Input Vector Research Articles

The heart sound classification of congenital heart disease by using median EEMD-Hurst and threshold denoising method.

Heart sound signals are vital for the machine-assisted detection of congenital heart disease. However, the performance of diagnostic results is limited by noise during heart sound acquisition. A limitation of existing noise reduction schemes is that the pathological components of the signal are weak, which have the potential to be filtered out with the noise. In this research, a novel approach for classifying heart sounds based on median ensemble empirical mode decomposition (MEEMD), Hurst analysis, improved threshold denoising, and neural networks are presented. In decomposing the heart sound signal into several intrinsic mode functions (IMFs), mode mixing and mode splitting can be effectively suppressed by MEEMD. Hurst analysis is adopted for identifying the noisy content of IMFs. Then, the noise-dominated IMFs are denoised by an improved threshold function. Finally, the noise reduction signal is generated by reconstructing the processed components and the other components. A database of 5000 heart sounds from congenital heart disease and normal volunteers was constructed. The Mel spectral coefficients of the denoised signals were used as input vectors to the convolutional neural network for classification to verify the effectiveness of the preprocessing algorithm. An accuracy of 93.8%, a specificity of 93.1%, and a sensitivity of 94.6% were achieved for classifying the normal cases from abnormal one.

A variational approach to quantum gated recurrent units

Quantum Recurrent Neural Networks are receiving an increased attention thanks to their enhanced generalization capabilities in time series analysis. However, their performances were bottlenecked by long training times and unscalable architectures. In this paper, we propose a novel Quantum Recurrent Neural Network model based on Quantum Gated Recurrent Units. It uses a learnable Variational Quantum Layer to process temporal data, interspersed with two classical layers to properly match the dimensionality of the input and output vectors. Such an architecture has fewer quantum parameters than existing Quantum Long Short-Term Memory models. Both the quantum networks were evaluated on periodic and real-world time series datasets, together with the classical counterparts. The quantum models exhibited superior performances compared to the classical ones in all the test cases. The Quantum Gated Recurrent Units outperformed the Quantum Long Short-Term Memory network despite having a simpler internal configuration. Moreover, the Quantum Gated Recurrent Units network demonstrated to be about 25% faster during the training and inference procedure over the Quantum Long Short-Term Memory. This improvement in speed comes with one less quantum circuit to be executed, suggesting that our model may offer a more efficient alternative for implementing Quantum Recurrent Neural Networks on both simulated and real quantum hardware.

ARA-RCIV: Identifying Reliability-Critical Input Vectors of Logic Circuits Based on the Association Rules Analysis Approach

ARA-RCIV: Identifying Reliability-Critical Input Vectors of Logic Circuits Based on the Association Rules Analysis Approach

Application of Improved Class of Weighted Averaging Operators in Intuitionistic Fuzzy Ann Guided MAGDM E-Commerce Problems

Objectives: To propose a novel and improvised Artificial Neural Network (ANN) technique to solve Multiple Attribute Group Decision Making (MAGDM) problems and an improved class of Aggregation operators for combining Intuitionistic Fuzzy Set (IFS) matrices for the ANN algorithm. Methods: A novel class of improved aggregation operators namely the Improved Intuitionistic Fuzzy Weighted Arithmetic Averaging (IM-IFWAA) operator and the Improved Intuitionistic Fuzzy Ordered Weighted Averaging (IM-IFOWA) operator are proposed in this work. The proposed improved class of aggregation operators will aggregate the IFS matrix data sets appearing in the form of matrices and then the revised input vectors which is then fed into the ANN algorithm following Delta, Perceptron, and Hebb Learning Rule for the next phase. Findings: Aggregating the Intuitionistic Fuzzy set information or data in today’s digital world is a tedious task in the field of MAGDM problem-solving. In this work, two new classes of operators for aggregating the data sets are proposed namely the IM-IFWAA operator and the IM-IFOWA operator which will improve the performance of the ANN. Necessary theorems for the proposed operators are proved to provide consistency of the same. The input created using the aforementioned operators is then fed into the novel ANN algorithm for further computations. Varieties of learning rules are then engaged for ranking of the best alternative for the decision problem. The developed theory is supported by a numerical example which is computed using all the proposed techniques. Novelty: Most of the research done on Intuitionistic Fuzzy Artificial Neural Network models are based on learning rules or using some other calculations. The proposed methods of using novel and improvised aggregation operators for ANN are used to find the inputs for ANN where varieties of learning rules for ANN are employed for effective decision analysis. Keywords: ANN, Learning Rules, MAGDM, Intuitionistic Fuzzy Sets, Weighted Aggregation Operator

Cylinder pressure reconstruction to compensate for crankshaft flexibility based on flexible crank model

Amid escalating economic demands and emissions regulations for internal combustion engines, an array of control strategies grounded in in-cylinder state feedback has been introduced and implemented. The exploration of cylinder state feedback has captured the attention of researchers, and one area of intense focus involves reconstructing cylinder pressure based on engine state information due to its cost-effectiveness. In this paper, we introduce a method for compensating crankshaft flexibility. This method encompasses a crankshaft dynamic model, a 17-dimensional input vector, the PCA (Principal Component Analysis) algorithm, and a signal-layer perceptron. This approach efficiently addresses the impact of flexible crankshaft deformation and ensures high accuracy. The results demonstrate that all R2 values for cylinder pressure signals reconstructed via the proposed method exceed 0.9997, with RMSE predominantly ranging between 0.4 and 0.6 bar. Furthermore, the error in Pmax calculation based on cylinder pressure signals is under 0.04 bar, LPP (Location of Peak Pressure) error is below 2°CA, CA50 error remains under 0.5°CA, and IMEPH error is within 0.3 bar. In summation, the presented method facilitates highly precise in-cylinder pressure reconstruction, satisfies the prerequisites for in-cylinder combustion state feedback.

BP Neural Network-Enhanced System for Employment and Mental Health Support for College Students

This paper employs BP Neural Network (BPNN) theory to evaluate innovation and entrepreneurship education in universities. It utilizes students' evaluation indexes as input vectors and determines the number of hidden layer neurons. Experimental results serve as output vectors. The BPNN method proves reasonable and feasible for vocational education course evaluation, exhibiting a 14.96% higher accuracy than traditional genetic algorithms. The paper discusses the model, configuration, characteristics, training process, algorithm enhancement, and limitations of neural networks, followed by an introduction to genetic algorithms. Through analysis of principles, basic operations, and common operators, it establishes a theoretical foundation for subsequent discussions.

Estimation of wind dynamic load linear transfer matrix using proper orthogonal decomposition method and genetic algorithm

ABSTRACT Due to the advantages of Laplace domain in both time and frequency domains, the dynamic analysis and control tools in engineering software like MATLAB and Python have been designed based on it. Dynamic analysis of structures requires determination of the overall transfer matrix, which is obtained by multiplying the structure's transfer matrix (TM) with the load TM. With the input vector of unit intensity white-noise processes and the overall TM, the structural responses can be obtained. Furthermore, having the load TM is crucial for implementation of active control systems. In this article, the TM of along-wind loads was estimated for a tall building using the proper orthogonal decomposition (POD) method and the genetic algorithm (GA). To evaluate the effectiveness of the proposed approach, an example of a tall building was provided. The wind load cross-power spectral matrix (XPSD) was decomposed using POD technique, followed by the truncation of higher loading modes. Subsequently, the loading TM was derived by estimating the target non-linear functions with linear transfer functions through GA technique. Then, the responses of the structure were computed using the loading TM. The results demonstrated the efficacy of the proposed method in acquiring the loading TM and predicting wind-induced responses.

Multi-task neural networks by learned contextual inputs

This paper explores learned-context neural networks. It is a multi-task learning architecture based on a fully shared neural network and an augmented input vector containing trainable task parameters. The architecture is interesting due to its powerful task adaption mechanism, which facilitates a low-dimensional task parameter space. Theoretically, we show that a scalar task parameter is sufficient for universal approximation of all tasks, which is not necessarily the case for more common architectures. Empirically it is shown that, for homogeneous tasks, the dimension of the task parameter may vary with the complexity of the tasks, but a small task parameter space is generally viable. The task parameter space is found to be well-behaved, which simplifies workflows related to updating models as new data arrives, and learning new tasks with the shared parameters are frozen. Additionally, the architecture displays robustness towards datasets where tasks have few data points. The architecture’s performance is compared to similar neural network architectures on ten datasets, with competitive results.

A combined technique for power transformer fault diagnosis based on k‐means clustering and support vector machine

AbstractThis contribution presents a two‐step hybrid diagnostic approach, combining k‐means clustering for subset formation, followed by subset analysis conducted by human experts. As the feature input vector has a significant influence on the performance of unsupervised machine learning algorithms, seven feature input vectors derived from traditional methods, including Duval pentagon method, Rogers ratio method, three ratios technique, Denkyoken method, ensemble gas characteristics method, Duval triangle method, and Gouda triangle method were explored for the subset formation stage. The seven proposed individual methods, corresponding to the seven feature input vectors, were implemented using a dataset of 595 DGA samples and tested on an additional 254 DGA samples. Furthermore, a combined technique based on a support vector machine was introduced, utilising the diagnostic results of the individual methods as input features. From training and testing, with diagnostic outcomes of 91.09% and 90.94%, the combined technique demonstrated the highest overall diagnostic accuracies. Using the IEC TC10 database, the diagnosis accuracies of the proposed diagnostic methods were compared to existing methods of literature. From the results obtained, the combined technique outperformed the proposed individual methods and existing methods used for comparison.

An aging simulation method based on the change of input vector inside the critical path

Abstract With the large-scale expansion and process shrinking of modern integrated circuits, aging has become one of the main factors threatening circuit reliability. To evaluate the impact of aging on circuit life, it is important to investigate aging simulation methods. Aiming at the problem of slow speed and insufficient accuracy of large-scale digital circuit aging simulation methods, a circuit aging simulation method based on the change of input vector inside the critical path (CICP) is proposed in this paper. First, the critical path (CP) with the tightest timing is extracted by static timing analysis (STA), and SPICE simulation is carried out to accurately predict the aging of the CP of the circuit. Second, the aging simulation is carried out considering the change of the internal input vector of the CP. The simulation results show that after changing the internal input signal, the aging path delay increases up to 3.5%.

Research on laser communication ranging Integration and VLC nonlinear compensation technology

Abstract Visible light communication (VLC) is a new spectrum communication technology that provides a new direction to solve spectrum resource problems. The nonlinearity problem in VLC will lead to a significant reduction in the performance of the communication system. To solve this problem, this paper studies the integration of laser communication ranging and VLC nonlinear compensation technology based on analyzing the principles of ranging methods and factors affecting ranging performance. Aiming at the problem that the complexity of the Random Fourier Features Kernel adaptive filter (RFF-KAF) method will increase significantly as the dimension of the mapping space increases, we introduce some second-order Volterra series square terms into the input vector of RFF-KAF and propose an improved prediction method. Experimental simulation results show that the method proposed in this article can greatly improve the performance of the RFF-KAF method while maintaining the same mapping space dimension. Compared with obtaining similar performance by increasing the mapping space dimension, the cost of this method is greatly reduced.

A Partial Information Decomposition for Multivariate Gaussian Systems Based on Information Geometry.

There is much interest in the topic of partial information decomposition, both in developing new algorithms and in developing applications. An algorithm, based on standard results from information geometry, was recently proposed by Niu and Quinn (2019). They considered the case of three scalar random variables from an exponential family, including both discrete distributions and a trivariate Gaussian distribution. The purpose of this article is to extend their work to the general case of multivariate Gaussian systems having vector inputs and a vector output. By making use of standard results from information geometry, explicit expressions are derived for the components of the partial information decomposition for this system. These expressions depend on a real-valued parameter which is determined by performing a simple constrained convex optimisation. Furthermore, it is proved that the theoretical properties of non-negativity, self-redundancy, symmetry and monotonicity, which were proposed by Williams and Beer (2010), are valid for the decomposition Iig derived herein. Application of these results to real and simulated data show that the Iig algorithm does produce the results expected when clear expectations are available, although in some scenarios, it can overestimate the level of the synergy and shared information components of the decomposition, and correspondingly underestimate the levels of unique information. Comparisons of the Iig and Idep (Kay and Ince, 2018) methods show that they can both produce very similar results, but interesting differences are provided. The same may be said about comparisons between the Iig and Immi (Barrett, 2015) methods.

Intuitionistic Fuzzy Gram-Schmidt Orthogonalized Artificial Neural Network for Solving MAGDM Problems

Objectives: To propose a suitable decision-making model based on Intuitionistic Fuzzy sets (IFSs) and Gram-Schmidt orthogonalization process for Artificial Neural Network (ANN). Methods: The IFS data sets appearing in the form of matrices are aggregated using the available aggregation operators in the literature and then the collective aggregated information is processed through Gram-Schmidt orthogonalization for the revised input vectors which is then fed into the ANN algorithm following Delta Learning Rule for the next phase. The weight updation is performed through the ANN and the output is improvised. Findings: The proposed Gram-Scmidt Orthogonalization process is utilized in Intuitionistic Fuzzy Artificial Neural Network model. The Delta learning rule is utilized in the process of the Neural Network, where the Intuitionistic Fuzzy nature of the input data is transformed into a fuzzy data and then the ranking of the alternatives is done based on the weights updation through the learning phase of the ANN. Once the vector is trained out of the learning phase, it is then processed through the activation function for the final selection of the best alternative required of the Multiple Attribute Group Decision Making (MAGDM) problem posed in this work. To demonstrate the usefulness and applicability of this new method with the Gram-Schmidt process, the numerical example also adds more insight to the proposed methodology of ANN with the application of some Linear Space techniques. Novelty: Most of the research done on Intuitionistic Fuzzy Artificial Neural Network model are based on learning rules or using some other calculations. The proposed Gram-Schmidt Orthogonalization process is used to find the orthogonal basis that are used as input training vectors in the Delta learning rule for ANN. Keywords: MAGDM, ANN, Aggregation operators, Learning Rules, Intuitionistic Fuzzy sets, Gram-Scmidt Orthogonalization

Predictive Modeling of Canadian Carbonatite-Hosted REE +/− Nb Deposits

Carbonatites are the primary geological sources for rare earth elements (REEs) and niobium (Nb). This study applies machine learning techniques to generate national-scale prospectivity models and support mineral exploration targeting of Canadian carbonatite-hosted REE +/− Nb deposits. Extreme target feature label imbalance, diverse geological settings hosting these deposits throughout Canada, selecting negative labels, and issues regarding the interpretability of some machine learning models are major challenges impeding data-driven prospectivity modeling of carbonatite-hosted REE +/− Nb deposits. A multi-stage framework, exploiting global hierarchical tessellation model systems, data-space similarity measures, ensemble modeling, and Shapley additive explanations was coupled with convolutional neural networks (CNN) and random forest to meet the objectives of this work. A risk–return analysis was further implemented to assist with model interpretation and visualization. Multiple models were compared in terms of their predictive ability and their capability of reducing the search space for mineral exploration. The best-performing model, derived using a CNN that incorporates public geoscience datasets, exhibits an area under the curve for receiver operating characteristics plot of 0.96 for the testing labels, reducing the search area by 80%, while predicting all known carbonatite-hosted REE +/− Nb occurrences. The framework used in our study allows for an explicit definition of input vectors and provides a clear interpretation of outcomes generated by prospectivity models.

Adaptive weighted multi-view subspace clustering method for recognizing urban functions from multi-source social sensing data

ABSTRACT Multi-source social sensing data provide new opportunities to identify urban functions from the perspective of human activity. The information embedded in multi-source data typically needs to be fused to obtain a comprehensive view of urban functions. Although multi-view clustering has been successfully used to fuse multi-source social sensing data, the adaptive determination of fusion weights for high-dimensional and noisy multi-source social sensing data remains challenging. Therefore, this study proposes an adaptive weighted multi-view subspace clustering (AWMSC) method. First, we use two neural networks to map multi-source data into a common latent representation and multiple specific latent representations, which serve as the query vector and input vectors of the attention mechanism, respectively. Then, the weight of each type of data is calculated based on the attention mechanism. Finally, the specific latent representations of the multi-source data are weighted and fused into a shared subspace representation, which is used as the input of the spectral clustering algorithm to obtain clustering results. AWMSC is applied to identify urban functional zones in Beijing using bus transactions, taxi trajectories, and points of interest datasets. The results show that AWMSC outperforms the typical single-view, weighted-average, and representative multi-view methods. AWMSC can obtain a comprehensive understanding of urban functional zones which may help government departments make more accurate strategic decisions.

Tool wear monitoring strategy during micro-milling of TC4 alloy based on a fusion model of recursive feature elimination-bayesian optimization-extreme gradient boosting

Online monitoring of tool wear is an indispensable part of industrial production. It allows for real-time assessment of tool condition, enabling tool replacement at the optimal time. This not only reduces the time costs associated with downtime for inspections but also effectively prevents the deterioration of workpiece quality due to excessive wear. Therefore, online monitoring of tool wear is essential for ensuring machining quality and efficiency. This research presents a monitoring technique for tool wear while performing micro-milling by extracting features from machining signals. Initially, the wear mechanism, which includes initial, regular, and severe wear, is analyzed. Tool wear labels are then constructed. Subsequently, the recursive feature elimination (RFE) algorithm optimizes the original feature set from the processed signal, resulting in a subset of relevant features that accurately describe the tool wear. The optimal subset is utilized as an input vector for extreme gradient boosting (XGBoost) training. Next, the best hyperparameter combination for the monitoring model is determined using Bayesian optimization (BO), ensuring the generalization performance of the monitoring model. Finally, the two-edge wear monitoring model is established based on the RFE-BO-XGBoost. To validate the superiority of the RFE-BO-XGBoost model, the performance of the XGBoost model with default parameters in tool wear monitoring is also investigated. The results demonstrate that the constructed monitoring model can effectively identify the tool wear stage. More notably, it precisely predicts the wear status of two cutting edges simultaneously, enabling qualitative and quantitative monitoring of tool wear under normal manufacturing settings.

Actuator multiplicative and additive simultaneous faults estimation using a qLPV proportional integral unknown input observer

AbstractThis paper introduces a technique for simultaneous estimation of additive and multiplicative faults in the actuators of nonlinear systems represented by quasi‐linear parameter varying (qLPV) models based on a proportional‐integral unknown input observer. The qLPV model, structured with a tensor product, allows for optimized flexibility of the observer gain. A distinguishing aspect of our method is the novel approach to nonlinearity, which is not only recast as a convex sum but also in the input vector. The study comprehensively analyses the robustness and convergence conditions through Lyapunov stability evaluation. A robust performance criterion is incorporated to minimize the influence of measurement noise and disturbances. As a result, a set of linear matrix inequalities are obtained. Two examples are examined to demonstrate the practical applicability and efficacy of the proposed method, highlighting the observer's performance under the actuator faults.

Binarized Neural Network Comprising Quasi‐Nonvolatile Memory Devices for Neuromorphic Computing

AbstractThis study presents a binarized neural network (BNN) comprising quasi‐nonvolatile memory (QNVM) devices that operate in a positive feedback loop mechanism and exhibit an extremely low subthreshold swing (≤ 5 mV dec−1) and a high on/off ratio (≥ 107). A pair of QNVM devices are used for a single synaptic cell in a cell array, in which its memory state represents the synaptic weight, and the voltages applied to the pair act as input in a complementary fashion. The array of synaptic cells performs matrix multiply‐accumulate (MAC) operations between the weight matrix and input vector using XNOR and current summation. All the results of the MAC operations and vector‐matrix multiplications are equivalent. Moreover, the BNN features a high accuracy of 93.32% in the MNIST image recognition simulation owing to high device uniformity (1.35%), which demonstrates the feasibility of compact and high‐performance neuromorphic computing.

Recurrent neural networks-guided vector-valued synchronized key exchange for secure and privacy-preserving communication in Industrial Internet of Things

This paper presents an innovative approach to the problem of key exchange in the Industrial Internet of Things (IIoT) implementation. Recurrent Neural Networks (RNNs) and vector-valued neural synchronization are the key components of the proposed secure transmission method. Drive-response methods are integrated to improve speed in important applications, meeting the continuous need for effective cryptographic key exchange between IIoT devices. Conventional algorithms face drawn-out assessment procedures that jeopardize neural synchronization concealment. This work examines how random input vector generation and synchronization issues in RNNs with drive-response are affected by proportional and non-proportional delays. Furthermore, it delves into an unexplored domain, investigating the synchronization of response-based RNN systems without delays and drive-response-based RNN systems with various proportional delays. It also suggests a simplified analysis of Artificial Neural Networks (ANNs) synchronization, organizing ANNs for session key switch-over using an RNN system. To achieve polynomial and non-polynomial synchronization in the proposed driver response systems, this method offers several benefits: it introduces a polynomial synchronization theory for RNNs to generate synchronized input vectors for ANN synchronization; it uses inequality assessment techniques and Lyapunov formulas to derive relevant control inputs and time-dependent conditions; it establishes the relationship between polynomial and non-polynomial synchronization; and it provides numerical examples demonstrating its effectiveness. It also builds a neural network for generating session keys throughout the IIoT network by aligning vector-valued ANNs in a reciprocal manner. This strategy outperforms previous approaches in the literature, validated through simulations, balances resilience against attacks with minimal computational load, resulting in more effective and resilient industrial applications.

A novel approach of brain-computer interfacing (BCI) and Grad-CAM based explainable artificial intelligence: Use case scenario for smart healthcare

BackgroundIn order to push the frontiers of brain-computer interface (BCI) and neuron-electronics, this research presents a novel framework that combines cutting-edge technologies for improved brain-related diagnostics in smart healthcare. This research offers a ground-breaking application of transparent strategies to BCI, promoting openness and confidence in brain-computer interactions and taking inspiration from Grad-CAM (Gradient-weighted Class Activation Mapping) based Explainable Artificial Intelligence (XAI) methodology. The landscape of healthcare diagnostics is about to be redefined by the integration of various technologies, especially when it comes to illnesses related to the brain. New methodA novel approach has been proposed in this study comprising of Xception architecture which is trained on imagenet database following transfer learning process for extraction of significant features from magnetic resonance imaging dataset acquired from publicly available distinct sources as an input and linear support vector machine has been used for distinguishing distinct classes.Afterwards, gradient-weighted class activation mapping has been deployed as the foundation for explainable artificial intelligence (XAI) for generating informative heatmaps, representing spatial localization of features which were focused to achieve model’s predictions. ResultsThus, the proposed model not only provides accurate outcomes but also provides transparency for the predictions generated by the Xception network to diagnose presence of abnormal tissues and avoids overfitting issues. Hyperparameters along with performance-metrics are also obtained while validating the proposed network on unseen brain MRI scans to ensure effectiveness of the proposed network. Comparison with existing methods and conclusionsThe integration of Grad-CAM based explainable artificial intelligence with deep neural network namely Xception offers a significant impact in diagnosing brain tumor disease while highlighting the specific regions of input brain MRI images responsible for making predictions. In this study, the proposed network results in 98.92% accuracy, 98.15% precision, 99.09% sensitivity, 98.18% specificity and 98.91% dice-coefficient while identifying presence of abnormal tissues in the brain. Thus, Xception model trained on distinct dataset following transfer learning process offers remarkable diagnostic accuracy and linear support vector act as a classifier to provide efficient classification among distinct classes. In addition, the deployed explainable artificial intelligence approach helps in revealing the reasoning behind predictions made by deep neural network having black-box nature and provides a clear perspective to assist medical experts in achieving trustworthiness and transparency while diagnosing brain tumor disease in the smart healthcare