP) has made many surprising progress due to the rapid development of Deep Learning(DL) and further explored the possibility of future development. This article briefly introduces the NLP field, the basic structure of DL, and the impact of the combination of DL and NLP on the NLP field. Finally, it reviews the limitations of the two under the constraints of current science and technology and looks forward to the possibility and direction of their future development. Appropriately applying DL to NLP can indeed bring great progress to the core areas and applications of NLP. Still, at the same time, the development of NLP will also be limited by the shortcomings of DL. It is necessary to continuously optimize the DL model while taking advantage of the advantages of DL. The most critical factor to promote the development of DL and NLP in the future.

  • Open Access | Article 2024-02-23 Doi: 10.54254/2755-2721/42/20230687

    Comparative study of sequence-to-sequence models: From RNNs to transformers

    In this comprehensive exploration of sequence-to-sequence models in Natural Language Processing (NLP), we have traced the trajectory of their evolution and contributions. Starting from foundational Recurrent Neural Networks (RNNs) to the revolutionary capabilities of Long Short-Term Memory (LSTM), In this comprehensive exploration of sequence-to-sequence models in Natural Language Processing (NLP), we have meticulously traced the trajectory of their evolution and impactful contributions. From the foundational Recurrent Neural Networks (RNNs) to the revolutionary capabilities of Long Short-Term Memory (LSTM), as well as the transformative innovations brought forth by Transformers and BERT, this review eloquently highlights the monumental advancements that have fundamentally reshaped our understanding and generation of language. The crux of our comparative analysis lies in its ability to spotlight the distinctive strengths and limitations inherent in each model. Through an intricate examination, we uncover their nuanced applications across a diverse spectrum of NLP tasks. Particularly noteworthy is the pivotal role played by Transformers and the transformative Bidirectional Encoder Representations from Transformers (BERT). The paper concludes with a summary and outlook of the entire paper.

  • Open Access | Article 2024-02-23 Doi: 10.54254/2755-2721/42/20230688

    A concise analysis of low-rank adaptation

    Recent years the pre-trained language models have been proved to be a transformative technology within the domain of Natural Language Processing (NLP). From early word embeddings to modern transformer-based architectures, the success of models like BERT, GPT-3, and their variants has led to remarkable advancements in various NLP tasks. This paper is based on the Transformer model and explores and summarizes the application of the lightweight fine-tuning technique LoRA in pretrained language models, as well as improvements and derived technologies based on LoRA. Moreover, this paper categorizes these techniques into two main directions according to the advancements: enhancing training efficiency and improving training performance. Under these two major directions, several representative optimization and derived techniques are summarized and analyzed. Furthermore, this paper offers a perspective on the hot topics and future prospects of this research subject, and summarizes and proposes several directions that hold exploration value for the future, such as the possible avenues for further optimization and integration with other lightweight technologies.

  • Open Access | Article 2024-02-23 Doi: 10.54254/2755-2721/42/20230693

    The application of artificial intelligence in the game field

    With the rapid development of artificial intelligence technology, its application in the field of games is increasingly widespread. At present, the application of artificial intelligence in games has become a research hotspot. This article mainly explores the application of AI in various types of games such as first person shooter (FPS), Role playing Games (RPGs), Strategy, and analyzes their advantages and disadvantages based on the category of the game. Specifically, this article explores the application of AI in FPS games, focusing on how AI controls the behavior and strategies of enemies to provide players with challenging and realistic experiences. In the context of RPGs, the paper analyzes AI's impact on intelligent decision-making and interaction with non-playable characters (NPCs). Intelligent NPCs create a more authentic and immersive interaction between players and game characters. In the case of strategy games, AI enhances the strategic and challenging aspects, offering a more layered and dynamic gaming experience, and pushing players' decision-making abilities and strategic thinking. Additionally, the article discusses the limitations and challenges of AI in games. This paper summarizes and prospects the application of AI in the field of games.

  • Open Access | Article 2024-02-23 Doi: 10.54254/2755-2721/42/20230694

    The application and challenges of artificial intelligence in the fashion and luxury industry

    The concept of artificial intelligence (AI) involves the scientific and technological simulation of human intelligence, utilizing technologies such as deep learning, virtual reality, natural language processing, deep learning and more. Its core objective is to enable computers to process human- like abilities in perception, understanding, reasoning, learning, and decision-making. AI has achieved significant achievements and offers huge potential and applications across numerous areas, including the fashion and luxury industry. There, this article is to examine the application of AI technology in the fashion and luxury industry, specifically focusing on its utilization in personalized customer experience, market promotion and sales strategies, product design and innovation, as well as inventory and supply chain management. Additionally, this article aims to analyze the key existing issues and challenges brought about by these applications. This article a prospectus on the current focal points and future prospects of this research topic.

  • Open Access | Article 2024-02-23 Doi: 10.54254/2755-2721/42/20230695

    Current study on HCI based AR technology in the medical industry

    Augmented Reality (AR) is a new technology that based on Human-Computer Interaction (HCI) can combine our real life with 3D virtual information through real-time computing and multiple sensors. It simulates people's senses, such as hearing, vision, touch, etc., bringing things that cannot be seen in reality to people's eyes, which will bring people a feeling beyond reality. It has already appeared in our lives and has applications in many fields, such as architecture. Especially in the gaming field, AR, an innovative emerging technology, is widely loved by young people. With the development of technology, the forms of AR games have also become diverse. It has also developed rapidly in the medical field in recent years. This article will discuss the current situation of AR and its advantages in the medical industry based on Human-Computer Interaction (HCI) from three aspects: doctor diagnosis, patient rehabilitation, and medical education with examples of applications. Then, this article will discuss some of the drawbacks of using AR and the problems that will be encountered in future development, and propose solutions. Finally, analysis and predictions will be made for the future development of AR in the industry.

