Mathematics

Research

12 pages, 976 KiB

Open AccessArticle

Order-Preserving Pattern Matching with Partition

by Joong Chae Na, Youngjoon Kim, Seokchul Kang and Jeong Seop Sim

Mathematics 2024, 12(21), 3381; https://doi.org/10.3390/math12213381 - 29 Oct 2024

Viewed by 566

Order-preserving pattern matching, which considers the relative orders of strings, can be applied to time-series data analysis. To perform a more meaningful analysis of time-series data, approximate criteria for the order-isomorphism are necessary, considering diverse types of errors. In this paper, we introduce [...] Read more.

Order-preserving pattern matching, which considers the relative orders of strings, can be applied to time-series data analysis. To perform a more meaningful analysis of time-series data, approximate criteria for the order-isomorphism are necessary, considering diverse types of errors. In this paper, we introduce a novel approximation criterion for the order-isomorphism, called the partitioned order-isomorphism. We then propose an efficient

O (n + s o r t (m))

-time algorithm for the order-preserving pattern matching problem considering the criterion of partition. A comparative experiment demonstrates that the proposed algorithm is more effective than the exact order-preserving pattern matching algorithm. Full article

(This article belongs to the Special Issue Artificial Intelligence and Algorithms with Their Applications)

► Show Figures

Figure 1

24 pages, 11857 KiB

Open AccessArticle

Deep Reinforcement-Learning-Based Air-Combat-Maneuver Generation Framework

by Junru Mei, Ge Li and Hesong Huang

Mathematics 2024, 12(19), 3020; https://doi.org/10.3390/math12193020 - 27 Sep 2024

Cited by 1 | Viewed by 1254

Abstract

With the development of unmanned aircraft and artificial intelligence technology, the future of air combat is moving towards unmanned and autonomous direction. In this paper, we introduce a new layered decision framework designed to address the six-degrees-of-freedom (6-DOF) aircraft within-visual-range (WVR) air-combat challenge. [...] Read more.

With the development of unmanned aircraft and artificial intelligence technology, the future of air combat is moving towards unmanned and autonomous direction. In this paper, we introduce a new layered decision framework designed to address the six-degrees-of-freedom (6-DOF) aircraft within-visual-range (WVR) air-combat challenge. The decision-making process is divided into two layers, each of which is addressed separately using reinforcement learning (RL). The upper layer is the combat policy, which determines maneuvering instructions based on the current combat situation (such as altitude, speed, and attitude). The lower layer control policy then uses these commands to calculate the input signals from various parts of the aircraft (aileron, elevator, rudder, and throttle). Among them, the control policy is modeled as a Markov decision framework, and the combat policy is modeled as a partially observable Markov decision framework. We describe the two-layer training method in detail. For the control policy, we designed rewards based on expert knowledge to accurately and stably complete autonomous driving tasks. At the same time, for combat policy, we introduce a self-game-based course learning, allowing the agent to play against historical policies during training to improve performance. The experimental results show that the operational success rate of the proposed method against the game theory baseline reaches 85.7%. Efficiency was also outstanding, with an average 13.6% reduction in training time compared to the RL baseline. Full article

(This article belongs to the Special Issue Artificial Intelligence and Algorithms with Their Applications)

► Show Figures

Figure 1

18 pages, 4142 KiB

Open AccessArticle

ConvNext as a Basis for Interpretability in Coffee Leaf Rust Classification

by Adrian Chavarro, Diego Renza and Ernesto Moya-Albor

Mathematics 2024, 12(17), 2668; https://doi.org/10.3390/math12172668 - 27 Aug 2024

Cited by 1 | Viewed by 801

Abstract

The increasing complexity of deep learning models can make it difficult to interpret and fit models beyond a purely accuracy-focused evaluation. This is where interpretable and eXplainable Artificial Intelligence (XAI) come into play to facilitate an understanding of the inner workings of models. [...] Read more.

The increasing complexity of deep learning models can make it difficult to interpret and fit models beyond a purely accuracy-focused evaluation. This is where interpretable and eXplainable Artificial Intelligence (XAI) come into play to facilitate an understanding of the inner workings of models. Consequently, alternatives have emerged, such as class activation mapping (CAM) techniques aimed at identifying regions of importance for an image classification model. However, the behavior of such models can be highly dependent on the type of architecture and the different variants of convolutional neural networks. Accordingly, this paper evaluates three Convolutional Neural Network (CNN) architectures (VGG16, ResNet50, ConvNext-T) against seven CAM models (GradCAM, XGradCAM, HiResCAM, LayerCAM, GradCAM++, GradCAMElementWise, and EigenCAM), indicating that the CAM maps obtained with ConvNext models show less variability among them, i.e., they are less dependent on the selected CAM approach. This study was performed on an image dataset for the classification of coffee leaf rust and evaluated using the RemOve And Debias (ROAD) metric. Full article

