Search

Point cloud registration is the process of aligning and merging multiple point clouds into a same coordinate system. It has many applications in computer vision, robotics, 3D reconstruction, augmented reality, and autonomous driving. Despite its wide-ranging utility, traditional algorithms grapple with challenges such as substantial noise, outliers, limited overlap, motion distortions, and handling large scenes. These complexities impede the effective deployment of point cloud registration in practical real-world scenarios. This paper conducts a comprehensive inquiry into the domain of deep learning-based point cloud registration. It synthesizes recent advancements in algorithms about point cloud registration grounded in deep learning. The exposition delineates insights from four distinct perspectives: multi-layer perceptron, deep neural network, graph convolutional network, and attention mechanism. Furthermore, the paper systematically reviews prevalent datasets and evaluation metrics associated with deep learning-based point cloud registration. A discussion on the existing challenges in point cloud registration and a forward-looking exploration of potential research directions are included. [ABSTRACT FROM AUTHOR]

Artificial Intelligence is quickly emerging as a technological solution for the agriculture industry to surmount its classical challenges. Artificial Intelligence is facilitating farmers to refine their products and alleviate unfavourable impacts due to the environment. The central concern of this paper is predictive analytics to develop a machine learning model to identify and predict crop yield based on multiple environmental factors. In this paper, a hybrid learner 'RaNN' is proposed that combines the feature sampling and majority voting technique of Random Forest in-combination with the multilayer Feedforward Neural Network to predict the crop yield. Research has also ascertained the essential features responsible for accurate yield prediction. The proposed model works for rice yield prediction, one of the chief grains of India. The region chosen for the work is Punjab, which is among the largest producer states of India for rice. The dataset consists of 15 attributes comprising the weather and agriculture data collected from the Indian Meteorological Department Pune, and Punjab Environment Information System (ENVIS) Center, Government of India. The study has also made a comparative assessment of 'RaNN' with machine learning methods like Multiple Linear Regression, Random Forest, Decision Tree, Boosting Regression, Support Vector Machine Regression, Ensemble Learner, and Artificial Neural Network. Our model RaNN has listed a better prediction accuracy with minimal error among the other techniques providing a 98% correlation between the actual and the predicted yield. Abbreviations: AI – Artificial Intelligence; ANN – Artificial Neural Network; BR – Boosting Regression; Chem Fert – chemical fertilisers; DT – Decision Tree; EL – Ensemble Learner; ENVIS – Punjab Environment Information System; GBM – Stochastic Gradient Boosting Method; GPS – Global Positioning System; HMAX – highest maximum temperature in degrees C; IMD – Indian Meteorological Department; L1 – Lasso regression; L2 – Ridge regression; LMIN – lowest minimum temperature; ML – Machine Learning; MAE – Mean Absolute Error; MEVP – mean evaporation in mm; MLR – Multiple Linear Regression; MMAX – mean maximum temperature in degrees C; MMIN – mean minimum temperature in degrees C; MSSH – Mean sunshine duration in hours; MWS – mean wind speed in km/h; P1 – number of days with precipitation (0.1–0.2 mm); P2 – number of days with precipitation (greater than or equal to 0.3 mm); RaNN – Hybrid RF-ANN model; RMSE – Root Mean Squared Error; $${R^2}$$ R 2 – Coefficient of determination; RD – number of rainy days; RF – Random Forest; SVM Reg – Support Vector Machine Regression; TMRF – total rainfall per month in mm [ABSTRACT FROM AUTHOR]

Despite the complex punching shear behavior of reinforced concrete slabs have been comprehensively addressed in the literature, it is further essential to develop a universal design model comprising high accuracy and the simplicity for design practicability, adaptable to diverse conditions encountered in practice. Artificial intelligence applications, artificial neural networks (ANN), and more recently, various machine learning (ML) and deep learning (DL) techniques veer off in a new direction in structural engineering context with improved accuracy and efficiency. The paper begins with the assessment of the capabilities of various artificial intelligence applications in predicting the punching shear strength of slab-column connections without shear reinforcement through the extensive database using 650 punching shear experiments from the literature. Critical parameters influencing the punching shear strength as well as the precision of the current code provisions in predicting this feature were then thoroughly examined in the paper. The results shown in this paper validated the competency of artificial intelligence applications in predicting the punching shear strength of such connections with increased accuracy and improved simplicity in practical terms. The proposed models utilizing the artificial intelligence applications encourage the ultimate rehabilitation policies to be proposed and improved code provisions to be developed for contemporary structures. [ABSTRACT FROM AUTHOR]

This paper presents an investigation into the performance of radial distribution systems (DS) with the installation of series capacitors in feeder sections. While the use of shunt capacitors to enhance voltage profile in DS has been acknowledged, the benefits of series capacitors have only been explored to a limited extent. Load flow analysis, while commonly used for offline evaluation of DS, can at times yield inconclusive results due to convergence issues. To mitigate this, an alternative approach is proposed using Artificial Neural Networks (ANN) to directly determine system performance. The viability of the proposed technique is evaluated for IEEE 12 and IEEE 33 bus DS's having series capacitor in feeder section for voltage improvement and line loss minimization. Therefore, this paper serves to contributes to the two main novelties namely, (1) Development of efficient ANN model to directly determine the maximum voltage regulation and line losses and (2) improvement of voltage and line losses reduction through series capacitor installation in feeder section of the DS. The results show that the utilization of an ANN model enhances accuracy and speeds up predictions, while the installation of series capacitors in feeder sections improves voltage regulation and reduces line losses. [ABSTRACT FROM AUTHOR]

