University Of California , Irvine Research Articles

A Feature-Weighted Support Vector Regression Machine Based on Hilbert–Schmidt Independence Criterion Least Absolute Shrinkage and Selection Operator

Support vector regression (SVR) is a powerful kernel-based regression prediction algorithm that performs excellently in various application scenarios. However, for real-world data, the general SVR often fails to achieve good predictive performance due to its inability to assess feature contribution accurately. Feature weighting is a suitable solution to address this issue, applying correlation measurement methods to obtain reasonable weights for features based on their contributions to the output. In this paper, based on the idea of a Hilbert–Schmidt independence criterion least absolute shrinkage and selection operator (HSIC LASSO) for selecting features with minimal redundancy and maximum relevance, we propose a novel feature-weighted SVR that considers the importance of features to the output and the redundancy between features. In this approach, the HSIC is utilized to effectively measure the correlation between features as well as that between features and the output. The feature weights are obtained by solving a LASSO regression problem. Compared to other feature weighting methods, our method takes much more comprehensive consideration of weight calculation, and the obtained weighted kernel function can lead to more precise predictions for unknown data. Comprehensive experiments on real datasets from the University of California Irvine (UCI) machine learning repository demonstrate the effectiveness of the proposed method.

A comparative performance assessment of artificial intelligence based classifiers and optimized feature reduction technique for breast cancer diagnosis

Breast cancer (BC) is a catastrophic global health concern that causes numerous fatalities worldwide. Early detection of breast cancer may mitigate death rates; however, the prevailing diagnostic procedure for the malignancy necessitates numerous multifaceted laboratory tests that must be performed by medical professionals. In this article machine learning, a branch of Artificial Intelligence (AI), has been employed to improve cancer diagnosis, prognoses and survival rates while reducing the vulnerability of humans. Support Vector Machine (SVM), K-nearest Neighbors (KNN), Decision Tree (DT), Random Forest (RF) and Grey Wolf Optimizer (GWO) are implemented to prognosticate breast cancer. Comprehensive insights into the efficacy of these approaches for breast cancer prognosis are provided by the performance assessment that is accomplished using the confusion matrix, Receiver Operating Characteristic (ROC) curves and parallel coordinate plots. Both UCI (University of California Irvine) and SEER (Surveillance, Epidemiology and End Results) datasets have been utilized to confirm the investigation's findings and ensure their generalizability across diverse data sources. The results conclusively demonstrate that SVM is the cohort's most accurate classifier. With a stupendous accuracy rate of 99.1 %, the GWO-SVM compares favorably to all other algorithms. Furthermore, feature reduction approaches such as Minimum Redundancy Maximum Relevance (mRMR), ReliefF and Principal Component Analysis (PCA) are utilized. ReliefF has demonstrated exceptional effectiveness with a maximum accuracy of 98.2 %.

Initial Clinical Experience With a Novel Robotically Assisted Platform for Combined Mini-Percutaneous Nephrolithotomy and Flexible Ureteroscopic Lithotripsy.

We sought to evaluate the technical feasibility of performing a combined robotically assisted mini-percutaneous nephrolithotomy (PCNL) and flexible ureteroscopy (URS) procedure by a single urologist using the MONARCH Platform, Urology (Johnson & Johnson MedTech, Redwood City, California). In this prospective, first-in-human clinical trial, 13 patients underwent robotically-assisted PCNL for renal calculi at the University of California-Irvine, Department of Urology. Successful completion of the procedure was assessed as the primary endpoint. Postoperative adverse events were monitored for 30 days following the completion of the procedure. Stone ablation efficiency was evaluated on postoperative day 30 with low-dose 2-3 mm slice CT scans. Patients were classified according to the maximum length of their residual stone fragments as either absolute stone-free (Grade A), < 2 mm remnants (Grade B), or 2.1-4.0 mm remnants (Grade C). The combined robotic mini-PCNL and URS procedure was successfully completed in 12 of 13 procedures. No robotic device-related adverse events occurred. Preoperative stone burden was quantified by both maximum linear measurement (median 32.8 mm) as well as by CT-based volume (median 1645.9 mm3). Using the unique robotically assisted targeting system, percutaneous access was gained directly through the center of the renal papilla in a single pass in all cases. Median operative time was 187 minutes (range: 83-383 minutes). On postoperative day 30, a 98.7% (range: 72.9%-100.0%) volume reduction was achieved, with 5 Grade A (38.5%), 1 Grade B (7.7%), and 2 Grade C (15.4%). Three patients experienced complications (2 grade 1 and one grade 2 Clavien-Dindo). Our preliminary investigation demonstrates the safety, efficacy, and feasibility of a unique robotic-assisted combined mini-PCNL and URS platform.

