Linear Discriminant Analysis Classifier Research Articles

Fault detection and diagnosis in refrigeration systems using machine learning algorithms

The functionality of industrial refrigeration systems is important for environment-friendly companies and organizations, since faulty systems can impact human health by lowering food quality, cause pollution, and even lead to increased global warming. Therefore, in this industry, there is a high demand among manufacturers for early and automatic fault diagnosis. In this paper, different machine learning classifiers are tested to find the best solution for diagnosing twenty faults possibly encountered in such systems. All sensor faults and some relevant component faults are simulated in a high fidelity Matlab/Simscape model of the system, which has previously been used for controller development and verification. In this work, Convolutional Neural Networks, Support Vector Machines (SVM), Principal Components Analysis-SVM, Linear Discriminant Analysis-SVM, and Linear Discriminant Analysis classifiers are compared. The results indicate that the fault detection reliability of the algorithms highly depends on how well the training data covers the operation regime. Furthermore, it is found that a well-trained SVM can simultaneously classify twenty types of fault with 95% accuracy when the verification data is taken from different system configurations.

A method for identifying moonlighting proteins based on linear discriminant analysis and bagging-SVM.

Moonlighting proteins have at least two independent functions and are widely found in animals, plants and microorganisms. Moonlighting proteins play important roles in signal transduction, cell growth and movement, tumor inhibition, DNA synthesis and repair, and metabolism of biological macromolecules. Moonlighting proteins are difficult to find through biological experiments, so many researchers identify moonlighting proteins through bioinformatics methods, but their accuracies are relatively low. Therefore, we propose a new method. In this study, we select SVMProt-188D as the feature input, and apply a model combining linear discriminant analysis and basic classifiers in machine learning to study moonlighting proteins, and perform bagging ensemble on the best-performing support vector machine. They are identified accurately and efficiently. The model achieves an accuracy of 93.26% and an F-sorce of 0.946 on the MPFit dataset, which is better than the existing MEL-MP model. Meanwhile, it also achieves good results on the other two moonlighting protein datasets.

Analysis of microstructural parameters of trabecular bone based on electrical impedance spectroscopy and deep neural networks

The potential of electrical impedance spectroscopy (EIS) was demonstrated for the investigation of microstructural properties of osseous tissue. Therefore, a deep neural network (DNN) was implemented for a sensitive assessment of different structural features that were derived on the basis of dielectric parameters, especially relative permittivities, recorded over a frequency range from 40 Hz to 5 MHz. The advantages of the developed method over conventional approaches, including equivalent circuit models (ECMs), linear regression and effective medium approximation (EMA), is the comprehensive quantification of bone morphologies by several microstructural parameters simultaneously, such as bone volume fraction (BV/TV), bone surface-volume-ratio (BS/BV), structure model index (SMI), trabecular number (Tb.N) and trabecular thickness (Tb.Th). The comparison of predictions of the DNN with an analysis of µCT-images confirmed a high accuracy for different microstructural parameters, which was indicated by corresponding Pearson correlation coefficients, especially for Tb.Th (r = 0.89) and BS/BV (r = 0.80). Concurrently, the approach was able to unambiguously discriminate anatomically similar bone regions (femoral head, greater trochanter and femoral neck) and therefore was capable to determine the morphological status of osseous tissue in detail. The classification was more discriminative than one based on classical linear discriminant analysis (LDA), due to the distinguishing features extracted by the DNN model. Accordingly, the method and model can serve as a potential tool for evaluating bone quality and bone status.

