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

    978-1-83558-301-2 (Print)

    978-1-83558-302-9 (Online)

    Published Date

    2024-02-07

    Editors

    Mustafa İSTANBULLU, Cukurova University

Articles

  • Open Access | Article 2024-02-07 Doi: 10.54254/2755-2721/38/20230521

    A review of virtual reality technology

    Virtual reality technology (VR) is a computer simulation system that can create and experience virtual worlds. It utilizes computers to generate a simulated environment, allowing users to immerse themselves in the environment. Virtual reality technology has been one of the fastest-developing information technologies in recent years. It, along with multimedia technology and network technology, is known as the three most promising computer technologies. As an emerging science and technology, it has been less than 100 years since its emergence, and there is still great room for development in its theory and practical application. This article focuses on virtual reality technology and its applications, based on existing literature and statistical data. The main content includes its advantages, characteristics, technical composition, development history, and applications in different directions. The development process of virtual reality technology is not long, but it has unique advantages and technologies specifically serving it. It does not require much physical participation and has positive implications in applications such as education, entertainment, and healthcare. Its future direction will be towards replacing real hardware with virtual hardware, becoming more practical, intelligent, and refined.

  • Open Access | Article 2024-02-07 Doi: 10.54254/2755-2721/38/20230522

    Sentiment analysis of hotel comments based on LSTM and GRU

    Sentiment analysis, which tries to examine the emotional information in the provided text data, has always been a popular topic in the community of natural language processing. Sentiment analysis is currently used in many different contexts, including e-commerce platforms, social media platforms, public opinion platforms, and chatbots. These applications are crucial to the advancement of society and the domestic economy. However, due to the personalization of text data, especially comments, and the presence of acronyms, it is a challenging problem to obtain accurate sentiment information from large and complex unstructured text data. This study presents a comparative examination of various text sentiment analysis approaches, including LSTM, CNN, and GRU. These methods are employed to evaluate their respective performance on sentiment analysis tasks, specifically using a dataset of hotel reviews for training the models. The method presented in this research has been extensively validated through numerous experimental results, affirming its efficacy and its potential to offer novel perspectives for the practical implementation of sentiment analysis.

  • Open Access | Article 2024-02-07 Doi: 10.54254/2755-2721/38/20230524

    Movie sentiment analysis based on Long Short-Term Memory Network

    An important task in the study of Natural Language Processing (NLP) is the analysis of movie reviews. It finishes the task of classifying movie review texts into sentiment, such as positive, negative or neutral sentiment. Previous works mainly follow the pipeline of LSTM (Long Short-Term Memory Network). The network model is a variant of Recurrent Neural Network (RNN) and particularly suitable for processing natural language texts. Though existing LSTM-based works have improved the performance significantly, we argue that most of them deal with the problem of analyzing the sentiment of movie reviews while ignore analyze the model performance in different application scenarios, such as different lengths of the reviews and the frequency of sentiment adverbs in the reviews. To alleviate the above issue, in this paper, we constructed a simple LSTM model containing an embedding layer, a batch normalization layer, a dropout layer, a one-dimensional convolutional layer, a maximal pooling layer, a bi-directional LSTM layer and a fully connected layer. We used the existing IMDB movie review dataset to train the model, and selected two research scenarios of movie review length and frequency of occurrence of sentiment adverbs to test the model, respectively. From the experimental results, we proposed a model for the scenarios in which the LSTM model handles the problem of sentiment analysis with respect to the dataset construction, model stability and generalization ability, text fragment processing, data preprocessing and feature extraction, model optimization and improvement.

