Research

24 pages, 7480 KiB

Open AccessArticle

HVAC Load Forecasting Based on the CEEMDAN-Conv1D-BiLSTM-AM Model

by Zhicheng Xiao, Lijuan Yu, Huajun Zhang, Xuetao Zhang and Yixin Su

Mathematics 2023, 11(22), 4630; https://doi.org/10.3390/math11224630 - 13 Nov 2023

Cited by 1 | Viewed by 11155

Heating, ventilation, and air-conditioning (HVAC) systems consume approximately 60% of the total energy consumption in public buildings, and an effective way to reduce HVAC energy consumption is to provide accurate load forecasting. This paper proposes a load forecasting model CEEMDAN-Conv1D-BiLSTM-AM which combines empirical [...] Read more.

Heating, ventilation, and air-conditioning (HVAC) systems consume approximately 60% of the total energy consumption in public buildings, and an effective way to reduce HVAC energy consumption is to provide accurate load forecasting. This paper proposes a load forecasting model CEEMDAN-Conv1D-BiLSTM-AM which combines empirical mode decomposition and neural networks. The load data are decomposed into fifteen sub-sequences using complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN). The neural network inputs consist of the decomposition results and five exogenous variables. The neural networks contain a one-dimensional convolutional layer, a BiLSTM layer, and an attention mechanism layer. The Conv1D is employed to extract deep features from each input variable, while BiLSTM and the attention mechanism layer are used to learn the characteristics of the load time series. The five exogenous variables are selected based on the correlation analysis between external factors and load series, and the number of input steps for the model is determined through autocorrelation analysis of the load series. The performance of CEEMDAN-Conv1D-BiLSTM-AM is compared with that of five other models and the results show that the proposed model has a higher prediction accuracy than other models. Full article

(This article belongs to the Special Issue Advanced Artificial Intelligence Models and Its Applications)

► Show Figures

Figure 1

12 pages, 639 KiB

Open AccessArticle

Deep Learning Architecture for Detecting SQL Injection Attacks Based on RNN Autoencoder Model

by Maha Alghawazi, Daniyal Alghazzawi and Suaad Alarifi

Mathematics 2023, 11(15), 3286; https://doi.org/10.3390/math11153286 - 26 Jul 2023

Cited by 6 | Viewed by 3195

Abstract

SQL injection attacks are one of the most common types of attacks on Web applications. These attacks exploit vulnerabilities in an application’s database access mechanisms, allowing attackers to execute unauthorized SQL queries. In this study, we propose an architecture for detecting SQL injection [...] Read more.

SQL injection attacks are one of the most common types of attacks on Web applications. These attacks exploit vulnerabilities in an application’s database access mechanisms, allowing attackers to execute unauthorized SQL queries. In this study, we propose an architecture for detecting SQL injection attacks using a recurrent neural network autoencoder. The proposed architecture was trained on a publicly available dataset of SQL injection attacks. Then, it was compared with several other machine learning models, including ANN, CNN, decision tree, naive Bayes, SVM, random forest, and logistic regression models. The experimental results showed that the proposed approach achieved an accuracy of 94% and an F1-score of 92%, which demonstrate its effectiveness in detecting QL injection attacks with high accuracy in comparison to the other models covered in the study. Full article

(This article belongs to the Special Issue Advanced Artificial Intelligence Models and Its Applications)

► Show Figures

Figure 1

12 pages, 1117 KiB

Open AccessArticle

Alleviating Long-Tailed Image Classification via Dynamical Classwise Splitting

by Ye Yuan, Jiaqi Wang, Xin Xu, Ruoshi Li, Yongtong Zhu, Lihong Wan, Qingdu Li and Na Liu

Mathematics 2023, 11(13), 2996; https://doi.org/10.3390/math11132996 - 05 Jul 2023

Viewed by 1001

Abstract

With the rapid increase in data scale, real-world datasets tend to exhibit long-tailed class distributions (i.e., a few classes account for most of the data, while most classes contain only a few data points). General solutions typically exploit class rebalancing strategies involving resampling [...] Read more.

