Search

To ensure the stability of the communication architecture in the power monitoring system, we propose an intelligent grid cyber-physical communication architecture modelling method based on the correlation characteristic matrix model. The article connects the physical entity layer, the information physical coupling layer, and the information system layer through an incidence matrix to form a complete power information physical system unit model. Through this system, we call the link and each node on the call link as the monitoring object, collect the relevant index data, and establish the business alarm mapping model of the communication network failure. The experimental results verify the reliability of the system and algorithm.

The advancement of Chinese education informatisation construction has injected new vitality into the development of Chinese educational technology in the new era and brought new challenges to the development of Chinese educational technology. Nonlinear dissipative structure theory has been a necessary enlightenment for the development of education informatisation. Based on the theory of nonlinear dissipative structure, the paper explores the relationship between the theory and education and teaching. It constructs a diversified regression calculation model of the information-based teaching ecology. Finally, it points out the strategies and ways to apply the dissipative structure theory to improve information-based teaching.

This article takes the nonlinear differential equation model as an example and uses information technology to create a new course teaching model. The computing software Maple is effectively applied to the precise solution of nonlinear differential equations through the analysis of examples. The overall goal and specific implementation of the teaching plan to integrate ordinary differential equations and information technology have been completed. The study found that the teaching plan proposed in the article is assisted by information technology, with teachers and students participating in an interactive and exploratory teaching method. This method is worthy of further promotion.

The dichotomy model of education informatisation is essential, which means the measurement of education informatisation construction and development. Finite element differential equations play an essential role in signal and information teaching. To improve teaching information, the paper applies the dichotomy model of finite element differential equations to the reform of physics education information teaching. This article fully introduces the basic principles of the dichotomy model in finite element differential equations and introduces several analysis methods of the inverse Laplace transform of differential equations. At last, the method is applied to the informatisation of physics education to improve the quality of teaching.

The digital and physical methods of establishing minimal curved surfaces are the basis for realizing the design of the minimal curved surface modeling structure. Based on this research background, the paper showed an artistic surface modeling method based on nonlinear over-limit difference equations. The article combines parameter optimization and 3D modeling methods to model the constructed surface modeling. The research found that the nonlinear out-of-limit difference equation proposed in the paper is more accurate than the standard fractional differential equation algorithm. For this reason, the method can be extended and applied to the design of artistic surface modeling.

Machine Learning (ML) has become a potent predictive analytics tool in several fields, including the study of social media data. Social media sites have developed into massive repositories of user-generated information, providing insightful data about user trends, interests, and behavior. This abstract emphasizes the use of machine learning methods for predictive analytics in social media data and examines the potential and problems unique to this field. Utilizing the capabilities of machine learning algorithms to identify significant trends and forecast user behavior from social media data is the goal of this study. The study makes use of a sizable dataset made up of user profiles, blog posts, comments, and engagement metrics gathered from well-known social networking sites. Predictive models are created using a variety of machine learning algorithms, such as ensemble methods, neural networks, decision trees, and support vector machines. As a result, this study emphasizes how important machine learning is for doing predictive analytics on social media data. The employment of diverse algorithms and preprocessing methods yields insightful information about user behavior and enables precise prediction of user behaviors. To improve the prediction powers of machine learning in this area, future research should concentrate on tackling the obstacles related to social media data, such as privacy concerns and data quality issues.

Recently, the number of Internet of Things (IoT)-connected devices has increased daily. Consequently, cybersecurity challenges have increased due to the natural diversity of the IoT, limited hardware resources, and limited security capabilities. Intrusion detection systems (IDSs) play a substantial role in securing IoT networks. Several researchers have focused on machine learning (ML) and deep learning (DL) to develop intrusion detection techniques. Although ML is good for classification, other methods perform better in feature transformation. However, at the level of accuracy, both learning techniques have their own certain compromises. Although IDSs based on ML and DL methods can achieve a high detection rate, the performance depends on the training dataset size. Incidentally, collecting a large amount of data is one of the main drawbacks that limits performance when training datasets are lacking, and such methods can fail to detect novel attacks. Few-shot learning (FSL) is an emerging approach that is employed in different domains because of its proven ability to learn from a few training samples. Although numerous studies have addressed the issues of IDSs and improved IDS performance, the literature on FSL-based IDSs is scarce. Therefore, an investigation is required to explore the performance of FSL in IoT IDSs. This work proposes an IoT intrusion detection model based on a convolutional neural network as a feature extractor and a prototypical network as an FSL classifier. The empirical results were analyzed and compared with those of recent intrusion detection approaches. The accuracy results reached 99.44%, which shows a promising direction for involving FSL in IoT IDSs. [ABSTRACT FROM AUTHOR]