Novel Radiomics-Clinical Model for the Noninvasive Prediction of New Fractures After Vertebral Augmentation

To investigate the noninvasive prediction model for new fractures after percutaneous vertebral augmentation (PVA) based on radiomics signature and clinical parameters. Data from patients who were diagnosed with osteoporotic vertebral compression fracture (OVCF) and treated with PVA in our hospital between May 2014 and April 2019 were retrospectively analyzed. Radiomics features were extracted from T1-weighted magnetic resonance imaging (MRI) of the T11-L5 segments taken before PVA. Different radiomics models was developed by using linear discriminant analysis (LDA), multilayer perceptron (MLP), and stochastic gradient descent (SGD) classifiers. A nomogram was constructed by integrating clinical parameters and Radscore that calculated by the best radiomics model. The model performance was quantified in terms of discrimination, calibration and clinical usefulness. Four clinical parameters and 16 selected radiomics features were used for model development. The clinical model showed poor discrimination capability with area under the curves (AUCs) yielding of 0.522 in the training dataset and 0.517 in the validation dataset. The LDA, MLP and SGD classifier-based radiomics model had achieved AUCs of 0.793, 0.810, and 0.797 in the training dataset, and 0.719, 0.704, and 0.725 in the validation dataset, respectively. The nomogram showed the best performance with AUCs achieving 0.810 and 0.754 in the training and validation datasets, respectively. The decision curve analysis demonstrated the net benefit of the nomogram was higher than that of other models. Our findings indicate that combining clinical features with radiomics features from pre-augmentation T1-weighted MRI can be used to develop a nomogram that can predict new fractures in patients after PVA.

Adaptive binary multi-objective harmony search algorithm for channel selection and cross-subject generalization in motor imagery-based BCI

Objective. Multi-channel electroencephalogram data containing redundant information and noise may result in low classification accuracy and high computational complexity, which limits the practicality of motor imagery (MI)-based brain-computer interface (BCI) systems. Therefore, channel selection can improve BCI performance and contribute to user convenience. Additionally, cross-subject generalization is a key topic in the channel selection of MI-based BCI. Approach. In this study, an adaptive binary multi-objective harmony search (ABMOHS) algorithm is proposed to select the optimal set of channels. Furthermore, a new adaptive cross-subject generalization model (ACGM) is proposed. Three public MI datasets were used to validate the effectiveness of the proposed method. Main results. The Wilcoxon signed-rank test was performed on the test accuracies, and the results indicated that the ABMOHS method significantly outperformed all channels (p< 0.001), the C3–Cz–C4 channels (p< 0.001), and 20 channels (p< 0.001) in the sensorimotor cortex. The ABMOHS algorithm based on Fisher’s linear discriminant analysis (FLDA) and support vector machine (SVM) classifiers greatly reduces the number of selected channels, especially for larger channel sizes (Dataset 2), and obtains a comparative classification performance. Although there was no significant difference in test classification performance between ABMOHS and non-dominated sorting genetic algorithm II (NSGA-II) when FLDA and SVM were used, ABMOHS required less computational time than NSGA-II. Furthermore, the number of channels obtained by ABMOHS algorithm were significantly smaller than those obtained by common spatial pattern-Rank and correlation-based channel selection algorithm. Additionally, the generalization of ACGM to untrained subjects shows that the mean test classification accuracy of ACGM created by a small sample of trained subjects is significantly better than that of Special-16 and Special-32. Significance. The proposed method can reduce the calibration time in the training phase and improve the practicability of MI-BCI.

Efficient Prediction of Ki-67 Proliferation Index in Meningiomas on MRI: From Traditional Radiological Findings to a Machine Learning Approach.

