Invisible experience to real-time assessment in elite tennis athlete training: Sport-specific movement classification based on wearable MEMS sensor data

This study examined the reliability of a tennis stroke classification and assessment platform consisting of a single low-cost MEMS sensor in a wrist-worn wearable device, smartphone, and computer. The data that was collected was transmitted via Bluetooth and analyzed by machine learning algorithms. Twelve right-handed male elite tennis athletes participated in the study, and each athlete performed 150 strokes. The results from three machine learning algorithms regarding their recognition and classification of the real-time data stream were compared. Stroke recognition and classification went through pre-processing, segmentation, feature extraction, and classification with Support Vector Machine (SVM), including SVM without normalization, SVM with Min–Max, SVM with Z-score normalization, K-nearest neighbor (K-NN), and Naive Bayes (NB) machine learning algorithms. During the data training process, 10-fold cross-validation was used to avoid overfitting and suitable parameters were found within the SVM classifiers. The best classifier was achieved when C = 1 using the RBF kernel function. Different machine learning algorithms’ classification of unique stroke types yielded highly reliable clusters within each stroke type with the highest test accuracy of 99% achieved by SVM with Min–Max normalization and 98.4% achieved using SVM with a Z-score normalization classifier.

Peningkatan Hasil Klasifikasi pada Algoritma Random Forest untuk Deteksi Pasien Penderita Diabetes Menggunakan Metode Normalisasi

Diabetes is a disease caused by high blood sugar in the body or beyond normal limits. Diabetics in Indonesia have experienced a significant increase, Basic Health Research states that diabetics in Indonesia were 6.9% to 8.5% increased from 2013 to 2018 with an estimated number of sufferers more than 16 million people. Therefore, it is necessary to have a technology that can detect diabetes with good performance, accurate level of analysis, so that diabetes can be treated early to reduce the number of sufferers, disabilities, and deaths. The different scale values for each attribute in Gula Karya Medika’s data can complicate the classification process, for this reason the researcher uses two data normalization methods, namely min-max normalization, z-score normalization, and a method without data normalization with Random Forest (RF) as a classification method. Random Forest (RF) as a classification method has been tested in several previous studies. Moreover, this method is able to produce good performance with high accuracy. Based on the research results, the best accuracy is model 1 (Min-max normalization-RF) of 95.45%, followed by model 2 (Z-score normalization-RF) of 95%, and model 3 (without data normalization-RF) of 92%. From these results, it can be concluded that model 1 (Min-max normalization-RF) is better than the other two data normalization models and is able to increase the performance of classification Random Forest by 95.45%.

The Non-Intellectual Norm of Middle School Students’ Mathematics Learning and Its Grade Evaluation Standard: Taking Tianjin as an Example

Using the "Middle School Student Mathematics Learning Non-intellectual Questionnaire," a total of 1,400 middle school students in 11 districts and counties of Tianjin were surveyed. According to the data, using the raw score normalization method and the formula “T = 50+10×Z”, the middle school student mathematics learning non-intellectual population and its sub-dimensions norm table were established the corresponding grade evaluation standard was determined. The results of applied research were analyzed for class and individual application cases, and corresponding suggestions were made based on the analysis results.

Performa Comparison of the K-Means Method for Classification in Diabetes Patients Using Two Normalization Methods

The diabetes classification system is very useful in the health sector. This paper discusses the classification system for diabetes using the K-Means algorithm. The Pima Indian Diabetes (PID) dataset is used to train and evaluate this algorithm. The unbalanced value range in the attributes affects the quality of the classification result, so it is necessary to preprocess the data which is expected to improve the accuracy of the PID dataset classification result. Two types of preprocessing methods are used that are min-max normalization and z-score normalization. These two normalization methods are used and the classification accuracies are compared. Before the data classification process is carried out, the data is divided into training data and test data. The result of the classification test using the K-Means algorithm has shown that the best accuracy lies in the PID dataset which has been normalized using the min-max normalization method, which 79% compared to z-score normalization.

Confound Removal and Normalization in Practice: A Neuroimaging Based Sex Prediction Case Study

Machine learning (ML) methods are increasingly being used to predict pathologies and biological traits using neuroimaging data. Here controlling for confounds is essential to get unbiased estimates of generalization performance and to identify the features driving predictions. However, a systematic evaluation of the advantages and disadvantages of available alternatives is lacking. This makes it difficult to compare results across studies and to build deployment quality models. Here, we evaluated two commonly used confound removal schemes–whole data confound regression (WDCR) and cross-validated confound regression (CVCR)–to understand their effectiveness and biases induced in generalization performance estimation. Additionally, we study the interaction of the confound removal schemes with Z-score normalization, a common practice in ML modelling. We applied eight combinations of confound removal schemes and normalization (pipelines) to decode sex from resting-state functional MRI (rfMRI) data while controlling for two confounds, brain size and age. We show that both schemes effectively remove linear univariate and multivariate confounding effects resulting in reduced model performance with CVCR providing better generalization estimates, i.e., closer to out-of-sample performance than WDCR. We found no effect of normalizing before or after confound removal. In the presence of dataset and confound shift, four tested confound removal procedures yielded mixed results, raising new questions. We conclude that CVCR is a better method to control for confounding effects in neuroimaging studies. We believe that our in-depth analyses shed light on choices associated with confound removal and hope that it generates more interest in this problem instrumental to numerous applications.

Openfinger: Towards a Combination of Discriminative Power of Fingerprints and Finger Vein Patterns in Multimodal Biometric System

Multimodal biometric systems are nowadays considered as state of the art subject. Since identity establishment in everyday situations has become very significant and rather difficult, there is a need for reliable means of identification. Multimodal systems establish identity based on more than one biometric trait. Hence one of their most significant advantages is the ability to provide greater recognition accuracy and resistance against the forgery. Many papers have proposed various combinations of biometric traits. However, there is an inferior number of solutions demonstrating the use of fingerprint and finger vein patterns. Our main goal was to contribute to this particular field of biometrics.In this paper, we propose OpenFinger, an automated solution for identity recognition utilizing fingerprint and finger vein pattern which is robust to finger displacement as well as rotation. Evaluation and experiments were conducted using SDUMLA-HMT multimodal database. Our solution has been implemented using C++ language and is distributed as a collection of Linux shared libraries.First, fingerprint images are enhanced by means of adaptive filtering where Gabor filter plays the most significant role. On the other hand, finger vein images require the bounding rectangle to be accurately detected in order to focus just on useful biometric pattern. At the extraction stage, Level-2 features are extracted from fingerprints using deep convolutional network using a popular Caffe framework. We employ SIFT and SURF features in case of finger vein patterns. Fingerprint features are matched using closed commercial algorithm developed by Suprema, whereas finger vein features are matched using OpenCV library built-in functions, namely the brute force matcher and the FLANN-based matcher. In case of SIFT features score normalization is conducted by means of double sigmoid, hyperbolic tangens, Z-score and Min-Max functions.On the side of finger veins, the best result was obtained by a combination of SIFT features, brute force matcher with scores normalized by hyperbolic tangens method. In the end, fusion of both biometric traits is done on a score level basis. Fusion was done by means of sum and mean methods achieving 2.12% EER. Complete evaluation is presented in terms of general indicators such as FAR/FRR and ROC.