Enhancing the physician-scientist workforce: evaluating a mentored research program for medical students' research competencies and intentions.

The growing recognition of the need to incorporate scientific discoveries into healthcare decisions underscores an urgency for a robust physician-scientist workforce to advance translational research. Despite the correlation between medical students' research engagement and their academic productivity and success, significant gaps remain in the scientific workforce exacerbated by the "leaky pipeline" phenomenon from medical school to academic medicine, where potential physician-scientists veer away from research careers.The purpose of this study was to assess the effectiveness of a structured mentored research program for enhancing medical students' research competencies and sustaining their interest in research careers, thereby potentially enhancing the physician-scientist workforce. The Medical Student Research Program (MSRP) implemented at the University of California, Irvine (UCI) was designed to provide comprehensive research training and support to medical students through a series of structured lectures, mentorship by dedicated faculty, and administrative support for research activities. Students were surveyed upon enrollment and one year later to assess the change in research competencies from baseline to follow-up (paired samples t-test), students' intent to use research in clinical practice (paired samples t-test), and their intent to conduct research in the future (McNemar's test and McNemar Bowker test). Preliminary evaluations indicated that the MSRP enhanced students' research competencies and has the potential to enhance medical students' research skills. However, similar to national trends, there was a decrease in students' intentions to engage with research in their future clinical career. Our preliminary findings demonstrate MSRP students' enhanced research competencies during the first year of the program. However, the decline in students' intentions to engage in future research highlights the need for continued innovation in research training programs to sustain future intent to conduct research, in turn helping to address the "leaky pipeline" in the physician-scientist workforce. Future studies should focus on mid and long-term outcomes to fully assess research program impact on the physician-scientist pipeline and on integrating such programs more broadly into medical education.

Intelligent Health Care Data Analysis System Using Swarm based Optimization Algorithm

Large amounts of clinical data present both opportunities and challenges in modern healthcare. Effective data analysis improves patient care, early disease detection, and personalised treatment. This paper proposes an Intelligent Health Care Data Analysis System employing PSO and neural networks to improve disease detection. Missing values, normalisation, and feature selection ensure high-quality analysis inputs. Disease classification and prediction from clinical data are improved by PSO optimising neural network weights and biases. This method works on Hepatitis, Wisconsin Breast Cancer, and Cleveland Heart Disease datasets with and without missing values. PSO-optimized neural networks outperform regular neural networks in accuracy and robustness. Scalable and adaptable for real-time diagnostic applications, this intelligent system may improve healthcare delivery by enabling more precise and timely interventions. Using neural networks and advanced swarm-based optimisation, medical data analytics has improved patient outcomes and healthcare system efficiency. Particle Swarm Optimization-based Neural Network (IPSONN) diagnoses clinical illnesses better. IPSONN was created using K-means clustering and IPSO-trained Neural Networks. K-means clusterings optimal cluster number determines the hidden layers neurones. Cluster approximation error determines best clusters. Mean square error calculates hidden and output layer weights in QPSO. The classifier was tested with four clinical datasets from the University of California, Irvine (UCI) machine learning repository: Pima Indian Diabetes, Hepatitis, Wisconsin Breast Cancer, and Cleveland Heart Disease.

Prediction of heart disease using a novel slap swarm optimized multi-objective random forest

Heart disease is a leading cause of death worldwide, becoming a major health concern for many people. Among the most important tasks and regular diagnostic research entails the identified cardiac issues, like heart diseases, valve conditions, etc. Early detection of heart disease may save many lives. The application of machine learning techniques in the medical sector has advanced significantly. A novel Slap Swarm Optimized Multi-Objective Random Forest (SSO-MORF) approach was presented in the proposed work for predicting cardiac disease. For this suggested investigation, heart disease information using individual customer identification at the University of California Irvine (UCI) was utilized, and data mining methods like categorization were applied. Min–max normalization and principal component analysis (PCA) were used for data preparation and feature extraction. As a result, a rather basic supervised machine learning technique may be used to predict heart disease quite accurately and with excellent potential value. According to this study, a classification based on the RF technique produced results with 99.45% accuracy, 98.3% recall, 98.6% precision, and a 98.9% f1 score. This finding demonstrates that our system is more efficient at predicting cardiac disease than other cutting-edge techniques.

Feature Selection AI Technique for Predicting Chronic Kidney Disease

The kidney is a vital organ that plays a crucial role in eliminating waste and excess water from the bloodstream. When renal function is impaired, the filtration process also ceases. This leads to an elevation of harmful molecules in the body, a condition referred to as chronic kidney disease (CKD). Early-stage chronic kidney disease often lacks noticeable symptoms, making it challenging to detect in its early stages. Diagnosing chronic kidney disease (CKD) typically involves advanced blood and urine tests, but unfortunately, by the time these tests are conducted, the disease may already be life-threatening. Our research focuses on the early prediction of chronic kidney disease (CKD) using machine learning (ML) and deep learning (DL) techniques. Utilized a dataset from the machine learning repository at the University of California, Irvine (UCI) to train various machine learning algorithms in conjunction with a Convolutional Neural Network (CNN) model. The algorithms encompassed in this set are Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), and Gradient Boosting (GB). Based on the experimental results, the CNN model achieves a prediction accuracy of precisely 97% after feature selection, the highest among all models tested. Hence, the objective of this project is to develop a deep learning-based prediction model to aid healthcare professionals in the timely identification of chronic kidney disease (CKD), potentially leading to life-saving interventions for patients.

DynamicWeighted Particle Swarm Optimization - Support Vector Machine Optimization in Recursive Feature Elimination Feature Selection

Feature Selection is a crucial step in data preprocessing to enhance machine learning efficiency, reduce computational complexity, and improve classification accuracy. The main challenge in feature selection for classification is identifying the most relevant and informative subset to enhance prediction accuracy. Previous studies often resulted in suboptimal subsets, leading to poor model performance and low accuracy. This research aims to enhance classification accuracy by utilizing Recursive Feature Elimination (RFE) combined with Dynamic Weighted Particle Swarm Optimization (DWPSO) and Support Vector Machine (SVM) algorithms. The research method involves the utilization of 12 datasets from the University of California, Irvine (UCI) repository, where features are selected via RFE and applied to the DWPSO-SVM algorithm. RFE iteratively removes the weakest features, constructing a model with the most relevant features to enhance accuracy. The research findings indicate that DWPSO-SVM with RFE significantly improves classification accuracy. For example, accuracy on the Breast Cancer dataset increased from 58% to 76%, and on the Heart dataset from 80% to 97%. The highest accuracy achieved was 100% on the Iris dataset. The conclusion of these findings that RFE in DWPSO-SVM offers consistent and balanced results in True Positive Rate (TPR) and True Negative Rate (TNR), providing reliable and accurate predictions for various applications.

Using Machine Learning and Artificial Intelligence to Predict Diabetes Mellitus Among Women Population.

