University Of California , Irvine Research Articles

Detecting chronic kidney disease by using a voting classifier


 
 
 Chronic Kidney Disease (CKD) is a global health problem with high morbidity and mortality rate, and it induces other diseases. Since there are no obvious symptoms during the early stage of CKD, patients often fail to notice the disease. Early detection of CKD enables patients to receive timely treatment to ameliorate the progression of this disease. Machine learning models can effectively aid clinicians achieve this goal due to their fast and accurate recognition performance. In this, we proposed a machine learning methodology for diagnosing CKD. The CKD data set was obtained from the University of California Irvine (UCI) machine learning repository, which has a large number of missing values. In general we have six machine learning algorithms like logistic regression, random forest, support vector machine, k-nearest neighbour, naive Bayes, classifier and feed forward neural network to establish models. In existing system random forest achieved the performance with 99.75% diagnosis accuracy. In proposed system, By analysing the misjudgments generated by the above model, we proposed an integrated model that combines logistic regression and random forest by using perceptron which could achieve an efficient accuracy of 99.83% after ten times of simulation. Hence, we speculated that this methodology could be applicable to more complicated clinical data for disease diagnosis.
 
 

Commodity demand forecasting using modulated rank reduction for humanitarian logistics planning

Demand prediction for humanitarian logistics is a complex problem with immediate real-world consequences. This paper examines fuel demand during two regional humanitarian crisis events and the supply chain operated by the US Government as part of Operation Unified Response. Because typical machine learning algorithms require large amounts of training data, our methods for predictive analysis depend on rapid training of a model where re-sampling would not be useful due to dynamic time-series data. We propose an online robust principal components analysis (RPCA) model combined with a long short-term memory (LSTM) recurrent network to address this challenge. Our computational results demonstrate that the proposed model can predict demand efficiently on real-world humanitarian supply datasets and well-known benchmark datasets in the University of California, Irvine (UCI) Machine Learning Repository. This method also allows us to tune training lag in online learning.

RETRACTED: Detection and classification of epilepsy using hybrid convolutional neural network

In recent years, more than 50 million people have been affected by the epilepsy, neurological disorder diseases. To monitor the situation of the epilepsy patient requires experienced and skilled person. In order to overcome these issues, autonomous detection of electroencephalogram (EEG) signal by deep learning model has evolved. Convolutional neural network (CNN) is one of the sub-category of neural network and widely used in the various field such as weather forecasting, signal processing and medical applications. In this article, the University of California Irvine (UCI) respiratory EEG signals are used to analyse the proposed hybrid CNN and results are compared to the pre-trained GoogleNet Network. EEG signals are initially converted into three different forms such as scalogram, spectrogram and time domain images and classification of images are carried out by the pre-trained GoogleNet network results in an accuracy of 85%. Then time domain images are combined with spectrogram and scalogram EEG signal separately and detection has been carried out by the CNN. It is found that the CNN network yields an accuracy of 92% which was higher than the pre-trained GoogleNet. To enhance the classification accuracy further, scalogram, spectrogram and time domain images are combined as single input images and applied to the CNN network and it results with the accuracy of 98%. The performance metrics such as Sensitivity, Specificity, F1 Score, Precision and misclassification rate of GoogleNet and proposed hybrid CNN networks are evaluated. It is observed from the result that proposed CNN results less than 10% misclassification rate, whereas for GoogleNet it was more than 20%. Similarly, the precision value of GoogleNet and proposed CNN networks are 82% and 93%, respectively.

Development of a graphical user interface software for the prediction of chronic kidney disease

Chronic Kidney Disease (CKD) is a severe kidney damage that is difficult to diagnose at the early stages due to the absence of clear symptoms. Late diagnosis of CKD is a common problem in low-income countries and is often associated with lower chances of survival. This study was designed to develop a user-friendly web-based graphical user interface (GUI) software for the prediction of CKD using artificial neural networks (ANNs). The model was developed using Python programming language and trained with 1200 instances of CKD datasets obtained from the University of California Irvine (UCI) machine learning repository. This dataset was split into 80% for training and 20% for testing achieved through an iterative process. A GUI software was developed based on the model using Django, an open-source python web development framework. The model achieved an accuracy of 95.83%, a precision of 100%, a specificity of 100%, and a sensitivity of 89.80%. The GUI software was effectively used to predict CKD and could be of immense benefit as a point of care application for early CKD prediction

