Research

19 pages, 1932 KiB

Open AccessArticle

Attention Knowledge Network Combining Explicit and Implicit Information

by Shangju Deng, Jiwei Qin, Xiaole Wang and Ruijin Wang

Mathematics 2023, 11(3), 724; https://doi.org/10.3390/math11030724 - 01 Feb 2023

Cited by 1 | Viewed by 1199

The existing knowledge graph embedding (KGE) method has achieved good performance in recommendation systems. However, the relevancy degree among entities reduces gradually along the spread in the knowledge graph. Focusing on the explicit and implicit relationships among entities, this paper proposes an attention [...] Read more.

The existing knowledge graph embedding (KGE) method has achieved good performance in recommendation systems. However, the relevancy degree among entities reduces gradually along the spread in the knowledge graph. Focusing on the explicit and implicit relationships among entities, this paper proposes an attention knowledge network combining explicit and implicit information (AKNEI) to effectively capture and exactly describe the correlation between entities in the knowledge graph. First, we design an information-sharing layer (ISL) to realize information sharing between projects and entities through implicit interaction. We innovatively propose a cross-feature fusion module to extract high-order feature information in the model. At the same time, this paper uses the attention mechanism to solve the problem of the decline of information relevance in the process of knowledge graph propagation. Finally, the features of KGE and cross feature fusion module are integrated into the end-to-end learning framework, the item information in the recommendation task and the knowledge graph entity information are interacted implicitly and explicitly, and the characteristics between them are automatically learned. We performed extensive experiments on multiple public datasets that include movies, music, and books. According to the experimental results, our model has a great improvement in performance compared with the latest baseline. Full article

(This article belongs to the Special Issue Advances in Mathematical Methods, Machine Learning and Deep Learning Based Applications)

► Show Figures

Figure 1

18 pages, 753 KiB

Open AccessArticle

Deep Forest and Pruned Syntax Tree-Based Classification Method for Java Code Vulnerability

by Jiaman Ding, Weikang Fu and Lianyin Jia

Mathematics 2023, 11(2), 461; https://doi.org/10.3390/math11020461 - 15 Jan 2023

Cited by 1 | Viewed by 1444

Abstract

The rapid development of J2EE (Java 2 Platform Enterprise Edition) has brought unprecedented severe challenges to vulnerability mining. The current abstract syntax tree-based source code vulnerability classification method does not eliminate irrelevant nodes when processing the abstract syntax tree, resulting in a long [...] Read more.

The rapid development of J2EE (Java 2 Platform Enterprise Edition) has brought unprecedented severe challenges to vulnerability mining. The current abstract syntax tree-based source code vulnerability classification method does not eliminate irrelevant nodes when processing the abstract syntax tree, resulting in a long training time and overfitting problems. Another problem is that different code structures will be translated to the same sequence of tree nodes when processing abstract syntax trees using depth-first traversal, so in this process, the depth-first algorithm will lead to the loss of semantic structure information which will reduce the accuracy of the model. Aiming at these two problems, we propose a deep forest and pruned syntax tree-based classification method (PSTDF) for Java code vulnerability. First, the breadth-first traversal of the abstract syntax tree obtains the sequence of statement trees, next, pruning statement trees removes irrelevant nodes, then we use a depth-first based encoder to obtain the vector, and finally, we use deep forest as the classifier to get classification results. Experiments on publicly accessible vulnerability datasets show that PSTDF can reduce the loss of semantic structure information and effectively remove the impact of redundant information. Full article

(This article belongs to the Special Issue Advances in Mathematical Methods, Machine Learning and Deep Learning Based Applications)

► Show Figures

Figure 1

17 pages, 574 KiB

Open AccessArticle

Personalizing Hybrid-Based Dialogue Agents

by Yuri Matveev, Olesia Makhnytkina, Pavel Posokhov, Anton Matveev and Stepan Skrylnikov

Mathematics 2022, 10(24), 4657; https://doi.org/10.3390/math10244657 - 08 Dec 2022

Cited by 2 | Viewed by 1342

Abstract

In this paper, we present a continuation of our work on the personification of dialogue agents. We expand upon the previously demonstrated models—the ranking and generative models—and propose new hybrid models. Because there is no single definitive way to build a hybrid model, [...] Read more.