With the rapid increase in data scale, real-world datasets tend to exhibit long-tailed class distributions (i.e., a few classes account for most of the data, while most classes contain only a few data points). General solutions typically exploit class rebalancing strategies involving resampling and reweighting based on the sample number for each class. In this work, we explore an orthogonal direction, category splitting, which is motivated by the empirical observation that naive splitting of majority samples could alleviate the heavy imbalance between majority and minority classes. To this end, we propose a novel classwise splitting (CWS) method built upon a dynamic cluster, where classwise prototypes are updated using a moving average technique. CWS generates intra-class pseudo labels for splitting intra-class samples based on the point-to-point distance. Moreover, a group mapping module was developed to recover the ground truth of the training samples. CWS can be plugged into any existing method as a complement. Comprehensive experiments were conducted on artificially induced long-tailed image classification datasets, such as CIFAR-10-LT, CIFAR-100-LT, and OCTMNIST. Our results show that when trained with the proposed class-balanced loss, the network is able to achieve significant performance gains on long-tailed datasets. Full article

(This article belongs to the Special Issue Advanced Artificial Intelligence Models and Its Applications)

► Show Figures

Figure 1

17 pages, 2225 KiB

Open AccessArticle

Broad Embedded Logistic Regression Classifier for Prediction of Air Pressure Systems Failure

by Adegoke A. Muideen, Carman Ka Man Lee, Jeffery Chan, Brandon Pang and Hafiz Alaka

Mathematics 2023, 11(4), 1014; https://doi.org/10.3390/math11041014 - 16 Feb 2023

Cited by 3 | Viewed by 1420

Abstract

In recent years, the latest maintenance modelling techniques that adopt the data-based method, such as machine learning (ML), have brought about a broad range of useful applications. One of the major challenges in the automotive industry is the early detection of component failure [...] Read more.

In recent years, the latest maintenance modelling techniques that adopt the data-based method, such as machine learning (ML), have brought about a broad range of useful applications. One of the major challenges in the automotive industry is the early detection of component failure for quick response, proper action, and minimizing maintenance costs. A vital component of an automobile system is an air pressure system (APS). Failure of APS without adequate and quick responses may lead to high maintenance costs, loss of lives, and component damages. This paper addresses classification problem where we detect whether a fault does or does not belong to APS. If a failure occurs in APS, it is classified as positive class; otherwise, it is classified as negative class. Hence, in this paper, we propose broad embedded logistic regression (BELR). The proposed BELR is applied to predict APS failure. It combines a broad learning system (BLS) and logistic regression (LogR) classifier as a fusion model. The proposed approach capitalizes on the strength of BLS and LogR for a better APS failure prediction. Additionally, we employ the BLS’s feature-mapped nodes for extracting features from the input data. Additionally, we use the enhancement nodes of the BLS to enhance the features from feature-mapped nodes. Hence, we have features that can assist LogR for better classification performances, even when the data is skewed to the positive class or negative class. Furthermore, to prevent the curse of dimensionality, a common problem with high-dimensional data sets, we utilize principal component analysis (PCA) to reduce the data dimension. We validate the proposed BELR using the APS data set and compare the results with the other robust machine learning classifiers. The commonly used evaluation metrics, namely Recall, Precision, an F1-score, to evaluate the model performance. From the results, we validate that performance of the proposed BELR. Full article

(This article belongs to the Special Issue Advanced Artificial Intelligence Models and Its Applications)

► Show Figures

Figure 1

19 pages, 3856 KiB

Open AccessArticle

Vehicle Routing Optimization with Cross-Docking Based on an Artificial Immune System in Logistics Management

by Shih-Che Lo and Ying-Lin Chuang

Mathematics 2023, 11(4), 811; https://doi.org/10.3390/math11040811 - 05 Feb 2023

Cited by 3 | Viewed by 2189

Abstract

Background: Manufacturing companies optimize logistics network routing to reduce transportation costs and operational costs in order to make profits in an extremely competitive environment. Therefore, the efficiency of logistics management in the supply chain and the quick response to customers’ demands are treated [...] Read more.

