A Novel Hybrid Neural Network with Optimized Feature Selection for Spindle Thermal Error Prediction

To improve processing precision of numerical machine tool ,research on analyze the thermal error of spindle, the grey correlation analysis method is used to optimize the thermal key points to build the model of temperature field on the basis of temperature measurement experiment. By optimizing, the number of temperature measuring points from 8 to 3. In this way, the precision of thermal error model and thermal error prediction can be improved.

Active coolant strategy for thermal balance control of motorized spindle unit

Adaptive learning control of robot manipulators via incremental hybrid neural network

High-speed motorized spindle heating will produce thermal error, which is an important factor affecting the machining accuracy of machine tools. The thermal error model of high-speed motorized spindles can compensate for thermal error and improve machining accuracy effectively. In order to confirm the high precision thermal error model, Beetle antennae search algorithm (BAS) is proposed to optimize the thermal error prediction model of motorized spindle based on BP neural network. Through the thermal characteristic experiment, the A02 motorized spindle is used as the research object to obtain the temperature and axial thermal drift data of the motorized spindle at different speeds. Using fuzzy clustering and grey relational analysis to screen temperature-sensitive points. Beetle antennae search algorithm (BAS) is used to optimize the weights and thresholds of the BP neural network. Finally, the BAS-BP thermal error prediction model is established. Compared with BP and GA-BP models, the results show that BAS-BP has higher prediction accuracy than BP and GA-BP models at different speeds. Therefore, the BAS-BP model is suitable for prediction and compensation of spindle thermal error.

A novel rainfall prediction method has been proposed. In the present work rainfall prediction in Southern part of West Bengal (India) has been conducted. A two-step method has been employed. Greedy forward selection algorithm is used to reduce the feature set and to find the most promising features for rainfall prediction. First, in the training phase the data is clustered by applying k-means algorithm, then for each cluster a separate Neural Network (NN) is trained. The proposed two step prediction model (Hybrid Neural Network or HNN) has been compared with MLP-FFN classifier in terms of several statistical performance measuring metrics. The data for experimental purpose is collected by Dumdum meteorological station (West Bengal, India) over the period from 1989 to 1995. The experimental results have suggested a reasonable improvement over traditional methods in predicting rainfall. The proposed HNN model outperformed the compared models by achieving 84.26% accuracy without feature selection and 89.54% accuracy with feature selection.

The global health crisis due to the fast spread of coronavirus disease (Covid-19) has caused great danger to all aspects of healthcare, economy, and other aspects. The highly infectious and insidious nature of the new coronavirus greatly increases the difficulty of outbreak prevention and control. The early and rapid detection of Covid-19 is an effective way to reduce the spread of Covid-19. However, detecting Covid-19 accurately and quickly in large populations remains to be a major challenge worldwide. In this study, A CNN-transformer fusion framework is proposed for the automatic classification of pneumonia on chest X-ray. This framework includes two parts: data processing and image classification. The data processing stage is to eliminate the differences between data from different medical institutions so that they have the same storage format; in the image classification stage, we use a multi-branch network with a custom convolution module and a transformer module, including feature extraction, feature focus, and feature classification sub-networks. Feature extraction subnetworks extract the shallow features of the image and interact with the information through the convolution and transformer modules. Both the local and global features are extracted by the convolution module and transformer module of feature-focus subnetworks, and are classified by the feature classification subnetworks. The proposed network could decide whether or not a patient has pneumonia, and differentiate between Covid-19 and bacterial pneumonia. This network was implemented on the collected benchmark datasets and the result shows that accuracy, precision, recall, and F1 score are 97.09%, 97.16%, 96.93%, and 97.04%, respectively. Our network was compared with other researchers' proposed methods and achieved better results in terms of accuracy, precision, and F1 score, proving that it is superior for Covid-19 detection. With further improvements to this network, we hope that it will provide doctors with an effective tool for diagnosing Covid-19.

In CNC machine tools, transient temperature variation in the headstock assembly is the major contributors for spindle thermal error. The compensation of thermal error is critical for ensuring the accuracy of machine tool. The performance of an error compensation system depends largely on the accuracy and robustness of the thermal error model. In the present work, a robust thermal error model is developed for minimizing the error in lateral direction of the spindle which significantly influences the geometrical accuracy of the workpiece. Analysis-of-variance (ANOVA) is applied to the results of the experiments in determining the percentage contribution of each individual temperature key point against a stated level of confidence. Based on the analysis of existing approaches for thermal error modeling of machine tools, an approach of LASSO (least absolute shrinkage and selection operator) is proposed in order to avoid the multi collinearity problem. The proposed method is an innovative variable selection method to remove redundant or unimportant temperature key points in the linear thermal error model and minimize the residual sum of squares. The predictive error model is found to have better robustness and accuracy in comparison to the combination of grey correlation and step wise linear regression for error compensation of CNC lathe. Keywords: Analysis Of Variance (ANOVA), CNC Machine Tool, Grey Correlation Analysis (GCA), Headstock Assembly, LASSO Regression, Mean Absolute Deviation (MAD), Mean Square Error (MSE), Robustness, Standard Deviation (SD), Thermal Error.