Simple SummaryA high Ki-67 index usually suggests accelerated and uncontrolled cell proliferation correlated with tumor growth and is a prognostic factor that is associated with an increased recurrent risk in meningioma patients. The aim of our study is to predict the Ki-67 proliferative index in meningioma patients using machine learning technology. With 371 cases collected from two centers, we systematically analyzed the relevance between clinical/radiological features and the Ki-67 index. Moreover, with radiomic features extracted from postcontrast images, we built three radiomic models and three clinical radiological–radiomic models to predict the Ki-67 status. The models showed good performance, with an AUC of 0.837 in the internal test and 0.700 in the external test. The results provide a quantitative method to facilitate clinical decision making for meningioma patients.Background/aim This study aimed to explore the value of radiological and radiomic features retrieved from magnetic resonance imaging in the prediction of a Ki-67 proliferative index in meningioma patients using a machine learning model. Methods This multicenter, retrospective study included 371 patients collected from two centers. The Ki-67 expression was classified into low-expressed and high-expressed groups with a threshold of 5%. Clinical features and radiological features were collected and analyzed by using univariate and multivariate statistical analyses. Radiomic features were extracted from contrast-enhanced images, followed by three independent feature selections. Six predictive models were constructed with different combinations of features by using linear discriminant analysis (LDA) classifier. Results The multivariate analysis suggested that the presence of intratumoral necrosis (p = 0.032) and maximum diameter (p < 0.001) were independently correlated with a high Ki-67 status. The predictive models showed good performance with AUC of 0.837, accuracy of 0.810, sensitivity of 0.857, and specificity of 0.771 in the internal test and with AUC of 0.700, accuracy of 0.557, sensitivity of 0.314, and specificity of 0.885 in the external test. Conclusion The results of this study suggest that the predictive model can efficiently predict the Ki-67 index of meningioma patients to facilitate the therapeutic management.

Choosing an Optimal Machine Learning Classifier for Facial Recognition

Facial recognition is vital in today's technological world. There is a need to develop facial recognition systems which have high accuracy and at the same time high input to output response. To overcome the problem of low accuracy of facial recognition system we have attempted to combine different algorithm’s and develop a high accuracy facial recognition system. On combining different algorithms, we have observed that the Random Forest classifier achieved 96% accuracy in 2 secs. On the other hand, the Linear Discriminant Analysis classifier achieved 97% in 0 secs. Here we will compare the 6 classifiers to choose a optimal classifier.

Rapid diagnosis of diabetes based on ResNet and Raman spectroscopy

Diabetes mellitus is a global public health problem, and the epidemic situation in China is particularly serious. The prevalence of the disease has been increasing in recent years, and the number of patients is the highest in the world. Diabetes has become another chronic non-communicable disease that seriously endangers the health of our people after cardiovascular and cerebrovascular diseases and tumors. In this study, urine sample data were collected from 37 diabetic patients and 37 healthy volunteers using Raman spectroscopy. The collected data were preprocessed using an adaptive iterative reweighted penalized least squares (airPLS) algorithm and a polynomial Savitzky-Golay smoothing algorithm. After extracting features using principal component analysis (PCA) dimensionality reduction algorithm, ResNet, support vector machine (SVM) and linear discriminant analysis (LDA) classification models were selected to classify and identify diabetic patients and healthy controls. The results show that ResNet has the best discrimination effect, and the average accuracy, recall and F1-score can reach 84.28%, 86.20% and 84.02% respectively after five cross-validations, and the area under the subject working characteristic (ROC) curve is 0.93. The experimental results show that the model established in this paper is simple to operate, highly accurate and has good reference value for rapid screening of diabetes.

Cross-Platform Implementation of an SSVEP-Based BCI for the Control of a 6-DOF Robotic Arm.

Robotics has been successfully applied in the design of collaborative robots for assistance to people with motor disabilities. However, man-machine interaction is difficult for those who suffer severe motor disabilities. The aim of this study was to test the feasibility of a low-cost robotic arm control system with an EEG-based brain-computer interface (BCI). The BCI system relays on the Steady State Visually Evoked Potentials (SSVEP) paradigm. A cross-platform application was obtained in C++. This C++ platform, together with the open-source software Openvibe was used to control a Stäubli robot arm model TX60. Communication between Openvibe and the robot was carried out through the Virtual Reality Peripheral Network (VRPN) protocol. EEG signals were acquired with the 8-channel Enobio amplifier from Neuroelectrics. For the processing of the EEG signals, Common Spatial Pattern (CSP) filters and a Linear Discriminant Analysis classifier (LDA) were used. Five healthy subjects tried the BCI. This work allowed the communication and integration of a well-known BCI development platform such as Openvibe with the specific control software of a robot arm such as Stäubli TX60 using the VRPN protocol. It can be concluded from this study that it is possible to control the robotic arm with an SSVEP-based BCI with a reduced number of dry electrodes to facilitate the use of the system.

Real-Time Locomotion Recognition Algorithm for an Active Pelvis Orthosis to Assist Lower-Limb Amputees

Powered hip exoskeletons, in combination with passive prostheses, have been recently proposed to improve the economy and pattern of walking of lower-limb amputees within clinical scenarios. However, for everyday life support, a real-time control strategy that can accurately recognize different locomotion modes and transitions is required. In this letter, we proposed a novel locomotion recognition algorithm for an Active Pelvis Orthosis designed to assist people with lower-limb amputation, in quasi-static (sit-to-stand/stand-to-sit) and dynamic locomotion modes (walking and stairs negotiation). Two finite-state machines were combined to recognize in real-time the participants’ locomotion, one was a rule-based algorithm and one was based on four linear discriminant analysis classifiers. Four transfemoral amputees took part in the experiments and performed a circuit of tasks in two conditions, namely in <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">transparent mode</i> (the exoskeleton was controlled to provide null output impedance), and in <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">assistive mode</i> (the exoskeleton was controlled to output an assistive torque consistently with the locomotion mode recognized by the algorithm), to test the algorithm in real-time conditions. The median (25 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">th</sup> , 75 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">th</sup> percentile) between-subjects recognition accuracy was 94.8% (93.4%, 96.5%) with user-dependent models. Offline analysis on user-independent models with leave-one-subject-out validation resulted in between-subjects recognition accuracy equal to 95.9% (94.0%, 97.8%). The results of this study pave the way for future experimentations of the technology in ecological scenarios.

Recurrent Convolutional Neural Networks as an Approach to Position-Aware Myoelectric Prosthesis Control.

Persons with normal arm function can perform complex wrist and hand movements over a wide range of limb positions. However, for those with transradial amputation who use myoelectric prostheses, control across multiple limb positions can be challenging, frustrating, and can increase the likelihood of device abandonment. In response, the goal of this research was to investigate convolutional neural network (RCNN)-based position-aware myoelectric prosthesis control strategies. Surface electromyographic (EMG) and inertial measurement unit (IMU) signals, obtained from 16 non-disabled participants wearing two Myo armbands, served as inputs to RCNN classification and regression models. Such models predicted movements (wrist flexion/extension and forearm pronation/supination), based on a multi-limb-position training routine. RCNN classifiers and RCNN regressors were compared to linear discriminant analysis (LDA) classifiers and support vector regression (SVR) regressors, respectively. Outcomes were examined to determine whether RCNN-based control strategies could yield accurate movement predictions, while using the fewest number of available Myo armband data streams. An RCNN classifier (trained with forearm EMG data, and forearm and upper arm IMU data) predicted movements with 99.00% accuracy (versus the LDA's 97.67%). An RCNN regressor (trained with forearm EMG and IMU data) predicted movements with R2 values of 84.93% for wrist flexion/extension and 84.97% for forearm pronation/supination (versus the SVR's 77.26% and 60.73%, respectively). The control strategies that employed these models required fewer than all available data streams. RCNN-based control strategies offer novel means of mitigating limb position challenges. This research furthers the development of improved position-aware myoelectric prosthesis control.

Using Machine Learning Algorithms For Classifying Transmission Line Faults

The faults in transmission lines should be identified for attaining high quality energy in electrical power systems. Savings can be made in both time and energy if the transmission line faults are classified accurately. The present study examined phase-ground, phase-phase-ground, phase-phase, phase-phase-phase and no fault cases. Support Vector Machine (SVM), K-Nearest Neighbours Algorithm (KNN), Decision Tree (DT), Ensemble, Linear discriminant analysis (LDA) classifiers were used for classifying the transmission line faults. These algorithms were compared with regard to parameters such as accuracy, error rate, prediction speed and training time. The accuracy and minimum error of SVM and KNN classifiers were 99.7 % and 0.0011 respectively. DT classifier is faster than the other classifiers with a predicted speed of 29000 obs/sec. Whereas LDA had the shortest training time of 0.76992 sec. The results have indicated that SVM, KNN classifiers have similar performances. In addition, the classifiers SVM, KNN acquired minimum error with the highest accuracy compared with the other classifiers. While DT has the highest estimation speed, LDA has the shortest training time.

A comparative UHPLC-Q/TOF-MS-based metabolomics approach coupled with machine learning algorithms to differentiate Keemun black teas from narrow-geographic origins

Geographic-label is a remarkable feature for Chinese tea products. In this study, the UHPLC-Q/TOF-MS-based metabolomics approach coupled with chemometrics was used to determine the five narrow-geographic origins of Keemun black tea. Thirty-nine differentiated compounds (VIP > 1) were identified, of which eight were quantified. Chemometric analysis revealed that the linear discriminant analysis (LDA) classification accuracy model is 91.7%, with 84.7% cross-validation accuracy. Three machine learning algorithms, namely feedforward neural network (FNN), random forest (RF) and support vector machine (SVM), were introduced to improve the recognition of narrow-geographic origins, the performances of the model were evaluated by confusion matrix, receiver operating characteristic curve (ROC) and area under the curve (AUC). The recognition of RF, SVM and FNN for Keemun black tea from five narrow-geographic origins were 87.5%, 94.44%, and 100%, respectively. Importantly, FNN exhibited an excellent classification effect with 100% accuracy. The results indicate that metabolomics fingerprints coupled with chemometrics can be used to authenticate the narrow-geographic origins of Keemun black teas.

Multiclass recognition of AD neurological diseases using a bag of deep reduced features coupled with gradient descent optimized twin support vector machine classifier for early diagnosis

SummaryAlzheimer's disease (AD) is an advanced neurodegenerative disease of the brain that affects the nerve system of brain. Previously, several feature extraction and classification methods were discussed, but that methods provide high over fitting problem, which leads to minimization of detection accuracy. To overcome these issues, the multi class classification of AD diseases using bag of deep feature reduction technique and twin support vector machine classifier (TSVM) optimized with gradient decent optimizer is proposed in this manuscript for classifying the AD disease as severe AD, mild cognitive impairment, healthy control. At first, the input EEG signals are pre‐processed. To decrease the execution time and processing time with feature size, a bag of deep features reduction technique is used. The reduced feature signals are classified by optimized TSVM. The simulation process is implemented in MATLAB environment. The proposed model achieves higher accuracy 33.84%, 28.93%, 33.03%, 27.93%, higher precision 22.87%, 16.97%, 16.97%, and 36.97%, compared with the existing methods, such as piecewise aggregate approximation support vector machine (MCC‐EEG‐PAA‐SVM), convolutional neural network (MCC‐EEG‐CNN), conformal kernel‐based fuzzy support vector machine (MCC‐EEG‐CKF‐SVM), Pearson correlation coefficient‐based feature selection strategy with linear discriminant analysis classifier (MCC‐EEG‐ PCC‐LDA).

Application of Multiple-Source Data Fusion for the Discrimination of Two Botanical Origins of Magnolia Officinalis Cortex Based on E-Nose Measurements, E-Tongue Measurements, and Chemical Analysis.

Magnolia officinalis Rehd. et Wils. and Magnolia officinalis Rehd. et Wils. var. biloba Rehd. et Wils, as the legal botanical origins of Magnoliae Officinalis Cortex, are almost impossible to distinguish according to their appearance traits with respect to medicinal bark. The application of AFLP molecular markers for differentiating the two origins has not yet been successful. In this study, a combination of e-nose measurements, e-tongue measurements, and chemical analyses coupled with multiple-source data fusion was used to differentiate the two origins. Linear discriminant analysis (LDA) and quadratic discriminant analysis (QDA) were applied to compare the discrimination results. It was shown that the e-nose system presented a good discriminant ability with a low classification error for both LDA and QDA compared with e-tongue measurements and chemical analyses. In addition, the discriminating capacity of LDA for low-level fusion with original data, similar to a combined system, was superior or equal to that acquired individually with the three approaches. For mid-level fusion, the combination of different principals extracted by PCA and variables obtained on the basis of PLS-VIP exhibited an analogous discrimination ability for LDA (classification error 0.0%) and was significantly superior to QDA (classification error 1.67–3.33%). As a result, the combined e-nose, e-tongue, and chemical analysis approach proved to be a powerful tool for differentiating the two origins of Magnoliae Officinalis Cortex.