  • Open Access | Article 2024-02-07 Doi: 10.54254/2755-2721/38/20230525

    Sentiment analysis based on BiLSTM with attention mechanism on Chinese comment with stickers

    As the Internet is progressively becoming larger and more intricate, more and more users of various social media choose to post their comments to express their opinions and thinking on those platforms. Analyzing the emotions contained in user comments holds great business value, helping to accurately perceive user consumption habits and improve user service levels. However, the use of emoticons and stickers in comments has increased dramatically in recent years, which brings new challenges to text sentiment analysis based on natural language processing. In this paper, in order to alleviate the above problems, we propose a method for analyzing the sentiment of Chinese comments based on the attention mechanism and BiLSTM. Specifically, we partitioned the original dataset from the Weibo platform according to the number and type of emoticons in the comments. By analyzing the actual data, the specific features of emojis that affect the performance of sentiment analysis are identified, and corresponding explanations are given. In addition, a hypothesis is proposed to quantify the impact of emoticons on model effectiveness. All the results demonstrate the effectiveness of our proposed method.

  • Open Access | Article 2024-02-07 Doi: 10.54254/2755-2721/38/20230526

    The distinguish between cats and dogs based on Detectron2 for automatic feeding

    With the rapid growth of urbanization, the problem of stray animals on the streets is particularly prominent, especially the shortage of food for cats and dogs. This study introduces an automatic feeding system based on the Detectron2 deep learning framework, aiming to accurately identify and provide suitable food for these stray animals. Through training using Detectron2 with a large amount of image data, the system shows extremely high recognition accuracy in single-object images. When dealing with multi-object images, Detectron2 can generate independent recognition frames for each target and make corresponding feeding decisions. Despite the outstanding performance of the model, its potential uncertainties and errors still need to be considered. This research not only offers a practical solution to meet the basic needs of stray animals but also provides a new perspective for urban management and animal welfare. By combining technology with social responsibility, this innovative solution opens up a new path for solving the stray animal problem in cities, with broad application prospects and profound social significance.

  • Open Access | Article 2024-02-07 Doi: 10.54254/2755-2721/38/20230527

    The design of library database management system based on MySQL

    Database-manage-system has become a modern management among different enterprises. The enterprise’s data need managed by a well-performed system. Also, the database is an essential need for a modern library. In this case, more and more people start using different way to build the system which is suitable for the enterprises. The library system has become a famous one which need a large database system to encounter the huge amount of data. In this article, it shows the usage of database-manage-system in a local library and how does the system work. Also, the introduction of the function of MySQL usage in this application. Finally, after the test of the data and running the programme in MySQL, the database-manage-system realize the function of list the book, check of availability, make reservations and store different users’ status. In this essay, through the test of data and the code, a database-manage-system is designed. This database-manage-system could complete basic function which contain check status, make appointments and locate books.

  • Open Access | Article 2024-02-07 Doi: 10.54254/2755-2721/38/20230528

    An analysis of the applications of mechatronics in intelligent manufacturing

    With the continuous development of the social economy, countries increasingly pay more attention to mechatronics and put forward various relevant policies for the actual situation of mechatronics to promote mechatronics and achieve sustainable development. However, from the current actual situation of mechatronics, due to the influence of various external factors, its degree of development cannot meet the requirements of modern social development; therefore, the application of advanced intelligent technology to mechatronics design is inevitable. Based on this, this paper expounds the intelligent manufacturing technology and mechatronics system overview as the basis for analysing the actual situation of the development of modern mechanical and electrical equipment digital design, then analyses the advantages of intelligent technology from different aspects and applies them to the daily mechatronics design to bring huge economic benefits to enterprises, and concludes that the development level of social productivity in the future is closely related to the integration level of mechatronics and intelligent manufacturing.

  • Open Access | Article 2024-02-07 Doi: 10.54254/2755-2721/38/20230529

    The rise of educational robots: A review of classroom applications

    As critical mechanics and artificial intelligence have improved at a fast pace, the application of robots has become a trending research domain. Robot has a golden opportunity to be a game-changer in the education domain. A large group of studies have noted that robots can offer a promising learning design in the classroom to help students boost their studying. This article analysed papers published in the science database between 2012 and 2022 relating to robot settings and tried to conduct a review on robots used in the classroom. The review focuses on features in these studies, including the age of participants, duration of the study, field of discipline, interaction method, and studying strategies, identifying roles of robots and evaluating the performance of students. This study also indicates shortages in robot deployment and provides several suggestions for future research.

