scholarly journals Discrete Human Activity Recognition and Fall Detection by Combining FMCW RADAR Data of Heterogeneous Environments for Independent Assistive Living

Electronics ◽  
2021 ◽  
Vol 10 (18) ◽  
pp. 2237
Author(s):  
Umer Saeed ◽  
Syed Yaseen Shah ◽  
Syed Aziz Shah ◽  
Jawad Ahmad ◽  
Abdullah Alhumaidi Alotaibi ◽  
...  
Keyword(s):  
Human Activity ◽  
Human Activities ◽  
Daily Living ◽  
Continuous Wave ◽  
Learning Algorithm ◽  
Confusion Matrix ◽  
Research Work ◽  
Heterogeneous Environments ◽  
Fmcw Radar ◽  
Unseen Data

Human activity monitoring is essential for a variety of applications in many fields, particularly healthcare. The goal of this research work is to develop a system that can effectively detect fall/collapse and classify other discrete daily living activities such as sitting, standing, walking, drinking, and bending. For this paper, a publicly accessible dataset is employed, which is captured at various geographical locations using a 5.8 GHz Frequency-Modulated Continuous-Wave (FMCW) RADAR. A total of ninety-nine participants, including young and elderly individuals, took part in the experimental campaign. During data acquisition, each aforementioned activity was recorded for 5–10 s. Through the obtained data, we generated the micro-doppler signatures using short-time Fourier transform by exploiting MATLAB tools. Subsequently, the micro-doppler signatures are validated, trained, and tested using a state-of-the-art deep learning algorithm called Residual Neural Network or ResNet. The ResNet classifier is developed in Python, which is utilised to classify six distinct human activities in this study. Furthermore, the metrics used to analyse the trained model’s performance are precision, recall, F1-score, classification accuracy, and confusion matrix. To test the resilience of the proposed method, two separate experiments are carried out. The trained ResNet models are put to the test by subject-independent scenarios and unseen data of the above-mentioned human activities at diverse geographical spaces. The experimental results showed that ResNet detected the falling and rest of the daily living human activities with decent accuracy.

scholarly journals Developing Classification Model for Chickpea Types using Machine Learning Algorithms

2020 ◽  
Vol 10 (1) ◽  
pp. 5-11
Keyword(s):  
Machine Learning ◽  
Learning Algorithm ◽  
Confusion Matrix ◽  
Research Work ◽  
Machine Learning Algorithms ◽  
Classification Model ◽  
Research Center ◽  
Domain Experts ◽  
Selection Mechanisms ◽  
Type Classification

Ethiopia is the leading producer of chickpea in Africa and among the top ten most important producers of chickpea in the world. Debre Zeit Agriculture Research Center is a research center in Ethiopia which is mandated for the improvement of chickpea and other crops. Genome enabled prediction technologies trying to transform the classification of chickpea types and upgrading the existing identification paradigm.Current state of the identification of chickpea types in Ethiopia still sticks to a manual. Domain experts tried to recognize every chickpea type, the way and efficiency of identifying each chickpea types mainly depend on the skills and experience of experts in the domain area and this frequently causes error and sometimes inaccurate. Most of the classification and identification of crops researches were done outside Ethiopia; for local and emerging varieties, there is a need to design classification model that assists selection mechanisms of chickpea and even accuracy of an existing algorithm should be verified and optimized. The main aim of this study is to design chickpea type classification model using machine learning algorithm that classify chickpea types. This research work has a total of 8303 records with 8 features and 80% for training and 20% for testing were used. Data preprocessing were done to prepare the dataset for experiments. ANN, SVM and DT were used to build the model. For evaluating the performance of the model confusion matrix with Accuracy, Recall and Precision were used. The experimental results show that the best-performed algorithms were decision tree and achieve 97.5% accuracy. After the evaluation of results found in this research work, agriculture research centers and companies have benefited. The model of chickpea type classification will be applied in Debre Zeit agriculture research center in Ethiopia as a base to support the experts during chickpea type identification process. In addition it enables the expertise to save time, effort and cost with the support of the identification model. Moreover, this research can also be used as a corner stone in the area and will be referred by future researchers in the domain area.

Mobile Based Healthcare Tool an Integrated Disease Prediction & Recommendation System

2019 ◽  
Vol 10 (1) ◽  
pp. 38-62
Author(s):  
Megha Rathi ◽  
Vikas Pareek
Keyword(s):  
Machine Learning ◽  
Recommendation System ◽  
Learning Algorithm ◽  
Confusion Matrix ◽  
Research Work ◽  
Machine Learning Algorithms ◽  
Database Analysis ◽  
Statistical Parameters ◽  
Patient Profile ◽  
The Right

Recent advances in mobile technology and machine learning together steer us to create a mobile-based healthcare app for recommending disease. In this study, the authors develop an android-based healthcare app which will detect all kinds of diseases in no time. The authors developed a novel, hybrid machine-learning algorithm in order to provide more accurate results. For the same purpose, the authors have combined two machine-learning algorithms, SVM and GA. The proposed algorithms will enhance the accuracy and at the same time reduce the complexity and count of attributes in the database. Analysis of algorithm is also done using statistical parameters like accuracy, confusion matrix, and roc-curve. The pivotal intent of this research work is to create an android-based healthcare app which will predict disease when provided with certain details. For a disease like cancer, for which a series of tests are required for confirmation, this app will quickly detect cancer and it is helpful to doctors as they can start the right course of treatment right away. Further, this app will also recommend a diet fitting the patient profile.

scholarly journals A Machine Learning Framework for Improving Classification Performance on Credit Approval

2021 ◽  
Vol 10 (1) ◽  
pp. 47-52
Author(s):  
Pulung Hendro Prastyo ◽  
Septian Eko Prasetyo ◽  
Shindy Arti
Keyword(s):  
Machine Learning ◽  
Naive Bayes ◽  
Information Gain ◽  
Learning Algorithm ◽  
Confusion Matrix ◽  
Credit Scoring ◽  
Research Work ◽  
Classification Performance ◽  
Naïve Bayes ◽  
Bayes Algorithm

Credit scoring is a model commonly used in the decision-making process to refuse or accept loan requests. The credit score model depends on the type of loan or credit and is complemented by various credit factors. At present, there is no accurate model for determining which creditors are eligible for loans. Therefore, an accurate and automatic model is needed to make it easier for banks to determine appropriate creditors. To address the problem, we propose a new approach using the combination of a machine learning algorithm (Naïve Bayes), Information Gain (IG), and discretization in classifying creditors. This research work employed an experimental method using the Weka application. Australian Credit Approval data was used as a dataset, which contains 690 instances of data. In this study, Information Gain is employed as a feature selection to select relevant features so that the Naïve Bayes algorithm can work optimally. The confusion matrix is used as an evaluator and 10-fold cross-validation as a validator. Based on experimental results, our proposed method could improve the classification performance, which reached the highest performance in average accuracy, precision, recall, and f-measure with the value of 86.29%, 86.33%, 86.29%, 86.30%, and 91.52%, respectively. Besides, the proposed method also obtains 91.52% of the ROC area. It indicates that our proposed method can be classified as an excellent classification.

scholarly journals Smartphone and Smartwatch for Human Activity Recognition

2021 ◽  
Vol 4 (1) ◽  
Author(s):  
Mashhour M Bani Amer
Keyword(s):  
Activity Recognition ◽  
Human Activity ◽  
Human Activities ◽  
Elderly Care ◽  
Confusion Matrix ◽  
Ambient Assisted Living ◽  
Human Activity Recognition ◽  
Learning System ◽  
Support Vector ◽  
Close Monitoring

Human activity recognition (HAR) systems are developed as aspect of a model to allow continual assessment of human behaviors in IoT environments in the areas of ambient assisted living, sports injury detection, elderly care, rehabilitation, and entertainment and close monitoring. Smartphones are already used to recognize activity. Most of the research done in this field placed a restriction on fixing the smartphone securely in a certain location on the human body, along with the machine learning system, to promote the process of classifying raw data from smartphone sensors to human activities. Smartwatches solve this limitation by placing them in a consistent position, which becomes steady and precisely sensitive to body movements. For this experiment, we evaluate both the accelerometer and the gyroscope sensor on the smartphone and the smartwatch, and decide which sensors hybrid does superiorly. Five daily physical human activities are evaluated using five classifiers from WEKA, in addition to Artificial Neural Network (ANN), K- Nearest Neighbor (KNN), and Support Vector Machine (SVM) algorithms builtin MATLAB 2018a. We used confusion matrix and random simulation to compare the accuracy and efficiency of those models. The results showed that the accelerometer sensors combination has the highest accuracy among other combinations and achieved an overall accuracy of 97.7% using SVM that gives the best performance among all other classifiers.

scholarly journals Quantitative Association between Nighttime Lights and Geo-Tagged Human Activity Dynamics during Typhoon Mangkhut

2019 ◽  
Vol 11 (18) ◽  
pp. 2091
Author(s):  
Liu ◽  
Du ◽  
Yi ◽  
Liang ◽  
Ma ◽  
...  
Keyword(s):  
Human Activity ◽  
Human Activities ◽  
Confusion Matrix ◽  
County Level ◽  
Location Service ◽  
Nighttime Lights ◽  
Positive Correlations ◽  
Log Linear ◽  
Activity Dynamics ◽  
Damage Estimates

The daily nighttime lights (NTL) and the amount of location-service requests (NLR) data have been widely used as a proxy for measures of disaster-induced power outages and geo-tagged human activity dynamics. However, the association between the two datasets is not well understood. In this study, we investigated how the NTL signals and geo-tagged human activities changed in response to Typhoon Mangkhut. The confusion matrix is constructed to quantify the changes of the NLR in response to Typhoon Mangkhut, as well as the changes of the NTL signals at the grid level. Geographically-weighted regression and quantile regression were used to examine the associations between the changes of the NTL and the NLR at both grid and county levels. The quantile regressions were also used to quantify the relationships between the dimmed NTL signals and the change of the NLR in disaster damage estimates at the county level. Results show that the percent of the grids with anomalous human activities is significantly correlated with the nearby air pressure and wind speed. Geo-tagged human activities varied in response to the evolution of Mangkhut with significant areal differentiation. Over 69.3% of the grids with significant human activity change is also characterized by declined NTL brightness, which is closely associated with abnormal human activities. Significant log-linear and moderate positive correlations were found between the changes of the NTL and NLR at both the grid and county levels, as well as between the county-level changes of NLR/NTL and the damage estimates. This study shows the geo-tagged human activities are closely associated with the changes of the daily NTL signals in response to Typhoon Mangkhut. The two datasets are complimentary in sensing the typhoon-induced losses and damages.

scholarly journals Predictive Modelling of Employee Turnover in Indian IT Industry Using Machine Learning Techniques

2019 ◽  
Vol 23 (1) ◽  
pp. 12-21 ◽  
Author(s):  
Shikha N. Khera ◽  
Divya
Keyword(s):  
Machine Learning ◽  
Learning Algorithm ◽  
Confusion Matrix ◽  
Predictive Modelling ◽  
Supervised Machine Learning ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
It Industry ◽  
Knowledge Based ◽  
Employee Attrition

Information technology (IT) industry in India has been facing a systemic issue of high attrition in the past few years, resulting in monetary and knowledge-based loses to the companies. The aim of this research is to develop a model to predict employee attrition and provide the organizations opportunities to address any issue and improve retention. Predictive model was developed based on supervised machine learning algorithm, support vector machine (SVM). Archival employee data (consisting of 22 input features) were collected from Human Resource databases of three IT companies in India, including their employment status (response variable) at the time of collection. Accuracy results from the confusion matrix for the SVM model showed that the model has an accuracy of 85 per cent. Also, results show that the model performs better in predicting who will leave the firm as compared to predicting who will not leave the company.

scholarly journals Deep Convolutional Neural Network with RNNs for Complex Activity Recognition Using Wrist-Worn Wearable Sensor Data

Electronics ◽  
2021 ◽  
Vol 10 (14) ◽  
pp. 1685
Author(s):  
Sakorn Mekruksavanich ◽  
Anuchit Jitpattanakul
Keyword(s):  
Neural Networks ◽  
Activity Recognition ◽  
Human Activities ◽  
Recognition Performance ◽  
Confusion Matrix ◽  
Experimental Studies ◽  
Industrial Applications ◽  
Sensor Data ◽  
Complex Activity ◽  
Activity Data

Sensor-based human activity recognition (S-HAR) has become an important and high-impact topic of research within human-centered computing. In the last decade, successful applications of S-HAR have been presented through fruitful academic research and industrial applications, including for healthcare monitoring, smart home controlling, and daily sport tracking. However, the growing requirements of many current applications for recognizing complex human activities (CHA) have begun to attract the attention of the HAR research field when compared with simple human activities (SHA). S-HAR has shown that deep learning (DL), a type of machine learning based on complicated artificial neural networks, has a significant degree of recognition efficiency. Convolutional neural networks (CNNs) and recurrent neural networks (RNNs) are two different types of DL methods that have been successfully applied to the S-HAR challenge in recent years. In this paper, we focused on four RNN-based DL models (LSTMs, BiLSTMs, GRUs, and BiGRUs) that performed complex activity recognition tasks. The efficiency of four hybrid DL models that combine convolutional layers with the efficient RNN-based models was also studied. Experimental studies on the UTwente dataset demonstrated that the suggested hybrid RNN-based models achieved a high level of recognition performance along with a variety of performance indicators, including accuracy, F1-score, and confusion matrix. The experimental results show that the hybrid DL model called CNN-BiGRU outperformed the other DL models with a high accuracy of 98.89% when using only complex activity data. Moreover, the CNN-BiGRU model also achieved the highest recognition performance in other scenarios (99.44% by using only simple activity data and 98.78% with a combination of simple and complex activities).

scholarly journals Personalized Human Activity Recognition Based on Integrated Wearable Sensor and Transfer Learning

Sensors ◽  
2021 ◽  
Vol 21 (3) ◽  
pp. 885 ◽  
Author(s):  
Zhongzheng Fu ◽  
Xinrun He ◽  
Enkai Wang ◽  
Jun Huo ◽  
Jian Huang ◽  
...  
Keyword(s):  
Transfer Learning ◽  
Activity Recognition ◽  
Human Activity ◽  
Sensor Node ◽  
Learning Algorithm ◽  
Joint Probability ◽  
Human Activity Recognition ◽  
Sensor Technology ◽  
Measurement Unit ◽  
Wearable Sensor

Human activity recognition (HAR) based on the wearable device has attracted more attention from researchers with sensor technology development in recent years. However, personalized HAR requires high accuracy of recognition, while maintaining the model’s generalization capability is a major challenge in this field. This paper designed a compact wireless wearable sensor node, which combines an air pressure sensor and inertial measurement unit (IMU) to provide multi-modal information for HAR model training. To solve personalized recognition of user activities, we propose a new transfer learning algorithm, which is a joint probability domain adaptive method with improved pseudo-labels (IPL-JPDA). This method adds the improved pseudo-label strategy to the JPDA algorithm to avoid cumulative errors due to inaccurate initial pseudo-labels. In order to verify our equipment and method, we use the newly designed sensor node to collect seven daily activities of 7 subjects. Nine different HAR models are trained by traditional machine learning and transfer learning methods. The experimental results show that the multi-modal data improve the accuracy of the HAR system. The IPL-JPDA algorithm proposed in this paper has the best performance among five HAR models, and the average recognition accuracy of different subjects is 93.2%.

Sign in / Sign up

Export Citation Format

Share Document