(This article belongs to the Special Issue Artificial Intelligence and Algorithms with Their Applications)

► Show Figures

Figure 1

20 pages, 3724 KiB

Open AccessArticle

Get Spatial from Non-Spatial Information: Inferring Spatial Information from Textual Descriptions by Conceptual Spaces

by Omid Reza Abbasi, Ali Asghar Alesheikh and Seyed Vahid Razavi-Termeh

Mathematics 2023, 11(24), 4917; https://doi.org/10.3390/math11244917 - 11 Dec 2023

Cited by 1 | Viewed by 1286

Abstract

With the rapid growth of social media, textual content is increasingly growing. Unstructured texts are a rich source of latent spatial information. Extracting such information is useful in query processing, geographical information retrieval (GIR), and recommender systems. In this paper, we propose a [...] Read more.

With the rapid growth of social media, textual content is increasingly growing. Unstructured texts are a rich source of latent spatial information. Extracting such information is useful in query processing, geographical information retrieval (GIR), and recommender systems. In this paper, we propose a novel approach to infer spatial information from salient features of non-spatial nature in text corpora. We propose two methods, namely DCS and RCS, to represent place-based concepts. In addition, two measures, namely the Shannon entropy and the Moran’s I, are proposed to calculate the degree of geo-indicativeness of terms in texts. The methodology is compared with a Latent Dirichlet Allocation (LDA) approach to estimate the accuracy improvement. We evaluated the methods on a dataset of rental property advertisements in Iran and a dataset of Persian Wikipedia articles. The results show that our proposed approach enhances the relative accuracy of predictions by about 10% in case of the renting advertisements and by 13% in case of the Wikipedia articles. The average distance error is about 13.3 km for the advertisements and 10.3 km for the Wikipedia articles, making the method suitable to infer the general region of the city in which a property is located. The proposed methodology is promising for inferring spatial knowledge from textual content that lacks spatial terms. Full article

(This article belongs to the Special Issue Artificial Intelligence and Algorithms with Their Applications)

► Show Figures

Figure 1

17 pages, 3210 KiB

Open AccessArticle

Towards Efficient and Trustworthy Pandemic Diagnosis in Smart Cities: A Blockchain-Based Federated Learning Approach

by Mohamed Abdel-Basset, Ibrahim Alrashdi, Hossam Hawash, Karam Sallam and Ibrahim A. Hameed

Mathematics 2023, 11(14), 3093; https://doi.org/10.3390/math11143093 - 13 Jul 2023

Cited by 4 | Viewed by 1792

Abstract

In the aftermath of the COVID-19 pandemic, the need for efficient and reliable disease diagnosis in smart cities has become increasingly serious. In this study, we introduce a novel blockchain-based federated learning framework tailored specifically for the diagnosis of pandemic diseases in smart [...] Read more.

In the aftermath of the COVID-19 pandemic, the need for efficient and reliable disease diagnosis in smart cities has become increasingly serious. In this study, we introduce a novel blockchain-based federated learning framework tailored specifically for the diagnosis of pandemic diseases in smart cities, called BFLPD, with a focus on COVID-19 as a case study. The proposed BFLPD takes advantage of the decentralized nature of blockchain technology to design collaborative intelligence for automated diagnosis without violating trustworthiness metrics, such as privacy, security, and data sharing, which are encountered in healthcare systems of smart cities. Cheon–Kim–Kim–Song (CKKS) encryption is intelligently redesigned in BFLPD to ensure the secure sharing of learning updates during the training process. The proposed BFLPD presents a decentralized secure aggregation method that safeguards the integrity of the global model against adversarial attacks, thereby improving the overall efficiency and trustworthiness of our system. Extensive experiments and evaluations using a case study of COVID-19 ultrasound data demonstrate that BFLPD can reliably improve diagnostic accuracy while preserving data privacy, making it a promising tool with which smart cities can enhance their pandemic disease diagnosis capabilities. Full article

(This article belongs to the Special Issue Artificial Intelligence and Algorithms with Their Applications)

► Show Figures

Figure 1

18 pages, 2480 KiB

Open AccessArticle

Hybrid Fuzzy Rule Algorithm and Trust Planning Mechanism for Robust Trust Management in IoT-Embedded Systems Integration

by Nagireddy Venkata Rajasekhar Reddy, Pydimarri Padmaja, Miroslav Mahdal, Selvaraj Seerangan, Vrince Vimal, Vamsidhar Talasila and Lenka Cepova

Mathematics 2023, 11(11), 2546; https://doi.org/10.3390/math11112546 - 1 Jun 2023

Cited by 4 | Viewed by 1690

Abstract

The Internet of Things (IoT) is rapidly expanding and becoming an integral part of daily life, increasing the potential for security threats such as malware or cyberattacks. Many embedded systems (ESs), responsible for handling sensitive data or facilitating secure online activities, must adhere [...] Read more.