Background: Manufacturing companies optimize logistics network routing to reduce transportation costs and operational costs in order to make profits in an extremely competitive environment. Therefore, the efficiency of logistics management in the supply chain and the quick response to customers’ demands are treated as an additional source of profit. One of the warehouse operations for intelligent logistics network design, called cross-docking (CD) operations, is used to reduce inventory levels and improve responsiveness to meet customers’ requirements. Accordingly, the optimization of a vehicle dispatch schedule is imperative in order to produce a routing plan with the minimum transport cost while meeting demand allocation. Methods: This paper developed a two-phase algorithm, called sAIS, to solve the vehicle routing problem (VRP) with the CD facilities and systems in the logistics operations. The sAIS algorithm is based on a clustering-first and routing-later approach. The sweep method is used to cluster trucks as the initial solution for the second phase: optimizing routing by the Artificial Immune System. Results: In order to examine the performance of the proposed sAIS approach, we compared the proposed model with the Genetic Algorithm (GA) on the VRP with pickup and delivery benchmark problems, showing average improvements of 7.26%. Conclusions: In this study, we proposed a novel sAIS algorithm for solving VRP with CD problems by simulating human body immune reactions. The experimental results showed that the proposed sAIS algorithm is robustly competitive with the GA on the criterion of average solution quality as measured by the two-sample t-test. Full article

(This article belongs to the Special Issue Advanced Artificial Intelligence Models and Its Applications)

► Show Figures

Figure 1

14 pages, 7401 KiB

Open AccessArticle

MRBERT: Pre-Training of Melody and Rhythm for Automatic Music Generation

by Shuyu Li and Yunsick Sung

Mathematics 2023, 11(4), 798; https://doi.org/10.3390/math11040798 - 04 Feb 2023

Cited by 3 | Viewed by 2894

Abstract

Deep learning technology has been extensively studied for its potential in music, notably for creative music generation research. Traditional music generation approaches based on recurrent neural networks cannot provide satisfactory long-distance dependencies. These approaches are typically designed for specific tasks, such as melody [...] Read more.

Deep learning technology has been extensively studied for its potential in music, notably for creative music generation research. Traditional music generation approaches based on recurrent neural networks cannot provide satisfactory long-distance dependencies. These approaches are typically designed for specific tasks, such as melody and chord generation, and cannot generate diverse music simultaneously. Pre-training is used in natural language processing to accomplish various tasks and overcome the limitation of long-distance dependencies. However, pre-training is not yet widely used in automatic music generation. Because of the differences in the attributes of language and music, traditional pre-trained models utilized in language modeling cannot be directly applied to music fields. This paper proposes a pre-trained model, MRBERT, for multitask-based music generation to learn melody and rhythm representation. The pre-trained model can be applied to music generation applications such as web-based music composers that includes the functions of melody and rhythm generation, modification, completion, and chord matching after being fine-tuned. The results of ablation experiments performed on the proposed model revealed that under the evaluation metrics of HITS@k, the pre-trained MRBERT considerably improved the performance of the generation tasks by 0.09–13.10% and 0.02–7.37%, compared to the usage of RNNs and the original BERT, respectively. Full article

(This article belongs to the Special Issue Advanced Artificial Intelligence Models and Its Applications)

► Show Figures

Figure 1

17 pages, 3041 KiB

Open AccessArticle

Application of Artificial Intelligence for Better Investment in Human Capital

by Mohammed Abdullah Ammer, Zeyad A. T. Ahmed, Saleh Nagi Alsubari, Theyazn H. H. Aldhyani and Shahab Ahmad Almaaytah

Mathematics 2023, 11(3), 612; https://doi.org/10.3390/math11030612 - 26 Jan 2023

Cited by 1 | Viewed by 2217

Abstract

Selecting candidates for a specific job or nominating a person for a specific position takes time and effort due to the need to search for the individual’s file. Ultimately, the hiring decision may not be successful. However, artificial intelligence helps organizations or companies [...] Read more.