Rice is one of the fundamental food items that comes in many varieties with their associated benefits. It can be sub-categorized based on its visual features like texture, color, and shape. Using these features, the automatic classification of rice varieties has been studied using various machine learning approaches for marketing and industrial use. Due to the outstanding performance of deep learning, several models have been proposed to assist in vision tasks like classification and detection. Regardless of their best results on accuracy metrics, they have been observed as overly excessive for computational resources and expert supervision. To address these challenges, this paper proposes three deep learning models that offer similar performance with 10% lighter computational overhead in comparison to existing best models. Moreover, they have been trained for end-to-end flow to demonstrate minimum expert supervision for pre-processing and feature engineering sub-tasks. The results can be observed as promising for classifying rice among five varieties, namely Arborio, Basmati, Ipsala, Jasmine, and Karacadag. The process and performance of the trained models can be extended for edge and mobile devices for field-specific tasks autonomously. [ABSTRACT FROM AUTHOR]

Detecting cyber intrusions in network traffic is a tough task for cybersecurity. Current methods struggle with the complexity of understanding patterns in network data. To solve this, we present the Hybrid Deep Learning Intrusion Detection Model (HD-IDM), a new way that combines GRU and LSTM classifiers. GRU is good at catching quick patterns, while LSTM handles long-term ones. HD-IDM blends these models using weighted averaging, boosting accuracy, especially with complex patterns. We tested HD-IDM on four datasets: CSE-CIC-IDS2017, CSE-CIC-IDS2018, NSL KDD, and CIC-DDoS2019. The HD-IDM classifier achieved remarkable performance metrics on all datasets. It attains an outstanding accuracy of 99.91%, showcasing its consistent precision across the dataset. With an impressive precision of 99.62%, it excels in accurately categorizing positive cases, crucial for minimizing false positives. Additionally, maintaining a high recall of 99.43%, it effectively identifies the majority of actual positive cases while minimizing false negatives. The F1-score of 99.52% emphasizes its robustness, making it the top choice for classification tasks requiring precision and reliability. It is particularly good at ROC and precision/recall curves, discriminating normal and harmful network activities. While HD-IDM is promising, it has limits. It needs labeled data and may struggle with new intrusion methods. Future work should find ways to handle unlabeled data and adapt to emerging threats. Also, making HD-IDM work faster for real-time use and dealing with scalability challenges is key for its broader use in changing network environments. [ABSTRACT FROM AUTHOR]

An aim of the analysis of biomedical signals such as heart rate variability signals, brain signals, oxygen saturation variability (OSV) signals, etc., is for the design and development of tools to extract information about the underlying complexity of physiological systems, to detect physiological states, monitor health conditions over time, or predict pathological conditions. Entropy-based complexity measures are commonly used to quantify the complexity of biomedical signals; however novel complexity measures need to be explored in the context of biomedical signal classification. In this work, we present a novel technique that used Haar wavelets to analyze the complexity of OSV signals of subjects during COVID-19 infection and after recovery. The data used to evaluate the performance of the proposed algorithms comprised recordings of OSV signals from 44 COVID-19 patients during illness and after recovery. The performance of the proposed technique was compared with four, scale-based entropy measures: multiscale entropy (MSE); multiscale permutation entropy (MPE); multiscale fuzzy entropy (MFE); multiscale amplitude-aware permutation entropy (MAMPE). Preliminary results of the pilot study revealed that the proposed algorithm outperformed MSE, MPE, MFE, and MMAPE in terms of better accuracy and time efficiency for separating during and after recovery the OSV signals of COVID-19 subjects. Further studies are needed to evaluate the potential of the proposed algorithm for large datasets and in the context of other biomedical signal classifications. [ABSTRACT FROM AUTHOR]

The cultivation of creativity is closely related to language learning. How to design the creativity promotion mechanism of English teaching in the public environment is the challenge faced by English teachers. With the advent of the era of big data, English teachers can apply the latest research results to classroom teaching. For example, the rational use of social media helps students to learn and communicate in the language, cultivate students' creativity in learning English, and improves the quality of teaching. Corporate social media has become the most important way for corporate employees to record their lives, express opinions, share and communicate, and it is also one of the reliable and real-time sources of big data that reflects the true state of English learners. Real, accurate, and timely enterprise social media big data samples contain an enormous educational value, providing more possibilities for educational research. From the perspective of value, through sentiment analysis, topic mining, social network analysis, etc. on social media big data, learner portraits can be realized, thereby providing decision-making reference and support for stakeholders. This paper first builds a learning interest classification model based on TCNN-GRU deep learning, collects experimental data sets from an online English learner's social media platform and performs learning interest classification and labeling, and then uses the TCNN-GRU model to determine the user's learning interest tendency. On this basis, the concept of learning interest index is further proposed, and a neural network-based corporate social platform English learner portrait model is established. The experimental results show that, compared with the traditional machine learning model, convolutional neural network model, and recurrent neural network model, the TCNN-GRU model can obtain better results in learning interest classification. [ABSTRACT FROM AUTHOR]

