Computers

12 pages, 8479 KiB

Open AccessArticle

Automated Generation of Lung Cytological Images from Image Findings Using Text-to-Image Technology

by Atsushi Teramoto, Yuka Kiriyama, Ayano Michiba, Natsuki Yazawa, Tetsuya Tsukamoto, Kazuyoshi Imaizumi and Hiroshi Fujita

Computers 2024, 13(11), 303; https://doi.org/10.3390/computers13110303 - 19 Nov 2024

Abstract

Cytology, a type of pathological examination, involves sampling cells from the human body and observing the morphology of the nucleus, cytoplasm, and cell arrangement. In developing classification AI technologies to support cytology, it is essential to collect and utilize a diverse range of [...] Read more.

Cytology, a type of pathological examination, involves sampling cells from the human body and observing the morphology of the nucleus, cytoplasm, and cell arrangement. In developing classification AI technologies to support cytology, it is essential to collect and utilize a diverse range of images without bias. However, this is often challenging in practice because of the epidemiologic bias of cancer types and cellular characteristics. The main aim of this study was to develop a method to generate cytological diagnostic images from image findings using text-to-image technology in order to generate diverse images. In the proposed method, we collected Papanicolaou-stained specimens derived from the lung cells of 135 lung cancer patients, from which we extracted 472 patch images. Descriptions of the corresponding findings for these patch images were compiled to create a data set. This dataset was then utilized to finetune the Stable Diffusion (SD) v1 and v2 models. The cell images generated by this method closely resemble real images, and both cytotechnologists and cytopathologists provided positive subjective evaluations. Furthermore, SDv2 demonstrated shapes and contours of nuclei and cytoplasm that were more similar to real images compared to SDv1, showing superior performance in quantitative evaluation metrics. When the generated images were utilized in the classification tasks for cytological images, there was an improvement in classification performance. These results indicate that the proposed method may be effective for generating high-quality cytological images, which enables the image classification model to learn diverse features, thereby improving classification performance. Full article

(This article belongs to the Special Issue Applications of Machine Learning and Artificial Intelligence for Healthcare)

► Show Figures

Figure 1

16 pages, 282 KiB

Open AccessArticle

The Conundrum Challenges for Research Software in Open Science

by Teresa Gomez-Diaz and Tomas Recio

Computers 2024, 13(11), 302; https://doi.org/10.3390/computers13110302 - 19 Nov 2024

Abstract

In the context of Open Science, the importance of Borgman’s conundrum challenges that have been initially formulated concerning the difficulties to share Research Data is well known: which Research Data might be shared, by whom, with whom, under what conditions, why, and to [...] Read more.

In the context of Open Science, the importance of Borgman’s conundrum challenges that have been initially formulated concerning the difficulties to share Research Data is well known: which Research Data might be shared, by whom, with whom, under what conditions, why, and to what effects. We have recently reviewed the concepts of Research Software and Research Data, concluding with new formulations for their definitions, and proposing answers to these conundrum challenges for Research Data. In the present work we extend the consideration of the Borgman’s conundrum challenges to Research Software, providing answers to these questions in this new context. Moreover, we complete the initial list of questions/answers, by asking how and where the Research Software may be shared. Our approach begins by recalling the main issues involved in the Research Software definition, and its production context in the research environment, from the Open Science perspective. Then we address the conundrum challenges for Research Software by exploring the potential similarities and differences regarding our answers for these questions in the case of Research Data. We conclude emphasizing the usefulness of the followed methodology, exploiting the parallelism between Research Software and Research Data in the Open Science environment. Full article

(This article belongs to the Special Issue Best Practices, Challenges and Opportunities in Software Engineering)

► Show Figures

Figure 1

36 pages, 17182 KiB

Open AccessArticle

A Fuzzy-Immune-Regulated Single-Neuron Proportional–Integral–Derivative Control System for Robust Trajectory Tracking in a Lawn-Mowing Robot

by Omer Saleem, Ahmad Hamza and Jamshed Iqbal

Computers 2024, 13(11), 301; https://doi.org/10.3390/computers13110301 - 19 Nov 2024

Abstract

This paper presents the constitution of a computationally intelligent self-adaptive steering controller for a lawn-mowing robot to yield robust trajectory tracking and disturbance rejection behavior. The conventional fixed-gain proportional–integral–derivative (PID) control procedure lacks the flexibility to deal with the environmental indeterminacies, coupling issues, [...] Read more.