Due to the low thickness of cold-formed steel (CFS) sections, welding of traditional studs on them is not recommended; and there is a need to use shear connectors suitable for this type of sections. In this paper, the behavior of U-shaped shear connectors as connectors compatible with CFS composite beams has been investigated, to offer practical relationships for predicting the ultimate strength of this type of connectors. Accordingly, after the development of finite element (FE) models with the ability to predict the ultimate strength of U-shaped connectors, their performance against experimental results was validated. Then, an extensive parametric study, consisting of 216 numerical samples, was accomplished to provide a reliable database. As the main and most important of this study, two methods of artificial neural networks and stepwise regression were developed, and practical formulations were proposed to predict the ultimate strength of U-shaped shear connectors in CFS composite beams. Finally, in addition to evaluating the accuracy of the proposed formulas, a comparison was made between them and the relationships proposed by AISI, AS/NZS and EC3 codes for CFS screw connections. The relationships presented in this paper can be used by practical engineers in the design process of CFS composite beams. [ABSTRACT FROM AUTHOR]

In this paper, the spoke structure of a non-pneumatic tire is optimized. The finite element model of the spoke structure is created and structural dynamic analysis is made using ABAQUS. The optimization goal is to simultaneously reduce three characteristics of the spoke structure, the mass, vertical displacement and acceleration. Simulations are performed according to the center composite design table, and the objective function is estimated using response surface analysis (RSA), random forest regression (RFR), gradient boosting regression (GBR) and artificial neural network (ANN). The genetic algorithm is used for minimization, and the optimization results of each objective function are analyzed through verification simulation. As a result of the optimization, the error between the predicted value and the actual value is 18.6% for RSA 3.1% for RFR, 1.7% for GBR, and 15.0% for the ANN. The ANN proposes the optimum design variables which derive output values smaller than the current minimum value because the ANN properly represents the nonlinear characteristics of the spoke model generated in this study. Highlights Simulation based optimization of the spoke structure of a non-pneumatic tire Various regression models are used and their accuracy is compared A two-step genetic algorithm is used for optimization [ABSTRACT FROM AUTHOR]

The contribution of a plant is most significant for both human life and nature. The plant diseases affect whole plants, including leaves, stems, fruit, root, and flower. However, conventional approaches enclosed human involvement in classifying and identifying diseases. This process takes more time to complete a task. The main intention of this paper is to effectively develop a deep structured architecture for the detection of plant leaf diseases by introducing intelligent techniques, which have several processing steps. As a major contribution, Adaptive Fuzzy C-Means Clustering (FCM) is adopted for the abnormality segmentation. Moreover, the Improved Deep Neural Network (I-DNN) has achieved the greatest strength in enhancing the performance of plant leaf disease recognition. Here, Newly Updated Moth-Flame Optimization (NU-MFO) is utilised for enhancing the classification efficiency through a valuable objective function. The recommended method achieves higher accuracy rate in the recognition of diseases when compared to the baseline approaches. The precision of the NU-MFO-I-DNN at 85% learning rate is 0.01%, 0.26%, 0.07%, and 0.28% higher than MFO-I-DNN, GWO-I-DNN, SSO-I-DNN, and PSO-I-DNN, respectively. [ABSTRACT FROM AUTHOR]

Support vector machine (SVM) is a supervised machine-learning method which can be used for both classification and regression models. In this paper, we introduce a new model of SVM which any of training samples containing inputs and outputs are considered the random variables with known probability functions. The SVM is first converted into equivalent quadratic programming (QP) formulations in linear and nonlinear cases. An artificial neural network for SVM learning is then proposed. The presented neural network framework guarantees to obtain the optimal solution of the SVM problem. The existence and convergence of the trajectories of the network are studied. The Lyapunov stability for the considered neural network is also shown. The efficiency of the proposed method is shown by four illustrative examples. [ABSTRACT FROM AUTHOR]

As the world's transport infrastructure ages, the importance of bridge condition monitoring is becoming increasingly acknowledged. Large-scale deployment of existing inspection and monitoring techniques is infeasible due to cost and logistical challenges. The concept of using sensors located within vehicles for low cost 'drive-by' monitoring has become the focus of much attention in recent years. This paper presents a new data-driven approach for drive-by bridge monitoring. Machine learning techniques are leveraged to allow the influence of vehicle speed to be considered and the Operating Deflection Shape Ratio (ODSR) is presented as an alternative damage-sensitive feature to the commonly used frequency spectrum. Extensive laboratory experiments demonstrate that the method is capable of detecting midspan cracking and seized bearings. A statistical classification approach is adopted to classify damage indicators as either 'damaged' or 'healthy'. Classification accuracy is seen to vary between 65-96% and is similar whether using the frequency spectrum or ODSR. Based on the results of the laboratory testing, it is expected that this approach could be implemented on a large scale to act as an early warning tool for infrastructure owners to identify bridges presenting signs of distress or deterioration. [ABSTRACT FROM AUTHOR]

