Arabic Handwritten Word Recognition Based on Stationary Wavelet Transform Technique using Machine Learning

This paper is aimed at improving the performance of the word recognition system (WRS) of handwritten Arabic text by extracting features in the frequency domain using the Stationary Wavelet Transform (SWT) method using machine learning, which is a wavelet transform approach created to compensate for the absence of translation invariance in the Discrete Wavelets Transform (DWT) method. The proposed SWT-WRS of Arabic handwritten text consists of three main processes: word normalization, feature extraction based on SWT, and recognition. The proposed SWT-WRS based on the SWT method is evaluated on the IFN/ENIT database applying the Gaussian, linear, and polynomial support vector machine, the k-nearest neighbors, and ANN classifiers. ANN performance was assessed by applying the Bayesian Regularization (BR) and Levenberg-Marquardt (LM) training methods. Numerous wavelet transform (WT) families are applied, and the results prove that level 19 of the Daubechies family is the best WT family for the proposed SWT-WRS. The results also confirm the effectiveness of the proposed SWT-WRS in improving the performance of handwritten Arabic word recognition using machine learning. Therefore, the suggested SWT-WRS overcomes the lack of translation invariance in the DWT method by eliminating the up-and-down samplers from the proposed machine learning method.

CityLightSense: A Participatory Sensing-based System for Monitoring and Mapping of Illumination levels

Adequate nighttime lighting of city streets is necessary for safe vehicle and pedestrian movement, deterrent of crime, improvement of the citizens’ perceptions of safety, and so on. However, monitoring and mapping of illumination levels in city streets during the nighttime is a tedious activity that is usually based on manual inspection reports. The advancement in smartphone technology comes up with a better way to monitor city illumination using a rich set of smartphone-equipped inexpensive but powerful sensors (e.g., light sensor, GPS, etc). In this context, the main objective of this work is to use the power of smartphone sensors and IoT-cloud-based framework to collect, store, and analyze nighttime illumination data from citizens to generate high granular city illumination map. The development of high granular illumination map is an effective way of visualizing and assessing the illumination of city streets during nighttime. In this article, an illumination mapping algorithm called Street Illumination Mapping is proposed that works on participatory sensing-based illumination data collected using smartphones as IoT devices to generate city illumination map. The proposed method is evaluated on a real-world illumination dataset collected by participants in two different urban areas of city Kolkata. The results are also compared with the baseline mapping techniques, namely, Spatial k-Nearest Neighbors, Inverse Distance Weighting, Random Forest Regressor, Support Vector Regressor, and Artificial Neural Network.

Behavioral biometric based personal authentication in feature phones

<p><span>The usage of mobile phones has increased multifold in the recent decades mostly because of its utility in most of the aspects of daily life, such as communications, entertainment, and financial transactions. Feature phones are generally the keyboard based or lower version of touch based mobile phones, mostly targeted for efficient calling and messaging. In comparison to smart phones, feature phones have no provision of a biometrics system for the user access. The literature, have shown very less attempts in designing a biometrics system which could be most suitable to the low-cost feature phones. A biometric system utilizes the features and attributes based on the physiological or behavioral properties of the individual. In this research, we explore the usefulness of keystroke dynamics for feature phones which offers an efficient and versatile biometric framework. In our research, we have suggested an approach to incorporate the user’s typing patterns to enhance the security in the feature phone. We have applied k-nearest neighbors (k-NN) with fuzzy logic and achieved the equal error rate (EER) 1.88% to get the better accuracy. The experiments are performed with 25 users on Samsung On7 Pro C3590. On comparison, our proposed technique is competitive with almost all the other techniques available in the literature.</span></p>

Sentiment analysis on film review in Gujarati language using machine learning

<span>Opinion analysis is by a long shot most basic zone of characteristic language handling. It manages the portrayal of information to choose the motivation behind the wellspring of the content. The reason might be of a type of gratefulness (positive) or study (negative). This paper offers a correlation between the outcomes accomplished by applying the calculation arrangement using various classifiers for instance K-nearest neighbor and multinomial naive Bayes. These techniques are utilized to assess a significant assessment with either a positive remark or negative remark. The gathered information considered on the grounds of the extremity film datasets and an association with the results accessible proof has been created for a careful assessment. This paper investigates the word level count vectorizer and term frequency inverse document frequency (TF-IDF) influence on film sentiment analysis. We concluded that multinomial Naive Bayes (MNB) classier generate more accurate result using TF-IDF vectorizer compared to CountVectorizer, K-nearest-neighbors (KNN) classifier has the same accuracy result in case of TF-IDF and CountVectorizer.</span>

Improving Site-Dependent Wind Turbine Performance Prediction Accuracy Using Machine Learning

Data-driven wind turbine performance predictions, such as power and loads, are important for planning and operation. Current methods do not take site-specific conditions such as turbulence intensity and shear into account, which could result in errors of up to 10%. In this work, four different machine learning models (k-nearest neighbors regression, random forest regression, extreme gradient boosting regression and artificial neural networks (ANN) are trained and tested, firstly on a simulation dataset and then on a real dataset. It is found that machine learning methods that take site-specific conditions into account can improve prediction accuracy by a factor of two to three, depening on the error indicator chosen. Similar results are observed for multi-output ANNs for simulated in- and out-of-plane rotor blade tip deflection and root loads. Future work focuses on understanding transferability of results between different turbines within a wind farm and between different wind turbine types.

Application of Deep Learning and Symmetrized Dot Pattern to Detect Surge Arrester Status

Surge arresters primarily restrain lightning and switch surges in the power system to avoid damaging power equipment. When a surge arrester fails, it leads to huge damage to the power equipment. Therefore, this study proposed the application of a convolutional neural network (CNN) combined with a symmetrized dot pattern (SDP) to detect the state of the surge arrester. First, four typical fault types were constructed for the 18 kV surge arrester, including its normal state, aging of the internal valve, internal humidity, and salt damage to the insulation. Then, the partial discharge signal was measured and extracted using a high-speed data acquisition (DAQ) card, while a snowflake map was established by SDP for the features of each fault type. Finally, CNN was used to detect the status of the surge arrester. This study also used a histogram of oriented gradient (HOG) with support vendor machine (SVM), backpropagation neural network (BPNN), and k-nearest neighbors (KNN) for image feature extraction and identification. The result shows that the proposed method had the highest accuracy at 97.9%, followed by 95% for HOG + SVM, 94.6% for HOG + BPNN, and 91.2% for HOG + KNN. Therefore, the proposed method can effectively detect the fault status of surge arresters.

AI-Based Quantification of Fitness Activities Using Smartphones

To encourage more active activities that have the potential to significantly reduce the risk of people’s health, we aim to develop an AI-based mobile app to identify four gym activities accurately: ascending, cycling, elliptical, and running. To save computational cost, the present study deals with the dilemma of the performance provided by only a phone-based accelerometer since a wide range of activity recognition projects used more than one sensor. To attain this goal, we derived 1200 min of on-body data from 10 subjects using their phone-based accelerometers. Subsequently, three subtasks have been performed to optimize the performances of the K-nearest neighbors (KNN), Support Vector Machine (SVM), Shallow Neural Network (SNN), and Deep Neural Network (DNN): (1) During the process of the raw data converted to a 38-handcrafted feature dataset, different window sizes are used, and a comparative analysis is conducted to identify the optimal one; (2) principal component analysis (PCA) is adopted to extract the most dominant information from the 38-feature dataset described to a simpler and smaller size representation providing the benefit of ease of interpreting leading to high accuracy for the models; (3) with the optimal window size and the transformed dataset, the hyper-parameters of each model are tuned to optimal inferring that DNN outperforms the rest three with a testing accuracy of 0.974. This development can be further implemented in Apps Store to enhance public usage so that active physical human activities can be promoted to enhance good health and wellbeing in accordance with United Nation’s sustainable development goals.

A Machine Learning Analysis of COVID-19 Mental Health Data

In late December 2019, the novel coronavirus (Sars-Cov-2) and the resulting disease COVID-19 were first identified in Wuhan China. The disease slipped through containment measures, with the first known case in the United States being identified on January 20th, 2020. In this paper, we utilize survey data from the Inter-university Consortium for Political and Social Research and apply several statistical and machine learning models and techniques such as Decision Trees, Multinomial Logistic Regression, Naive Bayes, k-Nearest Neighbors, Support Vector Machines, Neural Networks, Random Forests, Gradient Tree Boosting, XGBoost, CatBoost, LightGBM, Synthetic Minority Oversampling, and Chi-Squared Test to analyze the impacts the COVID-19 pandemic has had on the mental health of frontline workers in the United States. Through the interpretation of the many models applied to the mental health survey data, we have concluded that the most important factor in predicting the mental health decline of a frontline worker is the healthcare role the individual is in (Nurse, Emergency Room Staff, Surgeon, etc.), followed by the amount of sleep the individual has had in the last week, the amount of COVID-19 related news an individual has consumed on average in a day, the age of the worker, and the usage of alcohol and cannabis.

Supervised Classification of Operator Functional State Based on Physiological Data: Application to Drones Swarm Piloting

To improve the safety and the performance of operators involved in risky and demanding missions (like drone operators), human-machine cooperation should be dynamically adapted, in terms of dialogue or function allocation. To support this reconfigurable cooperation, a crucial point is to assess online the operator’s ability to keep performing the mission. The article explores the concept of Operator Functional State (OFS), then it proposes to operationalize this concept (combining context and physiological indicators) on the specific activity of drone swarm monitoring, carried out by 22 participants on simulator SUSIE. With the aid of supervised learning methods (Support Vector Machine, k-Nearest Neighbors, and Random Forest), physiological and contextual are classified into three classes, corresponding to different levels of OFS. This classification would help for adapting the countermeasures to the situation faced by operators.

Constrained ESKF for UAV Positioning in Indoor Corridor Environment Based on IMU and WiFi

The indoor autonomous navigation of unmanned aerial vehicles (UAVs) is the current research hotspot. Unlike the outdoor broad environment, the indoor environment is unknown and complicated. Global Navigation Satellite System (GNSS) signals are easily blocked and reflected because of complex indoor spatial features, which make it impossible to achieve positioning and navigation indoors relying on GNSS. This article proposes a set of indoor corridor environment positioning methods based on the integration of WiFi and IMU. The zone partition-based Weighted K Nearest Neighbors (WKNN) algorithm is used to achieve higher WiFi-based positioning accuracy. On the basis of the Error-State Kalman Filter (ESKF) algorithm, WiFi-based and IMU-based methods are fused together and realize higher positioning accuracy. The probability-based optimization method is used for further accuracy improvement. After data fusion, the positioning accuracy increased by 51.09% compared to the IMU-based algorithm and by 66.16% compared to the WiFi-based algorithm. After optimization, the positioning accuracy increased by 20.9% compared to the ESKF-based data fusion algorithm. All of the above results prove that methods based on WiFi and IMU (low-cost sensors) are very capable of obtaining high indoor positioning accuracy.