This paper presents the constitution of a computationally intelligent self-adaptive steering controller for a lawn-mowing robot to yield robust trajectory tracking and disturbance rejection behavior. The conventional fixed-gain proportional–integral–derivative (PID) control procedure lacks the flexibility to deal with the environmental indeterminacies, coupling issues, and intrinsic nonlinear dynamics associated with the aforementioned nonholonomic system. Hence, this article contributes to formulating a self-adaptive single-neuron PID control system that is driven by an extended Kalman filter (EKF) to ensure efficient learning and faster convergence speeds. The neural adaptive PID control formulation improves the controller’s design flexibility, which allows it to effectively attenuate the tracking errors and improve the system’s trajectory tracking accuracy. To supplement the controller’s robustness to exogenous disturbances, the adaptive PID control signal is modulated with an auxiliary fuzzy-immune system. The fuzzy-immune system imitates the automatic self-learning and self-tuning characteristics of the biological immune system to suppress bounded disturbances and parametric variations. The propositions above are verified by performing the tailored hardware in the loop experiments on a differentially driven lawn-mowing robot. The results of these experiments confirm the enhanced trajectory tracking precision and disturbance compensation ability of the prescribed control method. Full article

(This article belongs to the Special Issue Feature Papers in Computers 2024)

► Show Figures

Figure 1

20 pages, 691 KiB

Open AccessArticle

DiscHAR: A Discrete Approach to Enhance Human Activity Recognition in Cyber Physical Systems: Smart Homes

by Ishrat Fatima, Asma Ahmad Farhan, Maria Tamoor, Shafiq ur Rehman, Hisham Abdulrahman Alhulayyil and Fawaz Tariq

Computers 2024, 13(11), 300; https://doi.org/10.3390/computers13110300 - 19 Nov 2024

Abstract

The main challenges in smart home systems and cyber-physical systems come from not having enough data and unclear interpretation; thus, there is still a lot to be done in this field. In this work, we propose a practical approach called Discrete Human Activity [...] Read more.

The main challenges in smart home systems and cyber-physical systems come from not having enough data and unclear interpretation; thus, there is still a lot to be done in this field. In this work, we propose a practical approach called Discrete Human Activity Recognition (DiscHAR) based on prior research to enhance Human Activity Recognition (HAR). Our goal is to generate diverse data to build better models for activity classification. To tackle overfitting, which often occurs with small datasets, we generate data and convert them into discrete forms, improving classification accuracy. Our methodology includes advanced techniques like the R-Frame method for sampling and the Mixed-up approach for data generation. We apply K-means vector quantization to categorize the data, and through the elbow method, we determine the optimal number of clusters. The discrete sequences are converted into one-hot encoded vectors and fed into a CNN model to ensure precise recognition of human activities. Evaluations on the OPP79, PAMAP2, and WISDM datasets show that our approach outperforms existing models, achieving 89% accuracy for OPP79, 93.24% for PAMAP2, and 100% for WISDM. These results demonstrate the model’s effectiveness in identifying complex activities captured by wearable devices. Our work combines theory and practice to address ongoing challenges in this field, aiming to improve the reliability and performance of activity recognition systems in dynamic environments. Full article

► Show Figures

Figure 1

28 pages, 44234 KiB

Open AccessArticle

Exploring Park and Ride: A Spatial Analysis of Transit Catchment in Outer Melbourne

by Yanlin Chen, Kiki Adhinugraha, Shiyang Lyu and David Taniar

Computers 2024, 13(11), 299; https://doi.org/10.3390/computers13110299 - 18 Nov 2024

Abstract

Public transportation is essential for improving urban mobility, enhancing travel quality, reducing reliance on private vehicles, and alleviating traffic congestion. However, inadequate public transportation in outer Melbourne is a significant issue limiting urban development. While existing research primarily focuses on walking distance to [...] Read more.