In this paper, we present a continuation of our work on the personification of dialogue agents. We expand upon the previously demonstrated models—the ranking and generative models—and propose new hybrid models. Because there is no single definitive way to build a hybrid model, we explore various architectures where the components adopt different roles, sequentially and in parallel. Applying the perplexity and BLEU performance metrics, we discover that the Retrieve and Refine and KG model—a modification of the Retrieve and Refine model where the ranking and generative components work in parallel and compete based on the proximity of the candidate found by the ranking model with a knowledge-grounded generation block—achieves the best performance, with values of 1.64 for perplexity and 0.231 for BLEU scores. Full article

(This article belongs to the Special Issue Advances in Mathematical Methods, Machine Learning and Deep Learning Based Applications)

► Show Figures

Figure 1

22 pages, 2632 KiB

Open AccessArticle

Blockchain and Deep Learning-Based Fault Detection Framework for Electric Vehicles

by Mihir Trivedi, Riya Kakkar, Rajesh Gupta, Smita Agrawal, Sudeep Tanwar, Violeta-Carolina Niculescu, Maria Simona Raboaca, Fayez Alqahtani, Aldosary Saad and Amr Tolba

Mathematics 2022, 10(19), 3626; https://doi.org/10.3390/math10193626 - 04 Oct 2022

Cited by 8 | Viewed by 1963

Abstract

The gradual transition from a traditional transportation system to an intelligent transportation system (ITS) has paved the way to preserve green environments in metro cities. Moreover, electric vehicles (EVs) seem to be beneficial choices for traveling purposes due to their low charging costs, [...] Read more.

The gradual transition from a traditional transportation system to an intelligent transportation system (ITS) has paved the way to preserve green environments in metro cities. Moreover, electric vehicles (EVs) seem to be beneficial choices for traveling purposes due to their low charging costs, low energy consumption, and reduced greenhouse gas emission. However, a single failure in an EV’s intrinsic components can worsen travel experiences due to poor charging infrastructure. As a result, we propose a deep learning and blockchain-based EV fault detection framework to identify various types of faults, such as air tire pressure, temperature, and battery faults in vehicles. Furthermore, we employed a 5G wireless network with an interplanetary file system (IPFS) protocol to execute the fault detection data transactions with high scalability and reliability for EVs. Initially, we utilized a convolutional neural network (CNN) and a long-short term memory (LSTM) model to deal with air tire pressure fault, anomaly detection for temperature fault, and battery fault detection for EVs to predict the presence of faulty data, which ensure safer journeys for users. Furthermore, the incorporated IPFS and blockchain network ensure highly secure, cost-efficient, and reliable EV fault detection. Finally, the performance evaluation for EV fault detection has been simulated, considering several performance metrics, such as accuracy, loss, and the state-of-health (SoH) prediction curve for various types of identified faults. The simulation results of EV fault detection have been estimated at an accuracy of 70% for air tire pressure fault, anomaly detection of the temperature fault, and battery fault detection, with R² scores of 0.874 and 0.9375. Full article

(This article belongs to the Special Issue Advances in Mathematical Methods, Machine Learning and Deep Learning Based Applications)

► Show Figures

Figure 1

8 pages, 2341 KiB

Open AccessArticle

The ASR Post-Processor Performance Challenges of BackTranScription (BTS): Data-Centric and Model-Centric Approaches

by Chanjun Park, Jaehyung Seo, Seolhwa Lee, Chanhee Lee and Heuiseok Lim

Mathematics 2022, 10(19), 3618; https://doi.org/10.3390/math10193618 - 02 Oct 2022

Cited by 1 | Viewed by 1473

Abstract

Training an automatic speech recognition (ASR) post-processor based on sequence-to-sequence (S2S) requires a parallel pair (e.g., speech recognition result and human post-edited sentence) to construct the dataset, which demands a great amount of human labor. BackTransScription (BTS) proposes a data-building method to mitigate [...] Read more.