The Internet of Things (IoT) is rapidly expanding and becoming an integral part of daily life, increasing the potential for security threats such as malware or cyberattacks. Many embedded systems (ESs), responsible for handling sensitive data or facilitating secure online activities, must adhere to stringent security standards. For instance, payment processors employ security-critical components as distinct chips, maintaining physical separation from other network components to prevent the leakage of sensitive information such as cryptographic keys. Establishing a trusted environment in IoT and ESs, where interactions are based on the trust model of communication nodes, is a viable approach to enhance security in IoT and ESs. Although trust management (TM) has been extensively studied in distributed networks, IoT, and ESs, significant challenges remain for real-world implementation. In response, we propose a hybrid fuzzy rule algorithm (FRA) and trust planning mechanism (TPM), denoted FRA + TPM, for effective trust management and to bolster IoT and ESs reliability. The proposed system was evaluated against several conventional methods, yielding promising results: trust prediction accuracy (99%), energy consumption (53%), malicious node detection (98%), computation time (61 s), latency (1.7 ms), and throughput (9 Mbps). Full article

(This article belongs to the Special Issue Artificial Intelligence and Algorithms with Their Applications)

► Show Figures

Figure 1

14 pages, 1171 KiB

Open AccessArticle

Enhancing Data Security in IoT Networks with Blockchain-Based Management and Adaptive Clustering Techniques

by Ajmeera Kiran, Prasad Mathivanan, Miroslav Mahdal, Kanduri Sairam, Deepak Chauhan and Vamsidhar Talasila

Mathematics 2023, 11(9), 2073; https://doi.org/10.3390/math11092073 - 27 Apr 2023

Cited by 16 | Viewed by 4008

Abstract

The rapid proliferation of smart devices in Internet of Things (IoT) networks has amplified the security challenges associated with device communications. To address these challenges in 5G-enabled IoT networks, this paper proposes a multi-level blockchain security architecture that simplifies implementation while bolstering network [...] Read more.

The rapid proliferation of smart devices in Internet of Things (IoT) networks has amplified the security challenges associated with device communications. To address these challenges in 5G-enabled IoT networks, this paper proposes a multi-level blockchain security architecture that simplifies implementation while bolstering network security. The architecture leverages an adaptive clustering approach based on Evolutionary Adaptive Swarm Intelligent Sparrow Search (EASISS) for efficient organization of heterogeneous IoT networks. Cluster heads (CH) are selected to manage local authentication and permissions, reducing overhead and latency by minimizing communication distances between CHs and IoT devices. To implement network changes such as node addition, relocation, and deletion, the Network Efficient Whale Optimization (NEWO) algorithm is employed. A localized private blockchain structure facilitates communication between CHs and base stations, providing an authentication mechanism that enhances security and trustworthiness. Simulation results demonstrate the effectiveness of the proposed clustering algorithm compared to existing methodologies. Overall, the lightweight blockchain approach presented in this study strikes a superior balance between network latency and throughput when compared to conventional global blockchain systems. Further analysis of system under test (SUT) behavior was accomplished by running many benchmark rounds at varying transaction sending speeds. Maximum, median, and lowest transaction delays and throughput were measured by generating 1000 transactions for each benchmark. Transactions per second (TPS) rates varied between 20 and 500. Maximum delay rose when throughput reached 100 TPS, while minimum latency maintained a value below 1 s. Full article

(This article belongs to the Special Issue Artificial Intelligence and Algorithms with Their Applications)

► Show Figures

Figure 1

20 pages, 1322 KiB

Open AccessArticle

Local Property of Depth Information in 3D Images and Its Application in Feature Matching

by Erbing Yang, Fei Chen, Meiqing Wang, Hang Cheng and Rong Liu

Mathematics 2023, 11(5), 1154; https://doi.org/10.3390/math11051154 - 26 Feb 2023

Cited by 2 | Viewed by 1798

Abstract

In image registration or image matching, the feature extracted by using the traditional methods does not include the depth information which may lead to a mismatch of keypoints. In this paper, we prove that when the camera moves, the ratio of the depth [...] Read more.

In image registration or image matching, the feature extracted by using the traditional methods does not include the depth information which may lead to a mismatch of keypoints. In this paper, we prove that when the camera moves, the ratio of the depth difference of a keypoint and its neighbor pixel before and after the camera movement approximates a constant. That means the depth difference of a keypoint and its neighbor pixel after normalization is invariant to the camera movement. Based on this property, all the depth differences of a keypoint and its neighbor pixels constitute a local depth-based feature, which can be used as a supplement of the traditional feature. We combine the local depth-based feature with the SIFT feature descriptor to form a new feature descriptor, and the experimental results show the feasibility and effectiveness of the new feature descriptor. Full article

(This article belongs to the Special Issue Artificial Intelligence and Algorithms with Their Applications)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Artificial Intelligence and Algorithms with Their Applications

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (8 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI