Artificial Intelligence and Machine Learning Based Methods and Applications

A special issue of Mathematics (ISSN 2227-7390). This special issue belongs to the section "Mathematics and Computer Science".

Deadline for manuscript submissions: closed (31 December 2023) | Viewed by 44826

Special Issue Editors

Department of Computer Science, Faculty of Mathematics and Computer Science, Babes Bolyai University, 1st Mihail Kogălniceanu Street, 400084 Cluj-Napoca, Romania
Interests: computer vision; deep learning; convolutional neural networks; unsupervised learning; methods; facial feature analysis; mathematical models
Department of Computer Science, Faculty of Mathematics and Computer Science, Babes Bolyai University, 1st Mihail Kogălniceanu Street, 400084 Cluj-Napoca, Romania
Interests: deep learning; biometrics; visual surveillance; facial feature analysis

Special Issue Information

Dear Colleagues,

Recent developments in artificial intelligence and especially machine learning have led these fields of research from purely theoretic approaches to fully applied industrial research not only in computer science, but in pretty much every other conceivable domain as well.

Globally, artificial intelligence (AI) has become one of the core areas providing fundamental building blocks for computer vision systems, computational modeling, security threat assessment, systems mimicking biological intelligence, multiagent systems, data transformation methods, etc.

The purpose of this Special Issue is to provide a research-publishing environment where articles with the latest developments not only in theoretical mathematical aspects of AI and machine learning, but also practical applications of ML and AI in computer vision, vision systems, statistical learning, reinforcement learning, and deep learning, data analysis and filtering, data transformation, speech processing, clustering and classification, knowledge extraction and discovery, natural language processing, and parallel and distributed AI methods could be submitted.

Contributions are welcome on both theoretical and practical models. The selection criteria will be based on formal and technical soundness, experimental support, and the relevance of the contribution.

Dr. Adrian Sergiu Darabant
Dr. Diana-Laura Borza
Guest Editors

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. Mathematics 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 2600 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.

Keywords

  • computer vision
  • classification and clustering
  • reinforcement learning
  • learning algorithms
  • pattern recognition
  • data filtering and transformation
  • parallelization in learning algorithms
  • probabilistic and statistical methods
  • deep neural networks
  • convolutional neural networks
  • adversarial systems
  • intelligent agents
  • evolutionary programming
  • text analysis
  • natural language processing (NLP)
  • feature extraction and analysis

Published Papers (25 papers)

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

Research

36 pages, 4271 KiB  
Article
Automated Classification of Agricultural Species through Parallel Artificial Multiple Intelligence System–Ensemble Deep Learning
by Keartisak Sriprateep, Surajet Khonjun, Paulina Golinska-Dawson, Rapeepan Pitakaso, Peerawat Luesak, Thanatkij Srichok, Somphop Chiaranai, Sarayut Gonwirat and Budsaba Buakum
Mathematics 2024, 12(2), 351; https://0-doi-org.brum.beds.ac.uk/10.3390/math12020351 - 22 Jan 2024
Viewed by 1126
Abstract
The classification of certain agricultural species poses a formidable challenge due to their inherent resemblance and the absence of dependable visual discriminators. The accurate identification of these plants holds substantial importance in industries such as cosmetics, pharmaceuticals, and herbal medicine, where the optimization [...] Read more.
The classification of certain agricultural species poses a formidable challenge due to their inherent resemblance and the absence of dependable visual discriminators. The accurate identification of these plants holds substantial importance in industries such as cosmetics, pharmaceuticals, and herbal medicine, where the optimization of essential compound yields and product quality is paramount. In response to this challenge, we have devised an automated classification system based on deep learning principles, designed to achieve precision and efficiency in species classification. Our approach leverages a diverse dataset encompassing various cultivars and employs the Parallel Artificial Multiple Intelligence System–Ensemble Deep Learning model (P-AMIS-E). This model integrates ensemble image segmentation techniques, including U-Net and Mask-R-CNN, alongside image augmentation and convolutional neural network (CNN) architectures such as SqueezeNet, ShuffleNetv2 1.0x, MobileNetV3, and InceptionV1. The culmination of these elements results in the P-AMIS-E model, enhanced by an Artificial Multiple Intelligence System (AMIS) for decision fusion, ultimately achieving an impressive accuracy rate of 98.41%. This accuracy notably surpasses the performance of existing methods, such as ResNet-101 and Xception, which attain 93.74% accuracy on the testing dataset. Moreover, when applied to an unseen dataset, the P-AMIS-E model demonstrates a substantial advantage, yielding accuracy rates ranging from 4.45% to 31.16% higher than those of the compared methods. It is worth highlighting that our heterogeneous ensemble approach consistently outperforms both single large models and homogeneous ensemble methods, achieving an average improvement of 13.45%. This paper provides a case study focused on the Centella Asiatica Urban (CAU) cultivar to exemplify the practical application of our approach. By integrating image segmentation, augmentation, and decision fusion, we have significantly enhanced accuracy and efficiency. This research holds theoretical implications for the advancement of deep learning techniques in image classification tasks while also offering practical benefits for industries reliant on precise species identification. Full article
Show Figures

Figure 1

23 pages, 14459 KiB  
Article
Investigating Effective Geometric Transformation for Image Augmentation to Improve Static Hand Gestures with a Pre-Trained Convolutional Neural Network
by Baiti-Ahmad Awaluddin, Chun-Tang Chao and Juing-Shian Chiou
Mathematics 2023, 11(23), 4783; https://0-doi-org.brum.beds.ac.uk/10.3390/math11234783 - 27 Nov 2023
Cited by 1 | Viewed by 809
Abstract
Hand gesture recognition (HGR) is a challenging and fascinating research topic in computer vision with numerous daily life applications. In HGR, computers aim to identify and classify hand gestures. The limited diversity of the dataset used in HGR is due to the limited [...] Read more.
Hand gesture recognition (HGR) is a challenging and fascinating research topic in computer vision with numerous daily life applications. In HGR, computers aim to identify and classify hand gestures. The limited diversity of the dataset used in HGR is due to the limited number of hand gesture demonstrators, acquisition environments, and hand pose variations despite previous efforts. Geometric image augmentations are commonly used to address these limitations. These augmentations include scaling, translation, rotation, flipping, and image shearing. However, research has yet to focus on identifying the best geometric transformations for augmenting the HGR dataset. This study employed three commonly utilized pre-trained models for image classification tasks, namely ResNet50, MobileNetV2, and InceptionV3. The system’s performance was evaluated on five static HGR datasets: DLSI, HG14, ArabicASL, MU HandImages ASL, and Sebastian Marcell. The experimental results demonstrate that many geometric transformations are unnecessary for HGR image augmentation. Image shearing and horizontal flipping are the most influential transformations for augmenting the HGR dataset and achieving better classification performance. Moreover, ResNet50 outperforms MobileNetV2 and InceptionV3 for static HGR. Full article
Show Figures