Diabetes Mellitus (DM) is a chronic health condition (long-lasting) due to inadequate control of blood levels of glucose. This study presents a prediction of type 2 diabetes mellitus among women using various Machine Learning (ML) algorithms deployed to predict the diabetic condition. A University of California Irvine (UCI) diabetes mellitus dataset posted on Kaggle was used for analysis. The dataset included eight risk factors for type 2 diabetes mellitus prediction, including age, systolic blood pressure, glucose, body mass index (BMI), insulin, skin thickness, diabetic pedigree function, and pregnancy. R language was used for the data visualization, while the algorithms considered for the study were logistic regression, Support Vector Machines (SVM), Decision Trees, and Extreme Gradient Boost (XGB). The performance analysis of these algorithms on various classification metrics was also presented, considering that the AUC-ROC score is the best for Extreme Gradient Boost (XGB) with 85%, followed by SVM and Decision Trees (DT). The Logistic Regression (LR) demonstrated low performance, but the decision trees and XGB showed promising performance against all the classification metrics. Moreover, SVM offers a lower support value, so it cannot be considered a good classifier. The model showed that the most significant predictors of type 2 diabetes mellitus were glucose levels and body mass index, whereas age, skin thickness, systolic blood pressure, insulin, pregnancy, and pedigree function were less significant. This type of real-time analysis has proven that the symptoms of type 2 diabetes mellitus in women fall entirely different compared to men, which highlights the importance of glucose levels and body mass index in women. The prediction of type 2 diabetes mellitus helps public health professionals to suggest proper food intake and adjust lifestyle activities with good fitness management in women to make glucose levels controlled. Therefore, the healthcare systems should give special attention to diabetic conditions in women. This work attempts to predict the occurrence of type 2 diabetes mellitus among women from their various behavioral and biological conditions.

Evidence representation of uncertain information on a frame of discernment with semantic association

Belief functions as a powerful model to represent and deal with uncertain information are widely used in information fusion. However, semantic association within a frame of discernment is not well defined in traditional framework of belief function theory. To solve the problem, in this work models and methods for evidence representation of uncertain information on a frame of discernment with semantic association are studied. These contributions are made in the study. At first, a formal definition for the concept of semantic association is proposed via an axiomatic manner. Second, new evidence representation models including belief, plausibility and commonality measures, are designed with the consideration of semantic association. Third, a novel evidence discounting operation, called associative discounting, is proposed to amend original evidence in terms of more refined meta-knowledge regarding the reliability of information sources. The effectiveness of proposed models and methods is verified through practical applications on UCI (University of California, Irvine) data sets for the combination of multiple classifiers. This work, on the one hand, has successfully imported the concept of semantic association into the framework of belief function theory; on the other hand, it provides a new scheme to correct original information in a more refined manner.

Linear discriminant analysis with trimmed and difference distribution modeling

Linear discriminant analysis (LDA) has been widely used to extract features to solve various machine learning problems. However, the current LDA methods can be confused by highly dispersed samples. To address this problem, we develop a new LDA method based on a new expression of the theoretical error in classification. The method first combines different class distributions and then constructs the projection matrix on the basis of the statistics of the combined distribution. This is very different from conventional methods that estimate the statistics from individual classes first. The statistics are then combined to construct the projection matrix. The merit of the proposed approach is that it selects discriminant pairs of the combined distribution and discards the scatter structure caused by the dispersed samples. The statistics of this trimmed distribution are less sensitive to the dispersed samples and produce a robust projection matrix. The pairs are selected by a trimming model. The solution is obtained by the alternating direction method of multipliers (ADMM). The proposed LDA method is compared with 17 other LDA methods over 13 datasets belonging to the UC Irvine (UCI) repository, the knowledge extraction based on evolutionary learning (KEEL) repository, and publicly available image websites with different numbers of training samples. The experimental results indicate that the proposed method outperforms the existing methods in many cases.