Public transportation is essential for improving urban mobility, enhancing travel quality, reducing reliance on private vehicles, and alleviating traffic congestion. However, inadequate public transportation in outer Melbourne is a significant issue limiting urban development. While existing research primarily focuses on walking distance to define service catchments, commuters in transit-disadvantaged or outlying urban areas often drive to transit, noted as the park-and-ride mode. This research uniquely examines drive-distance catchments for park-and-ride transit accessibility in outer Melbourne, using spatial SQL and GIS techniques to provide a detailed, multi-dimensional analysis of population coverage, parking capacity, and accessibility gaps. This approach fills a gap in the existing literature by offering adaptable insights and approaches to other outer urban areas with transit disadvantages. The findings underscore the necessity for targeted enhancements in public transportation in outer Melbourne: Most of the outer residents concentrate near the train stations, though significant spatial gaps exist; The general accessibility status of residential mesh blocks is found; Parking capacity varies with high tension found at certain stations. This study contributes insights to create more equitable and sustainable transportation systems by providing a detailed spatial analysis of current transit coverage and identifying critical gaps. Full article

(This article belongs to the Special Issue Computational Science and Its Applications 2024 (ICCSA 2024))

► Show Figures

Figure 1

14 pages, 731 KiB

Open AccessArticle

Quantum Congestion Game for Overcrowding Prevention Within Airport Common Areas

by Evangelos D. Spyrou, Vassilios Kappatos and Chrysostomos Stylios

Computers 2024, 13(11), 298; https://doi.org/10.3390/computers13110298 - 17 Nov 2024

Abstract

Quantum game theory merges principles from quantum mechanics with game theory, exploring how quantum phenomena such as superposition and entanglement can influence strategic decision making. It offers a novel approach to analyzing and optimizing complex systems where traditional game theory may fall short. [...] Read more.

Quantum game theory merges principles from quantum mechanics with game theory, exploring how quantum phenomena such as superposition and entanglement can influence strategic decision making. It offers a novel approach to analyzing and optimizing complex systems where traditional game theory may fall short. Congestion of passengers, if considered as a network, may fall into the categories of optimization cases of quantum games. This paper explores the application of quantum potential games to minimize congestion in common areas at airports. The players/passengers of the airport have identical interests and they share the same utility function. A metric is introduced that considers a passenger’s visit to a common area by setting their preferences, in order to avoid congestion. Passengers can decide whether to visit a specific common area or choose an alternative. This study demonstrates that the proposed game is a quantum potential game for tackling congestion, with identical interests, ensuring the existence of a Nash equilibrium. We consider passengers to be players that want to ensure their interests. Quantum entanglement is utilized to validate the concept, and the results highlight the effectiveness of this approach. The objective is to ensure that not all passengers select the same common place of the airport to reduce getting crowded; hence, the airborne disease infection probability increases due to overcrowding. Our findings provide a promising framework for optimizing passenger flow and reducing congestion in airport common areas through quantum game theory. We showed that the proposed system is stable by encapsulating the Lyapunov stability. We compared it to a simulated annealing approach to show the efficacy of the quantum game approach. We acknowledge that this framework can be utilized in other disciplines as well. For our future work, we will research different strategies than binary ones to investigate the efficacy of the approach. Full article

► Show Figures

Figure 1

19 pages, 1382 KiB

Open AccessArticle

On the Robustness of Compressed Models with Class Imbalance

by Baraa Saeed Ali, Nabil Sarhan and Mohammed Alawad

Computers 2024, 13(11), 297; https://doi.org/10.3390/computers13110297 - 16 Nov 2024

Abstract

Deep learning (DL) models have been deployed in various platforms, including resource-constrained environments such as edge computing, smartphones, and personal devices. Such deployment requires models to have smaller sizes and memory footprints. To this end, many model compression techniques proposed in the literature [...] Read more.