Figure 1

12 pages, 1271 KiB  
Article
Predictive Prompts with Joint Training of Large Language Models for Explainable Recommendation
by Ching-Sheng Lin, Chung-Nan Tsai, Shao-Tang Su, Jung-Sing Jwo, Cheng-Hsiung Lee and Xin Wang
Mathematics 2023, 11(20), 4230; https://0-doi-org.brum.beds.ac.uk/10.3390/math11204230 - 10 Oct 2023
Viewed by 1197
Abstract
Large language models have recently gained popularity in various applications due to their ability to generate natural text for complex tasks. Recommendation systems, one of the frequently studied research topics, can be further improved using the capabilities of large language models to track [...] Read more.
Large language models have recently gained popularity in various applications due to their ability to generate natural text for complex tasks. Recommendation systems, one of the frequently studied research topics, can be further improved using the capabilities of large language models to track and understand user behaviors and preferences. In this research, we aim to build reliable and transparent recommendation system by generating human-readable explanations to help users obtain better insights into the recommended items and gain more trust. We propose a learning scheme to jointly train the rating prediction task and explanation generation task. The rating prediction task learns the predictive representation from the input of user and item vectors. Subsequently, inspired by the recent success of prompt engineering, these predictive representations are served as predictive prompts, which are soft embeddings, to elicit and steer any knowledge behind language models for the explanation generation task. Empirical studies show that the proposed approach achieves competitive results compared with other existing baselines on the public English TripAdvisor dataset of explainable recommendations. Full article
Show Figures

Figure 1

30 pages, 699 KiB  
Article
Item Difficulty Prediction Using Item Text Features: Comparison of Predictive Performance across Machine-Learning Algorithms
by Lubomír Štěpánek, Jana Dlouhá and Patrícia Martinková
Mathematics 2023, 11(19), 4104; https://0-doi-org.brum.beds.ac.uk/10.3390/math11194104 - 28 Sep 2023
Cited by 1 | Viewed by 1287
Abstract
This work presents a comparative analysis of various machine learning (ML) methods for predicting item difficulty in English reading comprehension tests using text features extracted from item wordings. A wide range of ML algorithms are employed within both the supervised regression and the [...] Read more.
This work presents a comparative analysis of various machine learning (ML) methods for predicting item difficulty in English reading comprehension tests using text features extracted from item wordings. A wide range of ML algorithms are employed within both the supervised regression and the classification tasks, including regularization methods, support vector machines, trees, random forests, back-propagation neural networks, and Naïve Bayes; moreover, the ML algorithms are compared to the performance of domain experts. Using f-fold cross-validation and considering the root mean square error (RMSE) as the performance metric, elastic net outperformed other approaches in a continuous item difficulty prediction. Within classifiers, random forests returned the highest extended predictive accuracy. We demonstrate that the ML algorithms implementing item text features can compete with predictions made by domain experts, and we suggest that they should be used to inform and improve these predictions, especially when item pre-testing is limited or unavailable. Future research is needed to study the performance of the ML algorithms using item text features on different item types and respondent populations. Full article
Show Figures

Figure 1

14 pages, 2721 KiB  
Article
BAE: Anomaly Detection Algorithm Based on Clustering and Autoencoder
by Dongqi Wang, Mingshuo Nie and Dongming Chen
Mathematics 2023, 11(15), 3398; https://0-doi-org.brum.beds.ac.uk/10.3390/math11153398 - 03 Aug 2023
Viewed by 1127
Abstract
In this paper, we propose an outlier-detection algorithm for detecting network traffic anomalies based on a clustering algorithm and an autoencoder model. The BIRCH clustering algorithm is employed as the pre-algorithm of the autoencoder to pre-classify datasets with complex data distribution characteristics, while [...] Read more.
In this paper, we propose an outlier-detection algorithm for detecting network traffic anomalies based on a clustering algorithm and an autoencoder model. The BIRCH clustering algorithm is employed as the pre-algorithm of the autoencoder to pre-classify datasets with complex data distribution characteristics, while the autoencoder model is used to detect outliers based on a threshold. The proposed BIRCH-Autoencoder (BAE) algorithm has been tested on four network security datasets, KDDCUP99, UNSW-NB15, CICIDS2017, and NSL-KDD, and compared with representative algorithms. The BAE algorithm achieved average F-scores of 96.160, 81.132, and 91.424 on the KDDCUP99, UNSW-NB15, and CICIDS2017 datasets, respectively. These experimental results demonstrate that the proposed approach can effectively and accurately detect anomalous data. Full article
Show Figures

Figure 1

11 pages, 481 KiB  
Article
Global-Local Dynamic Adversarial Learning for Cross-Domain Sentiment Analysis
by Juntao Lyu, Zheyuan Zhang, Shufeng Chen and Xiying Fan
Mathematics 2023, 11(14), 3130; https://0-doi-org.brum.beds.ac.uk/10.3390/math11143130 - 15 Jul 2023
Viewed by 776
Abstract
As one of the most widely used applications in domain adaption (DA), Cross-domain sentiment analysis (CDSA) aims to tackle the barrier of lacking in sentiment labeled data. Applying an adversarial network to DA to reduce the distribution discrepancy between source and target domains [...] Read more.
As one of the most widely used applications in domain adaption (DA), Cross-domain sentiment analysis (CDSA) aims to tackle the barrier of lacking in sentiment labeled data. Applying an adversarial network to DA to reduce the distribution discrepancy between source and target domains is a significant advance in CDSA. This adversarial DA paradigm utilizes a single global domain discriminator or a series of local domain discriminators to reduce marginal or conditional probability distribution discrepancies. In general, each discrepancy has a different effect on domain adaption. However, the existing CDSA algorithms ignore this point. Therefore, in this paper, we propose an effective, novel and unsupervised adversarial DA paradigm, Global-Local Dynamic Adversarial Learning (GLDAL). This paradigm is able to quantitively evaluate the weights of global distribution and every local distribution. We also study how to apply GLDAL to CDSA. As GLDAL can effectively reduce the distribution discrepancy between domains, it performs well in a series of CDSA experiments and achieves improvements in classification accuracy compared to similar methods. The effectiveness of each component is demonstrated through ablation experiments on different parts and a quantitative analysis of the dynamic factor. Overall, this approach achieves the desired DA effect with domain shifts. Full article
Show Figures

Figure 1

14 pages, 1943 KiB  
Article
Greenhouse Micro-Climate Prediction Based on Fixed Sensor Placements: A Machine Learning Approach
by Oladayo S. Ajani, Member Joy Usigbe, Esther Aboyeji, Daniel Dooyum Uyeh, Yushin Ha, Tusan Park and Rammohan Mallipeddi
Mathematics 2023, 11(14), 3052; https://0-doi-org.brum.beds.ac.uk/10.3390/math11143052 - 10 Jul 2023
Cited by 5 | Viewed by 1841
Abstract
Accurate measurement of micro-climates that include temperature and relative humidity is the bedrock of the control and management of plant life in protected cultivation systems. Hence, the use of a large number of sensors distributed within the greenhouse or mobile sensors that can [...] Read more.
Accurate measurement of micro-climates that include temperature and relative humidity is the bedrock of the control and management of plant life in protected cultivation systems. Hence, the use of a large number of sensors distributed within the greenhouse or mobile sensors that can be moved from one location to another has been proposed, which are both capital and labor-intensive. On the contrary, accurate measurement of micro-climates can be achieved through the identification of the optimal number of sensors and their optimal locations, whose measurements are representative of the micro-climate in the entire greenhouse. However, given the number of sensors, their optimal locations are proven to vary from time to time as the outdoor weather conditions change. Therefore, regularly shifting the sensors to their optimal locations with the change in outdoor conditions is cost-intensive and may not be appropriate. In this paper, a framework based on the dense neural network (DNN) is proposed to predict the measurements (temperature and humidity) corresponding to the optimal sensor locations, which vary relative to the outdoor weather, using the measurements from sensors whose locations are fixed. The employed framework demonstrates a very high correlation between the true and predicted values with an average coefficient value of 0.91 and 0.85 for both temperature and humidity, respectively. In other words, through a combination of the optimal number of fixed sensors and DNN architecture that performs multi-channel regression, we estimate the micro-climate of the greenhouse. Full article
Show Figures

Figure 1

13 pages, 5619 KiB  
Article
A Semi-Federated Active Learning Framework for Unlabeled Online Network Data
by Yuwen Zhou, Yuhan Hu, Jing Sun, Rui He and Wenjie Kang
Mathematics 2023, 11(8), 1972; https://0-doi-org.brum.beds.ac.uk/10.3390/math11081972 - 21 Apr 2023
Viewed by 1022
Abstract
Federated Learning (FL) is a newly emerged federated optimization technique for distributed data in a federated network. The participants in FL that train the model locally are classified into client nodes. The server node assumes the responsibility to aggregate local models from client [...] Read more.
Federated Learning (FL) is a newly emerged federated optimization technique for distributed data in a federated network. The participants in FL that train the model locally are classified into client nodes. The server node assumes the responsibility to aggregate local models from client nodes without data moving. In this regard, FL is an ideal solution to protect data privacy at each node of the network. However, the raw data generated on each node are unlabeled, making it impossible for FL to apply these data directly to train a model. The large volume of data annotating work prevents FL from being widely applied in the real world, especially for online scenarios, where the data are generated continuously. Meanwhile, the data generated on different nodes tend to be differently distributed. It has been proved theoretically and experimentally that non-independent and identically distributed (non-IID) data harm the performance of FL. In this article, we design a semi-federated active learning (semi-FAL) framework to tackle the annotation and non-IID problems jointly. More specifically, the server node can provide (i) a pre-trained model to help each client node annotate the local data uniformly and (ii) an estimation of the global gradient to help correct the local gradient. The evaluation results demonstrate our semi-FAL framework can efficiently handle unlabeled online network data and achieves high accuracy and fast convergence. Full article
Show Figures

Figure 1

15 pages, 2946 KiB  
Article
MelodyDiffusion: Chord-Conditioned Melody Generation Using a Transformer-Based Diffusion Model
by Shuyu Li and Yunsick Sung
Mathematics 2023, 11(8), 1915; https://0-doi-org.brum.beds.ac.uk/10.3390/math11081915 - 18 Apr 2023
Cited by 3 | Viewed by 2488
Abstract
Artificial intelligence, particularly machine learning, has begun to permeate various real-world applications and is continually being explored in automatic music generation. The approaches to music generation can be broadly divided into two categories: rule-based and data-driven methods. Rule-based approaches rely on substantial prior [...] Read more.
Artificial intelligence, particularly machine learning, has begun to permeate various real-world applications and is continually being explored in automatic music generation. The approaches to music generation can be broadly divided into two categories: rule-based and data-driven methods. Rule-based approaches rely on substantial prior knowledge and may struggle to handle large datasets, whereas data-driven approaches can solve these problems and have become increasingly popular. However, data-driven approaches still face challenges such as the difficulty of considering long-distance dependencies when handling discrete-sequence data and convergence during model training. Although the diffusion model has been introduced as a generative model to solve the convergence problem in generative adversarial networks, it has not yet been applied to discrete-sequence data. This paper proposes a transformer-based diffusion model known as MelodyDiffusion to handle discrete musical data and realize chord-conditioned melody generation. MelodyDiffusion replaces the U-nets used in traditional diffusion models with transformers to consider the long-distance dependencies using attention and parallel mechanisms. Moreover, a transformer-based encoder is designed to extract contextual information from chords as a condition to guide melody generation. MelodyDiffusion can automatically generate diverse melodies based on the provided chords in practical applications. The evaluation experiments, in which Hits@k was used as a metric to evaluate the restored melodies, demonstrate that the large-scale version of MelodyDiffusion achieves an accuracy of 72.41% (k = 1). Full article
Show Figures