Email classification analysis using machine learning techniques

PurposeIn this digital era, email is the most pervasive form of communication between people. Many users become a victim of spam emails and their data have been exposed.Design/methodology/approachResearchers contribute to solving this problem by a focus on advanced machine learning algorithms and improved models for detecting spam emails but there is still a gap in features. To achieve good results, features also play an important role. To evaluate the performance of applied classifiers, 10-fold cross-validation is used.FindingsThe results approve that the spam emails are correctly classified with the accuracy of 98.00% for the Support Vector Machine and 98.06% for the Artificial Neural Network as compared to other applied machine learning classifiers.Originality/valueIn this paper, Point-Biserial correlation is applied to each feature concerning the class label of the University of California Irvine (UCI) spambase email dataset to select the best features. Extensive experiments are conducted on selected features by training the different classifiers.

An Ensemble Clustering Framework Based on Hierarchical Clustering Ensemble Selection and Clusters Clustering

Ensemble clustering combines the results of multiple individual clustering methods for better results. Basically, all available clustering methods can be combined to produce final clusters. However, selecting a subset of optimal methods can reduce the complexity and increase the efficiency of ensemble clustering methods. This article examines the problem of selecting individual clustering methods to produce an ensemble hierarchical clustering method. Hierarchical clustering is a technique for grouping data at different scales by creating dendrograms. The aim is to select a subset of individual hierarchical clustering methods considering diversity and quality that can create an ensemble clustering method with minimal complexity. The proposed method consists of three main phases. The selection of a subset of individual hierarchical clustering methods is done in the first phase. In the second phase, the results of the selected clusters are re-clustered to create super-clusters. Super-clusters can combine clustering knowledge of different methods into one clustering form. Finally, the final clusters are formed by assigning each sample to a super-cluster with the shortest distance in the third phase. Experimental results on several datasets from the University of California Irvine (UCI) repository show that the proposed method performs better than the state-of-the-art algorithms.

Cuff-Less Blood Pressure Estimation From Photoplethysmography via Visibility Graph and Transfer Learning.

This paper presents a new solution that enables the use of transfer learning for cuff-less blood pressure (BP) monitoring via short duration of photoplethysmogram (PPG). The proposed method estimates BP with low computational budget by 1) creating images from segments of PPG via visibility graph (VG), hence, preserving the temporal information of the PPG waveform, 2) using pre-trained deep convolutional neural network (CNN) to extract feature vectors from VG images, and 3) solving for the weights and bias between the feature vectors and the reference BPs with ridge regression. Using the University of California Irvine (UCI) database consisting of 348 records, the proposed method achieves a best error performance of 0.00±8.46 mmHg for systolic blood pressure (SBP), and -0.04±5.36 mmHg for diastolic blood pressure (DBP), respectively, in terms of the mean error (ME) and the standard deviation (SD) of error, ranking grade B for SBP and grade A for DBP under the British Hypertension Society (BHS) protocol. Our novel data-driven method offers a computationally-efficient end-to-end solution for rapid and user-friendly cuff-less PPG-based BP estimation.

Adaptive multiple imputations of missing values using the class center

Big data has become a core technology to provide innovative solutions in many fields. However, the collected dataset for data analysis in various domains will contain missing values. Missing value imputation is the primary method for resolving problems involving incomplete datasets. Missing attribute values are replaced with values from a selected set of observed data using statistical or machine learning methods. Although machine learning techniques can generate reasonably accurate imputation results, they typically require longer imputation durations than statistical techniques. This study proposes the adaptive multiple imputations of missing values using the class center (AMICC) approach to produce effective imputation results efficiently. AMICC is based on the class center and defines a threshold from the weighted distances between the center and other observed data for the imputation step. Additionally, the distance can be an adaptive nearest neighborhood or the center to estimate the missing values. The experimental results are based on numerical, categorical, and mixed datasets from the University of California Irvine (UCI) Machine Learning Repository with introduced missing values rate from 10 to 50% in 27 datasets. The proposed AMICC approach outperforms the other missing value imputation methods with higher average accuracy at 81.48% which is higher than those of other methods about 9 – 14%. Furthermore, execution time is different from the Mean/Mode method, about seven seconds; moreover, it requires significantly less time for imputation than some machine learning approaches about 10 – 14 s.

An improved binary sparrow search algorithm for feature selection in data classification

Feature Selection (FS) is an important preprocessing step that is involved in machine learning and data mining tasks for preparing data (especially high-dimensional data) by eliminating irrelevant and redundant features, thus reducing the potential curse of dimensionality of a given large dataset. Consequently, FS is arguably a combinatorial NP-hard problem in which the computational time increases exponentially with an increase in problem complexity. To tackle such a problem type, meta-heuristic techniques have been opted by an increasing number of scholars. Herein, a novel meta-heuristic algorithm, called Sparrow Search Algorithm (SSA), is presented. The SSA still performs poorly on exploratory behavior and exploration-exploitation trade-off because it does not duly stimulate the search within feasible regions, and the exploitation process suffers noticeable stagnation. Therefore, we improve SSA by adopting: i) a strategy for Random Re-positioning of Roaming Agents (3RA); and ii) a novel Local Search Algorithm (LSA), which are algorithmically incorporated into the original SSA structure. To the FS problem, SSA is improved and cloned as a binary variant, namely, the improved Binary SSA (iBSSA), which would strive to select the optimal or near-optimal features from a given dataset while keeping the classification accuracy maximized. For binary conversion, the iBSSA was primarily validated against nine common S-shaped and V-shaped Transfer Functions (TFs), thus producing nine iBSSA variants. To verify the robustness of these variants, three well-known classification techniques, including k-Nearest Neighbor (k-NN), Support Vector Machine (SVM), and Random Forest (RF) were adopted as fitness evaluators with the proposed iBSSA approach and many other competing algorithms, on 18 multifaceted, multi-scale benchmark datasets from the University of California Irvine (UCI) data repository. Then, the overall best-performing iBSSA variant for each of the three classifiers was compared with binary variants of 12 different well-known meta-heuristic algorithms, including the original SSA (BSSA), Artificial Bee Colony (BABC), Particle Swarm Optimization (BPSO), Bat Algorithm (BBA), Grey Wolf Optimization (BGWO), Whale Optimization Algorithm (BWOA), Grasshopper Optimization Algorithm (BGOA) SailFish Optimizer (BSFO), Harris Hawks Optimization (BHHO), Bird Swarm Algorithm (BBSA), Atom Search Optimization (BASO), and Henry Gas Solubility Optimization (BHGSO). Based on a Wilcoxon’s non-parametric statistical test (alpha =0.05), the superiority of iBSSA with the three classifiers was very evident against counterparts across the vast majority of the selected datasets, achieving a feature size reduction of up to 92% along with up to 100% classification accuracy on some of those datasets.

A novel approach for cardiovascular disease prediction using machine learning algorithms

AbstractFor the past few decades, cardiovascular disease has shown a binding impact on the country's mortality rate. The prediction of cardiovascular disease is more challenging during the process of clinical data analysis. The emergence of Machine Learning approaches paved the way to predict the disease and determining the consequences of the disease in the earlier stage to help the physicians during complex decision‐making. This work adopts k‐Nearest Neighbor as baseline classifier and ensemble X‐boost, Adaboost, and Random subspace classifier model to predict heart disease and predict the features of cardiovascular disease using Linear Support Vector Feature Measure (). This model considers the diverse combination of features to make the better classification process. The model shows superior performance with precision via Clinical Decision Support System. The factors that influence the cardiovascular disease need to predict, and better decision is taken during the critical condition. Here, the online available University of California Irvine (UCI) Machine Learning dataset is used for training and testing where 80% data is considered for training and 20% considered for testing purpose. The simulation is done in MATLAB 2020b simulation environment, and the outcomes are compared with various existing approaches. Here, performance metrics like accuracy, precision, F‐measure, stability rate, region of curve, and recall is measured to show the model efficiency. The prediction accuracy of the proposed model is 96% which is higher than existing approaches. The overall performance of proposed ensemble model is 96% accuracy, 97% precision, 95% sensitivity, 95% F‐measure, 93% Matthew's correlation coefficients, 4.53% False Positive Rate, 3.10% False Negative Rate, and 96% True Positive Rate, respectively.