Differential diagnosis of erythemato-squamous diseases using a hybrid ensemble machine learning technique

Erythemato-squamous Diseases (ESD) encompass a group of common skin conditions, including psoriasis, seborrheic dermatitis, lichen planus, pityriasis rosea, chronic dermatitis, and pityriasis rubra pilaris. These dermatological conditions affect a significant portion of the population and present a current challenge for accurate diagnosis and classification. Traditional classification methods struggle due to shared characteristics among these diseases. Machine Learning offers a valuable tool for aiding clinical decision-making in ESD classification. In this study, we leverage the UC Irvine (UCI) dermatology dataset by applying necessary preprocessing steps to handle missing data. We conduct a comparative analysis of two feature selection methods: One-way ANOVA and Chi-square test. To enhance the model’s performance, we employ hyper-parameter tuning through GridSearchCV. The training process encompasses various algorithms, including Support Vector Machine (SVM), Logistic Regression, k-Nearest Neighbors (kNN), and Decision Trees. The culmination of our work is a hybrid ensemble machine learning model that combines the strengths of the trained classifiers. This ensemble classifier achieves an impressive accuracy of 98.9% when validated using a 10-fold cross-validation approach.

Overcoming racial and ethnic disparities in clinical trial enrollment real world evidence from an NCI-Designated Cancer Center in a minority majority county.

e13708 Background: Significant racial and ethnic disparities continue to persist in clinical trial enrollment. Specifically, Asian and Hispanic individuals are severely underrepresented compared to their census estimates and make up as little as 1% and 6% respectively of all clinical trial enrollments [PMID: 35875251]. This limits the generalizability of clinical trials and consequently the application of novel therapeutics for diverse populations. This observational study looks at enrollment demographics at the University of California, Irvine (UCI) with an emphasis on minority participation in clinical trials. We hypothesized that minorities would be underrepresented in our enrollment population. Methods: The UCI Chao Family Comprehensive Cancer Center (CFCCC) is located in Orange County (OC), CA, a minority-majority county. Enrollment data from clinical trials was collected from 2015-2023 through the CFCCC clinical research database. Demographics were compared to data provided by the NIH SEER reports in both OC and United States. Results: Between 2015-2023, 2315 individuals across 3 UCI Health facilities were enrolled. Demographics were as follows: White, Asian, Black, American Indian/Alaska Native, mixed/unknown race (66.4%/20.1%/2.4%/0.7%/0.7%/ 9.3%). Non-Hispanic vs Hispanic ethnicity (77.8%/20.6%). Female vs Male sex (47.6%/52.3%). Age &lt;70 vs &gt;70 years (78.6%/21.4%). Low Income/Health Professional Shortage Areas (HPSA) vs non-Low Income/HPSA (44.9%/55.0%). Study Phase: Phase I/II (39.2%), Phase II (28.0%), Phase III (29.3%), Phase II/III (3.0%), and Phase IV (0.3%). Study sponsor: Industry (61.2%), Investigator initiated (23.5), Cooperative group (14.9%), other (0.3%). Most notably, the Asian enrollment (20.1%) and Hispanic enrollment (20.6%) exceeded demographic representation of Asians (15.6%) and Hispanics (17.3%) in OC. Conclusions: Our results demonstrate that accrual of minorities is feasible across all types of clinical trials. These findings suggest that minorities are not inherently less likely to enroll in clinical trials. A clinical trial portfolio mirroring the catchment area might improve accrual of minorities. Enrollment based on race/ethnicity and trial phase/sponsor will be presented at the meeting.

Hybrid deep learning model for YouTube spam comment detection

Social media platforms, including YouTube and Facebook, allow users to interact through comments and videos. However, the openness of these platforms also makes them susceptible to spammers engaging in phishing, malware distribution, and advertisement dissemination. In response, our study introduces an innovative technique for detecting features indicative of spam within comments associated with shared videos. The initial phase involves data collection from the University of California, Irvine (UCI) machine learning repository and preprocessing using tokenization and lemmatization. Subsequently, a rigorous feature selection process is executed, and experiments are conducted with various proposed classification models. The performance evaluation demonstrates outstanding accuracy in identifying spam comments on YouTube: convolutional neural network with gated recurrent unit (CNN-GRU) at 95.92%, convolutional neural network with long short-term memory (CNN-LSTM) at 95.41%, convolutional neural network with bidirectional long short-term memory (CNN-biLSTM) at 96.43%, gated recurrent unit (GRU) at 95.41%, long short-term memory (LSTM) at 94.13%, and bidirectional long short-term memory (biLSTM) at 96.94% and convolutional neural network (CNN) at 94.64%. These results highlight the substantial contribution of our approach to spam detection and the fortification of online security.