  • Open Access | Article 2024-02-07 Doi: 10.54254/2755-2721/38/20230530

    Design and implementation of computer network security detection and control system

    With the widespread application of computer network technology, computer network security defense capability has become a focus of attention in various industries. The extensive use of computer information systems in various sectors has significantly improved work efficiency but has also introduced security risks and management issues. The deployment of network security detection and control systems allows for effective security monitoring and management of computer operations and real-time network information. This paper presents a computer network security detection and control system based on human-computer interaction, which enables users to handle daily key business processes. The work principles and overall architecture of the network security detection and control system are analyzed and demonstrated. It offers functions such as filtering options, address rules, network security detection, network unreachability, overall traffic analysis, subnet definition, fault diagnosis, and security analysis. Testing and analysis indicate that the system’s design achieves the intended goals. In the application of network security features, it can effectively combine various forces to enhance the quality and efficiency of network security, making it widely applicable in various industry units.

  • Open Access | Article 2024-02-07 Doi: 10.54254/2755-2721/38/20230532

    Research on unsupervised image retrieval methods based on contrastive learning

    In the convergence of fashion and artificial intelligence (AI), significant strides have been made in areas such as clothing recognition, retrieval, and classification, enabled by advanced AI technologies and expansive annotated datasets. As the AI in Fashion market continues to surge, the future of the fashion industry promises to be redefined by intelligent, efficient, and more accessible solutions. Image retrieval, one of the important parts in AI, has experienced remarkable growth, empowered by advanced algorithms and vast annotated datasets, making it a crucial component in various domains such as digital libraries, online marketing. Therefore, this report mainly provides an extensive review of image retrieval methods and the emerging paradigm of contrastive learning, underscoring their relevance and applications in the realm of artificial intelligence. This paper primarily reviews the technologies in the amalgamation of the image retrieval field and contrastive learning. It elucidates the history and progression of image retrieval, offers a methodical analysis of the two primary approaches—text-based image retrieval and content-based image retrieval—and examines how contrastive learning is employed in image retrieval systems.

  • Open Access | Article 2024-02-07 Doi: 10.54254/2755-2721/38/20230533

    Deep learning in multiplayer online battle arena games

    Multiplayer Online Battle Arena games, known as MOBA in abbreviation, are developing rapidly, and more and more new players are growing interests to it. But some parts of these games are quite complicate for those beginners, such as how to pick appropriate champions, how to choose suitable items for purchasing, what is the win rate for current game session and how to make correct strategy decisions. This paper summarized some works, that can help players to solve those complicate parts and understand the game well, using machine learning and deep learning models. These works have all proved their feasibility according to either their result comparing with other baseline methods, or simulating some game sessions played by or against AI using their champion picking, item purchasing and strategy making suggestions. There are also some limitations of these works and some improvements of using machine learning and deep learning in MOBA game industry mentioned in this paper.

  • Open Access | Article 2024-02-07 Doi: 10.54254/2755-2721/38/20230534

    Dense-connected Stacked Hourglass Networks for Human Pose Estimation

    The main idea of this project is to try to improve the accuracy of human pose estimation in previous models. The new model proposed is based on the Stacked Hourglass Network with new structures added. The new structures ensured that the preservation of features of the original data by adding connections across the network, which we refer to as a “Dense-connected Stacked Hourglass” network, and we expected the new structure and the feature preserved could be helpful in the later stages because the Stacked Hourglass network pools down to very low resolution, during which important information may be lost. The data sets used in the project are MPII Human Pose and FLIC (Frames Labelled in Cinema). The final results show that the proposed architecture is able to improve the estimation accuracy to certain extend in identifying head, wrist and hip, while further studies on the architecture and improvements are still required.