Optimization-Based Ensemble Feature Selection Algorithm and Deep Learning Classifier for Parkinson's Disease.

PD (Parkinson's Disease) is a severe malady that is painful and incurable, affecting older human beings. Identifying PD early in a precise manner is critical for the lengthened survival of patients, where DMTs (data mining techniques) and MLTs (machine learning techniques) can be advantageous. Studies have examined DMTs for their accuracy using Parkinson's dataset and analyzing feature relevance. Recent studies have used FMBOAs for feature selections and relevance analyses, where the selection of features aims to find the optimal subset of features for classification tasks and combine the learning of FMBOAs. EFSs (ensemble feature selections) are viable solutions for combining the benefits of multiple algorithms while balancing their drawbacks. This work uses OBEFSs (optimization-based ensemble feature selections) to select appropriate features based on agreements. Ensembles have the ability to combine results from multiple feature selection approaches, including FMBOAs, LFCSAs (Lévy flight cuckoo search algorithms), and AFAs (adaptive firefly algorithms). These approaches select optimized feature subsets, resulting in three feature subsets, which are subsequently matched for correlations by ensembles. The optimum features are generated by OBEFSs the trained on FCBi-LSTMs (fuzzy convolution bi-directional long short-term memories) for classifications. This work's suggested model uses the UCI (University of California-Irvine) learning repository, and the methods are evaluated using LOPO-CVs (Leave-One-Person-Out-Cross Validations) in terms of accuracies, F-measure values, and MCCs (Matthews correlation coefficients).

Accurate electricity consumption prediction using enhanced long short‐term memory

In the present era, the exponential growth in the human population and technological advancements has dramatically increased the power demand. As electricity is being used at the same time as it is produced at the power plant, effective forecasting of energy usage is crucial for maintaining a reliable power supply. In this work, a novel deep learning model named enhanced long short-term memory (E-LSTM) is proposed to accurately predict electricity consumption in advance as this deep learning model will accurately predict the electricity consumption by adjusting the number of hidden layers and optimizing the hyper-parameters. Until attaining high accuracy, hyper-parameters like learning rate (LR) and epochs along with hidden layers are adjusted to analyze the relative performance of the model. Also, rectified linear activation function alleviates the vanishing gradient problem of the model. Also, this work evaluated the seven LR policies using crucial policy (CP) benchmark on keras framework. Experiments using various evaluation criteria demonstrate that the developed E-LSTM model is efficient. When comparing some of the other state-of-the-art forecasting techniques, it has the lowest values of mean square error (MSE), mean absolute error (MAE), and root mean square error (RMSE) over the UC Irvine (UCI) residential building dataset.

Binary Golden Eagle Optimizer with Time-Varying Flight Length for feature selection

The concept of any method to resolve feature selection issues is to identify a subset of the original features. However, determining a minimal feature subset is considered an NP-hard problem. Many existing feature selection methods, namely particle swarm optimization (PSO), grey wolf optimization (GWO) etc., are complex and consume more time. This article proposes a new wrapper-based method that employs Binary Golden Eagle Optimizer with Time Varying Flight Length (BGEO-TVFL) to reduce the feature selection issues. The proposed method provides optimal feature selection based on Golden Eagle Optimizer (GEO). GEO is a recently presented swarm-based meta-heuristics algorithm that imitates the smartness of Golden Eagles (GEs). GEO algorithm performs on continuous space; however, the feature selection is in discrete space. Hence, the continuous space has transformed into a discrete space by employing transfer functions. Here, eight different transfer functions have been applied to determine the best transfer function and test the BGEO-TVFL. Moreover, a time-varying flight length (TVFL) has been employed to balance the exploration and exploitation in GEO. Finally, the performance of the proposed BGEO-TVFL has been determined by focusing on various metrics under different UC Irvine (UCI) datasets. The best variant has been selected and analyzed the performance with existing standard filter feature selection approaches and wrapper based feature selection methods. The existing methods include Bat Algorithm (BAT), Ant Colony Optimization (ACO) algorithm, PSO, GWO, Genetic Algorithm (GA), Cuckoo Search (CS), Golden Eagle Optimizer (GEO), ReliefF, Information Gain (IG), Correlation-based feature selection (CFS), and Gain Ratio (GR) respectively. In addition, the performance of BGEO-TVFL is also compared and analyzed with state-of-art methods to determine its superiority. Furthermore, the proposed BGEO-TVFL is analyzed with existing algorithms by employing 30 functions from CEC’2017, CEC’2018 and CEC’2020 benchmarks. As a result, the proposed BGEO-TVFL has achieved a better result than existing methods and is suitable for dealing with dimensionality reduction issues.

Health Disparities in Pharmacy Practice Within the Community: Let's Brainstorm for Solutions.

Health disparity is defined as a type of health difference that is closely linked with social, economic and/or environmental disadvantage. Over the past two decades, major efforts have been undertaken to mitigate health disparities and promote health equity in the United States. Within pharmacy practice, health disparities have also been identified to play a role in influencing pharmacists' practice across various clinical settings. However, well-characterized solutions to address such disparities, particularly within pharmacy practice, are lacking in the literature. Recognizing that a significant amount of work will be necessary to reduce or eliminate health disparities, the University of California, Irvine (UCI) School of Pharmacy and Pharmaceutical Sciences held a webinar in June 2021 to explore pertinent issues related to this topic. During the session, participants were given the opportunity to propose and discuss innovative solutions to overcome health disparities in pharmacy practice. The goal of this perspective article is to distill the essence of the presentations and discussions from this interactive session, and to synthesize ideas for practical solutions that can be translated to practice to address this public health problem.

Prediction of of heart diseases utilising support vector machine and artificial neural network

The heart, <span lang="EN-US">like a pump, is an organ about the size of a fist, mainly composed of muscle and connective tissue that functions to distribute blood to tissues. The heart is located under the rib cage, above the diaphragm between the lungs, slightly closer to the left. Sometimes a small, unexpected problem with the veins or the valves that supply the heart affects a person's life and can lead to death. Early diagnosis is essential to predict diseases that affect the human heart and lead people to live another period of life. In this context, the authors introduce two methods for early diagnosis of heart disease, the support vector machine and artificial neural network. The medical data is taken from the University of California Irvine (UCI) Machine Learning Repository database, and it contains reports of 170 people. The investigation results confirm that the optimal execution is the support vector machine technique. It gives high-accuracy prediction results. As for the performance of the forward propagation artificial neural networks (ANN) technique is acceptable.</span>

Multi-Objective Feature Selection With Missing Data in Classification

Feature selection (FS) is an important research topic in machine learning. Usually, FS is modelled as a bi-objective optimization problem whose objectives are: 1) classification accuracy; 2) number of features. One of the main issues in real-world applications is missing data. Databases with missing data are likely to be unreliable. Thus, FS performed on a data set missing some data is also unreliable. In order to directly control this issue plaguing the field, we propose in this study a novel modelling of FS: we include reliability as the third objective of the problem. In order to address the modified problem, we propose the application of the non-dominated sorting genetic algorithm-III (NSGA-III). We selected six incomplete data sets from the University of California Irvine (UCI) machine learning repository. We used the mean imputation method to deal with the missing data. In the experiments, k-nearest neighbors (K-NN) is used as the classifier to evaluate the feature subsets. Experimental results show that the proposed three-objective model coupled with NSGA-III efficiently addresses the FS problem for the six data sets included in this study.

Construction of Community Medical Communication Service and Rehabilitation Model for Elderly Patients under the Internet of Things.

The objective of this study was to discuss the health management of elderly patients in the community and the management of community rehabilitation under the support of the new Internet of Things (IoT). The IoT technology was adopted to monitor the wearable devices through mobile medical physiological data. The heart rate, blood pressure, respiratory rate, and other physiological indicators of the elderly were collected in real time. The support vector machine (SVM) algorithm was selected as the core algorithm for the elderly physiological index disease risk assessment, the fuzzy comprehensive evaluation method was adopted as the core method of the elderly disease risk quantitative assessment model to process the physiological indicators, and finally, a reasonable physiological index processing model and quantitative indicators of disease risk were obtained. The data on vascular disease were selected from the MIMIC database. In addition, the advantages and disadvantages of the SVM algorithm and the Backpropagation Neural Network (BPNN) algorithm were compared and analysed. The final verification results showed that the fusion accuracy of the SVM processing MIMIC database and the University of California Irvine (UCI) dataset was 0.8327 and 0.8045, respectively, while the fusion accuracy of the BPNN algorithm in processing the same data was 0.7792 and 0.7288, respectively. It was obvious that the fusion accuracy of the SVM algorithm was higher than that of the BPNN algorithm, and the accuracy difference of the SVM algorithm was lower than that of the BPNN algorithm in different groups of data. In the verification of the elderly disease risk quantitative assessment model, the results were consistent with the selected data, which verified the effectiveness of the design model in this study. Therefore, it can be used as a quantitative assessment model of general elderly physiological indicators of disease risk and can be applied to the community medical communication management system. It proved that the model of medical communication and rehabilitation services for elderly patients in the community constructed in this study can definitely help the development of community service for the elderly.

Identifying the outlier in tunnel monitoring data: An integration model

Structural health monitoring (SHM) system based on the Internet of Things is an important method to evaluate the safety of tunnel operation through the real-time monitoring data analysis. Identifying the outlier in SHM data is a non-trivial task but it is challenging for the tunnel engineers because the measurements are quite complicated with the characteristics of time series, unlabeled, high-dimensional, inter-correlations between variables, etc. To detect the outliers, an integration model is developed based on the independent data analysis from the Probabilistic, Proximity-Based (global), Proximity-Based (local), Linear Model and Outlier Ensembles. The model is examined with the shuttle data set in the University of California Irvine (UCI) database and its precision rate is up to 94.5%, highlighting the favorable performance in identifying the outliers. This method is thus applied to the outlier detection of the SHM data in the Nanjing Yangtze River tunnel. 6698 data sets collected from SHM are evaluated and 270 groups of outliers are identified effectively. By eliminating these outliers, comparisons between the proposed integrated model and the single model (i.e. IForest, ABOD, KNN, LOF) are further conducted to discuss the model performance based on the regression analysis. Results show that the integrated model is better than the single model and it possesses the great potential to detect the outliers in SHM system.

A hybrid clustering algorithm based on improved GWO and KHM clustering

To solve the problem that the K-means algorithm is sensitive to the initial clustering centers and easily falls into local optima, we propose a new hybrid clustering algorithm called the IGWOKHM algorithm. In this paper, we first propose an improved strategy based on a nonlinear convergence factor, an inertial step size, and a dynamic weight to improve the search ability of the traditional grey wolf optimization (GWO) algorithm. Then, the improved GWO (IGWO) algorithm and the K-harmonic means (KHM) algorithm are fused to solve the clustering problem. This fusion clustering algorithm is called IGWOKHM, and it combines the global search ability of IGWO with the local fast optimization ability of KHM to both solve the problem of the K-means algorithm’s sensitivity to the initial clustering centers and address the shortcomings of KHM. The experimental results on 8 test functions and 4 University of California Irvine (UCI) datasets show that the IGWO algorithm greatly improves the efficiency of the model while ensuring the stability of the algorithm. The fusion clustering algorithm can effectively overcome the inadequacies of the K-means algorithm and has a good global optimization ability.

Robust Maximum Mixture Correntropy Criterion Based One-Class Classification Algorithm

One-class classification achieves anomaly/outlier detection by exploiting the characteristics of target data. As a local similarity measure defined in kernel space, correntropy is generally more robust than the mean square error (MSE) based criterion in dealing with large outliers. In this article, the maximum mixture correntropy criterion (MMCC) with multiple kernels are applied to the shallow and hierarchical one-class extreme learning machine to enhance the model robustness and learning speed. Experiments on benchmark University of California, Irvine (UCI) classification datasets, urban acoustic classification dataset, and four synthetic datasets are carried out to show the effectiveness and comparisons with several state-of-the-art methods are provided to demonstrate the superiority of the proposed algorithms.