Training an automatic speech recognition (ASR) post-processor based on sequence-to-sequence (S2S) requires a parallel pair (e.g., speech recognition result and human post-edited sentence) to construct the dataset, which demands a great amount of human labor. BackTransScription (BTS) proposes a data-building method to mitigate the limitations of the existing S2S based ASR post-processors, which can automatically generate vast amounts of training datasets, reducing time and cost in data construction. Despite the emergence of this novel approach, the BTS-based ASR post-processor still has research challenges and is mostly untested in diverse approaches. In this study, we highlight these challenges through detailed experiments by analyzing the data-centric approach (i.e., controlling the amount of data without model alteration) and the model-centric approach (i.e., model modification). In other words, we attempt to point out problems with the current trend of research pursuing a model-centric approach and alert against ignoring the importance of the data. Our experiment results show that the data-centric approach outperformed the model-centric approach by +11.69, +17.64, and +19.02 in the F1-score, BLEU, and GLEU tests. Full article

(This article belongs to the Special Issue Advances in Mathematical Methods, Machine Learning and Deep Learning Based Applications)

► Show Figures

Figure 1

12 pages, 2621 KiB

Open AccessArticle

Stochastic Approach to Investigate Protected Access to Information Resources in Combined E-Learning Environment

by Radi Romansky

Mathematics 2022, 10(16), 2909; https://doi.org/10.3390/math10162909 - 12 Aug 2022

Cited by 1 | Viewed by 792

Abstract

The digital era expands the scope and application of information technologies, which also affects the forms of e-learning, motivating the development of combined systems with heterogeneous resources and services, including in the cloud. In this vein, the present article investigates the implementation of [...] Read more.

The digital era expands the scope and application of information technologies, which also affects the forms of e-learning, motivating the development of combined systems with heterogeneous resources and services, including in the cloud. In this vein, the present article investigates the implementation of a set of procedures for maintaining regulated access to resources (identification, authentication, authorization, etc.) in a combined e-learning environment, with the main goal to confirm their effectiveness and correctness. The study was conducted through analytical modelling using stochastic tools from the theory of Petri nets and Markov chains with additional statistical analysis. The application of such a combined approach allows increased research efficiency and better adequacy of the obtained estimates. Full article

(This article belongs to the Special Issue Advances in Mathematical Methods, Machine Learning and Deep Learning Based Applications)

► Show Figures

Figure 1

12 pages, 1127 KiB

Open AccessArticle

Development of CNN-Based Data Crawler to Support Learning Block Programming

by HuiJae Park, JaMee Kim and WonGyu Lee

Mathematics 2022, 10(13), 2223; https://doi.org/10.3390/math10132223 - 25 Jun 2022

Cited by 1 | Viewed by 1933

Abstract

Along with the importance of digital literacy, the need for SW(Software) education is steadily emerging. Programming education in public education targets a variety of learners from elementary school to high school. This study was conducted for the purpose of judging the proficiency of [...] Read more.

Along with the importance of digital literacy, the need for SW(Software) education is steadily emerging. Programming education in public education targets a variety of learners from elementary school to high school. This study was conducted for the purpose of judging the proficiency of low school-age learners in programming education. To achieve the goal, a tool to collect data on the entire programming learning process was developed, and a machine learning model was implemented to judge the proficiency of learners based on the collected data. As a result of determining the proficiency of 20 learners, the model developed through this study showed an average accuracy of approximately 75%. Through the development of programming-related data collection tools and programming proficiency judging models for low school-age learners, this study is meaningful in that it presents basic data for providing learner-tailored feedback. Full article

(This article belongs to the Special Issue Advances in Mathematical Methods, Machine Learning and Deep Learning Based Applications)

► Show Figures

Figure 1

17 pages, 2239 KiB

Open AccessArticle

Machine Learning-Based Cardiac Arrest Prediction for Early Warning System

by Minsu Chae, Hyo-Wook Gil, Nam-Jun Cho and Hwamin Lee

Mathematics 2022, 10(12), 2049; https://doi.org/10.3390/math10122049 - 13 Jun 2022

Cited by 8 | Viewed by 2859

Abstract

The early warning system detects early and responds quickly to emergencies in high-risk patients, such as cardiac arrest in hospitalized patients. However, traditional early warning systems have the problem of frequent false alarms due to low positive predictive value and sensitivity. We conducted [...] Read more.

The early warning system detects early and responds quickly to emergencies in high-risk patients, such as cardiac arrest in hospitalized patients. However, traditional early warning systems have the problem of frequent false alarms due to low positive predictive value and sensitivity. We conducted early prediction research on cardiac arrest using time-series data such as biosignal and laboratory data. To derive the data attributes that affect the occurrence of cardiac arrest, we performed a correlation analysis between the occurrence of cardiac arrest and the biosignal data and laboratory data. To improve the positive predictive value and sensitivity of early cardiac arrest prediction, we evaluated the performance according to the length of the time series of measured biosignal data, laboratory data, and patient data range. We propose a machine learning and deep learning algorithm: the decision tree, random forest, logistic regression, long short-term memory (LSTM), gated recurrent unit (GRU) model, and the LSTM–GRU hybrid model. We evaluated cardiac arrest prediction models. In the case of our proposed LSTM model, the positive predictive value was 85.92% and the sensitivity was 89.70%. Full article

(This article belongs to the Special Issue Advances in Mathematical Methods, Machine Learning and Deep Learning Based Applications)

► Show Figures

Figure 1

24 pages, 3902 KiB

Open AccessEditor’s ChoiceArticle

A Safe and Efficient Lane Change Decision-Making Strategy of Autonomous Driving Based on Deep Reinforcement Learning

by Kexuan Lv, Xiaofei Pei, Ci Chen and Jie Xu

Mathematics 2022, 10(9), 1551; https://doi.org/10.3390/math10091551 - 05 May 2022

Cited by 15 | Viewed by 3418

Abstract

As an indispensable branch of machine learning (ML), reinforcement learning (RL) plays a prominent role in the decision-making process of autonomous driving (AD), which enables autonomous vehicles (AVs) to learn an optimal driving strategy through continuous interaction with the environment. This paper proposes [...] Read more.

As an indispensable branch of machine learning (ML), reinforcement learning (RL) plays a prominent role in the decision-making process of autonomous driving (AD), which enables autonomous vehicles (AVs) to learn an optimal driving strategy through continuous interaction with the environment. This paper proposes a deep reinforcement learning (DRL)-based motion planning strategy for AD tasks in the highway scenarios where an AV merges into two-lane road traffic flow and realizes the lane changing (LC) maneuvers. We integrate the DRL model into the AD system relying on the end-to-end learning method. An improved DRL algorithm based on deep deterministic policy gradient (DDPG) is developed with well-defined reward functions. In particular, safety rules (SR), safety prediction (SP) module and trauma memory (TM) as well as the dynamic potential-based reward shaping (DPBRS) function are adopted to further enhance safety and accelerate learning of the LC behavior. For validation, the proposed DSSTD algorithm is trained and tested on the dual-computer co-simulation platform. The comparative experimental results show that our proposal outperforms other benchmark algorithms in both driving safety and efficiency. Full article

(This article belongs to the Special Issue Advances in Mathematical Methods, Machine Learning and Deep Learning Based Applications)

► Show Figures

Figure 1

12 pages, 507 KiB

Open AccessArticle

AI Student: A Machine Reading Comprehension System for the Korean College Scholastic Ability Test

by Gyeongmin Kim, Soomin Lee, Chanjun Park and Jaechoon Jo

Mathematics 2022, 10(9), 1486; https://doi.org/10.3390/math10091486 - 29 Apr 2022

Cited by 2 | Viewed by 2343

Abstract

Machine reading comprehension is a question answering mechanism in which a machine reads, understands, and answers questions from a given text. These reasoning skills can be sufficiently grafted into the Korean College Scholastic Ability Test (CSAT) to bring about new scientific and educational [...] Read more.

