Special Issue "Applied Machine Learning Ⅱ"

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Computing and Artificial Intelligence".

Deadline for manuscript submissions: closed (20 August 2022) | Viewed by 10874

Special Issue Editor

Assoc. Prof. Grzegorz Dudek
E-Mail Website
Guest Editor
Faculty of Electrical Engineering, Czestochowa University of Technology, Częstochowa, Poland
Interests: machine learning; evolutionary computation; artificial intelligence; pattern recognition; data mining and their application to the forecasting, classification, regression and optimization problems
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Machine learning (ML) is one of the most exciting fields of computing today. Over recent decades, ML has become an entrenched part of everyday life and has been successfully used for solving practical problems. The application area of machine learning is very broad including engineering, industry, business, finance, medicine, and many other domains. ML covers a wide range of learning algorithms including the classical ones such as linear regression, k-nearest neighbors or decision trees, through support vector machines and neural networks, to newly developed algorithms such as deep learning and boosted tree models. In practice, it is quite challenging to properly determine an appropriate architecture and parameters of ML models so that the resulting learner model can achieve sound performance for both learning and generalization. Practical applications of ML bring additional challenges such as dealing with big, missing, distorted and uncertain data. In addition, interpretability is a paramount quality that ML methods should aim to achieve if they are to be applied in practice. Interpretability allows us to understand ML model operation and raises confidence in its results.

This Special Issue focuses on applications of ML models in a diverse range of fields and problems. Application papers are expected reporting substantive results on a wide range of learning methods, discussing conceptualization of a problem, data representation, feature engineering, ML models, critical comparisons with existing techniques and interpretation of results. Specific attention will be given to recently developed ML methods such as deep learning and boosted tree models.

Assoc. Prof. Grzegorz Dudek
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2300 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Published Papers (12 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Jump to: Other

Article
Systematic Machine Translation of Social Network Data Privacy Policies
Appl. Sci. 2022, 12(20), 10499; https://doi.org/10.3390/app122010499 - 18 Oct 2022
Viewed by 281
Abstract
With the growing popularity of online social networks, one common desire of people is to use of social networking services for establishing social relations with others. The boom of social networking has transformed common users into content (data) contributors. People highly rely on [...] Read more.
With the growing popularity of online social networks, one common desire of people is to use of social networking services for establishing social relations with others. The boom of social networking has transformed common users into content (data) contributors. People highly rely on social sites to share their ideas and interests and express opinions. Social network sites store all such activities in a data form and exploit the data for various purposes, e.g., marketing, advertisements, product delivery, product research, and even sentiment analysis, etc. Privacy policies primarily defined in Natural Language (NL) specify storage, usage, and sharing of the user’s data and describe authorization, obligation, or denial of specific actions under specific contextual conditions. Although these policies expressed in Natural Language (NL) allow users to read and understand the allowed (or obliged or denied) operations on their data, the described policies cannot undergo automatic control of the actual use of the data by the entities that operate on them. This paper proposes an approach to systematically translate privacy statements related to data from NL into a controlled natural one, i.e., CNL4DSA to improve the machine processing. The methodology discussed in this work is based on a combination of standard Natural Language Processing (NLP) techniques, logic programming, and ontologies. The proposed technique is demonstrated with a prototype implementation and tested with policy examples. The system is tested with a number of data privacy policies from five different social network service providers. Predominantly, this work primarily takes into account two key aspects: (i) The translation of social networks’ data privacy policy and (ii) the effectiveness and efficiency of the developed system. It is concluded that the proposed system can successfully and efficiently translate any common data policy based on an empirical analysis performed of the obtained results. Full article
(This article belongs to the Special Issue Applied Machine Learning Ⅱ)
Show Figures

Figure 1

Article
ReSTiNet: On Improving the Performance of Tiny-YOLO-Based CNN Architecture for Applications in Human Detection
Appl. Sci. 2022, 12(18), 9331; https://doi.org/10.3390/app12189331 - 17 Sep 2022
Cited by 2 | Viewed by 682
Abstract
Human detection is a special application of object recognition and is considered one of the greatest challenges in computer vision. It is the starting point of a number of applications, including public safety and security surveillance around the world. Human detection technologies have [...] Read more.
Human detection is a special application of object recognition and is considered one of the greatest challenges in computer vision. It is the starting point of a number of applications, including public safety and security surveillance around the world. Human detection technologies have advanced significantly in recent years due to the rapid development of deep learning techniques. Despite recent advances, we still need to adopt the best network-design practices that enable compact sizes, deep designs, and fast training times while maintaining high accuracies. In this article, we propose ReSTiNet, a novel compressed convolutional neural network that addresses the issues of size, detection speed, and accuracy. Following SqueezeNet, ReSTiNet adopts the fire modules by examining the number of fire modules and their placement within the model to reduce the number of parameters and thus the model size. The residual connections within the fire modules in ReSTiNet are interpolated and finely constructed to improve feature propagation and ensure the largest possible information flow in the model, with the goal of further improving the proposed ReSTiNet in terms of detection speed and accuracy. The proposed algorithm downsizes the previously popular Tiny-YOLO model and improves the following features: (1) faster detection speed; (2) compact model size; (3) solving the overfitting problems; and (4) superior performance than other lightweight models such as MobileNet and SqueezeNet in terms of mAP. The proposed model was trained and tested using MS COCO and Pascal VOC datasets. The resulting ReSTiNet model is 10.7 MB in size (almost five times smaller than Tiny-YOLO), but it achieves an mAP of 63.74% on PASCAL VOC and 27.3% on MS COCO datasets using Tesla k80 GPU. Full article
(This article belongs to the Special Issue Applied Machine Learning Ⅱ)
Show Figures

Figure 1

Article
Multi-Output Regression with Generative Adversarial Networks (MOR-GANs)
Appl. Sci. 2022, 12(18), 9209; https://doi.org/10.3390/app12189209 - 14 Sep 2022
Viewed by 332
Abstract
Regression modelling has always been a key process in unlocking the relationships between independent and dependent variables that are held within data. In recent years, machine learning has uncovered new insights in many fields, providing predictions to previously unsolved problems. Generative Adversarial Networks [...] Read more.
Regression modelling has always been a key process in unlocking the relationships between independent and dependent variables that are held within data. In recent years, machine learning has uncovered new insights in many fields, providing predictions to previously unsolved problems. Generative Adversarial Networks (GANs) have been widely applied to image processing producing good results, however, these methods have not often been applied to non-image data. Seeing the powerful generative capabilities of the GANs, we explore their use, here, as a regression method. In particular, we explore the use of the Wasserstein GAN (WGAN) as a multi-output regression method. The resulting method we call Multi-Output Regression GANs (MOR-GANs) and its performance is compared to a Gaussian Process Regression method (GPR)—a commonly used non-parametric regression method that has been well tested on small datasets with noisy responses. The WGAN regression model performs well for all types of datasets and exhibits substantial improvements over the performance of the GPR for certain types of datasets, demonstrating the flexibility of the GAN as a model for regression. Full article
(This article belongs to the Special Issue Applied Machine Learning Ⅱ)
Show Figures

Figure 1

Article
Towards Machine Learning Algorithms in Predicting the Clinical Evolution of Patients Diagnosed with COVID-19
Appl. Sci. 2022, 12(18), 8939; https://doi.org/10.3390/app12188939 - 06 Sep 2022
Viewed by 263
Abstract
Predictive modelling strategies can optimise the clinical diagnostic process by identifying patterns among various symptoms and risk factors, such as those presented in cases of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), also known as coronavirus (COVID-19). In this context, the present research [...] Read more.
Predictive modelling strategies can optimise the clinical diagnostic process by identifying patterns among various symptoms and risk factors, such as those presented in cases of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), also known as coronavirus (COVID-19). In this context, the present research proposes a comparative analysis using benchmarking techniques to evaluate and validate the performance of some classification algorithms applied to the same dataset, which contains information collected from patients diagnosed with COVID-19, registered in the Influenza Epidemiological Surveillance System (SIVEP). With this approach, 30,000 cases were analysed during the training and testing phase of the prediction models. This work proposes a comparative approach of machine learning algorithms (ML), working on the knowledge discovery task to predict clinical evolution in patients diagnosed with COVID-19. Our experiments show, through appropriate metrics, that the clinical evolution classification process of patients diagnosed with COVID-19 using the Multilayer Perceptron algorithm performs well against other ML algorithms. Its use has significant consequences for vital prognosis and agility in measures used in the first consultations in hospitals. Full article
(This article belongs to the Special Issue Applied Machine Learning Ⅱ)
Show Figures