Chemical Discrimination of Benzene Series and Molecular Recognition of the Sensing Process over Ti-Doped Co3O4.

This work achieved the chemical discrimination of benzene series (toluene, xylene isomers, and ethylbenzene gases) based on the Ti-doped Co3O4 sensor. Benzene series gases presented different gas-response features due to the differences in redox rate on the surface of the Ti-doped Co3O4 sensor, which created an opportunity to discriminate benzene series via the algorithm analysis. Excellent groupings were obtained via the principal component analysis. High prediction accuracies were acquired via k-nearest neighbors, linear discrimination analysis (LDA), and support vector machine classifiers. With the confusion matrix for the data set using the LDA classifier, the benzene series have been well classified with 100% accuracy. Furthermore, in situ diffuse reflectance infrared Fourier transform spectroscopy (DRIFTS) and density functional theory calculations were conducted to investigate the molecular gas-solid interfacial sensing mechanism. Ti-doped Co3O4 showed strong Lewis acid sites and adsorption capability toward reaction species, which benefited the toluene gas-sensing reaction and resulted in the highly boosted gas-sensing performance. Our research proposed a facile distinction methodology to recognize similar gases and provided new insights into the recognition of gas-solid interfacial sensing mechanisms.

Experimental data manipulations to assess performance of hyperspectral classification models of crop seeds and other objects

BackgroundOptical sensing solutions are being developed and adopted to classify a wide range of biological objects, including crop seeds. Performance assessment of optical classification models remains both a priority and a challenge.MethodsAs training data, we acquired hyperspectral imaging data from 3646 individual tomato seeds (germination yes/no) from two tomato varieties. We performed three experimental data manipulations: (1) Object assignment error: effect of individual object in the training data being assigned to the wrong class. (2) Spectral repeatability: effect of introducing known ranges (0–10%) of stochastic noise to individual reflectance values. (3) Size of training data set: effect of reducing numbers of observations in training data. Effects of each of these experimental data manipulations were characterized and quantified based on classifications with two functions [linear discriminant analysis (LDA) and support vector machine (SVM)].ResultsFor both classification functions, accuracy decreased linearly in response to introduction of object assignment error and to experimental reduction of spectral repeatability. We also demonstrated that experimental reduction of training data by 20% had negligible effect on classification accuracy. LDA and SVM classification algorithms were applied to independent validation seed samples. LDA-based classifications predicted seed germination with RMSE = 10.56 (variety 1) and 26.15 (variety 2), and SVM-based classifications predicted seed germination with RMSE = 10.44 (variety 1) and 12.58 (variety 2).ConclusionWe believe this study represents the first, in which optical seed classification included both a thorough performance evaluation of two separate classification functions based on experimental data manipulations, and application of classification models to validation seed samples not included in training data. Proposed experimental data manipulations are discussed in broader contexts and general relevance, and they are suggested as methods for in-depth performance assessments of optical classification models.

Staging and chemotherapy response assessment of bladder cancer using hybrid deep machine learning model on CT scan images.

