Partial Discharge Diagnostics: Data Cleaning and Feature Extraction

Detection of partial discharge (PD) in switchgears requires extensive data collection and time-consuming analyses. Data from real live operational environments pose great challenges in the development of robust and efficient detection algorithms due to overlapping PDs and the strong presence of random white noise. This paper presents a novel approach using clustering for data cleaning and feature extraction of phase-resolved partial discharge (PRPD) plots derived from live operational data. A total of 452 PRPD 2D plots collected from distribution substations over a six-month period were used to test the proposed technique. The output of the clustering technique is evaluated on different types of machine learning classification techniques and the accuracy is compared using balanced accuracy score. The proposed technique extends the measurement abilities of a portable PD measurement tool for diagnostics of switchgear condition, helping utilities to quickly detect potential PD activities with minimal human manual analysis and higher accuracy.

The Role of Structure MRI in Diagnosing Autism

This study proposes a Computer-Aided Diagnostic (CAD) system to diagnose subjects with autism spectrum disorder (ASD). The CAD system identifies morphological anomalies within the brain regions of ASD subjects. Cortical features are scored according to their contribution in diagnosing a subject to be ASD or typically developed (TD) based on a trained machine-learning (ML) model. This approach opens the hope for developing a new CAD system for early personalized diagnosis of ASD. We propose a framework to extract the cerebral cortex from structural MRI as well as identifying the altered areas in the cerebral cortex. This framework consists of the following five main steps: (i) extraction of cerebral cortex from structural MRI; (ii) cortical parcellation to a standard atlas; (iii) identifying ASD associated cortical markers; (iv) adjusting feature values according to sex and age; (v) building tailored neuro-atlases to identify ASD; and (vi) artificial neural networks (NN) are trained to classify ASD. The system is tested on the Autism Brain Imaging Data Exchange (ABIDE I) sites achieving an average balanced accuracy score of 97±2%. This paper demonstrates the ability to develop an objective CAD system using structure MRI and tailored neuro-atlases describing specific developmental patterns of the brain in autism.

Machine Learning and In Vitro Chemical Screening of Potential α-Amylase and α-Glucosidase Inhibitors from Thai Indigenous Plants

Diabetes mellitus is a major predisposing factor for cardiovascular disease and mortality. α-Amylase and α-glucosidase enzymes are the rate-limiting steps for carbohydrate digestion. The inhibition of these two enzymes is clinically used for the treatment of diabetes mellitus. Here, in vitro study and machine learning models were employed for the chemical screening of inhibiting the activity of 31 plant samples on α-amylase and α-glucosidase enzymes. The results showed that the ethanolic twig extract of Pinus kesiya had the highest inhibitory activity against the α-amylase enzyme. The respective ethanolic extract of Croton oblongifolius stem, Parinari anamense twig, and Polyalthia evecta leaf showed high inhibitory activity against the α-glucosidase enzyme. The classification analysis revealed that the α-glucosidase inhibitory activity of Thai indigenous plants was more predictive based on phytochemical constituents, compared with the α-amylase inhibitory activity (1.00 versus 0.97 accuracy score). The correlation loading plot revealed that flavonoids and alkaloids contributed to the α-amylase inhibitory activity, while flavonoids, tannins, and reducing sugars contributed to the α-glucosidase inhibitory activity. In conclusion, the ethanolic extracts of P. kesiya, C. oblongifolius, P. anamense, and P. evecta have the potential for further chemical characterization and the development of anti-diabetic recipes.

Analysis of Social Media Users Sentiments against Omnibus Law Based on Hashtags on Twitter

From the research that has been done, it can be concluded that Sentiment Analysis can be used to know the sentiment of the public, especially Twitter netizens against omnibus law. After the sentiment analysis, it looks neutral artmen with the largest percentage of 55%, then positive sentiment by 35% and negative sentiment by 10%. The results of the analysis showed that the Naïve Bayes Classifier method provides classification test results with accuracy in Hashtag Pro with an average accuracy score of 92.1%, precision values with an average of 94.8% and recall values with an average of 90.7%. While Hashtag Counter For data classification, with an average accuracy value of 98.3%, precision value with an average of 97.6% and recall value with an average of 98.7%. The result of text cloud analysis conducted on a combination of hashtags both Hashtag pros and Hashtags cons, the dominant word appears is Omnibus Law which means that all hashtags in scrap is really discussing the main topic that is about Omnibus Law

Analisis Sentimen Kinerja Dewan Perwakilan Rakyat (DPR) Pada Twitter Menggunakan Metode Naive Bayes Classifier

Abstrak~Dalam penelitian ini akan dilakukan analisis sentimen masyarakat terhadap kinerja Dewan Perwakilan Rakyat (DPR) yang diungkapkan melalui media sosial twitter. Ada beberapa tahap untuk melakukan analisis sentimen , yaitu pengumpulan data (crawling), preporcessing data yang terdiri dari proses cleaning data, tokenization, stop remova dan case folding, splitting data dan klasifikasi data menggunakan metode Naive Bayes Classifier. Penelitian ini menggunakan sebanyak 1546 data tweet. Hasil dari penelitian ini didapatkan bahwa DPR mendapatkan 95 tweet positif dengan polaritas 0.75 atau 75% sentimen positif, 693 tweet netral dengan polaritas 0.79 atau 79% sentimen netral dan 758 tweet negatif dengan polaritas 0.82 atau 82% sentimen negatif dengan accuracy score 0.8 atau 80% berdasarkan data testing sebanyak 20%.Kata kunci : Sentiment Analysis, DPR, Naive Bayes Classifier

Hate Speech Detection on Twitter in Indonesia with Feature Expansion Using GloVe

Twitter is one of the popular social media to channel opinions in the form of criticism and suggestions. Criticism could be a form of hate speech if the criticism implies attacking something (an individual, race, or group). With the limit of 280 characters in a tweet, there is often a vocabulary mismatch due to abbreviations which can be solved with word embedding. This study utilizes feature expansion to reduce vocabulary mismatches in hate speech on Twitter containing Indonesian language by using Global Vectors (GloVe). Feature selection related to the best model is carried out using the Logistic Regression (LR), Random Forest (RF), and Artificial Neural Network (ANN) algorithms. The results show that the Random Forest model with 5.000 features and a combination of TF-IDF and Tweet corpus built with GloVe produce the best accuracy rate between the other models with an average of 88,59% accuracy score, which is 1,25% higher than the predetermined Baseline. The number of features used is proven to improve the performance of the system.

Physical Activity Classification with Wearable Sensor Data in an eCoach Recommendation System (Preprint)

UNSTRUCTURED Leading a sedentary lifestyle may cause numerous health problems. Therefore, sedentary lifestyle changes should be given priority to avoid severe damage. Research in eHealth can provide methods to enrich personal healthcare with Information and Communication Technologies (ICTs). An eCoach system may allow people to manage a healthy lifestyle with health state monitoring and personalized recommendations. Using machine learning (ML) techniques, this study investigated the possibility of classifying daily physical activity for adults into the following classes - sedentary, low active, active, active, highly active, and rigorous active. The daily total step count, total daily minutes of sedentary time, low physical activity (LPA), medium physical activity (MPA), and vigorous physical activity (VPA) served as input for the classification models. We first used publicly available Fitbit data to build the classification models. Second, using the transfer learning approach, we re-used the top five best-performing models on a real dataset as collected from the MOX2-5 wearable medical-grade activity sensor. We found that ensemble ExtraTreesClassifier with an estimator value of 150 outperformed other classifiers with a mean accuracy score of 99.72% for single feature and support vector classifier (SVC) with “linear” kernel outpaced other classifiers with a mean accuracy score of 99.14% for five features, for the public Fitbit datasets. To demonstrate the practical usefulness of the classifiers, we conceptualized how the classifier model can be used in an eCoach prototype system to attain personalized activity goals (e.g., stay active for the entire week). After transfer learning, K-Nearest-Neighbor (KNN) outpaced the other four classifiers for a single feature, and SVC with a “linear” kernel outdid the other four classifiers for multiple features.

The Automatic Classification of Pyriproxyfen-Affected Mosquito Ovaries

Pyriproxyfen (PPF) may become an alternative insecticide for areas where pyrethroid-resistant vectors are prevalent. The efficacy of PPF can be assessed through the dissection and assessment of vector ovaries. However, this reliance on expertise is subject to limitations. We show here that these limitations can be overcome using a convolutional neural network (CNN) to automate the classification of egg development and thus fertility status. Using TensorFlow, a resnet-50 CNN was pretrained with the ImageNet dataset. This CNN architecture was then retrained using a novel dataset of 524 dissected ovary images from An. gambiae s.l. An. gambiae Akron, and An. funestus s.l., whose fertility status and PPF exposure were known. Data augmentation increased the training set to 6973 images. A test set of 157 images was used to measure accuracy. This CNN model achieved an accuracy score of 94%, and application took a mean time of 38.5 s. Such a CNN can achieve an acceptable level of precision in a quick, robust format and can be distributed in a practical, accessible, and free manner. Furthermore, this approach is useful for measuring the efficacy and durability of PPF treated bednets, and it is applicable to any PPF-treated tool or similarly acting insecticide.

Brain Tumor Classification using Machine Learning

This paper presents a technical analysis of tumor data with Machine Learning and Classification Approach. Feature parameters which are dependent for classification of tumor are used for analyzing and classifying the class of tumor. In the classification of tumor, KNN-Classifier is implemented with cross validating accuracy score and tuning hyper parameters. Experimental simulation for best average score for K makes it to the cross validation. Approaching the prediction with the best accuracy score, hyper parameters of KNN Classifier states the best score. Using Principal Component Analysis on the data, miss-classification of tumor class in data is visualized. Aims: To declare and analyse tumor data from the source of MRI, CT scan, etc. for medication of tumor. To utilize smart predictions for the upcoming tumor patients using Machine Learning. Study Design: Tumor classification using K Nearest Neighbor algorithm and analysis of the miss-classification. Methodology: We included 11 different studies and research papers which were relevant with tumor classification. Research papers include classification of tumors with different supervised learning approaches. Our proposed analysis and classification give visualization of two classes of tumor. Results: The Project results in classification of tumor data using Machine Learning and analyzing the miss-classification of tumor. In implementation of KNN Algorithm, the accuracy score after cross validation and tuning K values is 0.97. The confusion matrix shows 4 false positives and 1 false negative value in testing. Conclusion: Less miss-classification of tumor results best accuracy score and more efficient working on testing data. Visualizing the classification with 3-dimensional scatter plots made the analysis accurate.

Fake News detection using n-grams for PAN@CLEF competition

The paper presents a classifier for fake news spreaders detection in social media. Detecting fake news spreaders is an important task because this kind of disinformation aims to change the reader’s opinion about a relevant topic for the society. This work presents a classifier that can compete with the ones that are found in the state-of-the-art. In addition, this work applies Explainable Artificial Intelligence (XIA) methods in order to understand the corpora used and how the model estimates results. The work focuses on the corpora developed by members of the PAN@CLEF 2020 competition. The score obtained surpasses the state-of-the-art with a mean accuracy score of 0.7825. The solution uses XIA methods for the feature selection process, since they present more stability to the selection than most of traditional feature selection methods. Also, this work concludes that the detection done by the solution approach is generally based on the topic of the text.