Stroke is a sudden interruption in the blood flow to a portion of the brain that can result in the loss of capacity to move certain parts of the body. In this work, all elements that impact this disease are studied, their influences are extracted using exploratory data analysis, and a model is constructed to forecast the disease's likely existence in a patient. Using under sampling and over sampling strategies, several data balancing techniques are used to increase model performance. As a consequence of the findings, a 98 percent accuracy rate has been achieved compared to earlier research. While the class distribution is severely skewed, there are relatively few examples of a class. This study reveals that over-sampling approaches yield better results than under-sampling ones. When sampling-based techniques are used instead of sampling-based approaches, the outcomes improve by 46%. 

Analysis of Uneven Stroke Prediction Dataset using Machine Learning

There has recently been increasing interest in postural stability aimed at gaining a better understanding of the human postural system. This system controls human balance in quiet standing and during locomotion. Parkinson’s disease (PD) is the most common degenerative movement disorder that affects human stability and causes falls and injuries. This paper proposes a novel methodology to differentiate between healthy individuals and those with PD through the empirical mode decomposition (EMD) method. EMD enables the breaking down of a complex signal into several elementary signals called intrinsic mode functions (IMFs). Three temporal parameters and three spectral parameters are extracted from each stabilometric signal as well as from its IMFs. Next, the best five features are selected using the feature selection method. The classification task is carried out using four known machine-learning methods, KNN, decision tree, Random Forest and SVM classifiers, over 10-fold cross validation. The used dataset consists of 28 healthy subjects (14 young adults and 14 old adults) and 32 PD patients (12 young adults and 20 old adults). The SVM method has a performance of 92% and the Dempster–Sahfer formalism method has an accuracy of 96.51%.

/pdf/emd-based-method-for-supervised-classification-of-parkinsons-1kq7q1q2.pdf

EMD-Based Method for Supervised Classification of Parkinson’s Disease Patients Using Balance Control Data

Chaos plays a prominent role in nonlinear systems like energy, finance, and weather. In these systems, a changing parameter to time yields a chaotic time series that contains a lot of system information. This information helps to analyze and understand the behavior of the chaotic system. However, traditional methods of investigating these chaotic time series have low prediction accuracy. Recently, various researchers have got interested in applying machine learning models for these time series. Accordingly, this study has developed two machine learning models using LSTM and NAR neural networks to forecast monthly smoothed sunspot number time series. Further, Adam and Levenberg-Marquardt algorithms are utilized for LSTM and NAR neural networks during the training process. Besides, mean square error and <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathrm{R}^{2}$</tex> are used to assess the proposed models' performance. The simulation results demonstrated that the developed prediction models have successfully predicted the sunspot number. 

Time Series Forecasting Model for Sunspot Number

Sparse arrays with low cost and engineering complexity are widely applied in many fields. However, the high peak sidelobe level (PSLL) of a sparse array causes the degradation of weak target detection performance. Particularly for the large size of underwater low-frequency sensors, the design problem requires a minimum spacing constraint, which further increases the difficulty of PSLL suppression. In this paper, a novel swarm-intelligence-based approach for sparse sensor array design is proposed to reduce PSLL under spacing constrains. First, a global enhancement whale optimization algorithm (GEWOA) is introduced to improve the global search capability for optimal arrays. A three-step enhanced strategy is used to enhance the ergodicity of element positions over the aperture. In order to solve the adaptation problem for discrete array design, a position decomposition method and a V-shaped transfer function are introduced into off-grid and on-grid arrays, respectively. The effectiveness and superiority of the proposed approach is validated using experiments for designing large-scale low-frequency arrays in the marine environment. The PSLL of the off-grid array obtained by GEWOA was nearly 3.8 dB lower than that of WOA. In addition, compared with other intelligent algorithms, the on-grid array designed using GEWOA had the lowest PSLL.

/pdf/underwater-sparse-acoustic-sensor-array-design-under-spacing-24eb8i8w.pdf

Underwater Sparse Acoustic Sensor Array Design under Spacing Constraints Based on a Global Enhancement Whale Optimization Algorithm

Chaos plays a prominent role in nonlinear systems like energy, finance, and weather. In these systems, a changing parameter to time yields a chaotic time series that contains a lot of system information. This information helps to analyze and understand the behavior of the chaotic system. However, traditional methods of investigating these chaotic time series have low prediction accuracy. Recently, various researchers have got interested in applying machine learning models for these time series. Accordingly, this study has developed two machine learning models using LSTM and NAR neural networks to forecast monthly smoothed sunspot number time series. Further, Adam and Levenberg-Marquardt algorithms are utilized for LSTM and NAR neural networks during the training process. Besides, mean square error and $\mathrm{R}^{2}$ are used to assess the proposed models' performance. The simulation results demonstrated that the developed prediction models have successfully predicted the sunspot number.

This paper focuses on developing a prediction model to predict heart stroke using the parameters, namely, age, hypertension, previous heart disease status, average body glucose level, BMI, and smoking status. The prediction model is developed using a support vector machine (SVM) algorithm. Further, the SVM algorithm with various decision boundaries like linear, quadratic, and cubic are also produced. The performance prediction results show that the linear and quadratic SVM has performed better in predicting the heart stoke with greater accuracy values. This is true for both the male and female databases during training and testing.

Prediction of Heart Stroke Using Support Vector Machine Algorithm

This paper focuses on developing a weather prediction model to predict temperature and humidity. Further, a classification model is also extended to predict the weather condition using the expected model’s output. The proposed hybrid model can predict the temperature and humidity and forecast future weather conditions. The prediction and classification models are created using neural networks and k-nearest neighbors, respectively. The prediction model’s results have shown the best ability for both the output variables (temperature and humidity) with R2 values close to one and MSE values close to zero. Further, the classification model’s results also showed better execution in classifying the weather conditions with the highest accuracy values.

Weather Prediction and Classification Using Neural Networks and k-Nearest Neighbors

The principal focus of this paper is to develop a prediction model to predict the turbidity of beach waves. The prediction model is developed using a nonlinear autoregressive neural network model using three input parameters: water temperature, wave height, and wave period. The beach wave turbidity is predicted without installing any additional sensors. The performance of the developed model is evaluated on three beaches in Chicago Park’s district. The proposed model performance showed better tracking ability for all the three considered beaches. The R2 and mean square errors MSE also confirm the best prediction model’s performance for both training and testing.

Prediction of Turbidity in Beach Waves Using Nonlinear Autoregressive Neural Networks

This paper focuses on developing an adaptive weighted whale optimization algorithm that helps avoid the getting trap at local minima during the convergence. The adaptive weight during each iteration of the algorithm also helps achieve optimal solutions during exploration and exploitation. Further, various adaptive weights, including the chaotic consequences and traditional algorithm, are executed on multiple benchmark functions. The statistical results determined in terms of mean, best and standard deviation depict that the proposed adaptive weighted algorithm performs a higher level than conventional and chaotic weighted algorithms. The results also highlighted that the developed technique showed preferable performance for most minor functions than the traditional technique on achieving the worst global minima.

Design of Adaptive Weighted Whale Optimization Algorithm

This paper focuses on developing an adaptation algorithm for hypotrochoid spiral dynamic optimization using linear adaptive spiral radius and angle by dynamically varying the value for each iteration based on the fitness function value. The adaptive algorithm will help obtain the optimal search point compared to fixed radius and angle in conventional methods. The spiral radius and angle effect show that the spiral movement with a negative radius will boost the process of escaping from converging at local optima. The statistical results on various benchmark functions show that the proposed optimization has performed better than spiral dynamic, adaptive spiral dynamic, and hypotrochoid spiral dynamic algorithms.

Harshita Puri

Papers

Prediction of Heart Stroke Using Support Vector Machine Algorithm

Weather Prediction and Classification Using Neural Networks and k-Nearest Neighbors

Prediction of Turbidity in Beach Waves Using Nonlinear Autoregressive Neural Networks

Design of Adaptive Weighted Whale Optimization Algorithm

Adaptation of Spiral Radius and Angle in Hypotrochoid Spiral Dynamic Algorithm