A Machine Learning Approach for Early Identification of Prodromal Parkinson's Disease.

Parkinson's disease (PD) affects approximately 6 million people worldwide. Data analysis of early PD symptoms using machine learning (ML) models may provide an inexpensive, non-invasive, and simple method for the remote diagnosis of early PD. The aim of this project was to analyze voice, computer keystrokes, spiral drawings, and gait data involving PD patients and controls available in public databases using ML models and identify early PD characteristics that are more pronounced than others. An ML model was developed using Random Forest to analyze existing clinical data for PD patients, prodromal PD patients with REM (rapid eye movement) sleep behavior disorder (RBD) symptoms, and non-PD healthy controls. We reviewed and collected data from the UCI (University of California Irvine) Machine Learning Repository, PPMI (Parkinson's Progression Markers Initiative), and Kaggle databases. ML analysis was carried out on voice samples in PD and RBD patients, computer keystroke data, spiral drawings, and gait datasets. The ML prediction model developed may be helpful in improving risk prediction for PD, enabling early intervention and resource prioritization. The ML study suggests that voice analysis is the most robust test, followed by computer keystroke data, spiral drawings, and gait analysis, in that order. Voice is affected even in RBD patients, revealing that it is a sensitive and early measure of prodromal PD. The low accuracy of the analysis indicates that several PD-positive samples may remain undetected and unclassified. Combining all four features, that is, voice analysis, computer keystroke data, spiral drawings, and gait analysis, may improve the overall accuracy.

Model construction and empirical of urban characteristic planning evaluation index system

With accelerated urbanisation, the importance of urban characteristic planning has become increasingly prominent. It has been a focus on how to conduct scientific urban characteristic planning evaluation to ensure high quality and sustainable development of urban characteristic planning. Therefore, this study proposed an urban characteristic planning evaluation index system based on support vector machine (SVM). The process uses hierarchical analysis to determine the relative weight values, calculates fuzzy values for indicators that cannot be directly and objectively evaluated and then introduces SVM for precise processing of interval data. The test results showed that the accuracy of the research method was 0.9760, 0.9600 and 0.9750 when taking the maximum bias value of 0.5 in the three datasets. The optimisation time of the research method for the parameters of the UCI (University of California Irvine) dataset remained within 650–750 ms. The evaluation results of the research method fit well with the expert evaluation results. The above results show that the research method has high data accuracy and operational efficiency in the evaluation of urban characteristic planning, which can make reasonable evaluation of urban characteristic planning. This method can provide reliable reference basis for government decision making.

A novel hybrid deep learning model for early stage diabetes risk prediction

Diabetes is a prevalent global disease that significantly diminishes the quality of life and can even lead to fatalities due to its complications. Early detection and treatment of diabetes are crucial for mitigating and averting associated risks. This study aims to facilitate the prompt and straightforward diagnosis of individuals at risk of diabetes. To achieve this objective, a dataset for early stage diabetes risk prediction from the University of California Irvine (UCI) database, widely utilized in the literature, was employed. A hybrid deep learning model comprising genetic algorithm, stacked autoencoder, and Softmax classifier was developed for classification on this dataset. The performance of this model, wherein both the model architecture and all hyperparameters were specifically optimized for the given problem, was compared with commonly used methods in the literature. These methods include K-nearest neighbor, decision tree, support vector machine, and convolutional neural network, utilizing tenfold cross-validation. The results obtained with the proposed method surpassed those obtained with other methods, with higher accuracy rates than previous studies utilizing the same dataset. Furthermore, based on the study’s findings, a web-based application was developed for early diabetes diagnosis.