  • Open Access | Article 2024-02-23 Doi: 10.54254/2755-2721/42/20230696

    Human factors in game design: The importance of accessibility

    As the global gaming industry continues to grow, so does the need for game design to be accessible to people with different physical and cognitive abilities. Therefore, it is necessary to take accessibility design into consideration when developing a game. By using the interactive model of accessibility game design, this review explains why players with disabilities are unable to fully enjoy playing video games while playing. It then analyzes challenges and solutions related to visual, auditory, motor, and cognitive accessibility to gain a comprehensive understanding of how these elements interact in the game environment. Using case studies, this article lists a few games with accessibility in mind and illustrates the usability techniques they use. However, the process of achieving accessible gaming comes with its own challenges. This article analyzes the technical, economic, and creative barriers that developers often encounter, and provides a series of recommendations for game developers to address these challenges. By championing accessibility, the gaming industry can ensure that everyone, regardless of ability, can actively participate in video games.

  • Open Access | Article 2024-02-23 Doi: 10.54254/2755-2721/42/20230697

    Exploring the synergy of human-computer interaction in financial decision-making

    With the rapid development of technology, the combination and complementarity of artificial intelligence (AI) and human expertise in finance is becoming increasingly important. This research focuses on the synergistic effect of human-computer interaction (HCI) in financial decision-making, analyzes the operation mode of financial decision-making, lists examples of the combination of related fields and artificial intelligence technology, and focuses on showing that human-computer interaction technology enhances user experience and benefits in financial activities. Ability to invest in performance. Emerging features such as personalized financial services, intuitive user interfaces, and real-time feedback can dramatically improve user experience, research shows. Integrating artificial intelligence and professional knowledge can improve investment performance, assist risk management and decision support. The study emphasizes the importance of human-computer complementarity and balance, which has important reference value for financial institutions to adjust plans, policy makers to modify laws and regulations, and researchers to improve user experience and enhance investment results.

  • Open Access | Article 2024-02-23 Doi: 10.54254/2755-2721/42/20230698

    Current research on human-computer interaction based on VR in flight simulation driving

    With the rapid development of the aviation industry, the demand for pilots in the world is increasing day by day, and the flight simulator industry has received more and more attention and attention. However, due to the rapid upgrading of flight simulation technology, many problems arise. This review aims to deeply explore the application of human-computer interaction technology including VR technology in flight simulation driving, so as to reduce the driver's work burden during driving and improve the learning efficiency of flight simulation. Starting from virtual reality technology and human-computer interaction technology, this paper reviews the development and application of human-computer interaction technology based on virtual reality (VR) in the field of flight simulation and driving, and discusses the application of VR technology and human-computer interaction technology in the field of flight simulation and driving development and testing. Finally, this review summarizes the current application status and challenges of human-computer interaction technology in the field of flight simulation driving. Although human-computer interaction technologies such as VR have made remarkable progress in the field of flight simulation, there are still problems such as high cost of hardware equipment, operational stability, and fidelity that need to be solved. In the future, it is worth looking forward to the continuous innovation of VR-based human-computer interaction technology in flight simulation driving, bringing more development opportunities for flight training and the aviation industry.

  • Open Access | Article 2024-02-23 Doi: 10.54254/2755-2721/42/20230701

    Application of LSTM neural network based UAV attitude control in attitude estimation

    From now on, Unmanned Aerial Vehicle (UAV) technologies have become more mature, and UAV has been skillfully used in various regions under this mature technology. However, during UAV flight, they often encounter interference from external factors such as airflow, wind and temperature changes, which pose challenges to their stability and flight accuracy. This paper proposes an algorithm what is based on LSTM (Long, Short-Term Memory network), aiming that the flight attitude is affected when it is subject to external interference, while still ensuring the robustness of its flight performance in this state. In this paper, the optimization method of anti-jamming adaptive adjustment based on LSTM. In the meantime, a UAV dynamic model and neural network control based on dynamic modeling are established. Then article established the LSTM rule and designed the PID controller of LSTM. And to prove the effectiveness of the designed PID controller by pilot experiments with Matlab / simulated link simulation and flight experiments. Finally, step size response, autonomous tracking, robustness and anti-interference were tested by experimental simulations.

  • Open Access | Article 2024-02-23 Doi: 10.54254/2755-2721/42/20230769

    Integration and transformation: The impact and applications of artificial intelligence in the financial sector

    This paper explores the intersection of artificial intelligence (AI) and the financial sector, showcasing their transformative synergy. The integration of AI into finance has led to pioneering advancements like robo-advisors and AI-driven risk assessment methods. These innovations reshape investment strategies and risk management, ushering in a new era of financial operations. The study's focal question examines how AI recalibrates investment management, risk assessment, and fraud prevention in finance. The paper comprises sections on AI's impact on investment management, risk assessment, and fraud detection, detailing how robo-advisors provide personalized portfolio recommendations, AI aids risk identification and management, and transaction surveillance benefits from AI-powered fraud detection. Ethical, regulatory, and accountability considerations are discussed, reflecting AI's transformative influence on traditional financial paradigms. The application of AI in transaction detection and its role in enhancing portfolio recommendations, risk management, and automated trading are examined. While AI holds potential, its limitations such as data quality, model risks, and ethical concerns must be addressed. Regulatory oversight is crucial to ensure responsible AI implementation, fostering a balance between technological progress and financial stability. This paper underscores the intricate relationship between AI and finance, portraying AI's capacity to reshape the financial landscape and drive innovation

Copyright © 2023 EWA Publishing. Unless Otherwise Stated