The variable DC link direct torque control (DTC) for induction motors was proposed in this paper utilizing an artificial neural network (ANN). Variable DC-link voltage is utilized as the inverter's controlling input to improve the induction motor's performance. By injecting the dynamically variable dc-link voltage, inverter switching losses are decreased and inverter efficiency is increased. Two significant limitations are the torque ripple in DTC and the speed regulation of induction motors at low speeds. The driveline of an electric vehicle is modeled, and the suggested control is put into practice to enhance low-speed speed regulation, high dynamic performance, and minimal torque ripple. With variable DC-link voltage based on ANN, an improvement in torque and speed is made possible. Additionally, the suggested strategy minimizes the current ripples. To verify the improved efficacy of the electric driveline under various operating scenarios, a proposed control of the electric driveline is implemented using MATLAB SIMULINK, and the results are compared with the conventional scheme. The recommended speeds for the three speed ranges are as follows: 300 rpm for low speed, 900 rpm for medium speed, and 1275 rpm for high speed. The torque ripples decreased from 0.39 to 0.24 in the low-speed region, 0.38 to 0.24 in the medium-speed region, and 0.36 to 0.24 in the high-speed region while the motor was operated at a constant load torque of 2 N-m. The torque ripples decreased from 0.4 to 0.274 in the low speed region, 0.4 to 0.274 in the medium speed zone, and 0.2 to 0.274 in the medium speed region when the motor operated at various speed regions with a constant load. The main effect of running the motor at different load torques, such as 1.5 N-m, 2.5 N-m, and 2.0 N-m, is shown in Table 9 and numerical data of torque ripples is presented in Table 9. [ABSTRACT FROM AUTHOR]

Automatic building detection from remote sensing images holds significant applications in various domains, including cartography, land-use change detection, urban planning, and 3D intelligent city construction. Driven by the innovation of deep learning technology, convolutional neural networks (CNNs) have emerged as a powerful framework for automatic interpretation, exhibiting hierarchical feature generation and robust representation for building extraction. However, the inherent computational limitations of convolutional operators hinder the acquisition of an effective global receptive field. Recent advancements in deep learning have witnessed the adoption of the multi-head self-attention (MHSA) mechanism by Transformer, presenting the superiority of global context construction. Nonetheless, this network structure encounters difficulties in effectively modelling two-dimensional spatial structure features with scale variation in semantic segmentation and often has huge parameters with high algorithm complexity. To address the above problems, this paper proposed a hybrid deep neural network synergistically harnessing the superiority of CNN and Transformer to extract buildings from remote sensing images. Meanwhile, an improved MHSA mechanism is developed to facilitate the construction of multiscale global representations, concurrently reducing computational complexity. Furthermore, the cross-level MHSA modules the semantic correlation between the deep and shallow-level features to refine spatial fine-grained information. The proposed method was comprehensively evaluated on two building datasets via quantitative analysis and visualization. The experimental results confirmed that the developed network and modules outperform other state-of-the-art methods and can effectively improve the accuracy (93.4% F1-score on the WHU dataset, 89.38% F1-score on the CAMB dataset) with high efficiency for building extraction. [ABSTRACT FROM AUTHOR]

Rehabilitation robots with intent recognition are helping people with dysfunction to enjoy better lives. Many rehabilitation robots with intent recognition have been developed by academic institutions and commercial companies. However, there is no systematic summary about the application of intent recognition in the field of rehabilitation robots. Therefore, the purpose of this paper is to summarize the application of intent recognition in rehabilitation robots, analyze the current status of their research, and provide cutting-edge research directions for colleagues. Literature searches were conducted on Web of Science, IEEE Xplore, ScienceDirect, SpringerLink, and Medline. Search terms included "rehabilitation robot", "intent recognition", "exoskeleton", "prosthesis", "surface electromyography (sEMG)" and "electroencephalogram (EEG)". References listed in relevant literature were further screened according to inclusion and exclusion criteria. In this field, most studies have recognized movement intent by kinematic, sEMG, and EEG signals. However, in practical studies, the development of intent recognition in rehabilitation robots is limited by the hysteresis of kinematic signals and the weak anti-interference ability of sEMG and EEG signals. Intent recognition has achieved a lot in the field of rehabilitation robotics but the key factors limiting its development are still timeliness and accuracy. In the future, intent recognition strategy with multi-sensor information fusion may be a good solution. As a technology, intent recognition can become a part of rehabilitation, assist patients to complete daily life activities, and improve their quality of life. Rehabilitation training equipment for treatment usually adopts a relatively stable prediction method, which aims to stimulate the enthusiasm of users to participate in training. Functionally enhanced rehabilitation aids have high requirements for the timeliness of movement intent recognition, and its purpose is to assist patients to complete activities of daily life. [ABSTRACT FROM AUTHOR]