In order to solve the challenges brought by multi-source and cross-domain scenarios to online music education, this paper designs an online music education system based on advanced artificial intelligence technology, which can provide personalized learning course resource recommendations for music online learners. The system includes four layers, consisting of user interface layer, application module layer, function module layer and data storage layer. At the application module level, this paper proposes a music recommendation algorithm based on a personalized multimodal network model. The recommendation algorithm performs music information retrieval (MIR) based on the similarity judgment of the contour of music pitch and the overall change, and constructs a multimodal network model based on the user's preference for resources to achieve personalized music recommendation. This paper crawls more than one million music score data from a well-known music platform database in China to establish a dataset to evaluate the performance of this method. The comparison results with three existing works show that the method proposed in this paper has good performance and can provide users with suitable music recommendations. The artificial intelligence technology-driven online music education mechanism proposed in this paper has good prospects. [ABSTRACT FROM AUTHOR]

For the problem of class-imbalance in the operation monitoring data of wind turbine (WT) pitch connecting bolts, an improved Borderline-SMOTE oversampling method based on "two-step decision" with adaptive selection of synthetic instances (TSDAS-SMOTE) is proposed. Then, TSDAS-SMOTE is combined with XGBoost to construct a WT pitch connection bolt fault detection model. TSDAS-SMOTE generates new samples by "two-step decision making" to avoid the problem of class–class boundary blurring that Borderline-SMOTE tends to cause when oversampling. First, the nearest neighbor sample characteristics are perceived by the fault class samples in the first decision step. If the characteristics of this fault class sample are different from the characteristics of all its nearest neighbor samples, the fault class sample is identified as interference and filtered. Second, the faulty class samples in the boundary zone are extracted as synthetic instances to generate new samples adaptively. Finally, the normal class samples in the boundary zone are used to perceive the unqualified new generated samples in the boundary zone based on the minimum Euclidean distance characteristics, and these unqualified samples are eliminated. For the second step of decision making, since the first step decision removes some of the newly generated samples, the remaining fault class samples without interference samples and boundary zone samples are used as synthetic instances to continue adaptively generating new samples. Thus, a balanced data set with clear class–class boundary zone is obtained, which is then used to train a WT pitch connection bolt fault detection model based on the XGBoost algorithm. The experimental results show that compared with six popular oversampling methods such as Borderline-SMOTE, Cluster-SMOTE, K -means-SMOTE, etc., the fault detection model constructed by the proposed oversampling method is better than the compared fault detection models in terms of missed alarm rate (MAR) and false alarm rate (FAR). Therefore, it can well achieve the fault detection of large WT pitch connection bolts. [ABSTRACT FROM AUTHOR]

Abnormal detection of wind turbine converter (WT) is one of the key technologies to ensure long-term stable operation and safe power generation of WT. The number of normal samples in the SCADA data of WT converter operation is much larger than the number of abnormal samples. In order to solve the problem of low abnormal data and low recognition rate of WTs, we propose a sample enhancement method for WT abnormality detection based on an improved conditional Wasserstein generative adversarial network. Since the anomaly samples of WT converters are few and difficult to obtain, the CWGANGP oversampling method is constructed to increase the anomaly samples in the WT converter dataset. The method adds additional category labels to the inputs of the generative and discriminative models of the generative adversarial network, constrains the generative model to generate few types of anomalous samples, and enhances the generative model's ability to generate few types of anomalous samples, enabling data generation in a prescribed direction. The smooth continuous Wasserstein distance is used instead of JS divergence as a distance metric to measure the probability distribution of real and generated data in the conditional generative response network and reduce pattern collapse. The gradient constraint is added to the CWGANGP model to enhance the convergence of the WGAN model, so that the generative model can synthesize minority class anomalous samples more effectively and accurately under the condition of unbalanced sample data categories. The quality of anomalous sample generation is also improved. Finally, the anomaly detection is made on the actual operating variator dataset for the unbalanced dataset and the dataset after reaching Nash equilibrium. The experimental results show that the method used in this paper has lower MAR and FAR in WT converter anomaly detection compared with other oversampling data balance optimization methods such as SMOTE, RandomOverSampler, GAN, etc. The method can be well implemented for anomaly detection of large wind turbines and can be better applied in WT intelligent systems. [ABSTRACT FROM AUTHOR]