Recent technological advances allowed an exponential expansion of biological sequence data, and the extraction of meaningful information through Machine Learning (ML) algorithms. This knowledge improved the understanding of the mechanisms related to several fatal diseases, e.g., Cancer and COVID-19, helping to develop innovative solutions, such as CRISPR-based gene editing, coronavirus vaccine, and precision medicine. These advances benefit our society and economy, directly impacting peoples lives in various areas, such as health care, drug discovery, forensic analysis, and food analysis. Nevertheless, ML approaches applied to biological data require representative, quantitative, and informative features. Necessarily, as many ML algorithms can handle only numerical data, sequences need to be translated into a feature vector. This process, known as feature extraction, is a fundamental step for the elaboration of high-quality ML-based models in bioinformatics, by allowing the feature engineering stage, with the design and selection of suitable features. Feature engineering, ML algorithm selection, and hyperparameter tuning are often manual and time-consuming processes, requiring extensive domain knowledge, and performed manually by a human expert. To deal with this problem, we developed a new package, BioAutoML, which automatically runs an end-to-end ML pipeline. BioAutoML extracts numerical and informative features from biological sequence databases, automating feature selection, recommendation of ML algorithm(s), and tuning of hyperparameters, using Automated ML (AutoML). BioAutoML has two components, divided into four modules, (1) automated feature engineering (feature extraction and selection modules) and (2) Metalearning (algorithm recommendation and hyperparameter tuning modules). Our experimental results, assessing the relevance of our proposal, indicate robust results for different problem domains, such as SARS-CoV-2, anticancer peptides, HIV sequences, and non-coding RNAs. According to our systematic review, our proposal is innovative compared to available studies in the literature, being the first study to propose automated feature engineering and metalearning for biological sequences. BioAutoML has a high potential to significantly reduce the expertise required to use ML pipelines, aiding researchers in combating diseases, particularly in low- and middle-income countries. This initiative can provide biologists, physicians, epidemiologists, and other stakeholders with an opportunity for widespread use of these techniques to enhance the health and well-being of their communities.

Fault diagnosis of drainage pumps is essential for ensuring the safe and stable operation of drainage systems. However, vibration signals acquired from drainage pumps under practical operating conditions are often characterized by strong non-stationarity, unavoidable environmental interference, and fault features distributed across multiple temporal scales, which poses significant challenges to accurate multi-class fault identification. To tackle these challenges, this paper proposes a multi-scale residual attention convolutional neural network (MRANet) for drainage pump fault diagnosis. A multi-scale residual attention feature extraction (MRAFE) module is designed to jointly model fault-related information at different temporal scales by means of parallel convolutions and residual connections, while attention mechanisms are incorporated within each scale branch to enhance discriminative fault features. Furthermore, a complementary multi-level feature integration (CMFI) strategy is developed to effectively integrate features extracted at different network depths, enabling end-to-end fault identification directly from raw one-dimensional vibration signals. Extensive experiments are conducted on a drainage pump vibration dataset containing eight operating conditions. Experimental results show that MRANet achieves an accuracy of 95.43%, outperforming several benchmark models. These results verify the effectiveness and robustness of the proposed method for multi-class fault diagnosis of drainage pumps.

Knowledge about people's emotions can serve as an important context for automatic service delivery in context-aware systems. Hence, human facial expression recognition (FER) has emerged as an important research area over the last two decades. To accurately recognize expressions, FER systems require automatic face detection followed by the extraction of robust features from important facial parts. Furthermore, the process should be less susceptible to the presence of noise, such as different lighting conditions and variations in facial characteristics of subjects. Accordingly, this work implements a robust FER system, capable of providing high recognition accuracy even in the presence of aforementioned variations. The system uses an unsupervised technique based on active contour model for automatic face detection and extraction. In this model, a combination of two energy functions: Chan---Vese energy and Bhattacharyya distance functions are employed to minimize the dissimilarities within a face and maximize the distance between the face and the background. Next, noise reduction is achieved by means of wavelet decomposition, followed by the extraction of facial movement features using optical flow. These features reflect facial muscle movements which signify static, dynamic, geometric, and appearance characteristics of facial expressions. Post-feature extraction, feature selection, is performed using Stepwise Linear Discriminant Analysis, which is more robust in contrast to previously employed feature selection methods for FER. Finally, expressions are recognized using trained HMM(s). To show the robustness of the proposed system, unlike most of the previous works, which were evaluated using a single dataset, performance of the proposed system is assessed in a large-scale experimentation using five publicly available different datasets. The weighted average recognition rate across these datasets indicates the success of employing the proposed system for FER.

Automatic classification of the electrocardiogram (ECG) signals is an important subject for clinical diagnosis of heart disease. This study investigates the design of a high-efficient system to classify five types of ECG beat namely normal beats and four manifestations of heart arrhythmia, in twofold. First, we propose a system that includes two main modules: a feature extraction module and a classification module. Feature extraction module extracts a suitable combination of the ECG's morphological characteristics and timing interval features. Discrete wavelet transform is used to extract the morphological features. In the classification module, a multi-class support vector machine (SVM)-based classifier is employed. The parameters of this system are determined based on a trial and error method and its performance is evaluated for the MIT-BIH arrhythmia database. Extensive experiments on the parameters of this system such as classifier kernels and various types of features are conducted. These experiments show that in SVM training, the kernels, kernel parameters, and feature selection have very important roles for SVM classification accuracy. Therefore, most appropriates of these parameters should be used for SVM training. Then at the second fold, a novel hybrid intelligent system (HIS) is proposed that consists of three main modules. In the HIS, further to the two mentioned modules, an optimization module is added. In this module, a genetic algorithm is used for optimization of the relevant parameters of system. These parameters are: wavelet filter type for feature extraction, wavelet decomposition level, and classifier's parameters. Experimental results show that optimization improves the recognition system, efficiently, and HIS is more superior to the system, which as constant parameters.

Mental disorders, especially schizophrenia, still pose a great challenge for diagnosis in early stages. Recently, computer-aided diagnosis techniques based on resting-state functional magnetic resonance imaging (Rs-fMRI) have been developed to tackle this challenge. In this work, we investigate different decision-level and feature-level fusion schemes for discriminating between schizophrenic and normal subjects. Four types of fMRI features are investigated, namely the regional homogeneity, voxel-mirrored homotopic connectivity, fractional amplitude of low-frequency fluctuations and amplitude of low-frequency fluctuations. Data denoising and preprocessing were first applied, followed by the feature extraction module. Four different feature selection algorithms were applied, and the best discriminative features were selected using the algorithm of feature selection via concave minimization (FSV). Support vector machine classifiers were trained and tested on the COBRE dataset formed of 70 schizophrenic subjects and 70 healthy subjects. The decision-level fusion method outperformed the single-feature-type approaches and achieved a 97.85% accuracy, a 98.33% sensitivity, a 96.83% specificity. Moreover, feature-fusion scheme resulted in a 98.57% accuracy, a 99.71% sensitivity, a 97.66% specificity, and an area under the ROC curve of 0.9984. In general, decision-level and feature-level fusion schemes boosted the performance of schizophrenia detectors based on fMRI features.

Look-ahead prediction of spindle thermal errors with on-machine measurement and the cubic exponential smoothing-unscented Kalman filtering-based temperature prediction model of the machine tools

Data samples (temperature and thermal drifts) obtained in motorized spindle thermal experiments are usually small and contain much information. Some of the information cannot be fully comprehended by most regression modeling methods when modeling with small training samples; hence, the modeled thermal error predictors can seriously lack robustness, especially for the thermal tilt angle (vital for the boring accuracy of precision boring machines) predictors. To solve this problem, the LS-MLR (least-squares multivariable linear regression), the GA-SVR (genetic algorithm-support vector machine for regression), and the RFR (random forest regression) regression modeling methods are applied to construct the thermal error predictors (models) with the training sample, and the predictors are then evaluated with the testing sample. Comparisons of the three modeling methods are carried out afterwards; it is pointed out that predicting ability of the bias-corrected RFR predictor for thermal elongation is close to the GA-SVR predictor, and as for the thermal pitch and the thermal yaw, predicting ability of the RFR predictors are superior to the LS-MLR and the GA-SVR predictors. Finally, the evaluation results also indicate that the proposed RFR thermal error modeling method is promising to be used in motorized spindle thermal error predicting in machining processes even when the modeling data are poor.

Accurate identification of Parkinson's disease (PD), particularly during its prodromal stage, remains a major clinical challenge due to heterogeneous symptom presentation and overlapping neurological patterns. This study proposes an LLM-Guided Multimodal Attention Network (LLM-MAN) to improve PD staging by jointly modeling structural MRI and clinical/cognitive metadata. We develop a unified multimodal framework thatencodes structural MRI using a ResNet-18 backbone enhanced with Convolutional Block Attention Modules (CBAM) for discriminative neuroimaging feature extraction, and represents clinical/cognitive metadata using an LLM-based text encoder (pre-trained BERT) for contextualized semantic modeling. A Meta-Guided Cross-Attention (MGCA) module is introduced to align clinical semantic knowledge with imaging features, enabling robust cross-modal fusion for multiclass classification (Normal Control, prodromal PD, and diagnosed PD). The model is evaluated on the Parkinson's Progression Markers Initiative (PPMI) dataset and further validated on an independent external cohort. On the PPMI dataset, LLM-MAN achieved an accuracy of 95.68 % for distinguishing Normal Control, prodromal PD, and diagnosed PD. External validation on an independent cohort yielded 94.10 % accuracy, indicating strong generalization performance across datasets. LLM-guided multimodal fusion via MGCA provides reliable and interpretable approach for PD staging, substantially improving prodromal PD identification by integrating semantic clinical knowledge with neuroimaging representations.