The IETE Journal of Research's first issue of Volume 70 covers a wide range of topics in communications, electromagnetics, opto-electronics, computers and computing, control engineering, electronic circuits, devices and components, instrumentation and measurement, medical electronics, and power electronics. The articles in this issue discuss various subjects, including improved network performance in wireless sensor networks, machine learning-based classification of cervical cancer, optimal energy reduction in 5G communication systems, and secure data transmission in the Internet of Things. The issue also includes papers on photonic sensors, detection of diabetic retinopathy, optimisation models for home health care scheduling and wind-integrated power systems, and efficient task scheduling in cloud computing environments. One research paper introduces a smartwatch-based machine learning model for monitoring epilepsy and detecting seizures, achieving a high accuracy of 99.40% in cross-validation. The document provides a summary of articles published in the journal, with authors who are experts in their fields and provide experimental findings and simulations to support their research. [Extracted from the article]

This paper aims to build a machine learning and a neural network model to detect the probability of money laundering in banks. The paper's data came from a simulation of actual transactions flagged for money laundering in Middle Eastern banks. The main findings highlight that criminal networks mainly use the integration stage to integrate money into the financial system. Fraudsters prefer to launder funds in the early hours, morning followed by the business day's afternoon time intervals. Additionally, the Naïve Bayes and Random Forest classifiers were identified as the two best-performing models to predict bank money laundering transactions. [ABSTRACT FROM AUTHOR]

This paper proposes a novel approach, BTC-SAGAN-CHA-MRI, for the classification of brain tumors using a SAGAN optimized with a Color Harmony Algorithm. Brain cancer, with its high fatality rate worldwide, especially in the case of brain tumors, necessitates more accurate and efficient classification methods. While existing deep learning approaches for brain tumor classification have been suggested, they often lack precision and require substantial computational time.The proposed method begins by gathering input brain MR images from the BRATS dataset, followed by a pre-processing step using a Mean Curvature Flow-based approach to eliminate noise. The pre-processed images then undergo the Improved Non-Sub sampled Shearlet Transform (INSST) for extracting radiomic features. These features are fed into the SAGAN, which is optimized with a Color Harmony Algorithm to categorize the brain images into different tumor types, including Gliomas, Meningioma, and Pituitary tumors. This innovative approach shows promise in enhancing the precision and efficiency of brain tumor classification, holding potential for improved diagnostic outcomes in the field of medical imaging. The accuracy acquired for the brain tumor identification from the proposed method is 99.29%. The proposed BTC-SAGAN-CHA-MRI technique achieves 18.29%, 14.09% and 7.34% higher accuracy and 67.92%,54.04%, and 59.08% less Computation Time when analyzed to the existing models, like Brain tumor diagnosis utilizing deep learning convolutional neural network with transfer learning approach (BTC-KNN-SVM-MRI); M3BTCNet: multi model brain tumor categorization under metaheuristic deep neural network features optimization (BTC-CNN-DEMFOA-MRI), and efficient method depending upon hierarchical deep learning neural network classifier for brain tumour categorization (BTC-Hie DNN-MRI) respectively. This paper proposes a novel approach, BTC-SAGAN-CHA-MRI, for the classification of brain tumors using a Self-Attention based Generative Adversarial Network (SAGAN) optimized with a Color Harmony Algorithm. Brain cancer, with its high fatality rate worldwide, especially in the case of brain tumors, necessitates more accurate and efficient classification methods. While existing deep learning approaches for brain tumor classification have been suggested, they often lack precision and require substantial computational time. The proposed method begins by gathering input brain MR images from the BRATS dataset, followed by a pre-processing step using a Mean Curvature Flow-based approach to eliminate noise. The pre-processed images then undergo the Improved Non-Sub sampled Shearlet Transform (INSST) for extracting radiomic features. These features are fed into the SAGAN, which is optimized with a Color Harmony Algorithm to categorize the brain images into different tumor types, including Gliomas, Meningioma, and Pituitary tumors. This innovative approach shows promise in enhancing the precision and efficiency of brain tumor classification, holding potential for improved diagnostic outcomes in the field of medical imaging. [ABSTRACT FROM AUTHOR]

In the paper, the exponential synchronisation for delayed Clifford-valued coupled switched neural networks via static event-triggering rule is studied. Firstly, the drive-response systems for delayed Clifford-valued coupled neural network models are established. So as to avoid the non-commutativity issue of Clifford number multiplication, the original n-dimensional Clifford-valued models are decomposed into $ 2 ^mn $ 2 m n -dimensional real-valued models. On this basis, the error dynamics system is constructed, and then some new sufficient conditions are presented of the exponential synchronisation for the considered neural network models by using Lyapunov–Krasovskii (L-K) functional approach and the technique of linear matrix inequality. Finally, the effectiveness of the results are verified by numerical simulations. [ABSTRACT FROM AUTHOR]

This paper explores the different insider employee-led cyber frauds (IECF) based on the recent large-scale fraud events of prominent Indian banking institutions. Examining the different types of fraud and appropriate control measures will protect the banking industry from fraudsters. In this study, we identify and classify Cyber Fraud (CF), map the severity of the fraud on a scale of priority, test the mitigation effectiveness, and propose optimal mitigation measures. The identification and classification of CF losses were based on a literature review and focus group discussions with risk and vigilance officers and cyber cell experts. The CF was analyzed using secondary data. We predicted and prioritized CF based on machine learning-derived Random Forest (RF). An efficient fraud mitigation model was developed based on an offender-victim-centric approach. Mitigation is advised both before and after fraud occurs. Through the findings of this research, banks and fraud investigators can prevent CF by detecting it quickly and controlling it on time. This study proposes a structured, sustainable CF mitigation plan that protects banks, employees, regulators, customers, and the economy, thus saving time, resources, and money. Further, these mitigation measures will improve the reputation of the Indian banking industry and ensure its survival. [ABSTRACT FROM AUTHOR]