Machine reading comprehension is a question answering mechanism in which a machine reads, understands, and answers questions from a given text. These reasoning skills can be sufficiently grafted into the Korean College Scholastic Ability Test (CSAT) to bring about new scientific and educational advances. In this paper, we propose a novel Korean CSAT Question and Answering (KCQA) model and effectively utilize four easy data augmentation strategies with round trip translation to augment the insufficient data in the training dataset. To evaluate the effectiveness of KCQA, 30 students appeared for the test under conditions identical to the proposed model. Our qualitative and quantitative analysis along with experimental results revealed that KCQA achieved better performance than humans with a higher F1 score of 3.86. Full article

(This article belongs to the Special Issue Advances in Mathematical Methods, Machine Learning and Deep Learning Based Applications)

► Show Figures

Figure 1

14 pages, 282 KiB

Open AccessArticle

Efficiency and Productivity of Local Educational Administration in Korea Using the Malmquist Productivity Index

by Moonyoung Eom, Hyungchul Yoo and Jisung Yoo

Mathematics 2022, 10(9), 1449; https://doi.org/10.3390/math10091449 - 26 Apr 2022

Cited by 2 | Viewed by 2032

Abstract

As local governments around the world struggle to finance and deliver quality education under fiscal constraints, pressures mount to increase efficiency and productivity in order to obtain more output from the same or fewer resources. Focusing on the case of Korea, this study [...] Read more.

As local governments around the world struggle to finance and deliver quality education under fiscal constraints, pressures mount to increase efficiency and productivity in order to obtain more output from the same or fewer resources. Focusing on the case of Korea, this study investigates the productivity of outputs in local offices of education (OEs) through the analysis of personnel and financial factors by year (2012–2016). Overall, the results indicate the efficient operation of the OEs in Korea. The Malmquist productivity index (MPI) mean decreased from 2012 to 2014, increased from 2014 to 2015, and decreased from 2015 to 2016. The rate of chronological change in each OE’s MPI showed the same pattern of change in the distribution ratio of school expenditures. Finally, the MPI had the same pattern as the Technical Change Index. Policy implications are provided. Full article

(This article belongs to the Special Issue Advances in Mathematical Methods, Machine Learning and Deep Learning Based Applications)

12 pages, 447 KiB

Open AccessArticle

Dense-to-Question and Sparse-to-Answer: Hybrid Retriever System for Industrial Frequently Asked Questions

by Jaehyung Seo, Taemin Lee, Hyeonseok Moon, Chanjun Park, Sugyeong Eo, Imatitikua D. Aiyanyo, Kinam Park, Aram So, Sungmin Ahn and Jeongbae Park

Mathematics 2022, 10(8), 1335; https://doi.org/10.3390/math10081335 - 18 Apr 2022

Cited by 2 | Viewed by 2145

Abstract

The term “Frequently asked questions” (FAQ) refers to a query that is asked repeatedly and produces a manually constructed response. It is one of the most important factors influencing customer repurchase and brand loyalty; thus, most industry domains invest heavily in it. This [...] Read more.

The term “Frequently asked questions” (FAQ) refers to a query that is asked repeatedly and produces a manually constructed response. It is one of the most important factors influencing customer repurchase and brand loyalty; thus, most industry domains invest heavily in it. This has led to deep-learning-based retrieval models being studied. However, training a model and creating a database specializing in each industry domain comes at a high cost, especially when using a chatbot-based conversation system, as a large amount of resources must be continuously input for the FAQ system’s maintenance. It is also difficult for small- and medium-sized companies and national institutions to build individualized training data and databases and obtain satisfactory results. As a result, based on the deep learning information retrieval module, we propose a method of returning responses to customer inquiries using only data that can be easily obtained from companies. We hybridize dense embedding and sparse embedding in this work to make it more robust in professional terms, and we propose new functions to adjust the weight ratio and scale the results returned by the two modules. Full article

(This article belongs to the Special Issue Advances in Mathematical Methods, Machine Learning and Deep Learning Based Applications)

► Show Figures

Figure 1

22 pages, 6507 KiB

Open AccessArticle

CAC: A Learning Context Recognition Model Based on AI for Handwritten Mathematical Symbols in e-Learning Systems

by Sung-Bum Baek, Jin-Gon Shon and Ji-Su Park

Mathematics 2022, 10(8), 1277; https://doi.org/10.3390/math10081277 - 12 Apr 2022

Viewed by 1798

Abstract

The e-learning environment should support the handwriting of mathematical expressions and accurately recognize inputted handwritten mathematical expressions. To this end, expression-related information should be fully utilized in e-learning environments. However, pre-existing handwritten mathematical expression recognition models mainly utilize the shape of handwritten mathematical [...] Read more.