Figure 1

Article
Textual Emotional Tone and Financial Crisis Identification in Chinese Companies: A Multi-Source Data Analysis Based on Machine Learning
Appl. Sci. 2022, 12(13), 6662; https://doi.org/10.3390/app12136662 - 30 Jun 2022
Cited by 1 | Viewed by 598
Abstract
Nowadays, China is faced with increasing downward pressure on its economy, along with an expanding business risk on listed companies in China. Listed companies, as the solid foundation of the national economy, once they face a financial crisis, will experience hazards from multiple [...] Read more.
Nowadays, China is faced with increasing downward pressure on its economy, along with an expanding business risk on listed companies in China. Listed companies, as the solid foundation of the national economy, once they face a financial crisis, will experience hazards from multiple perspectives. Therefore, the construction of an effective financial crisis early warning model can help listed companies predict, control and resolve their risks. Based on textual data, this paper proposes a web crawler and textual analysis, to assess the sentiment and tone of financial news texts and that of the management discussion and analysis (MD&A) section in annual financial reports of listed companies. The emotional tones of the two texts are used as external and internal information sources for listed companies, respectively, to measure whether they can improve the prediction accuracy of a financial crisis early warning model based on traditional financial indicators. By comparing the early warning effects of thirteen machine learning models, this paper finds that financial news, as external texts, can provide more incremental information for prediction models. In contrast, the emotional tone of MD&A, which can be easily modified by the management, will distort predictions. Comparing the early warning effect of machine learning models with different input feature variables, this paper also finds that DBGT, AdaBoost, random forest and Bagging models maintain stable and accurate sample recognition ability. This paper quantifies financial news texts, unraveling implied information hiding behind the surface, to further improve the accuracy of the financial crisis early warning model. Thus, it provides a new research perspective for related research in the field of financial crisis warnings for listed companies. Full article
(This article belongs to the Special Issue Applied Machine Learning Ⅱ)
Show Figures

Figure 1

Article
Comparative Study of Machine Learning Classifiers for Modelling Road Traffic Accidents
Appl. Sci. 2022, 12(2), 828; https://doi.org/10.3390/app12020828 - 14 Jan 2022
Cited by 5 | Viewed by 917
Abstract
Road traffic accidents (RTAs) are a major cause of injuries and fatalities worldwide. In recent years, there has been a growing global interest in analysing RTAs, specifically concerned with analysing and modelling accident data to better understand and assess the causes and effects [...] Read more.
Road traffic accidents (RTAs) are a major cause of injuries and fatalities worldwide. In recent years, there has been a growing global interest in analysing RTAs, specifically concerned with analysing and modelling accident data to better understand and assess the causes and effects of accidents. This study analysed the performance of widely used machine learning classifiers using a real-life RTA dataset from Gauteng, South Africa. The study aimed to assess prediction model designs for RTAs to assist transport authorities and policymakers. It considered classifiers such as naïve Bayes, logistic regression, k-nearest neighbour, AdaBoost, support vector machine, random forest, and five missing data methods. These classifiers were evaluated using five evaluation metrics: accuracy, root-mean-square error, precision, recall, and receiver operating characteristic curves. Furthermore, the assessment involved parameter adjustment and incorporated dimensionality reduction techniques. The empirical results and analyses show that the RF classifier, combined with multiple imputations by chained equations, yielded the best performance when compared with the other combinations. Full article
(This article belongs to the Special Issue Applied Machine Learning Ⅱ)
Show Figures