In recent years, with the continuous advancement of remote sensing technology, remote sensing images have found widespread application in various fields. However, remote sensing images are often hindered by the presence of clouds, which can significantly reduce their usability. Removing clouds from remote sensing images has thus become an essential preprocessing step in remote sensing image analysis. While numerous models based on deep learning have produced impressive results in the domain of image denoising, there has been limited research on applying deep neural networks to tackle the issue of cloud removal in remote sensing images. This paper proposes a novel model, the Hybrid Attention Generative Adversarial Network (HyA-GAN), that blends the channel attention mechanism and the spatial attention mechanism and integrates it into a generative adversarial network. By incorporating both the channel attention mechanism and the spatial attention mechanism, HyA-GAN permits the network to prioritize regions that are vital for image processing. This feature leads to an improvement in the network's capacity to recover data and generate remote sensing images with superior cloud removal effects. When comparing HyA-GAN with other existing cloud removal models on the RICE dataset, it outperformed them in both peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM). The experiments demonstrate the high potential of HyA-GAN in addressing the challenge of removing clouds from remote sensing images. [ABSTRACT FROM AUTHOR]

This paper shows the outcomes of computer virus propagation (CVP) model, represented with susceptible, exposed, infected, quarantine and recovered computers (SEIRQ), classes based mathematical model using the stochastic procedures. The systematic study of the CVP based SEIRQ model represents that the equilibrium state of virus-free is stable globally with reproduction not more than one, while the viral symmetry is attractive globally. The numerical performances of the CVP based SEIRQ model are presented by using the stochastic computational framework based on the artificial neural networks (ANNs) together with the Levenberg-Marquardt backpropagation (LBMB) called as ANNs-LBMB. The learning procedures via ANNs-LBMB for solving the CVP based SEIRQ model are implemented to indorse the statics using the testing, authorization, and training. Thirteen numbers of neurons and the data selection for training 72%, testing 12% and validation 16% are selected to solve the model. For the numerical outcomes of the CVP based SEIRQ model using the ANNs-LBMB, a dataset is considered through the Adams approach. The accuracy and reliability performances of the scheme are presented by using the values of the absolute error (AE) along with the observations of state transitions (STs), regression, mean square error (MSE) and error histograms (EHs). [ABSTRACT FROM AUTHOR]

HyperGraph Neural Network (HGNN) has recently emerged as a promising approach for hyperspectral image classification (HSIC), reconciling state-of-the-art performance with powerful representation capabilities. However, existing HGNN-based methods have limited ability for hypergraph structure exploitation, leading to imperfect classification results. In this paper, we propose a framework called the residual enhanced hypergraph Neural Network (ResHGNN) to discover the potential structural features in hyperspectral image (HSI) data during deep neural networks. Specifically, ResHGNN first generates hyperedges from spatial-spectral features to construct a hypergraph representing fused spatial-spectral feature relationships in HSI. Then, the higher-order relationship among fused modal features is optimized by a residual enhanced hypergraph convolution learning process, to circumvent the HGNN-related over-smoothing issue. Experiments over three popular hyperspectral datasets show that the proposed classification method yields better performance than other models on the visual and numerical comparison. [ABSTRACT FROM AUTHOR]

Adaptive gradient algorithms such as ?>AdaGrad and its variants have gained popularity in the training of deep neural networks. While many works as for adaptive methods have focused on the static regret as a performance metric to achieve a good regret guarantee, the dynamic regret analyses of these methods remain unclear. As opposed to the static regret, dynamic regret is considered to be a stronger concept of performance measurement in the sense that it explicitly elucidates the non-stationarity of the environment. In this paper, we go through a variant of AdaGrad (referred to as M-AdaGrad) in a strong convex setting via the notion of dynamic regret, which measures the performance of an online learner against a reference (optimal) solution that may change over time. We demonstrate a regret bound in terms of the path-length of the minimizer sequence that essentially reflects the non-stationarity of environments. In addition, we enhance the dynamic regret bound by exploiting the multiple accesses of the gradient to the learner in each round. Empirical results indicate that M-AdaGrad works also well in practice. [ABSTRACT FROM AUTHOR]