Deep learning (DL) models have been deployed in various platforms, including resource-constrained environments such as edge computing, smartphones, and personal devices. Such deployment requires models to have smaller sizes and memory footprints. To this end, many model compression techniques proposed in the literature successfully reduce model sizes and maintain comparable accuracy. However, the robustness of compressed DL models against class imbalance, a natural phenomenon in real-life datasets, is still under-explored. We present a comprehensive experimental study of the performance and robustness of compressed DL models when trained on class-imbalanced datasets. We investigate the robustness of compressed DL models using three popular compression techniques (pruning, quantization, and knowledge distillation) with class-imbalanced variants of the CIFAR-10 dataset and show that compressed DL models are not robust against class imbalance in training datasets. We also show that different compression techniques have varying degrees of impact on the robustness of compressed DL models. Full article

(This article belongs to the Special Issue Emerging Trends in Machine Learning and Artificial Intelligence)

► Show Figures

Figure 1

35 pages, 9938 KiB

Open AccessArticle

Detection of Fake Instagram Accounts via Machine Learning Techniques

by Stefanos Chelas, George Routis and Ioanna Roussaki

Computers 2024, 13(11), 296; https://doi.org/10.3390/computers13110296 - 15 Nov 2024

Abstract

This paper focuses on the detection of fake accounts on Instagram and proposes a novel solution that aims to address this problem. More specifically, a machine learning-based solution is introduced that can be employed by Instagram-based applications to combat this phenomenon. To accomplish [...] Read more.

This paper focuses on the detection of fake accounts on Instagram and proposes a novel solution that aims to address this problem. More specifically, a machine learning-based solution is introduced that can be employed by Instagram-based applications to combat this phenomenon. To accomplish this, publicly available data from Instagram users are collected and processed. After making the necessary feature additions to and removals from these data, they are fed into machine learning algorithms with the aim of detecting fake Instagram accounts. The interest of the results presented in this study lies in their comparability with the results of other similar studies, with the difference that fewer input features have been used. This addresses significant research challenges regarding the performance of and confidence in obtained results in this specific problem domain. Full article

(This article belongs to the Special Issue Recent Advances in Social Networks and Social Media)

► Show Figures

Figure 1

19 pages, 2768 KiB

Open AccessArticle

Reinforcement-Learning-Based Edge Offloading Orchestration in Computing Continuum

by Ioana Ramona Martin, Gabriel Ioan Arcas and Tudor Cioara

Computers 2024, 13(11), 295; https://doi.org/10.3390/computers13110295 - 14 Nov 2024

Abstract

The AI-driven applications and large data generated by IoT devices connected to large-scale utility infrastructures pose significant operational challenges, including increased latency, communication overhead, and computational imbalances. Addressing these is essential to shift the workloads from the cloud to the edge and across [...] Read more.

The AI-driven applications and large data generated by IoT devices connected to large-scale utility infrastructures pose significant operational challenges, including increased latency, communication overhead, and computational imbalances. Addressing these is essential to shift the workloads from the cloud to the edge and across the entire computing continuum. However, to achieve this, significant challenges must still be addressed, particularly in decision making to manage the trade-offs associated with workload offloading. In this paper, we propose a task-offloading solution using Reinforcement Learning (RL) to dynamically balance workloads and reduce overloads. We have chosen the Deep Q-Learning algorithm and adapted it to our workload offloading problem. The reward system considers the node’s computational state and type to increase the utilization of the computational resources while minimizing latency and bandwidth utilization. A knowledge graph model of the computing continuum infrastructure is used to address environment modeling challenges and facilitate RL. The learning agent’s performance was evaluated using different hyperparameter configurations and varying episode lengths or knowledge graph model sizes. Results show that for a better learning experience, a low, steady learning rate and a large buffer size are important. Additionally, it offers strong convergence features, with relevant workload tasks and node pairs identified after each learning episode. It also demonstrates good scalability, as the number of offloading pairs and actions increases with the size of the knowledge graph and the episode count. Full article

(This article belongs to the Special Issue Intelligent Edge: When AI Meets Edge Computing)

► Show Figures

Figure 1

14 pages, 2039 KiB

Open AccessArticle

Deep Learning Based Breast Cancer Detection Using Decision Fusion

by Doğu Manalı, Hasan Demirel and Alaa Eleyan

Computers 2024, 13(11), 294; https://doi.org/10.3390/computers13110294 - 14 Nov 2024

Abstract

Breast cancer, which has the highest mortality and morbidity rates among diseases affecting women, poses a significant threat to their lives and health. Early diagnosis is crucial for effective treatment. Recent advancements in artificial intelligence have enabled innovative techniques for early breast cancer [...] Read more.