Figure 1

35 pages, 5054 KiB  
Article
Performance Analysis of Long Short-Term Memory Predictive Neural Networks on Time Series Data
by Roland Bolboacă and Piroska Haller
Mathematics 2023, 11(6), 1432; https://0-doi-org.brum.beds.ac.uk/10.3390/math11061432 - 15 Mar 2023
Cited by 9 | Viewed by 2369
Abstract
Long short-term memory neural networks have been proposed as a means of creating accurate models from large time series data originating from various fields. These models can further be utilized for prediction, control, or anomaly-detection algorithms. However, finding the optimal hyperparameters to maximize [...] Read more.
Long short-term memory neural networks have been proposed as a means of creating accurate models from large time series data originating from various fields. These models can further be utilized for prediction, control, or anomaly-detection algorithms. However, finding the optimal hyperparameters to maximize different performance criteria remains a challenge for both novice and experienced users. Hyperparameter optimization algorithms can often be a resource-intensive and time-consuming task, particularly when the impact of the hyperparameters on the performance of the neural network is not comprehended or known. Teacher forcing denotes a procedure that involves feeding the ground truth output from the previous time-step as input to the current time-step during training, while during testing feeding back the predicted values. This paper presents a comprehensive examination of the impact of hyperparameters on long short-term neural networks, with and without teacher forcing, on prediction performance. The study includes testing long short-term memory neural networks, with two variations of teacher forcing, in two prediction modes, using two configurations (i.e., multi-input single-output and multi-input multi-output) on a well-known chemical process simulation dataset. Furthermore, this paper demonstrates the applicability of a long short-term memory neural network with a modified teacher forcing approach in a process state monitoring system. Over 100,000 experiments were conducted with varying hyperparameters and in multiple neural network operation modes, revealing the direct impact of each tested hyperparameter on the training and testing procedures. Full article
Show Figures

Figure 1

16 pages, 2718 KiB  
Article
TwoViewDensityNet: Two-View Mammographic Breast Density Classification Based on Deep Convolutional Neural Network
by Mariam Busaleh, Muhammad Hussain, Hatim A. Aboalsamh, Fazal-e-Amin and Sarah A. Al Sultan
Mathematics 2022, 10(23), 4610; https://0-doi-org.brum.beds.ac.uk/10.3390/math10234610 - 05 Dec 2022
Cited by 2 | Viewed by 2146
Abstract
Dense breast tissue is a significant factor that increases the risk of breast cancer. Current mammographic density classification approaches are unable to provide enough classification accuracy. However, it remains a difficult problem to classify breast density. This paper proposes TwoViewDensityNet, an end-to-end deep [...] Read more.
Dense breast tissue is a significant factor that increases the risk of breast cancer. Current mammographic density classification approaches are unable to provide enough classification accuracy. However, it remains a difficult problem to classify breast density. This paper proposes TwoViewDensityNet, an end-to-end deep learning-based method for mammographic breast density classification. The craniocaudal (CC) and mediolateral oblique (MLO) views of screening mammography provide two different views of each breast. As the two views are complementary, and dual-view-based methods have proven efficient, we use two views for breast classification. The loss function plays a key role in training a deep model; we employ the focal loss function because it focuses on learning hard cases. The method was thoroughly evaluated on two public datasets using 5-fold cross-validation, and it achieved an overall performance (F-score of 98.63%, AUC of 99.51%, accuracy of 95.83%) on DDSM and (F-score of 97.14%, AUC of 97.44%, accuracy of 96%) on the INbreast. The comparison shows that the TwoViewDensityNet outperforms the state-of-the-art methods for classifying breast density into BI-RADS class. It aids healthcare providers in providing patients with more accurate information and will help improve the diagnostic accuracy and reliability of mammographic breast density evaluation in clinical care. Full article
Show Figures

Figure 1

35 pages, 1598 KiB  
Article
A Comparison of Several AI Techniques for Authorship Attribution on Romanian Texts
by Sanda-Maria Avram and Mihai Oltean
Mathematics 2022, 10(23), 4589; https://0-doi-org.brum.beds.ac.uk/10.3390/math10234589 - 03 Dec 2022
Cited by 2 | Viewed by 1690
Abstract
Determining the author of a text is a difficult task. Here, we compare multiple Artificial Intelligence techniques for classifying literary texts written by multiple authors by taking into account a limited number of speech parts (prepositions, adverbs, and conjunctions). We also introduce a [...] Read more.
Determining the author of a text is a difficult task. Here, we compare multiple Artificial Intelligence techniques for classifying literary texts written by multiple authors by taking into account a limited number of speech parts (prepositions, adverbs, and conjunctions). We also introduce a new dataset composed of texts written in the Romanian language on which we have run the algorithms. The compared methods are artificial neural networks, multi-expression programming, k-nearest neighbour, support vector machines, and decision trees with C5.0. Numerical experiments show, first of all, that the problem is difficult, but some algorithms are able to generate acceptable error rates on the test set. Full article
Show Figures

Figure 1

21 pages, 4079 KiB  
Article
Polynomial Fuzzy Information Granule-Based Time Series Prediction
by Xiyang Yang, Shiqing Zhang, Xinjun Zhang and Fusheng Yu
Mathematics 2022, 10(23), 4495; https://0-doi-org.brum.beds.ac.uk/10.3390/math10234495 - 28 Nov 2022
Cited by 1 | Viewed by 1335
Abstract
Fuzzy information granulation transfers the time series analysis from the numerical platform to the granular platform, which enables us to study the time series at a different granularity. In previous studies, each fuzzy information granule in a granular time series can reflect the [...] Read more.
Fuzzy information granulation transfers the time series analysis from the numerical platform to the granular platform, which enables us to study the time series at a different granularity. In previous studies, each fuzzy information granule in a granular time series can reflect the average, range, and linear trend characteristics of the data in the corresponding time window. In order to get a more general information granule, this paper proposes polynomial fuzzy information granules, each of which can reflect both the linear trend and the nonlinear trend of the data in a time window. The distance metric of the proposed information granules is given theoretically. After studying the distance measure of the polynomial fuzzy information granule and its geometric interpretation, we design a time series prediction method based on the polynomial fuzzy information granules and fuzzy inference system. The experimental results show that the proposed prediction method can achieve a good long-term prediction. Full article
Show Figures

Graphical abstract

12 pages, 2519 KiB  
Article
Novel Reinforcement Learning Research Platform for Role-Playing Games
by Petra Csereoka, Bogdan-Ionuţ Roman, Mihai Victor Micea  and Călin-Adrian Popa
Mathematics 2022, 10(22), 4363; https://0-doi-org.brum.beds.ac.uk/10.3390/math10224363 - 20 Nov 2022
Cited by 3 | Viewed by 1469
Abstract
The latest achievements in the field of reinforcement learning have encouraged the development of vision-based learning methods that compete with human-provided results obtained on various games and training environments. Convolutional neural networks together with Q-learning-based approaches have managed to solve and outperform human [...] Read more.
The latest achievements in the field of reinforcement learning have encouraged the development of vision-based learning methods that compete with human-provided results obtained on various games and training environments. Convolutional neural networks together with Q-learning-based approaches have managed to solve and outperform human players in environments such as Atari 2600, Doom or StarCraft II, but the niche of 3D realistic games with a high degree of freedom of movement and rich graphics remains unexplored, despite having the highest resemblance to real-world situations. In this paper, we propose a novel testbed to push the limits of deep learning methods, namely an OpenAI Gym-like environment based on Dark Souls III, a notoriously difficult role-playing game, where even human players have reportedly struggled. We explore two types of architectures, Deep Q-Network and Deep Recurrent Q-Network, providing the results of a first incursion into this new problem class. The source code for the training environment and baselines is made available. Full article
Show Figures

Figure 1

22 pages, 3864 KiB  
Article
On Methods for Merging Mixture Model Components Suitable for Unsupervised Image Segmentation Tasks
by Branislav Panić, Marko Nagode, Jernej Klemenc and Simon Oman
Mathematics 2022, 10(22), 4301; https://0-doi-org.brum.beds.ac.uk/10.3390/math10224301 - 16 Nov 2022
Cited by 2 | Viewed by 1465
Abstract
Unsupervised image segmentation is one of the most important and fundamental tasks in many computer vision systems. Mixture model is a compelling framework for unsupervised image segmentation. A segmented image is obtained by clustering the pixel color values of the image with an [...] Read more.
Unsupervised image segmentation is one of the most important and fundamental tasks in many computer vision systems. Mixture model is a compelling framework for unsupervised image segmentation. A segmented image is obtained by clustering the pixel color values of the image with an estimated mixture model. Problems arise when the selected optimal mixture model contains a large number of mixture components. Then, multiple components of the estimated mixture model are better suited to describe individual segments of the image. We investigate methods for merging the components of the mixture model and their usefulness for unsupervised image segmentation. We define a simple heuristic for optimal segmentation with merging of the components of the mixture model. The experiments were performed with gray-scale and color images. The reported results and the performed comparisons with popular clustering approaches show clear benefits of merging components of the mixture model for unsupervised image segmentation. Full article
Show Figures

Figure 1

15 pages, 632 KiB  
Article
Effective Online Knowledge Distillation via Attention-Based Model Ensembling
by Diana-Laura Borza, Adrian Sergiu Darabant, Tudor Alexandru Ileni and Alexandru-Ion Marinescu
Mathematics 2022, 10(22), 4285; https://0-doi-org.brum.beds.ac.uk/10.3390/math10224285 - 16 Nov 2022
Cited by 1 | Viewed by 2150
Abstract
Large-scale deep learning models have achieved impressive results on a variety of tasks; however, their deployment on edge or mobile devices is still a challenge due to the limited available memory and computational capability. Knowledge distillation is an effective model compression technique, which [...] Read more.
Large-scale deep learning models have achieved impressive results on a variety of tasks; however, their deployment on edge or mobile devices is still a challenge due to the limited available memory and computational capability. Knowledge distillation is an effective model compression technique, which can boost the performance of a lightweight student network by transferring the knowledge from a more complex model or an ensemble of models. Due to its reduced size, this lightweight model is more suitable for deployment on edge devices. In this paper, we introduce an online knowledge distillation framework, which relies on an original attention mechanism to effectively combine the predictions of a cohort of lightweight (student) networks into a powerful ensemble, and use this as a distillation signal. The proposed aggregation strategy uses the predictions of the individual students as well as ground truth data to determine a set of weights needed for ensembling these predictions. This mechanism is solely used during system training. When testing or at inference time, a single, lightweight student is extracted and used. The extensive experiments we performed on several image classification benchmarks, both by training models from scratch (on CIFAR-10, CIFAR-100, and Tiny ImageNet datasets) and using transfer learning (on Oxford Pets and Oxford Flowers datasets), showed that the proposed framework always leads to an improvement in the accuracy of knowledge-distilled students and demonstrates the effectiveness of the proposed solution. Moreover, in the case of ResNet architecture, we observed that the knowledge-distilled model achieves a higher accuracy than a deeper, individually trained ResNet model. Full article
Show Figures