  • Open Access | Article 2024-02-07 Doi: 10.54254/2755-2721/38/20230536

    Application and challenges of informer model in financial time series prediction: A review

    Time series prediction has shown excellent performance in various fields in recent years, such as stock prices, weather changes, traffic flow, and other fields. Its application development is becoming increasingly mature, and long series time prediction area of research has gained significant prominence. The excellent performance of deep learning in many models has unleashed the potential and possibility of time series prediction to a certain extent. Based on the above reasons, applying deep learning to the field of time series prediction has become a meaningful research. Therefore, the purpose of this article is to analyze the Informer algorithm model in the area of financial time series prediction and provide a comprehensive literature review on the implementation of Informer models in financial time series. Attempting to investigate and analyze the problems and challenges that Informer models may encounter in the area of financial time series prediction, with the hope of providing innovative inspiration and motivating new forms of knowledge for future workers.

  • Open Access | Article 2024-02-07 Doi: 10.54254/2755-2721/38/20230537

    Review of machine learning in traffic accident detection

    With the development and wide application of New Energy Vehicles (NEVs) in the past decade, the chip and power supply method for Machine Learning (ML) intervention provides a good hardware premise, while the 5G technology under the auspices of large-scale rapid data processing is also a prerequisite for the development of Auto Driving, moreover the current traffic accident prediction algorithms have a more critical role in the development of the field of Auto Driving. In this paper, I will consider these aspects as shown below. On the one hand, Anticipation of Traffic Accidents (ATAs) can be well used in today’s Autonomous Driving has not yet been popularized, the existing warning information into the corresponding automated driving intervention signals to achieve the possibility of improving the safety of automated driving to increase the possibility of future use of automated driving. On the other hand, the use of ML in the ATAs can be better in the complex traffic environment in a timely manner for the accident warning to achieve a certain degree of reduction in the rate of traffic accidents, in order to optimize the traffic and reduce the economic loss of people. At the same time, in this review, we will propose the combination of data from in-vehicle cameras and road surveillance cameras to analyze the current development of autonomous driving.

  • Open Access | Article 2024-02-07 Doi: 10.54254/2755-2721/38/20230538

    Chebyshev filter and Butterworth filters: Comparison and applications in different cases

    This study focuses on the filter selection problem in signal processing and wireless communication applications. Specifically, addressed two different filter selection problems: the Chebyshev filter and the Butterworth filter. Using MATLAB, in order to design and model these two types of filters. The performance, frequency response, transition band width, filter order, design complexity and target application of Chebyshev filter and Butterworth filter under different parameters are analyzed and compared. The selection of the two filters under different conditions and the reasons for choosing them are discussed. The Chebyshev filter is suited for applications that call for a high frequency response, and Chebyshev filters provide a steeper roll-down slope, which can suppress high-frequency noise and interference signals, according to the test results, it is widely used in communication systems. On the other hand, the Butterworth filter is more suitable for applications that require a flat passband and a wide stopband, such as audio systems.

  • Open Access | Article 2024-02-07 Doi: 10.54254/2755-2721/38/20230539

    Design and implementation of a preset operational amplifier based on basic digital and analog hybrid circuit

    In the vast landscape of electronic engineering, the indispensable roles of both analog and digital circuits are unequivocally recognized. Analog circuits, with their foundational principles, are extensively harnessed in areas encompassing audio, video, power systems, and particularly, amplifiers. Conversely, digital circuits, integral to modern-day technological advancements, are dominantly present in computing platforms, telecommunication systems, control mechanisms, and data storage infrastructures. Amplifiers, a cornerstone in analog circuit designs, principally focus on magnifying the amplitude of input signals, whether it be in terms of voltage or current. This amplification process hinges on the strategic configuration of electronic elements such as transistors, resistors, and capacitors. This paper endeavors to marry the attributes of digital and analog circuits. Through the adept utilization of fundamental electronic components, an innovative amplifier design capable of preset amplification ratios is birthed. The practicality and efficacy of this amplifier are rigorously validated via its hands-on assembly and experimental testing in a laboratory setting. Results consistently underscore the amplifier’s adeptness in delivering precise signal amplification, conforming to its predetermined ratios. Such a design, rooted in its simplicity yet offering profound versatility, beckons further exploration. It stands as a beacon for potential future adaptions, tailored to suit a gamut of applications, and is poised to seamlessly dovetail into more sophisticated circuit systems.

  • Open Access | Article 2024-02-07 Doi: 10.54254/2755-2721/38/20230540

    A small mobile communication system for communication in remote areas

    In the age of the Internet, mobile communications have become an indispensable part of our everyday lives, let us connect with other people, get information, and participate in various activities but the communication in remote areas is still difficult due to terrain constraints and other factors. Although communication in remote areas is very important and challenging, there are also many measures and real cases exist. The article describes a small mobile communication system that can be used in remote areas and analyses its characteristics. First, the coverage area is hexagonal base stations, and I draw the distribution map of base stations and users, and then design a switching criterion to determine when a user changes the service base station during the movement. Second, the distribution is compared with the distribution of different types of base stations to study the difference in their system capacity and the effect of the number of antennas on them. to determine who is more efficient.

  • Open Access | Article 2024-02-07 Doi: 10.54254/2755-2721/38/20230541

    Data privacy and protection in communication networks

    This exhaustive study examines the crucial topic of protecting user data and maintaining privacy within the complex realm of communication networks. It meticulously analyzes the multifarious dimensions of data privacy, including its conceptual foundations, the significant dangers resulting from intrusions, and the fundamental principles of privacy protection. The investigation encompasses a comprehensive evaluation of concrete strategies such as data anonymization, de-identification techniques, granular data sharing controls, and the use of cryptography. Real-world case studies attest to the efficacy of these methods, providing tangible evidence of their practical viability. The article predicts the evolving landscape of privacy protection, which will be driven by the rapid advancement of technologies and the adaptive responses required by regulations and social responsibilities. The collaborative engagement of individuals, corporations, and governing bodies emerges as crucial in charting the future of data privacy, highlighting the inherent interplay between technological innovations, legal frameworks, and proactive user participation.

  • Open Access | Article 2024-02-07 Doi: 10.54254/2755-2721/38/20230544

    Optimized 3D reconstruction in nearshore underwater environments: A cost-effective pre-processing strategy for Neural Radiance Fields implementation

    Nearshore oceans, teeming with diverse benthic ecosystems, continue to be a focal point for marine research. While 2D visual representations have been the mainstay in this area, the intricate, multi-dimensional nature of the seafloor ecosystems underscores the need for 3D modeling to capture their full essence. This study unveils a novel approach tailored for static image processing and 3D modeling through Neural Radiance Fields (NeRF), with a particular emphasis on the refined instantNGP variant. A meticulously crafted pipeline is employed, centered on neutralizing the visual impediments brought about by the interplay of light and seawater in underwater imaging. This refined pre-processing strategy ensures that images are primed for a seamless transition to NeRF-based 3D reconstruction, all the while conserving computational resources. The refined image processing techniques rectify underwater color discrepancies, notably the prevalent blue-green hue resulting from unique lighting conditions. Moreover, the system's ability to identify and excise seawater boundaries guarantees that the 3D models remain singularly focused on the richness of the seafloor ecosystems. Remarkably, achieving this does not demand vast datasets or exorbitant computational prowess, positioning it as an ideal fit for processing images from nearshore regions. As a more resource-friendly and efficient counterpart to existing methodologies, this study furnishes marine ecologists with a powerful instrument for RGB-centric 3D renderings of nearshore terrains. Nonetheless, for broader applicability in diverse marine settings, fusing this approach with neural networks could prove invaluable.

  • Open Access | Article 2024-02-07 Doi: 10.54254/2755-2721/38/20230545

    Practice and application of artificial intelligence technologies in the digital economy

    With the continuous development of the digital economy, artificial intelligence technology is becoming more and more widely used in various fields. This paper mainly discusses the practice and application of artificial intelligence technology in the digital economy, including its application field, technical principle, implementation method, and future development trends. Through analyzing the current application status and existing problems of artificial intelligence technology in the digital economy, this paper puts forward some improvement measures and development suggestions, aiming to provide a reference for promoting the better application of artificial intelligence technology in the digital economy.

Copyright © 2023 EWA Publishing. Unless Otherwise Stated