Breast cancer, which has the highest mortality and morbidity rates among diseases affecting women, poses a significant threat to their lives and health. Early diagnosis is crucial for effective treatment. Recent advancements in artificial intelligence have enabled innovative techniques for early breast cancer detection. Convolutional neural networks (CNNs) and support vector machines (SVMs) have been used in computer-aided diagnosis (CAD) systems to identify breast tumors from mammograms. However, existing methods often face challenges in accuracy and reliability across diverse diagnostic scenarios. This paper proposes a three parallel channel artificial intelligence-based system. First, SVM distinguishes between different tumor types using local binary pattern (LBP) features. Second, a pre-trained CNN extracts features, and SVM identifies potential tumors. Third, a newly developed CNN is trained and used to classify mammogram images. Finally, a decision fusion that combines results from the three channels to enhance system performance is implemented using different rules. The proposed decision fusion-based system outperforms state-of-the-art alternatives with an overall accuracy of 99.1% using the product rule. Full article

(This article belongs to the Special Issue Applications of Machine Learning and Artificial Intelligence for Healthcare)

► Show Figures

Figure 1

23 pages, 323 KiB

Open AccessReview

Advancements in Parkinson’s Disease Diagnosis: A Comprehensive Survey on Biomarker Integration and Machine Learning

by Ruchira Pratihar and Ravi Sankar

Computers 2024, 13(11), 293; https://doi.org/10.3390/computers13110293 - 14 Nov 2024

Abstract

This comprehensive review explores the advancements in machine learning algorithms in the diagnosis of Parkinson’s disease (PD) utilizing different biomarkers. It addresses the challenges in the assessment of PD for accurate diagnosis, treatment decisions, and patient care due to difficulties in early and [...] Read more.

This comprehensive review explores the advancements in machine learning algorithms in the diagnosis of Parkinson’s disease (PD) utilizing different biomarkers. It addresses the challenges in the assessment of PD for accurate diagnosis, treatment decisions, and patient care due to difficulties in early and differential diagnosis, subjective clinical assessments, symptom variability, limited objective biomarkers, comorbidity impacts, uneven access to specialized care, and gaps in clinical research. This review provides a detailed review of ongoing biomarker research, technological advancements for objective assessment, and enhanced healthcare infrastructure. It presents a comprehensive evaluation of the use of diverse biomarkers for diagnosing Parkinson’s disease (PD) across various datasets, utilizing machine learning models. Recent research findings are summarized in tables, showcasing key methodologies such as data preprocessing, feature selection, and classification techniques. This review also explores the performance, benefits, and limitations of different diagnostic approaches, providing valuable insights into their effectiveness in PD diagnosis. Moreover, the review addresses the integration of multimodal biomarkers, combining data from different sources to enhance diagnostic accuracy, and disease monitoring. Challenges such as data heterogeneity, variability in symptom progression, and model generalizability are discussed alongside emerging trends and future directions in the field. Ultimately, the application of machine learning (ML) in leveraging diverse biomarkers offers promising avenues for advancing PD diagnosis, paving the way for personalized treatment strategies and improving patient outcomes. Full article

(This article belongs to the Special Issue Applications of Machine Learning and Artificial Intelligence for Healthcare)

17 pages, 1448 KiB

Open AccessArticle

LLaMA 3 vs. State-of-the-Art Large Language Models: Performance in Detecting Nuanced Fake News

by Stefan Emil Repede and Remus Brad

Computers 2024, 13(11), 292; https://doi.org/10.3390/computers13110292 - 11 Nov 2024

Abstract

This study investigates the effectiveness of a proposed version of Meta’s LLaMA 3 model in detecting fake claims across bilingual (English and Romanian) datasets, focusing on a multi-class approach beyond traditional binary classifications in order to better mimic real-world scenarios. The research employs [...] Read more.