Figure 1

17 pages, 1976 KiB  
Article
Interpretable Deep Learning for Discriminating Pneumonia from Lung Ultrasounds
by Mohamed Abdel-Basset, Hossam Hawash, Khalid Abdulaziz Alnowibet, Ali Wagdy Mohamed and Karam M. Sallam
Mathematics 2022, 10(21), 4153; https://0-doi-org.brum.beds.ac.uk/10.3390/math10214153 - 06 Nov 2022
Cited by 3 | Viewed by 1622
Abstract
Lung ultrasound images have shown great promise to be an operative point-of-care test for the diagnosis of COVID-19 because of the ease of procedure with negligible individual protection equipment, together with relaxed disinfection. Deep learning (DL) is a robust tool for modeling infection [...] Read more.
Lung ultrasound images have shown great promise to be an operative point-of-care test for the diagnosis of COVID-19 because of the ease of procedure with negligible individual protection equipment, together with relaxed disinfection. Deep learning (DL) is a robust tool for modeling infection patterns from medical images; however, the existing COVID-19 detection models are complex and thereby are hard to deploy in frequently used mobile platforms in point-of-care testing. Moreover, most of the COVID-19 detection models in the existing literature on DL are implemented as a black box, hence, they are hard to be interpreted or trusted by the healthcare community. This paper presents a novel interpretable DL framework discriminating COVID-19 infection from other cases of pneumonia and normal cases using ultrasound data of patients. In the proposed framework, novel transformer modules are introduced to model the pathological information from ultrasound frames using an improved window-based multi-head self-attention layer. A convolutional patching module is introduced to transform input frames into latent space rather than partitioning input into patches. A weighted pooling module is presented to score the embeddings of the disease representations obtained from the transformer modules to attend to information that is most valuable for the screening decision. Experimental analysis of the public three-class lung ultrasound dataset (PCUS dataset) demonstrates the discriminative power (Accuracy: 93.4%, F1-score: 93.1%, AUC: 97.5%) of the proposed solution overcoming the competing approaches while maintaining low complexity. The proposed model obtained very promising results in comparison with the rival models. More importantly, it gives explainable outputs therefore, it can serve as a candidate tool for empowering the sustainable diagnosis of COVID-19-like diseases in smart healthcare. Full article
Show Figures

Figure 1

31 pages, 10190 KiB  
Article
An Improved Machine Learning Model with Hybrid Technique in VANET for Robust Communication
by Gagan Preet Kour Marwah, Anuj Jain, Praveen Kumar Malik, Manwinder Singh, Sudeep Tanwar, Calin Ovidiu Safirescu, Traian Candin Mihaltan, Ravi Sharma and Ahmed Alkhayyat
Mathematics 2022, 10(21), 4030; https://0-doi-org.brum.beds.ac.uk/10.3390/math10214030 - 30 Oct 2022
Cited by 21 | Viewed by 1810
Abstract
The vehicular ad hoc network, VANET, is one of the most popular and promising technologies in intelligent transportation today. However, VANET is susceptible to several vulnerabilities that result in an intrusion. This intrusion must be solved before VANET technology can be adopted. In [...] Read more.
The vehicular ad hoc network, VANET, is one of the most popular and promising technologies in intelligent transportation today. However, VANET is susceptible to several vulnerabilities that result in an intrusion. This intrusion must be solved before VANET technology can be adopted. In this study, we suggest a unique machine learning technique to improve VANET’s effectiveness. The proposed method incorporates two phases. Phase I detects the DDoS attack using a novel machine learning technique called SVM-HHO, which provides information about the vehicle. Phase II mitigates the impact of a DDoS attack and allocates bandwidth using a reliable resources management technique based on the hybrid whale dragonfly optimization algorithm (H-WDFOA). This proposed model could be an effective technique predicting and utilizing reliable information that provides effective results in smart vehicles. The novel machine learning-based technique was implemented through MATLAB and NS2 platforms. Network quality measurements included congestion, transit, collision, and QoS awareness cost. Based on the constraints, a different cost framework was designed. In addition, data preprocessing of the QoS factor and total routing costs were considered. Rider integrated cuckoo search (RI-CS) is a novel optimization algorithm that combines the concepts of the rider optimization algorithm (ROA) and cuckoo search (CS) to determine the optimal route with the lowest routing cost. The enhanced hybrid ant colony optimization routing protocol (EHACORP) is a networking technology that increases efficiency by utilizing the shortest route. The shortest path of the proposed protocol had the lowest communication overhead and the fewest number of hops between sending and receiving vehicles. The EHACORP involved two stages. To find the distance between cars in phase 1, EHACORP employed a method for calculating distance. Using starting point ant colony optimization, the ants were guided in phase 2 to develop the shortest route with the least number of connections to send information. The relatively short approach increases protocol efficiency in every way. The pairing of DCM and SBACO at H-WDFOA-VANET accelerated packet processing, reduced ant search time, eliminated blind broadcasting, and prevented stagnation issues. The delivery ratio and throughput of the H-WDFOA-packet VANET benefitted from its use of the shortest channel without stagnation, its rapid packet processing, and its rapid convergence speed. In conclusion, the proposed hybrid whale dragonfly optimization approach (H-WDFOA-VANET) was compared with industry standard models, such as rider integrated cuckoo search (RI-CS) and enhanced hybrid ant colony optimization routing protocol (EHACORP). With the proposed method, throughput could be increased. The proposed system had energy consumption values of 2.00000 mJ, latency values of 15.61668 s, and a drop at node 60 of 0.15759. Additionally, a higher throughput was achieved with the new method. With the suggested method, it is possible to meet the energy consumption targets, delay value, and drop value at node 60. The proposed method reduces the drop value at node 80 to 0.15504, delay time to 15.64318 s, and energy consumption to 2.00000 mJ. These outcomes demonstrate the effectiveness of our proposed method. Thus, the proposed system is more efficient than existing systems. Full article
Show Figures