In the world economy, agriculture is an essential part among individuals to earn money. But, the farmers face more obstacles because more diseases naturally affect the health of the plant. Hence, to overcome this limitation, automatic plant disease identification techniques are essential to monitor the growth as well as disease-affected plants and leaves. In most plants, symptoms related to plant disease can be identified by considering the leaves. Moreover, plant disease identification became more essential with deep learning architecture. Hence, it is important to enhance the solution for resource-constrained portable devices like smartphones, but it become a complicated issue as the deeply structured methods utilize extensive resources for the analysis. Hence, this paper aims to develop an automated plant disease detection framework with an advanced set of plant features. The plant images are taken from online sources. The acquired plant images undergo image enhancement using the contrast enhancement process. The enhanced images are fed in the feature retrieval phase 1, where the segmentation takes place using the Centre Optimized K-means clustering (CO-KMC) with the Modified Random Variable-based Black Widow Optimization (MRV-BWO). Later, the segmented images obtain the colour, shape, and texture features and they are considered as the first set of features. The second set of features is retrieved from the enhanced images using Multi-scale Dilated Attention CNN (MSDA-CNN). These two features are fused by the weighted feature fusion process using the developed MRV-BWO. Then, the plant diseases are detected using the Hybridized Deep Neural Network with Recurrent Neural Network (HDNN-RNN), which comprises RNN and DNN models. The parameter optimization takes place in the hybrid HDNN-RNN for improving the detection efficiency using MRV-BWO. From the verification of the findings, the recommended model obtains a 96.47 precision and accuracy rate. Therefore, the simulation results of the offered model reveal that it achieves enriched efficacy when comparing other baseline approaches. [ABSTRACT FROM AUTHOR]

An Artificial Neural Network (ANN) based Substrate Integrated Waveguide Band Pass Filter (SIW BPF) is proposed in this paper. A Feed Forward Back Propagation Neural Network (FF-BP NN) is utilized to optimize the filter dimensions. The Gradient Descent with Momentum and Adaptive Learning Rate algorithm is used to train the network at a learning rate of 0.01. The high pass characteristics of the SIW is converted into band pass by incorporating U slots on its top plane. Defected Ground Structure (DGS) is utilized in the bottom plane to improve the impedance matching. To validate, the prototype is fabricated using RT/Duroid 5880 and tested. The proposed filter has a center frequency at 14.68 GHz with a wide pass band from 12.92 to 16.43 GHz with a 3-dB Fractional Bandwidth (FBW) of 24%, return loss more than 20 dB and insertion loss of about 1.9 dB within the pass band. The filter has a small dimension of about 0.63 $ \lambda _g^2 $ λ g 2 , where λg is the guided wavelength at the center frequency. This filter offers wide passband, smaller size, low insertion loss, good return loss and it is useful in Ku-band satellite communication applications. [ABSTRACT FROM AUTHOR]

In this paper, a methodical strategy is put forth for the development of models for chemical processes by using an Artificial Neural Network (ANN). To show the effectiveness of the proposed methodology, three industrial chemical processes were considered. The intended work is to introduce the guideline for designing any ANN model by identifying the optimum number of neurons and hidden layers and coming up with the most suitable architecture for the neural network. The effect of viable parameters on predicting the specified parameter was evaluated using an ANN model. A systematic procedure adopted, ANN networks were designed to predict the boiler efficiency, frost thermal conductivity, and gas holdup under different operating conditions. At last, a comparative study on the experimental output and ANN approximated output for the three chemical processes was done. For developing the ANN model for boiler and frost conductivity, it was found that employing two layers provided a superior fit. The R² values for these fits were found to be 0.98877 and 0.9891, respectively. On the other hand, when configuring the column flotation model, a single layer with nine nodes was identified as the optimal ANN structure, yielding an excellent R² fit value of 0.99337. [ABSTRACT FROM AUTHOR]

Emerging technology plays a crucial role in promoting the development of the industrial economy, and identifying potential emerging technology is significant for innovation strategy. This study aimed to propose an identifying framework that can match the different stages of emerging technology, while most prior studies adopted a static method. Taking high-speed railway track (HSRT) technology as a case study, this paper presents an empirical application based on the growth model of the technology lifecycle, artificial neural network, and ordinal regression. The result indicates that the emerging technology branches of the HSRT technology include B66, C04, B28, and C08 represented by IPC categories, among which B66 is the most prominent. Besides, this study concluded that explosiveness, persistence, breakthrough, and competitive advantage in technology development are the typical characteristics for identifying emerging technology. The contribution of this study is enlightening a dynamic view of technology identification, which promotes the understanding of emerging technology by applying and integrating quantitative methods. [ABSTRACT FROM AUTHOR]

The shortage of obstetricians and gynecologists is increasing in developed countries; therefore, there is a need to improve prenatal care procedures. To automate fetal ultrasound (US) imaging, this paper presents a deep neural network (DNN) model that generates US scan motions for a robot. Additionally, the robot can adapt to the abdominal surface even if the abdominal shape is not precisely known. The latent space of the DNN model is designed to represent the abdominal-shape information. The DNN model can predict the proper trajectory by mapping the height and width of the abdomen to the latent space. Moreover, the robot can detect any deviations from the correct trajectory and return to the right position. For validation, we performed a US scan using the proposed model on tissue-mimicked phantoms that were not used for training. Subsequently, we evaluated the number of dots that were wiped off by the robot from the phantom surface. Overall, the number of dots removed accounted for 91.7% of the total dots. The results demonstrated the feasibility of using the DNN model for motion generation. Hence, the proposed system has the potential to automate fetal US scans according to the individual differences in the abdominal shape. [ABSTRACT FROM AUTHOR]