This study investigates the effectiveness of a proposed version of Meta’s LLaMA 3 model in detecting fake claims across bilingual (English and Romanian) datasets, focusing on a multi-class approach beyond traditional binary classifications in order to better mimic real-world scenarios. The research employs a proposed version of the LLaMA 3 model, optimized for identifying nuanced categories such as “Mostly True” and “Mostly False”, and compares its performance against leading large language models (LLMs) including Open AI’s ChatGPT versions, Google’s Gemini, and similar LLaMA models. The analysis reveals that the proposed LLaMA 3 model consistently outperforms its base version and older LLaMA models, particularly in the Romanian dataset, achieving the highest accuracy of 39% and demonstrating superior capabilities in identifying nuanced claims, over all the compared large language models. However, the model’s performance across both languages highlights some challenges, with generally low accuracy and difficulties in handling ambiguous categories by all the LLMs. The study also underscores the impact of language and cultural context on model reliability, noting that even state-of-the-art models like ChatGPT 4.o and Gemini exhibit inconsistencies when applied to Romanian text and more than a binary true/false approach. Full article

(This article belongs to the Special Issue Natural Language Processing (NLP) and Large Language Modelling)

► Show Figures

Figure 1

18 pages, 1079 KiB

Open AccessArticle

A Threefold Approach for Enhancing Fuzzy Interpolative Reasoning: Case Study on Phishing Attack Detection Using Sparse Rule Bases

by Mohammad Almseidin, Maen Alzubi, Jamil Al-Sawwa, Mouhammd Alkasassbeh and Mohammad Alfraheed

Computers 2024, 13(11), 291; https://doi.org/10.3390/computers13110291 - 8 Nov 2024

Abstract

Fuzzy systems are powerful modeling systems for uncertainty applications. In contrast to traditional crisp systems, fuzzy systems offer the opportunity to extend the binary decision to continuous space, which could offer benefits for various application areas such as intrusion detection systems (IDSs), because [...] Read more.

Fuzzy systems are powerful modeling systems for uncertainty applications. In contrast to traditional crisp systems, fuzzy systems offer the opportunity to extend the binary decision to continuous space, which could offer benefits for various application areas such as intrusion detection systems (IDSs), because of their ability to measure the degree of attacks instead of making a binary decision. Furthermore, fuzzy systems offer a suitable environment that is able to deal with uncertainty. However, fuzzy systems face a critical challenge represented by the sparse fuzzy rules. Typical fuzzy systems demand complete fuzzy rules in order to offer the required results. Additionally, generating complete fuzzy rules can be difficult due to many factors, such as a lack of knowledge base or limited data availability, such as in IDS applications. Fuzzy rule interpolation (FRI) was introduced to overcome this limitation by generating the required interpolation results in cases with sparse fuzzy rules. This work introduces a threefold approach designed to address the cases of missing fuzzy rules, which uses a few fuzzy rules to handle the limitations of missing fuzzy rules. This is achieved by finding the interpolation condition of neighboring fuzzy rules. This procedure was accomplished based on the concept of factors (which determine the degree to which each neighboring fuzzy rule contributes to the interpolated results, in cases of missing fuzzy rules). The evaluation procedure for the threefold approach was conducted using the following two steps: firstly, using the FRI benchmark numerical metrics, the results demonstrated the ability of the threefold approach to generate the required results for the various benchmark scenarios. Secondly, using a real-life dataset (phishing attacks dataset), the results demonstrated the effectiveness of the suggested approach to handle cases of missing fuzzy rules in the area of phishing attacks. Consequently, the suggested threefold approach offers an opportunity to reduce the number of fuzzy rules effectively and generate the required results using only a few fuzzy rules. Full article

(This article belongs to the Special Issue Multimedia Data and Network Security)

► Show Figures

Figure 1

19 pages, 37808 KiB

Open AccessArticle

Modified Multiresolution Convolutional Neural Network for Quasi-Periodic Noise Reduction in Phase Shifting Profilometry for 3D Reconstruction

by Osmar Antonio Espinosa-Bernal, Jesús Carlos Pedraza-Ortega, Marco Antonio Aceves-Fernandez, Juan Manuel Ramos-Arreguín, Saul Tovar-Arriaga and Efrén Gorrostieta-Hurtado

Computers 2024, 13(11), 290; https://doi.org/10.3390/computers13110290 - 8 Nov 2024

Abstract

Fringe profilometry is a method that obtains the 3D information of objects by projecting a pattern of fringes. The three-step technique uses only three images to acquire the 3D information from an object, and many studies have been conducted to improve this technique. [...] Read more.

Fringe profilometry is a method that obtains the 3D information of objects by projecting a pattern of fringes. The three-step technique uses only three images to acquire the 3D information from an object, and many studies have been conducted to improve this technique. However, there is a problem that is inherent to this technique, and that is the quasi-periodic noise that appears due to this technique and considerably affects the final 3D object reconstructed. Many studies have been carried out to tackle this problem to obtain a 3D object close to the original one. The application of deep learning in many areas of research presents a great opportunity to to reduce or eliminate the quasi-periodic noise that affects images. Therefore, a model of convolutional neural network along with four different patterns of frequencies projected in the three-step technique is researched in this work. The inferences produced by models trained with different frequencies are compared with the original ones both qualitatively and quantitatively. Full article

(This article belongs to the Special Issue Advanced Image Processing and Computer Vision)

► Show Figures

Figure 1

20 pages, 6745 KiB

Open AccessArticle

A Proposed Method of Automating Data Processing for Analysing Data Produced from Eye Tracking and Galvanic Skin Response

by Javier Sáez-García, María Consuelo Sáiz-Manzanares and Raúl Marticorena-Sánchez

Computers 2024, 13(11), 289; https://doi.org/10.3390/computers13110289 - 8 Nov 2024

Abstract

The use of eye tracking technology, together with other physiological measurements such as psychogalvanic skin response (GSR) and electroencephalographic (EEG) recordings, provides researchers with information about users’ physiological behavioural responses during their learning process in different types of tasks. These devices produce a [...] Read more.

The use of eye tracking technology, together with other physiological measurements such as psychogalvanic skin response (GSR) and electroencephalographic (EEG) recordings, provides researchers with information about users’ physiological behavioural responses during their learning process in different types of tasks. These devices produce a large volume of data. However, in order to analyse these records, researchers have to process and analyse them using complex statistical and/or machine learning techniques (supervised or unsupervised) that are usually not incorporated into the devices. The objectives of this study were (1) to propose a procedure for processing the extracted data; (2) to address the potential technical challenges and difficulties in processing logs in integrated multichannel technology; and (3) to offer solutions for automating data processing and analysis. A Notebook in Jupyter is proposed with the steps for importing and processing data, as well as for using supervised and unsupervised machine learning algorithms. Full article

(This article belongs to the Special Issue Smart Learning Environments)

► Show Figures

Figure 1

30 pages, 1844 KiB

Open AccessArticle

Exploring Machine Learning Methods for Aflatoxin M1 Prediction in Jordanian Breast Milk Samples

by Abdullah Aref, Eman Omar, Eman Alseidi, Nour Elhuda A. Alqudah and Sharaf Omar

Computers 2024, 13(11), 288; https://doi.org/10.3390/computers13110288 - 7 Nov 2024

Abstract

The presence of aflatoxin M1 in breast milk poses a serious risk to the health of infants because of its potential to cause cancer and have negative effects on development. Detecting AFM1 in milk samples using conventional methods is often time-consuming and may [...] Read more.

The presence of aflatoxin M1 in breast milk poses a serious risk to the health of infants because of its potential to cause cancer and have negative effects on development. Detecting AFM1 in milk samples using conventional methods is often time-consuming and may not provide real-time monitoring capabilities. The use of machine learning techniques to forecast aflatoxin M1 levels in breast milk samples is examined in this study. To develop predictive models of aflatoxin M1 in breast milk, we employed well-known supervised machine learning algorithms such as Random Forest and Gradient Boosting. The findings show that machine learning can be used for the identification of aflatoxin M1 in breast milk. By actively monitoring breast quality, this research highlights the significance of machine learning in protecting babies’ health and advances the prediction skills in food safety. Full article

(This article belongs to the Special Issue Harnessing Artificial Intelligence for Social and Semantic Understanding)

► Show Figures

Figure 1

5 pages, 164 KiB

Open AccessEditorial

Misconduct, Mishaps, and Misranking in Bibliometric Databases: Inflating the Production and Impact of Scientists

by Leandros Maglaras and Dimitrios Katsaros

Computers 2024, 13(11), 287; https://doi.org/10.3390/computers13110287 - 7 Nov 2024

Abstract

Today, academics and researchers constantly strive to achieve more in their respective fields [...] Full article

(This article belongs to the Section ICT Infrastructures for Cybersecurity)

40 pages, 5965 KiB

Open AccessSystematic Review

A Systematic Review and Comparative Analysis Approach to Boom Gate Access Using Plate Number Recognition

by Asaju Christine Bukola, Pius Adewale Owolawi, Chuling Du and Etienne Van Wyk

Computers 2024, 13(11), 286; https://doi.org/10.3390/computers13110286 - 4 Nov 2024

Abstract

Security has been paramount to many organizations for many years, with access control being one of the critical measures to ensure security. Among various approaches to access control, vehicle plate number recognition has received wide attention. However, its application to boom gate access [...] Read more.