Figure 1

15 pages, 1605 KiB  
Article
Residual Information in Deep Speaker Embedding Architectures
by Adriana Stan
Mathematics 2022, 10(21), 3927; https://0-doi-org.brum.beds.ac.uk/10.3390/math10213927 - 23 Oct 2022
Cited by 1 | Viewed by 2026
Abstract
Speaker embeddings represent a means to extract representative vectorial representations from a speech signal such that the representation pertains to the speaker identity alone. The embeddings are commonly used to classify and discriminate between different speakers. However, there is no objective measure to [...] Read more.
Speaker embeddings represent a means to extract representative vectorial representations from a speech signal such that the representation pertains to the speaker identity alone. The embeddings are commonly used to classify and discriminate between different speakers. However, there is no objective measure to evaluate the ability of a speaker embedding to disentangle the speaker identity from the other speech characteristics. This means that the embeddings are far from ideal, highly dependent on the training corpus and still include a degree of residual information pertaining to factors such as linguistic content, recording conditions or speaking style of the utterance. This paper introduces an analysis over six sets of speaker embeddings extracted with some of the most recent and high-performing deep neural network (DNN) architectures, and in particular, the degree to which they are able to truly disentangle the speaker identity from the speech signal. To correctly evaluate the architectures, a large multi-speaker parallel speech dataset is used. The dataset includes 46 speakers uttering the same set of prompts, recorded in either a professional studio or their home environments. The analysis looks into the intra- and inter-speaker similarity measures computed over the different embedding sets, as well as if simple classification and regression methods are able to extract several residual information factors from the speaker embeddings. The results show that the discriminative power of the analyzed embeddings is very high, yet across all the analyzed architectures, residual information is still present in the representations in the form of a high correlation to the recording conditions, linguistic contents and utterance duration. However, we show that this correlation, although not ideal, could still be useful in downstream tasks. The low-dimensional projections of the speaker embeddings show similar behavior patterns across the embedding sets with respect to intra-speaker data clustering and utterance outlier detection. Full article
Show Figures

Figure 1

19 pages, 2027 KiB  
Article
Predicting Subgrade Resistance Value of Hydrated Lime-Activated Rice Husk Ash-Treated Expansive Soil: A Comparison between M5P, Support Vector Machine, and Gaussian Process Regression Algorithms
by Mahmood Ahmad, Badr T. Alsulami, Ramez A. Al-Mansob, Saerahany Legori Ibrahim, Suraparb Keawsawasvong, Ali Majdi and Feezan Ahmad
Mathematics 2022, 10(19), 3432; https://0-doi-org.brum.beds.ac.uk/10.3390/math10193432 - 21 Sep 2022
Cited by 3 | Viewed by 1306
Abstract
Resistance value (R-value) is one of the basic subgrade stiffness characterizations that express a material’s resistance to deformation. In this paper, artificial intelligence (AI)-based models—especially M5P, support vector machine (SVM), and Gaussian process regression (GPR) algorithms—are built for R-value evaluation that meets the [...] Read more.
Resistance value (R-value) is one of the basic subgrade stiffness characterizations that express a material’s resistance to deformation. In this paper, artificial intelligence (AI)-based models—especially M5P, support vector machine (SVM), and Gaussian process regression (GPR) algorithms—are built for R-value evaluation that meets the high precision and rapidity requirements in highway engineering. The dataset of this study comprises seven parameters: hydrated lime-activated rice husk ash, liquid limit, plastic limit, plasticity index, optimum moisture content, and maximum dry density. The available data are divided into three parts: training set (70%), test set (15%), and validation set (15%). The output (i.e., R-value) of the developed models is evaluated using the performance measures coefficient of determination (R2), mean absolute error (MAE), relative squared error (RSE), root mean square error (RMSE), relative root mean square error (RRMSE), performance indicator (ρ), and visual framework (Taylor diagram). GPR is concluded to be the best performing model (R2, MAE, RSE, RMSE, RRMSE, and ρ equal to 0.9996, 0.0258, 0.0032, 0.0012, 0.0012, and 0.0006, respectively, in the validation phase), very closely followed by SVM, and M5P. The application used for the aforementioned approaches for predicting the R-value is also compared with the recently developed artificial neural network model in the literature. The analysis of performance measures for the R-value dataset demonstrates that all the AI-based models achieved comparatively better and reliable results and thus should be encouraged in further research. Sensitivity analysis suggests that all the input parameters have a significant influence on the output, with maximum dry density being the highest. Full article
Show Figures

Figure 1

10 pages, 365 KiB  
Article
Co-Occurrence-Based Double Thresholding Method for Research Topic Identification
by Christian-Daniel Curiac, Alex Doboli and Daniel-Ioan Curiac
Mathematics 2022, 10(17), 3115; https://0-doi-org.brum.beds.ac.uk/10.3390/math10173115 - 30 Aug 2022
Cited by 3 | Viewed by 1250
Abstract
Identifying possible research gaps is a main step in problem framing, however it is increasingly tedious and expensive considering the continuously growing amount of published material. This situation suggests the critical need for methodologies and tools that can assist researchers in their selection [...] Read more.
Identifying possible research gaps is a main step in problem framing, however it is increasingly tedious and expensive considering the continuously growing amount of published material. This situation suggests the critical need for methodologies and tools that can assist researchers in their selection of future research topics. Related work mostly focuses on trend analysis and impact prediction but less on research gap identification. This paper presents our first approach in automated identification of feasible research gaps by using a double-threshold procedure to eliminate the research gaps that are currently difficult to study or offer little novelty. Gaps are then found by extracting subgraphs for the less-frequent co-occurrences and correlations of key terms describing domains. A case study applying the methodology for electronic design automation (EDA) domain is also discussed in the paper. Full article
Show Figures

Figure 1

24 pages, 9948 KiB  
Article
Online Support Vector Machine with a Single Pass for Streaming Data
by Lisha Hu, Chunyu Hu, Zheng Huo, Xinlong Jiang and Suzhen Wang
Mathematics 2022, 10(17), 3113; https://0-doi-org.brum.beds.ac.uk/10.3390/math10173113 - 30 Aug 2022
Cited by 1 | Viewed by 1631
Abstract
In this paper, we focus on training a support vector machine (SVM) online with a single pass over streaming data.Traditional batch-mode SVMs require previously prepared training data; these models may be unsuitable for streaming data circumstances. Online SVMs are effective tools for solving [...] Read more.
In this paper, we focus on training a support vector machine (SVM) online with a single pass over streaming data.Traditional batch-mode SVMs require previously prepared training data; these models may be unsuitable for streaming data circumstances. Online SVMs are effective tools for solving this problem by receiving data streams consistently and updating model weights accordingly. However, most online SVMs require multiple data passes before the updated weights converge to stable solutions, and may be unable to address high-rate data streams. This paper presents OSVM_SP, a new online SVM with a single pass over streaming data, and three budgeted versions to bound the space requirement with support vector removal principles. The experimental results obtained with five public datasets show that OSVM_SP outperforms most state-of-the-art single-pass online algorithms in terms of accuracy and is comparable to batch-mode SVMs. Furthermore, the proposed budgeted algorithms achieve comparable predictive performance with only 1/3 of the space requirement. Full article
Show Figures