In this paper, we introduce novel instructional approaches to engage students in using modelling with data to motivate and teach differential equations. Specifically, we introduce a pedagogical framework that will execute instructional modules to teach different solution techniques for differential equations through repositories and notebook environments during real-time instruction. Each of these teaching modules employs a literate programming approach that uses the notebook environment to explain the concepts in a natural language, such as English, interspersed with snippets of macros and traditional source code on a web browser. The pedagogical approach employed is reproducible and leads to openaccess material for students to motivate and teach differential equations efficiently. We will share examples of this framework applied to teaching advanced concepts such as machine learning and neural network approaches for solving ordinary and partial differential equations as well as estimating parameters in these equations for given datasets. More details of the work can be accessed from . [ABSTRACT FROM AUTHOR]

This paper presents a novel neuro-stochastic adaptive processing to investigate the dynamic behavior of the nonlinear SIS epidemic delayed model with the impact of double disease (SIS-EDDM) using the knack of prediction and modeling of artificial neural networks (ANNs) optimized through Levenberg-Marquardt technique (LMT), i.e. ANNs-LMT. The model captures the dynamic progression of individuals in the population, differentiating between those susceptible to infection and affected by two unique viruses. The inclusion of time delays in the differential equations introduces a critical temporal aspect to the model, enhancing its precision in portraying the transmutation process. The reference dataset for ANNs-LMT is produced using the explicit Runge-Kutta method, with variations in the transmission coefficients between susceptible and infective populations, the death rate of infective population caused by diseases, the cure rate of treatment for infected population, vaccination proportional coefficient for the susceptible population, white noise of the environment, and time delay. The designed computing framework of ANNs-LMT is used to determine the numerical solutions of the variants of SIS-EDDM by incorporating the training, testing, and validation samples based adaptive learning processing. The neuro-stochastic adaptive processing of ANNs-LMT is validated by minimal absolute and mean squared errors, coupled with the attainment of nearly optimal regression measures, demonstrating its accuracy and effectiveness. [ABSTRACT FROM AUTHOR]

AbstractConsidering the differences between individuals, in this paper, an uncertainty analysis model for predicting rupture risk of atherosclerotic arteries is established based on a back-propagation artificial neural network. The influence of isotropy and anisotropy on the rupture risk of atherosclerotic arteries is analyzed, and the results demonstrate the effectiveness of the artificial neural network in predicting the rupture risk. Moreover, the rupture risk of atherosclerotic arteries at different inflation sizes are simulated. This study contributes to a better understanding of the underlying mechanisms of atherosclerotic arteries rupture and promotes the advancement of artificial neural networks in atherosclerosis research. [ABSTRACT FROM AUTHOR]

The optimal experimental design (OED) provides informative experimental resources and reduces the inherent uncertainty of the experiment. The OED is a framework to maximize performed experiments by controlling design variables. This paper proposes the OED framework combined with deep neural network (DNN) surrogate model to find the optimal design over large and complex design space. The OED has the optimization process to maximize the conditional mutual information (CMI) between hidden properties and composite structural performances. Approximate coordinate exchange (ACE) algorithm was applied to find the optimal design over a high and complicated design space. For fast optimization, surrogate DNN model was used instead of finite element analysis. Two examples were executed for the demonstration of the OED frameworks. From the results of each demonstration, OED provided the results that are consistent with heuristic knowledge. [ABSTRACT FROM AUTHOR]

Children without obvious disabilities (hearing loss/low intellectual capacity) may have language skill development issues due to specific language impairment (SLI), a communication disorder. The SLI has a significant impact on a child's speaking, listening, reading, and writing abilities. SLI is typically known as development language disorder, developmental dysphasia, or language delay. Recently, machine learning as well as deep learning techniques have been quite effective in predicting the early stage of SLI, analyzing the disorder severity, and predicting the treatment efficiency. Existing approaches primarily exploited auditory indicators to diagnose communication disorders, frequently leaving out hidden information acquired in the temporal domain. To overcome this drawback, an optimized Bidirectional Long Short Term Memory (BiLSTM) architecture is presented in this paper to handle the speech dynamics. The Improved Hybrid Aquila Optimizer and Flow Directional algorithm known as IHAOFDA is integrated with the BiLSTM architecture to optimize the hyperparameters of the BiLSTM structure. When assessed using the information from the SLI children in the Laboratory of Artificial Neural Network Applications (LANNA) dataset, the proposed model performs better. The IHAOFDA-optimized BiLSTM architecture improves accuracy in classifying different severity levels such as mild, moderate, and severe. [ABSTRACT FROM AUTHOR]

Data security concerns safeguarding the data from unauthorized users. Numerous research works have been conducted using Reversible Data Hiding (RDH) technique, but not been found to be fooproof. In this paper, a novel reversible data hiding method, based on an Artificial Neural Network, called Histogram Transpose and Naor Pseduorandom Arnold (HT-NPA) data security system for handling health care reports and securely transferring patient information, is proposed to evaluate the embedding capacity, improve the visual quality of the recovered image and ensure security via duplex scramble. This entire process is performed by means of an Artificial Neural Network (i.e. multilayer perceptron). The experimental results reveal that the HT-NPA performs better with 29%, 16%, 19%, and 9% improvement in embedding rate, PSNR, SSIM, entropy, and NPCR, and 26% reduction of bit error rate, respectively for retrieved medical images compared to existing works. [ABSTRACT FROM AUTHOR]