e16550 Background: Improved computational power and modern algorithms have generated significant interest in radiomics for cancer diagnosis and staging. Here we assess the performance of deep learning (DL) models as a means for feature extraction in combination with supervised machine learning (ML) algorithms for accurate staging and chemotherapy response assessment of bladder cancer. Methods: Deidentified grayscale CT images from bladder cancer patients scheduled to undergo radical cystectomy were included in this retrospective study. These images were manually annotated with two regional masks (normal region and cancer region). Five DL models- namely, AlexNet, GoogleNet, InceptionV3, ResNet-50, and XceptionNet pre-trained on the ImageNet dataset, a public dataset, were then fine-tuned on our bladder CT scan data to extract features. Through feature selection process, the subset of the features was used to build ML classifiers for classification. The classification was performed using five different ML classifiers, namely k-Nearest Neighbor (KNN), Naïve-Bayes (NB), Support Vector Machine (SVM), Linear Discriminant Analysis (LDA), and Decision Tree (DT). The classification task was performed with 10-fold cross-validation, and each of the experiments contained a different but not mutually exclusive subset of samples. The evaluation metrics include accuracy, sensitivity, specificity, precision, and F1-score. Results: A total of 200 deidentified grayscale CT images of 100 patients with histologically proven bladder cancer, were included in this study. For experiment (1) normal vs. cancer, the LDA classifier on XceptionNet based features provides the best performance with an accuracy of 86.07%, sensitivity of 96.75%, specificity of 69.65%, precision of 83.07%, and F1-score of 89.39%. For experiment (2) non-muscle invasive Cancer (NMIBC) vs. muscle invasive bladder cancer (MIBC), the LDA classifier on XceptionNet based features provided the best performance with an accuracy of 79.72%, sensitivity of 66.62%, specificity of 87.39%, precision of 75.58%, and F1-score of 70.81%. For experiment (3) T0 lesion vs. MIBC, the LDA classifier on XceptionNet based features provides the best performance with an accuracy of 74.96%, sensitivity of 80.51%, specificity of 70.22%, precision of 69.78%, and F1-score of 74.73%. Conclusions: Our proposed model has shown good results in differentiating normal vs cancer and promising performance in differentiating T0 vs MIBC after chemotherapy treatment. We are expanding our dataset to further improve the performance in differentiating T0 vs MIBC. In addition, we will investigate the applicability of GAN for data augmentation to address data limit. We believe the hybrid DL and ML framework may facilitates radiologists' decisions and clinical decision-making in patients with bladder cancer.

VLSI test through an improved LDA classification algorithm for test cost reduction

During manufacturing test, more and more test patterns are required as the growing complexity of integrated circuits (ICs), resulting the test time increasing and consequently test cost. Aiming at the problem that test time is too long and the test pattern efficiency is affected, this study proposed an improved linear discriminant analysis (LDA) classification algorithm to select the valid test patterns (pattern that can make the test fail) only, so that the classification results can make the test cost reduction in logic circuit test. In addition, the valid test patterns can be selected in terms of polynomial regression function and to accomplish this, consequently convert the optimization problem into a mathematical function, so as to achieve broader adaptability. Experimental results demonstrate that the proposed method succeeds in saving 1.75 times test time compared with traditional methods. In addition, the proposed method outperformed the conventional test method in the hardware area/power/speed aspect.

An Activity Recognition Framework for Continuous Monitoring of Non-Steady-State Locomotion of Individuals with Parkinson’s Disease

Fundamental knowledge in activity recognition of individuals with motor disorders such as Parkinson’s disease (PD) has been primarily limited to detection of steady-state/static tasks (e.g., sitting, standing, walking). To date, identification of non-steady-state locomotion on uneven terrains (stairs, ramps) has not received much attention. Furthermore, previous research has mainly relied on data from a large number of body locations which could adversely affect user convenience and system performance. Here, individuals with mild stages of PD and healthy subjects performed non-steady-state circuit trials comprising stairs, ramp, and changes of direction. An offline analysis using a linear discriminant analysis (LDA) classifier and a Long-Short Term Memory (LSTM) neural network was performed for task recognition. The performance of accelerographic and gyroscopic information from varied lower/upper-body segments were tested across a set of user-independent and user-dependent training paradigms. Comparing the F1 score of a given signal across classifiers showed improved performance using LSTM compared to LDA. Using LSTM, even a subset of information (e.g., feet data) in subject-independent training appeared to provide F1 score &gt; 0.8. However, employing LDA was shown to be at the expense of being limited to using a subject-dependent training and/or biomechanical data from multiple body locations. The findings could inform a number of applications in the field of healthcare monitoring and developing advanced lower-limb assistive devices by providing insights into classification schemes capable of handling non-steady-state and unstructured locomotion in individuals with mild Parkinson’s disease.