The e-learning environment should support the handwriting of mathematical expressions and accurately recognize inputted handwritten mathematical expressions. To this end, expression-related information should be fully utilized in e-learning environments. However, pre-existing handwritten mathematical expression recognition models mainly utilize the shape of handwritten mathematical symbols, thus limiting the models from improving the recognition accuracy of a vaguely represented symbol. Therefore, in this paper, a context-aided correction (CAC) model is proposed that adjusts an output of handwritten mathematical symbol (HMS) recognition by additionally utilizing information related to the HMS in an e-learning system. The CAC model collects learning contextual data associated with the HMS and converts them into learning contextual information. Next, contextual information is recognized through artificial intelligence to adjust the recognition output of the HMS. Finally, the CAC model is trained and tested using a dataset similar to that of a real learning situation. The experiment results show that the recognition accuracy of handwritten mathematical symbols is improved when using the CAC model. Full article

(This article belongs to the Special Issue Advances in Mathematical Methods, Machine Learning and Deep Learning Based Applications)

► Show Figures

Figure 1

17 pages, 4633 KiB

Open AccessArticle

Classification of Alzheimer’s Disease and Mild-Cognitive Impairment Base on High-Order Dynamic Functional Connectivity at Different Frequency Band

by Uttam Khatri and Goo-Rak Kwon

Mathematics 2022, 10(5), 805; https://doi.org/10.3390/math10050805 - 03 Mar 2022

Cited by 4 | Viewed by 1693

Abstract

Functional brain connectivity networks obtained from resting-state functional magnetic resonance imaging (rs-fMRI) have been extensively utilized for the diagnosis of Alzheimer’s disease (AD). However, the traditional correlation analysis technique only explores the pairwise relation, which may not be suitable for revealing sufficient and [...] Read more.

Functional brain connectivity networks obtained from resting-state functional magnetic resonance imaging (rs-fMRI) have been extensively utilized for the diagnosis of Alzheimer’s disease (AD). However, the traditional correlation analysis technique only explores the pairwise relation, which may not be suitable for revealing sufficient and proper functional connectivity links among brain regions. Additionally, previous literature typically focuses on only lower-order dynamics, without considering higher-order dynamic networks properties, and they particularly focus on single frequency range time series of rs-fMRI. To solve these problems, in this article, a new diagnosis scheme is proposed by constructing a high-order dynamic functional network at different frequency level time series (full-band (0.01–0.08 Hz); slow-4 (0.027–0.08 Hz); and slow-5 (0.01–0.027 Hz)) data obtained from rs-fMRI to build the functional brain network for all brain regions. Especially, to tune the precise analysis of the regularized parameters in the Support Vector Machine (SVM), a nested leave-one-out cross-validation (LOOCV) technique is adopted. Finally, the SVM classifier is trained to classify AD from HC based on these higher-order dynamic functional brain networks at different frequency ranges. The experiment results illustrate that for all bands with a LOOCV classification accuracy of 94.10% with a 90.95% of sensitivity, and a 96.75% of specificity outperforms the individual networks. Utilization of the given technique for the identification of AD from HC compete for the most state-of-the-art technology in terms of the diagnosis accuracy. Additionally, results obtained for the all-band shows performance further suggest that our proposed scheme has a high-rate accuracy. These results have validated the effectiveness of the proposed methods for clinical value to the identification of AD. Full article

(This article belongs to the Special Issue Advances in Mathematical Methods, Machine Learning and Deep Learning Based Applications)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Advances in Mathematical Methods, Machine Learning and Deep Learning Based Applications

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (14 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI