Forest fires are burning areas of forest or land in large or small areas. Forest fires are often uncontrollable and when this happens, the fire will burn anything nearby for two reasons, one of which is burning naturally or burning caused by humans. One of the man-made fires deliberate by humans is the burning used by the community around the forest to open or clear agricultural or plantation land. The community feels that clearing land with fire does not require a long time and is more economical, if the use of fire is not used properly it can cause the forest to burn. Forest fires in Riau area are still classified as minimal or fires rarely occur. However, the community is at least aware of the forest fires in Riau due to a lack of media information about where the fire hotspots occurred. With this application, it can help the public to better know where the hotspots have been burned. This application consists of 2 levels of access, namely: admin and user. For admins and users, the manufacturing process uses the Android Studio application with Java as the programming language, this application uses Firebase as its database to find out the location of fire hotspots using the Google Maps API. Testing on the application is created to test whether the application has run as desired. Test results using white box testing method.

A QR code is a two-dimensional code that encodes data but it is unattractive and not ideal. QR codes have been applied in item identifications, publicity campaigns, advertisements, product promotions, etc. so they need to be visually good in appearance. Visually good and decorated QR codes degrade the decoding rate as compared to the standard QR code decoding rate. As they are used for mobile payments and logins some security must be there. For this many researchers have contributed using various approaches to beautify QR codes with high decoding accuracy and to make them secure. This paper aims towards the study of works carried out in the direction of beautification of QR codes using blended type techniques and artificial intelligence based techniques by different authors. The present state of prior strategies, methods, and major features used are described in this survey.

The deployment of mobile health (mHealth) apps can transform healthcare in rural and remote communities worldwide. Rural communities in Zimbabwe have limited access to information that affects their health, economic and social being due to structural and social barriers related to the inaccessibility of traditional media. mhealth apps are a valuable tool to monitor disease outbreaks and provide preventative information to the public. Lack of access to COVID-19 information results in high fatalities and public panic, and it is critical to publish reliable and timely information. The study’s objective was to demonstrate the utility of a mHealth app prototype developed to enhance access to COVID-19 information in rural and remote communities in Zimbabwe. The prototype provides COVID-19 information such as statistics, preventative measures, self-diagnostics, social distancing information, and general hygiene to rural communities with limited access to official information channels on the pandemic. A design science research methodology was used to design, build and evaluate the COVID-19 mHealth app and fulfil the study’s objectives. Thirty potential users participated in the evaluation of the prototype. The evaluation results show that potential users perceived that the prototype was useful, engaging, easy to learn, well designed, and provided relevant information. A strong correlation was observed between the design, engagement, functionality, and learnability. More widespread usability and more representative tests should be conducted to ascertain the efficacy and usability of the app. The study contributes literature on usability studies in developing countries. As more mHealth apps are being developed and deployed, more usability tests will be required to ensure that they are fit for purpose. The paper provides a baseline for developing related health information apps. Policymakers, health practitioners, technologists, and scholars can further investigate the deployment of digital technologies to improve healthcare and control the transmission and spread of COVID-19.

Facial Recognition is the task of processing an image or video content in order to identify and recognize the faces of individuals. Its area of applications are wide and a lot of research efforts have been invested which led to introduction of techniques/algorithms and programming language libraries for implementation of those techniques. Facial recognition relies heavily on the use of machine learning techniques. Convolutional Neural Network (CNN), a deep learning algorithm has been successfully applied for face recognition task. However, because of its requirements, it may not be applicable in all cases. Where application scenario cannot cope with CNN, it is necessary to resort to other techniques that use traditional Machine Learning (ML) techniques. Previous studies that performed comparison on face recognition algorithms that use traditional ML techniques only disclosed the best algorithm without revealing the best image processing library used. Considering the fact that people now depend on these libraries to build face recognition systems, it is important to empirically show the best library. In this paper an experiment was conducted with aim of assessing the performance of Fisherface and Eigenface algorithms, and that of Scikit-learn and OpenCV libraries. Eigenface and Fisherface algorithms were combined with K-Nearest Neighbors (KNN) and Support Vector Machines (SVM) classifiers respectively. The algorithms were evaluated using LFW dataset, and implemented in two Python libraries for image processing Scikit-learn and OpenCV. This is to enable us determine the best performing technique/algorithm and at the same time the best library, thereby achieving dual aims. Experimental results show that Scikit-learn implementation of Fisherface with KNN recorded the highest F-score of 67.23% while the OpenCV implementation of Eigenface with SVM recorded the lowest F-score of 14.53%. Comparing the algorithms, Fisherface with SVM produced better results than Eigenface with SVM. The same story holds for Fisherface with KNN, and Eigenface with KNN. This suggests that irrespective of classifier, Fisherface outperform Eigenface in terms of accuracy of recognition. Comparing the libraries, Scikit-learn implementations of Fisherface with SVM and Eigenface with SVM, outperform the OpenCV implementation of the same algorithms. This means scikit-learn implementation produces better results than its counterpart, the OpenCV.

Gait based gender classification is an emerging area in the field of biometrics that has received a lot of interest from researchers mainly due to its advantages over the other methods and its potential application. Gait based gender classification helps a vision based biometric analysis system by focusing the gender-unique features. This helps to improves the performance of the model by limiting the authentication database searching to only one gender. Through the years, researchers have tried a wide variety of techniques and their combinations to improve the accuracy of gait based biometric systems in varying use-cases. In this study, we have given a brief overview of some of the recent and pioneering works done in the field of gait-based gender classification.