Security has been paramount to many organizations for many years, with access control being one of the critical measures to ensure security. Among various approaches to access control, vehicle plate number recognition has received wide attention. However, its application to boom gate access has not been adequately explored. This study proposes a method to access the boom gate by optimizing vehicle plate number recognition. Given the speed and accuracy of the YOLO (You Only Look Once) object detection algorithm, this study proposes using the YOLO deep learning algorithm for plate number detection to access a boom gate. To identify the gap and the most suitable YOLO variant, the study systematically surveyed the publication database to identify peer-reviewed articles published between 2020 and 2024 on plate number recognition using different YOLO versions. In addition, experiments are performed on four YOLO versions: YOLOv5, YOLOv7, YOLOv8, and YOLOv9, focusing on vehicle plate number recognition. The experiments, using an open-source dataset with 699 samples in total, reported accuracies of 81%, 82%, 83%, and 73% for YOLO V5, V7, V8, and V9, respectively. This comparative analysis aims to determine the most appropriate YOLO version for the task, optimizing both security and efficiency in boom gate access control systems. By optimizing the capabilities of advanced YOLO algorithms, the proposed method seeks to improve the reliability and effectiveness of access control through precise and rapid plate number recognition. The result of the analysis reveals that each YOLO version has distinct advantages depending on the application’s specific requirements. In complex detection conditions with changing lighting and shadows, it was revealed that YOLOv8 performed better in terms of reduced loss rates and increased precision and recall metrics. Full article

(This article belongs to the Special Issue Machine Learning Applications in Pattern Recognition)

► Show Figures

Figure 1

19 pages, 2223 KiB

Open AccessArticle

Performance Analysis of Wireless Sensor Networks Using Damped Oscillation Functions for the Packet Transmission Probability

by Izlian Y. Orea-Flores, Mario E. Rivero-Angeles, Sergio-Jesus Gonzalez-Ambriz, Eleazar Aguirre Anaya and Sumera Saleem

Computers 2024, 13(11), 285; https://doi.org/10.3390/computers13110285 - 4 Nov 2024

Abstract

Wireless sensor networks are composed of many nodes distributed in a region of interest to monitor different environments and physical variables. In many cases, access to nodes is not easy or feasible. As such, the system lifetime is a primary design parameter to [...] Read more.

Wireless sensor networks are composed of many nodes distributed in a region of interest to monitor different environments and physical variables. In many cases, access to nodes is not easy or feasible. As such, the system lifetime is a primary design parameter to consider in the design of these networks. In this regard, for some applications, it is preferable to extend the system lifetime by actively reducing the number of packet transmissions and, thus, the number of reports. The system administrator can be aware of such reporting reduction to distinguish this final phase from a malfunction of the system or even an attack. Given this, we explore different mathematical functions that drastically reduce the number of packet transmissions when the residual energy in the system is low but still allow for an adequate number of transmissions. Indeed, in previous works, where the negative exponential distribution is used, the system reaches the point of zero transmissions extremely fast. Hence, we propose different dampening functions with different decreasing rates that present oscillations to allow for packet transmissions even at the end of the system lifetime. We compare the system performance under these mathematical functions, which, to the best of our knowledge, have never been used before, to find the most adequate transmission scheme for packet transmissions and system lifetime. We develop an analytical model based on a discrete-time Markov chain to show that a moderately decreasing function provides the best results. We also develop a discrete event simulator to validate the analytical results. Full article

(This article belongs to the Special Issue Wireless Sensor Network, IoT and Cloud Computing Technologies for Smart Cities)

► Show Figures

Figure 1

Journal Description

Computers

Latest Articles

Journal Menu

Journal Browser

Highly Accessed Articles

Latest Books

E-Mail Alert

News

Topics

Conferences

Special Issues

Further Information

Guidelines

MDPI Initiatives

Follow MDPI