Multimedia security is important as privacy and protection has to be ensured when images from military, medical and other confidential services are sent through the unprotected channel. In this paper, an attempt to develop reconfigurable hardware for an encryption scheme using FPGA has been carried out and tested successfully for its features. In this proposed encryption scheme, chaos and a novel artificial neural network-based diffusion have been used along with zig-zag permutation for pixel level and novel enhanced Fisher-Yates permutation for bit level. The ANN is composed of additive and multiplicative convolution and the 2D cellular automata as an activation function for diffusion. A novel key generation algorithm is adopted to produce the key values for generating the chaos sequence. Every image gets a new key, hence differential attack possibility is negligible. The encryption algorithm is designed in MATLAB and coded in Verilog HDL to develop it as reconfigurable hardware. The hamming distance is analyzed to know the difference between the key sequence generated. The average hamming distance is 0.5111 and the highest value is 0.8796 to show that the randomness of the sequence. Similarly, equidistribution, autocorrelation and periodicity analysis are performed. The NIST SP 800–22 randomness test was also performed on keys and encrypted images to analyze its randomness. The results obtained from the encryption process are tested for their efficiency related to statistical and differential attacks. It gives better results when compared with a few encryption algorithms in the literature. [ABSTRACT FROM AUTHOR]

Natural streamflow data is required in many hydrological applications. However, many basins are located in data-scarce regions or are impacted by human construction and activities. In this paper, we explore three machine learning algorithms, namely artificial neural networks, random forest and light gradient boosting machine, to simultaneously estimate all the parameters of the coupled modèle du Génie Rural à 4 paramètres Journaliers (GR4J) and snow accounting routine called CemaNeige model. A database of 675 basins in the USA and Quebec is used to train and test ensembles. After using the estimated parameters in GR4J, the resulting naturalized streamflow series are compared with those obtained by the established drainage area ratio and spatial proximity transfer methods in 11 test basins. The results indicate that the machine learning algorithms outperform the drainage area ratio and spatial proximity transfer methods. Among machine learning algorithms, random forests obtain lower (better) continuous ranked probability scores than the other methods for 10 out of 11 test basins. [ABSTRACT FROM AUTHOR]

Carbon emission reduction is an important part of regional low-carbon economic development. In this paper, gray correlation analysis, neural network model, Gaussian multi-mode fitting and other methods were used to analyze the relationship between total carbon emissions and regional economic development, industrial structure, and energy consumption in Henan Province. On this basis, the future development of carbon emissions is predicted. The calculation results showed that the correlation between the three industries and carbon emissions in Henan Province is more than .7, among which the secondary industry has the highest correlation (.77). In the secondary industry, the correlation coefficient between coal and carbon emissions is the highest .87, while the correlation coefficient between other energy sources is about .5. In the neural network prediction model, the correlation coefficient between the prediction curve and the actual total carbon emission curve is .989, and the prediction results have a good degree of fit. The carbon emission prediction curve was divided into two parts: a linear decline stage from 2018 to 2024, and a rapid decline stage after 2024.The results showed that more efforts should be made in industrial structure, energy consumption structure and environmental protection to achieve low-carbon development in Henan province. [ABSTRACT FROM AUTHOR]

Recent earthquakes clarified that existing a soft/weak-story in a building could completely invert the failure mechanisms of the structure. Several studies were implemented to evaluate the potential risk subjected to the buildings under the earthquake hazard. However, these researchers discarded the effect of soft/weak-story on the demand parameters of their models. This paper presents a rapid demand estimation framework for generic buildings considering the effect of soft/weak-story. In this regard, the simplified model developed according to the HAZUS approach is rectified to apply the effect of soft/weak-story on the structural behavior of the generic buildings. Artificial neural networks are implemented to remove the required time-consuming nonlinear response history analyses from the post-earthquake actions. This research utilized a suite of 111 earthquake records, originally developed by the SAC project. These motions are uniformly scaled from 0:1g to 1:5g to obtain a generalized dataset with different intensities. Bayesian optimization algorithm is conducted to achieve a prediction model with optimized hyperparameters. Results clarify that the proposed method is reliable and computationally cost-effective in predicting the demand parameters of generic buildings. This framework can be used in the body of a risk assessment platform to facilitate the emergency response to the earthquake hazard. [ABSTRACT FROM AUTHOR]

Driving behavior monitoring by smartphone sensors is one of the most investigated approaches to ameliorate road safety. Various methods are adopted in the literature; however, to the best of our knowledge, their robustness to the prediction of new unseen data from different drivers and road conditions is not explored. In this paper, a two-phase Machine Learning (ML) method with taking advantage of high-pass, low-pass, and wavelet filters is developed to detect driving brakes and turns. In the first phase, accelerometer and gyroscope filtered time series are fed into Random Forest and Artificial Neural Network classifiers, and the suspicious intervals are extracted by a high recall. Following that, in the next phase, statistical features calculated based on the obtained intervals are used to determine the false and true positive events. To compare the predicted and real labels of the recorded events and calculate the accuracy, a method that covers the limitations of previous sliding windows is also employed. Real-world experimental result shows that the proposed method can predict new unseen datasets with average F1-scores of 71% in brake detection and 82% in turn detection which is comparable with previous works. Moreover, by sensitivity analysis of our proposed model, it is proven that implementing high-pass and low-pass filters can affect the accuracy for turn detection up to 30%. [ABSTRACT FROM AUTHOR]