Development of a Model to Classify Skin Diseases using Stacking Ensemble Machine Learning Techniques

Skin diseases are highly prevalent and transmissible. It has been one of the major health problems that most people face. The diseases are dangerous to the skin and tend to spread over time. A patient can be cured of these skin diseases if they are detected on time and treated early. However, it is difficult to identify these diseases and provide the right medications. This study's research objectives involve developing an ensemble machine learning based model for classifying Erythemato-Squamous Diseases (ESD). The ensemble techniques combine five different classifiers, Naïve Bayes, Support Vector Classifier, Decision Tree, Random Forest, and Gradient Boosting, by merging their predictions and utilizing them as input features for a meta-classifier during training. We tested and validated the ensemble model using the dataset from the University of California, Irvine (UCI) repository to assess its effectiveness. The Individual classifiers achieved different accuracies: Naïve Bayes (85.41%), Support Vector Machine (98.61%), Random Forest (97.91%), Decision Tree (95.13%), Gradient Boosting (95.83%). The stacking method yielded a higher accuracy of 99.30% and a precision of 1.00, recall of 0.96, F1 score of 0.97, and specificity of 1.00 compared to the base models. The study confirms the effectiveness of ensemble learning techniques in classifying ESD.

Ensemble Machine Learning Approach for Parkinson’s Disease Detection Using Speech Signals

The detection of Parkinson’s disease (PD) is vital as it affects the population worldwide and decreases the quality of life. The disability and death rate due to PD is increasing at an unprecedented rate, more than any other neurological disorder. To this date, no diagnostic procedures exist for this disease. However, several computational approaches have proven successful in detecting PD at early stages, overcoming the disadvantages of traditional methods of diagnosis. In this study, a machine learning (ML) detection system based on the voice signals of PD patients is proposed. The AdaBoost classifier has been utilized to construct the model and trained on a dataset obtained from the machine learning repository of the University of California, Irvine (UCI). This dataset includes voice attributes such as time-frequency features, Mel frequency cepstral coefficients, wavelet transform features, vocal fold features, and tremor waveform quality time. The model demonstrated promising performance, achieving high accuracy, precision, recall, F1 score, and AUC score of 0.96, 0.98, 0.93, 0.95, and 0.99, respectively. Furthermore, the robustness of the proposed model is rigorously assessed through cross-validation, revealing consistent performance across all iterations. The overarching objective of this study is to contribute to the scientific community by furnishing a robust system for the detection of PD.

A Fast Feedforward Small-World Neural Network for Nonlinear System Modeling.

It is well-documented that cross-layer connections in feedforward small-world neural networks (FSWNNs) enhance the efficient transmission for gradients, thus improving its generalization ability with a fast learning. However, the merits of long-distance cross-layer connections are not fully utilized due to the random rewiring. In this study, aiming to further improve the learning efficiency, a fast FSWNN (FFSWNN) is proposed by taking into account the positive effects of long-distance cross-layer connections, and applied to nonlinear system modeling. First, a novel rewiring rule by giving priority to long-distance cross-layer connections is proposed to increase the gradient transmission efficiency when constructing FFSWNN. Second, an improved ridge regression method is put forward to determine the initial weights with high activation for the sigmoidal neurons in FFSWNN. Finally, to further improve the learning efficiency, an asynchronous learning algorithm is designed to train FFSWNN, with the weights connected to the output layer updated by the ridge regression method and other weights by the gradient descent method. Several experiments are conducted on four benchmark datasets from the University of California Irvine (UCI) machine learning repository and two datasets from real-life problems to evaluate the performance of FFSWNN on nonlinear system modeling. The results show that FFSWNN has significantly faster convergence speed and higher modeling accuracy than the comparative models, and the positive effects of the novel rewiring rule, the improved weight initialization, and the asynchronous learning algorithm on learning efficiency are demonstrated.