Selecting candidates for a specific job or nominating a person for a specific position takes time and effort due to the need to search for the individual’s file. Ultimately, the hiring decision may not be successful. However, artificial intelligence helps organizations or companies choose the right person for the right job. In addition, artificial intelligence contributes to the selection of harmonious working teams capable of achieving an organization’s strategy and goals. This study aimed to contribute to the development of machine-learning models to analyze and cluster personality traits and classify applicants to conduct correct hiring decisions for particular jobs and identify their weaknesses and strengths. Helping applicants to succeed while managing work and training employees with weaknesses is necessary to achieving an organization’s goals. Applying the proposed methodology, we used a publicly available Big-Five-personality-traits-test dataset to conduct the analyses. Preprocessing techniques were adopted to clean the dataset. Moreover, hypothesis testing was performed using Pearson’s correlation approach. Based on the testing results, we concluded that a positive relationship exists between four personality traits (agreeableness, conscientiousness, extraversion, and openness), and a negative correlation occurred between neuroticism traits and the four traits. This dataset was unlabeled. However, we applied the K-mean clustering algorithm to the data-labeling task. Furthermore, various supervised machine-learning models, such as random forest (RF), support vector machine (SVM), K-nearest neighbor (KNN), and AdaBoost, were used for classification purposes. The experimental results revealed that the SVM attained the highest results, with an accuracy of 98%, outperforming the other classification models. This study adds to the current literature and body of knowledge through examining the extent of the application of artificial intelligence in the present and, potentially, the future of human-resource management. Our results may be of significance to companies, organizations and their leaders and human-resource executives, in addition to human-resource professionals. Full article

(This article belongs to the Special Issue Advanced Artificial Intelligence Models and Its Applications)

► Show Figures

Figure 1

20 pages, 5429 KiB

Open AccessFeature PaperArticle

Self-Writer: Clusterable Embedding Based Self-Supervised Writer Recognition from Unlabeled Data

by Zabir Mohammad, Muhammad Mohsin Kabir, Muhammad Mostafa Monowar, Md Abdul Hamid and Muhammad Firoz Mridha

Mathematics 2022, 10(24), 4796; https://doi.org/10.3390/math10244796 - 16 Dec 2022

Viewed by 2056

Abstract

Writer recognition based on a small amount of handwritten text is one of the most challenging deep learning problems because of the implicit characteristics of handwriting styles. In a deep convolutional neural network, writer recognition based on supervised learning has shown great success. [...] Read more.

Writer recognition based on a small amount of handwritten text is one of the most challenging deep learning problems because of the implicit characteristics of handwriting styles. In a deep convolutional neural network, writer recognition based on supervised learning has shown great success. These supervised methods typically require a lot of annotated data. However, collecting annotated data is expensive. Although unsupervised writer recognition methods may address data annotation issues significantly, they often fail to capture sufficient feature relationships and usually perform less efficiently than supervised learning methods. Self-supervised learning may solve the unlabeled dataset issue and train the unsupervised datasets in a supervised manner. This paper introduces Self-Writer, a self-supervised writer recognition approach dealing with unlabeled data. The proposed scheme generates clusterable embeddings from a small fixed-length image frame such as a text block. The training strategy presumes that a small image frame of handwritten text should include the writer’s handwriting characteristics. We construct pairwise constraints and nongenerative augmentation to train Siamese architecture to generate embeddings depending on such an assumption. Self-Writer is evaluated on the two most widely used datasets, IAM and CVL, on pairwise and triplet architecture. We find Self-Writer to be convincing in achieving satisfactory performance using pairwise architectures. Full article

(This article belongs to the Special Issue Advanced Artificial Intelligence Models and Its Applications)

► Show Figures

Figure 1

15 pages, 1013 KiB

Open AccessArticle

Fully Connected Hashing Neural Networks for Indexing Large-Scale Remote Sensing Images

by Na Liu, Haiming Mou, Jun Tang, Lihong Wan, Qingdu Li and Ye Yuan

Mathematics 2022, 10(24), 4716; https://doi.org/10.3390/math10244716 - 12 Dec 2022

Cited by 1 | Viewed by 1227

Abstract

With the emergence of big data, the efficiency of data querying and data storage has become a critical bottleneck in the remote sensing community. In this letter, we explore hash learning for the indexing of large-scale remote sensing images (RSIs) with a supervised [...] Read more.

With the emergence of big data, the efficiency of data querying and data storage has become a critical bottleneck in the remote sensing community. In this letter, we explore hash learning for the indexing of large-scale remote sensing images (RSIs) with a supervised pairwise neural network with the aim of improving RSI retrieval performance with a few binary bits. First, a fully connected hashing neural network (FCHNN) is proposed in order to map RSI features into binary (feature-to-binary) codes. Compared with pixel-to-binary frameworks, such as DPSH (deep pairwise-supervised hashing), FCHNN only contains three fully connected layers and incorporates another new constraint, so it can be significantly accelerated to obtain desirable performance. Second, five types of image features, including mid-level and deep features, were investigated in the learning of the FCHNN to achieve state-of-the-art performances. The mid-level features were based on Fisher encoding with affine-invariant local descriptors, and the deep features were extracted by pretrained or fine-tuned CNNs (e.g., CaffeNet and VGG-VD16). Experiments on five recently released large-scale RSI datasets (i.e., AID, NWPU45, PatternNet, RSI-CB128, and RSI-CB256) demonstrated the effectiveness of the proposed method in comparison with existing handcrafted or deep-based hashing methods. Full article