Figure 1

Article
Finger-Gesture Recognition for Visible Light Communication Systems Using Machine Learning
Appl. Sci. 2021, 11(24), 11582; https://doi.org/10.3390/app112411582 - 07 Dec 2021
Cited by 5 | Viewed by 667
Abstract
Gesture recognition (GR) has many applications for human-computer interaction (HCI) in the healthcare, home, and business arenas. However, the common techniques to realize gesture recognition using video processing are computationally intensive and expensive. In this work, we propose to task existing visible light [...] Read more.
Gesture recognition (GR) has many applications for human-computer interaction (HCI) in the healthcare, home, and business arenas. However, the common techniques to realize gesture recognition using video processing are computationally intensive and expensive. In this work, we propose to task existing visible light communications (VLC) systems with gesture recognition. Different finger movements are identified by training on the light transitions between fingers using the long short-term memory (LSTM) neural network. This paper describes the design and implementation of the gesture recognition technique for a practical VLC system operating over a distance of 48 cm. The platform uses a single low-cost light-emitting diode (LED) and photo-diode sensor at the receiver side. The system recognizes gestures from interruptions in the direct light transmission, and is therefore suitable for high-speed communication. Gesture recognition accuracies were conducted for five gestures, and results demonstrate that the proposed system is able to accurately identify the gestures in up to 88% of cases. Full article
(This article belongs to the Special Issue Applied Machine Learning Ⅱ)
Show Figures

Figure 1

Article
Ellipsoidal Path Planning for Unmanned Aerial Vehicles
Appl. Sci. 2021, 11(17), 7997; https://doi.org/10.3390/app11177997 - 29 Aug 2021
Cited by 3 | Viewed by 794
Abstract
The research in path planning for unmanned aerial vehicles (UAV) is an active topic nowadays. The path planning strategy highly depends on the map abstraction available. In a previous work, we presented an ellipsoidal mapping algorithm (EMA) that was designed using covariance ellipsoids [...] Read more.
The research in path planning for unmanned aerial vehicles (UAV) is an active topic nowadays. The path planning strategy highly depends on the map abstraction available. In a previous work, we presented an ellipsoidal mapping algorithm (EMA) that was designed using covariance ellipsoids and clustering algorithms. The EMA computes compact in-memory maps, but still with enough information to accurately represent the environment and to be useful for robot navigation algorithms. In this work, we develop a novel path planning algorithm based on a bio-inspired algorithm for navigation in the ellipsoidal map. Our approach overcomes the problem that there is no closed formula to calculate the distance between two ellipsoidal surfaces, so it was approximated using a trained neural network. The presented path planning algorithm takes advantage of ellipsoid entities to represent obstacles and compute paths for small UAVs regardless of the concavity of these obstacles, in a very geometrically explicit way. Furthermore, our method can also be used to plan routes in dynamical environments without adding any computational cost. Full article
(This article belongs to the Special Issue Applied Machine Learning Ⅱ)
Show Figures

Figure 1

Article
Automotive OEM Demand Forecasting: A Comparative Study of Forecasting Algorithms and Strategies
Appl. Sci. 2021, 11(15), 6787; https://doi.org/10.3390/app11156787 - 23 Jul 2021
Cited by 10 | Viewed by 1693
Abstract
Demand forecasting is a crucial component of demand management, directly impacting manufacturing companies’ planning, revenues, and actors through the supply chain. We evaluate 21 baseline, statistical, and machine learning algorithms to forecast smooth and erratic demand on a real-world use case scenario. The [...] Read more.
Demand forecasting is a crucial component of demand management, directly impacting manufacturing companies’ planning, revenues, and actors through the supply chain. We evaluate 21 baseline, statistical, and machine learning algorithms to forecast smooth and erratic demand on a real-world use case scenario. The products’ data were obtained from a European original equipment manufacturer targeting the global automotive industry market. Our research shows that global machine learning models achieve superior performance than local models. We show that forecast errors from global models can be constrained by pooling product data based on the past demand magnitude. We also propose a set of metrics and criteria for a comprehensive understanding of demand forecasting models’ performance. Full article
(This article belongs to the Special Issue Applied Machine Learning Ⅱ)
Show Figures

Figure 1

Article
A Heterogeneous Learning Framework for Over-the-Top Consumer Analysis Reflecting the Actual Market Environment
Appl. Sci. 2021, 11(11), 4783; https://doi.org/10.3390/app11114783 - 23 May 2021
Cited by 2 | Viewed by 886
Abstract
The over-the-top (OTT) market for media consumption over wired and wireless Internet is growing. It is, therefore, crucial that service providers and carriers participating in the OTT market analyze consumer traffic for pricing, service delivery, infrastructure investments, etc. The OTT market has many [...] Read more.
The over-the-top (OTT) market for media consumption over wired and wireless Internet is growing. It is, therefore, crucial that service providers and carriers participating in the OTT market analyze consumer traffic for pricing, service delivery, infrastructure investments, etc. The OTT market has many consumer groups, but the proportion of users is not consistent in each. Furthermore, as multimedia consumption has increased owing to the COVID-19 epidemic, the OTT market has changed rapidly. If this is not reflected, the analysis will not be accurate. Therefore, we propose a framework that can classify consumers well based on actual OTT market environment conditions. First, by applying our proposed conditional probability-based method to basic machine learning techniques, such as support vector machine, k-nearest neighbor, and decision tree, we can improve the classification performance, even for an imbalanced OTT consumer distribution. Then, it is possible to analyze the changing consumer trends by dynamically retraining the incoming OTT consumer data. Conventional methods result in low classification accuracy in low-number classes, but our method shows an improvement of 5.3–19.2% based on recall. Moreover, conventional methods have shown large fluctuations in performance as the OTT market environment has changed, but our framework consistently maintains high performance. Full article
(This article belongs to the Special Issue Applied Machine Learning Ⅱ)
Show Figures

Figure 1

Article
Dynamic Segmentation for Physical Activity Recognition Using a Single Wearable Sensor
Appl. Sci. 2021, 11(6), 2633; https://doi.org/10.3390/app11062633 - 16 Mar 2021
Cited by 9 | Viewed by 1052
Abstract
Data segmentation is an essential process in activity recognition when using machine learning techniques. Previous studies on physical activity recognition have mostly relied on the sliding window approach for segmentation. However, choosing a fixed window size for multiple activities with different durations may [...] Read more.
Data segmentation is an essential process in activity recognition when using machine learning techniques. Previous studies on physical activity recognition have mostly relied on the sliding window approach for segmentation. However, choosing a fixed window size for multiple activities with different durations may affect recognition accuracy, especially when the activities belong to the same category (i.e., dynamic or static). This paper presents and verifies a new method for dynamic segmentation of physical activities performed during the rehabilitation of individuals with spinal cord injuries. To adaptively segment the raw data, signal characteristics are analyzed to determine the suitable type of boundaries. Then, the algorithm identifies the time boundaries to represent the start- and endpoints of each activity. To verify the method and build a predictive model, an experiment was conducted in which data were collected using a single wrist-worn accelerometer sensor. The experimental results were compared with the sliding window approach, indicating that the proposed method outperformed the sliding window approach in terms of overall accuracy, which exceeded 5%, as well as model robustness. The results also demonstrated efficient physical activity segmentation using the proposed method, resulting in high classification performance for all activities considered. Full article
(This article belongs to the Special Issue Applied Machine Learning Ⅱ)
Show Figures

Figure 1

Other

Jump to: Research

Concept Paper
DNA Computing: Concepts for Medical Applications
Appl. Sci. 2022, 12(14), 6928; https://doi.org/10.3390/app12146928 - 08 Jul 2022
Viewed by 639
Abstract
The branch of informatics that deals with construction and operation of computers built of DNA, is one of the research directions which investigates issues related to the use of DNA as hardware and software. This concept assumes the use of DNA computers due [...] Read more.
The branch of informatics that deals with construction and operation of computers built of DNA, is one of the research directions which investigates issues related to the use of DNA as hardware and software. This concept assumes the use of DNA computers due to their biological origin mainly for intelligent, personalized and targeted diagnostics frequently related to therapy. Important elements of this concept are (1) the retrieval of unique DNA sequences using machine learning methods and, based on the results of this process, (2) the construction/design of smart diagnostic biochip projects. The authors of this paper propose a new concept of designing diagnostic biochips, the key elements of which are machine-learning methods and the concept of biomolecular queue automata. This approach enables the scheduling of computational tasks at the molecular level by sequential events of cutting and ligating DNA molecules. We also summarize current challenges and perspectives of biomolecular computer application and machine-learning approaches using DNA sequence data mining. Full article
(This article belongs to the Special Issue Applied Machine Learning Ⅱ)
Show Figures

Figure 1

Back to TopTop