Alzheimer's disease has become a major concern in the healthcare domain as it is growing rapidly. Much research has been conducted to detect it from MRI images through various deep learning approaches.However, the problems of the availability of medical data and preserving the privacy of patients still exists. To mitigate this issue in Alzheimer's disease detection, we implement the federated approach, which is found to be more efficient, robust, and consistent compared with the conventional approach. For this, we need deep excavation on various orientations of MRI images and transfer learning architectures. Then, we utilize two publicly available datasets (OASIS and ADNI) and design various cases to evaluate the performance of the federated approach. The federated approach achieves better accuracy and sensitivity compared with the conventional approaches in most of the cases. Moreover, the robustness of the proposed approach is also found to be better than the conventional approach. In our federated approach, MobileNet, a low-cost transfer learning architecture, achieves the highest 95.24%, 81.94%, and 83.97% accuracy in the OASIS, ADNI, and merged (ADNI + OASIS) test sets, which is much higher than the achieved performance in the conventional approach. Furthermore, in the proposed approach, only the weights of the model are shared, which keeps the original MRI images in their respective hospital or institutions, preserving privacy in the healthcare domain. [ABSTRACT FROM AUTHOR]

Contemporarily numerous analysts labored in the field of Vehicle detection which improves Intelligent Transport System (ITS) and reduces road accidents. The major obstacles in automatic detection of tiny vehicles are due to occlusion, environmental conditions, illumination, view angles and variation in size of objects. This research centers on tiny and partially occluded vehicle detection and identification in challenging scene specifically in crowed area. In this paper we present comprehensive methodology of tiny vehicle detection using Deep Neural Networks (DNN) namely CenterNet. Substantially DNN disregards objects that are small in size 5 pixels and more false positives likely to happen in crowded area. Primarily there are two categories of deep learning models single-step and two-step. A single forward pass model is the one in which detection is performed directly to possible location over dense sampling, wherein two-step models incorporated by Region proposals followed by object detection. We in this research scrutinize one-step State of the art (SOTA) model CenteNet as proposed recently with three different feature extractor ResNet-50, HourGlass-104 and ResNet-101 one by one. We train our model on challenging KITTI dataset which outperforms in comparison with SOTA single-step technique MSSD300* which depicts performance improvement by 20.2%mAPandSMOKEby with 13.2% mAP respectively. Effectiveness of CenterNet can be justified through the huge improved performance. The performance of our model is evaluated on KITTI (Karlsruhe Institute of Technology and Toyota Technological Institute) benchmark dataset with different backbones such as ResNet-50 gives 62.3% mAP ResNet-101 82.5% mAP, last but not the least HourGlass-104 outperforms with 98.2% mAP CenterNet-HourGlass-104 achieved high mAP among above mentioned feature extractors. We also compare our model with other SOTA techniques. [ABSTRACT FROM AUTHOR]

The Internet of Things (IoT) has grown more pervasive in recent years. It makes it possible to describe the physical world in detail and interact with it in several different ways. Consequently, IoT has the potential to be involved in many different applications, including healthcare, supply chain, logistics, and the automotive sector. IoT-based smart healthcare systems have significantly increased the value of organizations that rely heavily on IoT infrastructures and solutions. In fact, with the recent COVID-19 pandemic, IoT played an important role in combating diseases. However, IoT devices are tiny, with limited capabilities. Therefore, IoT systems lack encryption, insufficient privacy protection, and subject to many attacks. Accordingly, IoT healthcare systems are extremely vulnerable to several security flaws that might result in more accurate, quick, and precise diagnoses. On the other hand, blockchain technology has been proven to be effective in many critical applications. Blockchain technology combined with IoT can greatly improve the healthcare industry's efficiency, security, and transparency while opening new commercial choices. This paper is an extension of the current effort in the IoT smart healthcare systems. It has three main contributions, as follows: (1) it proposes a smart unsupervised medical clinic without medical staff interventions. It tries to provide safe and fast services confronting the pandemic without exposing medical staff to danger. (2) It proposes a deep learning algorithm for COVID-19 detection-based X-ray images; it utilizes the transfer learning (ResNet152) model. (3) The paper also presents a novel blockchain-based pharmaceutical system. The proposed algorithms and systems have proven to be effective and secure enough to be used in the healthcare environment. [ABSTRACT FROM AUTHOR]

Deep learning is expanding and continues to evolve its capabilities toward more accuracy, speed, and cost-effectiveness. The core ingredients for getting its promising results are appropriate data, sufficient computational resources, and best use of a particular algorithm. The application of these algorithms in medical image analysis tasks has achieved outstanding results compared to classical machine learning approaches. Localizing the area-of-interest is a challenging task that has vital importance in computer aided diagnosis. Generally, radiologists interpret the radiographs based on their knowledge and experience. However, sometimes, they can overlook or misinterpret the findings due to various reasons, e.g., workload or judgmental error. This leads to the need for specialized AI tools that assist radiologists in highlighting abnormalities if exist. To develop a deep learning driven localizer, certain alternatives are available within architectures, datasets, performance metrics, and approaches. Informed decision for selection within the given alternative can lead to batter outcome within lesser resources. This paper lists the required components along-with explainable AI for developing an abnormality localizer for X-ray images in detail. Moreover, strong-supervised vs weak-supervised approaches have been majorly discussed in the light of limited annotated data availability. Likewise, other correlated challenges have been presented along-with recommendations based on a relevant literature review and similar studies. This review is helpful in streamlining the development of an AI based localizer for X-ray images while extendable for other radiological reports. [ABSTRACT FROM AUTHOR]

The effect of the COVID-19 pandemic on crude oil prices just faded; at this moment, the Russia–Ukraine war brought a new crisis. In this paper, a new application is developed that predicts the change in crude oil prices by incorporating these two global effects. Unlike most existing studies, this work uses a dataset that involves data collected over twenty-two years and contains seven different features, such as crude oil opening, closing, intraday highest value, and intraday lowest value. This work applies cross-validation to predict the crude oil prices by using machine learning algorithms (support vector machine, linear regression, and rain forest) and deep learning algorithms (long short-term memory and bidirectional long short-term memory). The results obtained by machine learning and deep learning algorithms are compared. Lastly, the high-performance estimation can be achieved in this work with the average mean absolute error value over 0.3786. [ABSTRACT FROM AUTHOR]

The finite-time tracking control issue for a class of nonlinear pure-feedback system with prescribed performance and unknown hysteresis is investigated in this work. To solve the Bouc-Wen hysteresis with unknown parameters and direction conditions, the Nussbaum function and auxiliary virtual control function are used. A finite-time performance function is applied in prescribed performance, which can make the tracking error is limited to a pre-given boundary in finite time. Moreover, the mean-value theorem is applied to solve the difficulty of pure-feedback form. Combined with backstepping technique, an adaptive tracking control scheme is designed to make sure that all the closed-loop signals are bounded and that the tracking error converges to pro-given boundary. Finally, a simulation example is presented to show the effectiveness of the proposed control scheme. [ABSTRACT FROM AUTHOR]

In today's sophisticated global marketplace, supply chains are complex nonlinear systems in the presence of different types of uncertainties, including supply-demand and delivery uncertainties. Though up to now, some features of these systems are studied, there are still many aspects of these systems which need more attention. This necessitates more research studies on these systems. Hence, in this study, we propose a variable-order fractional supply chain network. The dynamic of the system is investigated using the Lyapunov exponent and bifurcation diagram. It is demonstrated that a minor change in the system's fractional-derivative may dramatically affect its behavior. Then, distributed consensus tracking of the multi-agent network is studied. To this end, a control technique based on the sliding concept and Chebyshev neural network estimator is offered. The system's stability is demonstrated using the Lyapunov stability theorem and Barbalat's lemma. Finally, through numerical results, the proposed controller's excellent performance for distributed consensus tracking of multi-agent supply chain network is demonstrated. [ABSTRACT FROM AUTHOR]

In this study, a novel heuristic computing technique is presented to solve bioinformatics problem for the corneal shape model of eye surgery using Morlet wavelet artificial neural network optimized by the global search schemes, i.e. genetic algorithm (GA), local search technique, i.e. sequential quadratic programming (SQP) and the hybrid of GA-SQP. To measure the performance of the design network configuration, different cases based on nonlinear second-order differential equations governing the corneal model have been solved effectively. The numerical procedure of Adams method is implemented for the comparison purpose of the presented outcomes of the stochastic solver, which shows the worth of the present scheme based on accuracy and convergence with negligible values of absolute error in the range 10 − 7 to 10 − 8 . Furthermore, statistical measures are presented based on "mean absolute error", "root mean square error" and "coefficient of Theil's inequality" which additionally endorsed consistently accurate performance of integrated intelligent computing framework for solving the corneal shape model. [ABSTRACT FROM AUTHOR]