Applied and Computational Engineering

- The Open Access Proceedings Series for Conferences

Volume Info.

  • Title

    Proceedings of the 4th International Conference on Signal Processing and Machine Learning

    Conference Date

    2024-01-15

    Website

    https://www.confspml.org/

    Notes

     

    ISBN

    978-1-83558-336-4 (Print)

    978-1-83558-338-8 (Online)

    Published Date

    2024-03-19

    Editors

    Marwan Omar, Illinois Institute of Technology

Articles

  • Open Access | Article 2024-03-19 Doi: 10.54254/2755-2721/48/20241057

    A new branch of fake review detection research -- A review of fake review detection in the Chinese film industry in the post-epidemic era

    In the post-pandemic era, Chinese moviegoers increasingly rely on online movie reviews, but fake reviews by spreaders can mislead moviegoers to make wrong decisions. Fake review detection has been developed to a certain extent in China. However, there is a lack of application research in the film industry. This paper summarizes some of the more advanced fake review detection methods in China in the post-epidemic era from the perspectives of review text detection and reviewer detection, introduces their indicators, feature selection methods, and training methods, and further discusses the specific steps of these methods in the detection of fake movie reviews combined with the characteristics of fake movie reviews. The research of this paper can bring guidance for the future detection of fake movie reviews, and provide a decision-making basis for consumers and investors.

  • Open Access | Article 2024-03-19 Doi: 10.54254/2755-2721/48/20241060

    The impact of artificial intelligence on human resource management systems - Applications and risks

    Organizations’ traditional human resource management model has been impacted by the ongoing optimization and advancement of artificial intelligence skills and technology, and the broadening of its application scope. The impact of artificial intelligence (AI) systems on employee recruitment, human resources allocations, and talent management is significant. This paper examines the interplay among AI, data applications, human resource management (HRM) systems and the resultant effects. It will examine the significance of effectively managing the deployment of AI systems, as existing literature defines. This study examines the effects of artificial intelligence AI technology on the effectiveness of company administration compared to traditional human resource management systems (HRMS). Several recommendations are offered to enhance the reformation and optimization of the organization’s human resources (HR) division. The research findings indicate that incorporating the new system in conjunction with human involvement can significantly enhance the efficiency of employee recruitment, allocation of human resources, and management of talent within the firm. There was an improvement observed in both employee happiness and productivity elements.

  • Open Access | Article 2024-03-19 Doi: 10.54254/2755-2721/48/20241072

    Reinforcement learning in autonomous driving

    Automatic driving technology has become a highly researched field in recent years, aiming to achieve vehicle driving without human intervention. In this regard, reinforcement learning techniques have played a crucial role. This study discusses and analyses the use of reinforcement learning in automatic driving methods. The research begins with the process of reinforcement learning. In the architectural framework, there is a special emphasis on designing innovative reward functions to encourage safe and socially acceptable driving behaviour, while considering uncertainty factors through advanced Bayesian neural networks. This paper primarily focuses on aspects such as scene understanding, localization and mapping, planning and driving strategies, and control. Furthermore, the paper analyses the key elements of automatic driving and delves into the specific complexities associated with each element. It highlights the utilization of reinforcement learning within the realm of autonomous driving. Reinforcement learning assists autonomous vehicles in understanding the surrounding environment, accurately identifying paths, making intelligent driving decisions, and safely controlling the vehicle. Reinforcement learning especially working with deep learning plays a crucial role in realizing and continuously improving automatic driving. Finally, the paper concludes with a summary and outlook on the entire study.

  • Open Access | Article 2024-03-19 Doi: 10.54254/2755-2721/48/20241087

    Exploring the influence of lifestyle on sleep health based on deep learning

    Sleep plays a crucial role in maintaining overall health. However, various lifestyle factors significantly influence sleep quality and duration. Understanding the relationship between lifestyle choices and sleep health is crucial for individuals seeking to improve their sleep patterns. The purpose of this study is to provide valuable insights into the causes and effects of sleep disorders in order to help individuals make informed decisions to optimize their sleep health. This article implements the CatBoost gradient algorithm for predictive modeling. Among various models including K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Xtreme Gradient Boosting (XGBoost), Gradient Boosting Decision Tree (GBDT), Random Forest (RF), Decision Tree (DT), Logistic Regression (LR), Deep Neural Network (DNN), CatBoost shows better overall performance with an accuracy of 0.93, an Fl-score of 0.925, and a recall of 0.95. Through data analysis, Blood-pressure-Systolic, Blood-Pressure-Diastolic, and Stress Level are found to have the greatest impact on the model's output.

  • Open Access | Article 2024-03-19 Doi: 10.54254/2755-2721/48/20241095

    The power of generative AI in cybersecurity: Opportunities and challenges

    This paper undertakes a comprehensive exploration of the potential and challenges presented by Generative Artificial Intelligence, with particular emphasis on the GPT models, in the field of cybersecurity. Through a meticulous examination of existing literature and pertinent case studies, the paper evaluates the capabilities of these models in the detection and rectification of vulnerabilities, as well as in identifying malicious code. It also highlights the pivotal role of generative AI in enhancing honeypot technology, which has shown promising results in proactive threat detection. While underscoring the significant advantages of utilizing generative AI in bolstering cybersecurity measures, the paper does not shy away from shedding light on the accompanying security exposures. These range from traditional threats like vulnerabilities and privacy breaches to novel dangers such as jailbreaking, prompt injection, and prompt leakage that are associated with the deployment of these AI models. The overarching objective of this paper is to contribute to the ongoing dialogue about the integration of advanced AI technologies into cybersecurity strategies while emphasizing the importance of vigilance against potential misuse. The paper concludes with a call for continued research and development to ensure a safer and more secure cyberspace for all.

  • Open Access | Article 2024-03-19 Doi: 10.54254/2755-2721/48/20241114

    Exploring the influence of generator channel number on the quality of anime-style portrait generation based on DCGAN

    In the realm of contemporary image synthesis, this research delves into a crucial objective: exploring the connection between the quantity of generator channels and the production of anime-style portraits through Deep Convolutional Generative Adversarial Networks (DCGAN). Employing an extensive dataset of anime faces encompassing diverse artistic styles, this study systematically examines the nuanced interplay between architectural parameters and the fidelity and intricacy of the generated images. By employing the Frechet Inception Distance (FID) as a metric for image quality, this investigation contributes significantly to the field by enhancing the understanding of how the number of generator channels impacts the ultimate quality of anime-style portraits. The DCGAN framework, and in particular its variants, is the backbone of this investigation. The generator and discriminator components are involved in adversarial training, a competitive process that improves image quality through iterations. The findings reveal a non-linear relationship between the number of generator channels and image quality. While increasing the number of channels initially improves image quality and decreases the FID value, exceeding the optimal threshold leads to diminishing returns and image quality degradation. The intricate interplay between structure selection and image quality is further confirmed by the dynamics of the generator and discriminator loss functions. By elucidating the trade-off between complexity and image fidelity, this study contributes to the advancement of image synthesis techniques and encourages future exploration of architectural nuances in the field of artistic image generation.

  • Open Access | Article 2024-03-19 Doi: 10.54254/2755-2721/48/20241132

    Design, development, and deployment of decentralized applications

    Beginning with a comprehensive definition of Decentralized Applications (DApps) and their developmental trajectory, this treatise delves into their inception around 2010. It is intriguing to note that by 2020, DApps had already found preliminary applications in diverse sectors, ranging from finance to archaeology. Yet, there remains vast untapped potential awaiting exploration and refinement within the realm of DApps. The discourse then navigates the intricate web of DApps' system architecture, illuminating the cardinal aspects of their design, evolution, and eventual deployment. Herein, the essence of systematic planning during the design phase is underscored, underpinning its pivotal role in shaping the efficacy of the application. Further shedding light on DApps' expansive utility, the paper underscores their transformative influence in areas such as authentication systems and real-time operational control. However, the journey of DApps is not without its challenges. The document elucidates the complexities associated with crafting robust smart contracts, mitigating scalability concerns, and nurturing user acceptance and integration. In light of these hurdles, a clarion call is made for persistent research and avant-garde innovation, propelling DApps to their true potential in the evolving digital landscape.

  • Open Access | Article 2024-03-19 Doi: 10.54254/2755-2721/48/20241154

    Performance exploration of Generative Pre-trained Transformer-2 for lyrics generation

    In recent years, the field of Natural Language Processing (NLP) has undergone a revolution, with text generation playing a key role in this transformation. This shift is not limited to technological areas but has also seamlessly penetrated creative domains, with a prime example being the generation of song lyrics. To be truly effective, generative models, like Generative Pre-trained Transformer (GPT)-2, require fine-tuning as a crucial step. This paper, utilizing the robustness of the widely-referenced Kaggle dataset titled "Song Lyrics", carefully explores the impacts of modulating three key parameters: learning rate, batch size, and sequence length. The dataset presents a compelling narrative that highlights the learning rate as the most influential determinant, directly impacting the quality and coherence of the lyrics generated. While increasing the batch size and extending sequence lengths promise enhanced model performance, it is evident that there is a saturation point beyond which further benefits are limited. Through this exploration, the paper aims to demystify the complex world of model calibration and emphasize the importance of strategic parameter selection in pursuit of lyrical excellence.

  • Open Access | Article 2024-03-19 Doi: 10.54254/2755-2721/48/20241163

    Optimizing GAN parameters for efficient and accurate image generation: A study of WGAN-GP in brain tumor dataset

    In this era of unprecedented rapid development of artificial intelligence, researchers are moving forward to develop new neural networks. Nevertheless, few have considered optimizing the extant generative adversarial network (GAN) to achieve the most effective and accurate solutions to provide optimal results for the challenges. This study aims to investigate the critical role of parameter optimization in GAN neural networks, with a particular focus on the Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP) architecture applied to the generation of medical images, especially images depicting brain tumors. Therefore, the project used Kaggle’s brain tumor data set as a canvas to conduct an in-depth study of the impact of these parameters on the training model and generated results. For the starter, to investigate how alterations in the learning rate impact the model, this article selects a series of values for meticulous analysis to determine the most effective configuration. Then, evaluate and find a better and more suitable choice between Adam and SGD optimizers through comparison, focusing on their impact on training dynamics. As the last one, this study examines how the Tanh activation function constrains pixel values and shapes image realism through comparative results. By dissecting and understanding the interaction of these parameters in detail, we lay the foundation for optimizing GAN neural networks, increasing their efficiency, and producing accurate solutions for accurate diagnostics and healthcare applications. The journey through the labyrinth of GAN parameter tuning ultimately provided valuable insights into seamlessly synthesizing medical images.

  • Open Access | Article 2024-03-19 Doi: 10.54254/2755-2721/48/20241175

    Image Caption using VGG model and LSTM

    Deep convolutional networks and recurrent neural networks have gained significant popularity in the field of image captioning tasks in recent times. As we all know the performance and the architecture of models are still eternal topic. We constructed the model using a new method to enhance its performance and accuracy. In our model, we make use of pretrained CNN model VGG (Visual Geometry Group) to extract image features, and learn caption sentence features using bidirectional LSTM(Long-Short-Term-Memory) which can better understand the meaning of sentences in the text. Then we combine the image features and caption features to predict captions for images. The dataset Flickr8K is used to train and test the model. Additionally, the model has the ability to produce captions that are shorter than a specified caption length. We evaluated our model with Bilingual Evaluation Understudy (BLEU) score which measures the similarity of predicted text and to the real text. After evaluation and comparison, our model is proved to be well-done on some conditions.

  • Open Access | Article 2024-03-19 Doi: 10.54254/2755-2721/48/20241181

    Enhancing predictive models for illicit activities in the Bitcoin transaction network using advanced graph analytical techniques

    The Elliptic dataset compiles a comprehensive history of Bitcoin transactions, integrating both anti-money laundering (AML) tags and distinct graph network features. Given the nature of the Bitcoin transaction network—a complex, weakly interconnected structure—leveraging graph analysis techniques for its study holds immense potential, especially in the realm of detecting illicit activities like hacking, drug trades, gambling, and more. A detailed examination of the Elliptic dataset, encompassing transaction amounts, frequencies, source and destination addresses, sheds light on the inherent structure and peculiarities of the Bitcoin transaction ecosystem. By conceptualizing this transactional landscape as a graph, a slew of analytical attributes emerge: node degree distribution, community architecture, centrality measures, and so forth. Such attributes pave the way for the creation of predictive models that can pinpoint and prognosticate potential unlawful trade actions. Several computational models have been employed on the Elliptic dataset, such as Logistic Regression (LR), Random Forest (RF), Multilayer Perceptrons (MLP), and Graph Convolutional Networks (GCN). The authors of this particular study delve into augmentations of the GCN model, juxtaposing the efficacy of the original GCN model against their enhanced algorithm within the context of the Elliptic dataset.

  • Open Access | Article 2024-03-19 Doi: 10.54254/2755-2721/48/20241185

    Prediction and classification model of hornet sighting report in Washington state based on deep learning

    In recent years, the precise control of pests has become a concern for multiple departments. However, the accurate identification of misclassifications in eyewitness reports has remained a significant challenge. This study presents a comprehensive prediction and classification model designed for hornet sighting reports in Washington State. Leveraging deep learning, image analysis, and geographic location processing, the model aims to address the challenges associated with the accurate classification of reported sightings as ‘positive’, ‘negative’, or ‘unverified’. The methodology integrates transfer learning with ResNet and employs data augmentation techniques to enhance image-based predictions. The use of PyTorch facilitates neural network construction and training, leading to notable improvements in accuracy, especially in recognizing ‘negative’ cases. Furthermore, geographic location processing introduces an innovative dimension, utilizing spatial information for distance-based classification. By combining the sigmoid function with geographical distances, predictions are refined, particularly for ‘negative’ samples. An auxiliary function enhances predictions for samples lacking images. The practical prediction approach integrates image and location data, producing comprehensive results. The model evaluation demonstrates its efficacy through extensive data analysis. The significance of this study lies in its contribution to filling research gaps within related fields and supporting effective pest management, particularly in response to the threat posed by the Asian giant hornet. The obtained comprehensive model can accurately classify future collected eyewitness reports to guide relevant departments in their prevention and control strategies.

  • Open Access | Article 2024-03-19 Doi: 10.54254/2755-2721/48/20241199

    Artificial intelligence in clinical applications

    Modern medicine has improved to the point that intelligent diagnostic tools and auxiliary medical technology, such as surgical robots and image analysis systems, are now widespread in clinical settings. In clinical practice, the performance of different surgical robots and image analysis systems is very different, which seriously limits the use of complex medical scenes. The algorithm models and robotic arms that these intelligent robots and the supporting systems rely on have being recognized by the researchers. In this study, hardware and software algorithms are introduced one at a time, with a focus on the Da Vinci medical robot arm systems, the control mechanisms that run the surgical task optimization tools, in particular Proportional-Integral-Derivative (PID) and Remote Center of Motion (RCM), and the image algorithm active contour model that significantly increased the accuracy of tumor localization. Also provided are suggestions for improving the system's use, its limits, and future research possibilities.

  • Open Access | Article 2024-03-19 Doi: 10.54254/2755-2721/48/20241211

    Systematic analysis of the principles and application scenarios of Low-Noise Amplifier

    As society advances, new ideas and products are increasingly integrated into our daily lives. 5th generation mobile networks tech enables faster, lag-free connectivity, raising performance standards for components like Low-Noise Amplifiers. Summarizing Low-Noise Amplifier tech and applications helps researchers and firms leverage past knowledge and explore innovations. This paper analyzes Low-Noise Amplifier development and application, discussing types, principles, key performance indicators, and circuit structures of basic amplifiers. Five vital Low-Noise Amplifier characteristics—noise figure, impedance matching, linearity, stability, and gain—are examined. The author introduces design and application cases in radio astronomy, navigation systems, and 5th generation mobile networks communications based on Low-Noise Amplifier characteristics and performance requirements. The author concludes that advancing radio frequency tech requires improved Low-Noise Amplifiers, especially for high-frequency signals in 5th generation mobile networks. Promising noise performance enhancements come from technologies like modified high electron mobility transistors on GaAs and InP substrates. Monolithic Microwave Integrated Circuit integration reduces size while maintaining cost-effective performance. Future advancements in these areas could further boost Low-Noise Amplifier performance.

  • Open Access | Article 2024-03-19 Doi: 10.54254/2755-2721/48/20241219

    Optimized design of a 4-bits absolute-value detector based on linear programming

    Nowadays, neural signal acquisition systems are constantly developing, and spike classification algorithms have been widely studied and concerned. This paper designed a practical spike detection circuit, named as the absolute value detector. Project is committed to adopting only simple gate circuits, by using Morgan’s theorem to optimize the circuit structure, so that we can ensure that the detector has the following several advantages, simple and beautiful, easy to understand, powerful performance. In addition, this paper also considered the optimization of performance including latency and energy consumption. The increase of Vdd will increase the energy consumption and reduce the delay, while the increase of size will reduce the energy consumption and increase the delay. Using MATLAB software for linear programming, Under the condition of a 1.5-fold increase in the delay, and then adjusting Vdd and size, energy consumption was down by 78 percent.

  • Open Access | Article 2024-03-19 Doi: 10.54254/2755-2721/48/20241249

    Artificial intelligence's role in the realm of endangered languages: Documentation and teaching

    With numerous languages nearing extinction, the urgency to preserve endangered languages has become a prominent focus in the linguistic field. This paper delves into the transformative role of Artificial Intelligence (AI) in the domains of documentation and pedagogy for endangered languages, particularly highlighting its innovative applications and the associated challenges. It delves into how AI-powered tools reshape linguistic fieldwork, offering accelerated annotation, consistent data collection, and deeper analytical endeavors. Furthermore, this exploration highlights the potential of AI in revolutionizing the teaching of these languages, ushering in a new era marked by dynamic, scalable, and engaging learning experiences. While AI presents unparalleled efficiencies, its challenges, ranging from data scarcity to the looming digital divide, are addressed critically. As the digital age continues to evolve, merging AI’s capabilities with traditional linguistic approaches holds the promise of a more inclusive and comprehensive strategy to rejuvenate and preserve the world’s rich linguistic tapestry. This paper has summarized and provided an outlook on the research topic at hand.

  • Open Access | Article 2024-03-19 Doi: 10.54254/2755-2721/48/20241257

    Revolutionizing image recognition: The dominance and future potential of convolutional neural networks

    As AI technology advances swiftly and diverse industries increasingly require image processing, traditional image recognition methods are displaying their limitations. This paper explores the evolving landscape of AI technology in the context of image processing and highlights the limitations of traditional image recognition methods. With the proliferation of big data and the evolution of deep learning, convolutional neural networks (CNNs) have emerged as a dominant solution for image recognition across diverse industries. The paper begins by elucidating the architecture of CNNs and introduces commonly employed traditional CNN models. Furthermore, it offers practical insights into the application of CNNs within various industries, illuminating the path for future CNN development. The transformative potential of CNNs is underscored, as they possess the ability to extract intricate patterns from images, reshaping numerous domains. The paper's primary focus is on CNNs in the realm of image recognition, encompassing efforts to enhance precision and efficiency in CNN-based image recognition, as well as addressing real-world challenges in this domain using CNNs.

  • Open Access | Article 2024-03-19 Doi: 10.54254/2755-2721/48/20241260

    Application and evaluation of deep learning based image recognition techniques in agriculture

    Agriculture, as an important industry in society, is facing problems such as an aging population and rural labor exodus, which leads to rising labor costs and uncertainty in agricultural production. Deep learning techniques are considered as a key tool to solve this problem. In this paper, three popular deep learning algorithms, namely, Region-based Convolutional Neural Network, You Only Look Once, and Single Shot MultiBox Detector, are introduced and their working principles are described in detail, while the advantages and disadvantages of these algorithms are briefly analyzed. Additionally, this paper specifically analyzes the application of these three algorithms in three agricultural scenarios, such as timber species recognition, fruit picking, and pest identification. The results show that although the three algorithms are slightly different in terms of accuracy and detection speed, they all demonstrate the potential for a wide range of applications in the agricultural field. Therefore, deep learning technology is of great significance in solving the problem of rural labor shortage, especially when combined with advanced equipment, which is expected to significantly improve the efficiency of identification, monitoring, and harvesting in agriculture and promote the development of automated agriculture.

  • Open Access | Article 2024-03-19 Doi: 10.54254/2755-2721/48/20241289

    The advantage of artificial intelligence application in financial risk assessment and management

    The increasing perfection of artificial intelligence technology has brought subversive changes to the field of financial risk management. The application of artificial models such as neural networks, support vector machines, and mixed intelligence in financial risk management can improve the speed of data processing, provide deep insight into data analysis, reduce human labour costs, and hence improve the efficiency of financial risk control. Meanwhile, the increasing amount of data and the application of AI also bring new challenges to financial risk management, such as the risk of program error and information security. This paper introduces in detail the application status of three models, including Support Vector Machine, Support Vector Machine, and Large Language Model in risk management Based on this, this paper analyses the advantages of AI applications in promoting and reforming the financial industry. The goal is to provide an in-depth examination of present implementations and their respective benefits, as well as to investigate potential future advances in this sector.

  • Open Access | Article 2024-03-19 Doi: 10.54254/2755-2721/48/20241332

    Harnessing AI and machine learning for enhanced credit risk analysis: A comprehensive exploration of computational techniques in the financial realm

    Within the confluence of the banking and financial sectors, the integration of machine learning in credit risk analysis signifies a paradigm shift towards data-centric decision-making. Historically, methodologies for credit risk were limited in predictive accuracy and computational efficiency. The advent of expansive language models, exemplified by Ant Group's AntFinGLM, offers a solution. These models, underpinned by deep learning, amalgamate financial texts and transactional data, facilitating the discernment of intricate financial paradigms and market nuances. This paper conducts a rigorous exploration of machine learning methodologies, from Bayesian classifiers to k-means clustering, offering an analytical perspective on their advantages and challenges. As the industry inclines towards innovations like AntFinGLM, the imperatives of professionalism, precision, and data sanctity gain significance. Upholding standards that encompass five dimensions and 28 categories, AntFinGLM epitomises these benchmarks, championing enhanced functionalities while fostering collaborative initiatives with financial entities. Addressing challenges, particularly around data security and professional integrity, becomes crucial. Techniques encompassing intent recognition, fact verification, and robust data protection mechanisms are indispensable. In summation, the endeavours of entities like AntFinGLM underscore the transformative prowess of expansive language models, ushering the financial sector into an epoch characterised by astute, efficient, and safeguarded decision-making paradigms.

Copyright © 2023 EWA Publishing. Unless Otherwise Stated