Figure 1

19 pages, 2119 KiB  
Article
Automatic Speech Emotion Recognition of Younger School Age Children
by Yuri Matveev, Anton Matveev, Olga Frolova, Elena Lyakso and Nersisson Ruban
Mathematics 2022, 10(14), 2373; https://0-doi-org.brum.beds.ac.uk/10.3390/math10142373 - 06 Jul 2022
Cited by 9 | Viewed by 2750
Abstract
This paper introduces the extended description of a database that contains emotional speech in the Russian language of younger school age (8–12-year-old) children and describes the results of validation of the database based on classical machine learning algorithms, such as Support Vector Machine [...] Read more.
This paper introduces the extended description of a database that contains emotional speech in the Russian language of younger school age (8–12-year-old) children and describes the results of validation of the database based on classical machine learning algorithms, such as Support Vector Machine (SVM) and Multi-Layer Perceptron (MLP). The validation is performed using standard procedures and scenarios of the validation similar to other well-known databases of children’s emotional acting speech. Performance evaluation of automatic multiclass recognition on four emotion classes “Neutral (Calm)—Joy—Sadness—Anger” shows the superiority of SVM performance and also MLP performance over the results of perceptual tests. Moreover, the results of automatic recognition on the test dataset which was used in the perceptual test are even better. These results prove that emotions in the database can be reliably recognized both by experts and automatically using classical machine learning algorithms such as SVM and MLP, which can be used as baselines for comparing emotion recognition systems based on more sophisticated modern machine learning methods and deep neural networks. The results also confirm that this database can be a valuable resource for researchers studying affective reactions in speech communication during child-computer interactions in the Russian language and can be used to develop various edutainment, health care, etc. applications. Full article
Show Figures

Figure 1

13 pages, 2182 KiB  
Article
LSTM-Based Broad Learning System for Remaining Useful Life Prediction
by Xiaojia Wang, Ting Huang, Keyu Zhu and Xibin Zhao
Mathematics 2022, 10(12), 2066; https://0-doi-org.brum.beds.ac.uk/10.3390/math10122066 - 15 Jun 2022
Cited by 12 | Viewed by 2937
Abstract
Prognostics and health management (PHM) are gradually being applied to production management processes as industrial production is gradually undergoing a transformation, turning into intelligent production and leading to increased demands on the reliability of industrial equipment. Remaining useful life (RUL) prediction plays a [...] Read more.
Prognostics and health management (PHM) are gradually being applied to production management processes as industrial production is gradually undergoing a transformation, turning into intelligent production and leading to increased demands on the reliability of industrial equipment. Remaining useful life (RUL) prediction plays a pivotal role in this process. Accurate prediction results can effectively provide information about the condition of the equipment on which intelligent maintenance can be based, with many methods applied to this task. However, the current problems of inadequate feature extraction and poor correlation between prediction results and data still affect the prediction accuracy. To overcome these obstacles, we constructed a new fusion model that extracts data features based on a broad learning system (BLS) and embeds long short-term memory (LSTM) to process time-series information, named as the B-LSTM. First, the LSTM controls the transmission of information from the data to the gate mechanism, and the retained information generates the mapped features and forms the feature nodes. Then, the random feature nodes are supplemented by an activation function that generates enhancement nodes with greater expressive power, increasing the nonlinear factor in the network, and eventually the feature nodes and enhancement nodes are jointly connected to the output layer. The B-LSTM was experimentally used with the C-MAPSS dataset and the results of comparison with several mainstream methods showed that the new model achieved significant improvements. Full article
Show Figures

Figure 1

16 pages, 537 KiB  
Article
Correlation Assessment of the Performance of Associative Classifiers on Credit Datasets Based on Data Complexity Measures
by Francisco J. Camacho-Urriolagoitia, Yenny Villuendas-Rey, Itzamá López-Yáñez, Oscar Camacho-Nieto and Cornelio Yáñez-Márquez
Mathematics 2022, 10(9), 1460; https://0-doi-org.brum.beds.ac.uk/10.3390/math10091460 - 26 Apr 2022
Cited by 3 | Viewed by 1372
Abstract
One of the four basic machine learning tasks is pattern classification. The selection of the proper learning algorithm for a given problem is a challenging task, formally known as the algorithm selection problem (ASP). In particular, we are interested in the behavior of [...] Read more.
One of the four basic machine learning tasks is pattern classification. The selection of the proper learning algorithm for a given problem is a challenging task, formally known as the algorithm selection problem (ASP). In particular, we are interested in the behavior of the associative classifiers derived from Alpha-Beta models applied to the financial field. In this paper, the behavior of four associative classifiers was studied: the One-Hot version of the Hybrid Associative Classifier with Translation (CHAT-OHM), the Extended Gamma (EG), the Naïve Associative Classifier (NAC), and the Assisted Classification for Imbalanced Datasets (ACID). To establish the performance, we used the area under the curve (AUC), F-score, and geometric mean measures. The four classifiers were applied over 11 datasets from the financial area. Then, the performance of each one was analyzed, considering their correlation with the measures of data complexity, corresponding to six categories based on specific aspects of the datasets: feature, linearity, neighborhood, network, dimensionality, and class imbalance. The correlations that arise between the measures of complexity of the datasets and the measures of performance of the associative classifiers are established; these results are expressed with Spearman’s Rho coefficient. The experimental results correctly indicated correlations between data complexity measures and the performance of the associative classifiers. Full article
Show Figures

Figure 1

Back to TopTop