(This article belongs to the Special Issue Advanced Artificial Intelligence Models and Its Applications)

► Show Figures

Figure 1

21 pages, 607 KiB

Open AccessArticle

Employing Quantum Fruit Fly Optimization Algorithm for Solving Three-Dimensional Chaotic Equations

by Qasim M. Zainel, Saad M. Darwish and Murad B. Khorsheed

Mathematics 2022, 10(21), 4147; https://doi.org/10.3390/math10214147 - 06 Nov 2022

Cited by 9 | Viewed by 1388

Abstract

In a chaotic system, deterministic, nonlinear, irregular, and initial-condition-sensitive features are desired. Due to its chaotic nature, it is difficult to quantify a chaotic system’s parameters. Parameter estimation is a major issue because it depends on the stability analysis of a chaotic system, [...] Read more.

In a chaotic system, deterministic, nonlinear, irregular, and initial-condition-sensitive features are desired. Due to its chaotic nature, it is difficult to quantify a chaotic system’s parameters. Parameter estimation is a major issue because it depends on the stability analysis of a chaotic system, and communication systems that are based on chaos make it difficult to give accurate estimates or a fast rate of convergence. Several nature-inspired metaheuristic algorithms have been used to estimate chaotic system parameters; however, many are unable to balance exploration and exploitation. The fruit fly optimization algorithm (FOA) is not only efficient in solving difficult optimization problems, but also simpler and easier to construct than other currently available population-based algorithms. In this study, the quantum fruit fly optimization algorithm (QFOA) was suggested to find the optimum values for chaotic parameters that would help algorithms converge faster and avoid the local optimum. The recommended technique used quantum theory probability and uncertainty to overcome the classic FA’s premature convergence and local optimum trapping. QFOA modifies the basic Newtonian-based search technique of FA by including a quantum behavior-based searching mechanism used to pinpoint the position of the fruit fly swarm. The suggested model has been assessed using a well-known Lorenz system with a specified set of parameter values and benchmarked signals. The results showed a considerable improvement in the accuracy of parameter estimates and better estimation power than state-of-the art parameter estimation approaches. Full article

(This article belongs to the Special Issue Advanced Artificial Intelligence Models and Its Applications)

► Show Figures

Figure 1

18 pages, 3714 KiB

Open AccessArticle

Lightweight Target-Aware Attention Learning Network-Based Target Tracking Method

by Yanchun Zhao, Jiapeng Zhang, Rui Duan, Fusheng Li and Huanlong Zhang

Mathematics 2022, 10(13), 2299; https://doi.org/10.3390/math10132299 - 30 Jun 2022

Cited by 2 | Viewed by 1254

Abstract

Siamese network trackers based on pre-trained depth features have achieved good performance in recent years. However, the pre-trained depth features are trained in advance on large-scale datasets, which contain feature information of a large number of objects. There may be a pair of [...] Read more.

Siamese network trackers based on pre-trained depth features have achieved good performance in recent years. However, the pre-trained depth features are trained in advance on large-scale datasets, which contain feature information of a large number of objects. There may be a pair of interference and redundant information for a single tracking target. To learn a more accurate target feature information, this paper proposes a lightweight target-aware attention learning network to learn the most effective channel features of the target online. The lightweight network uses a designed attention learning loss function to learn a series of channel features with weights online with no complex parameters. Compared with the pre-trained features, the channel features with weights can represent the target more accurately. Finally, the lightweight target-aware attention learning network is unified into a Siamese tracking network framework to implement target tracking effectively. Experiments on several datasets demonstrate that the tracker proposed in this paper has good performance. Full article

(This article belongs to the Special Issue Advanced Artificial Intelligence Models and Its Applications)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Advanced Artificial Intelligence Models and Its Applications

Share This Special Issue

Special Issue Editor

Special Issue Information

Keywords

Related Special Issue

Published Papers (11 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI