Designing a Machine Learning – Based Framework for Enhancing Performance of Livestock Mobile Application System

The smart home is now an established area of interest and research that contributes to comfort in modern homes. With the Internet being an essential part of broad communication in modern life, IoT has allowed homes to go beyond building to interactive abodes. In many spheres of human life, the IoT has grown exponentially, including monitoring ecological factors, controlling the home and its appliances, and storing data generated by devices in the house in the cloud. Smart home includes multiple components, technologies, and devices that generate valuable data for predicting home and environment activities. This work presents the design and development of a ubiquitous, cloud-based intelligent home automation system. The system controls, monitors, and oversees the security of a home and its environment via an Android mobile application. One module controls and monitors electrical appliances and environmental factors, while another module oversees the home’s security by detecting motion and capturing images. Our work uses a camera to capture images of objects triggered by their motion being detected. To avoid false alarms, we used the concept of machine learning to differentiate between images of regular home occupants and those of an intruder. The support vector machine algorithm is proposed in this study to classify the features of the image captured and determine if it is that of a regular home occupant or an intruder before sending an alarm to the user. The design of the mobile application allows a graphical display of the activities in the house. Our work proves that machine learning algorithms can improve home automation system functionality and enhance home security. The work’s prototype was implemented using an ESP8266 board, an ESP32-CAM board, a 5 V four-channel relay module, and sensors.

Download Full-text

Deep Learning-Based Mobile Application for Plant Disease Diagnosis

Advances in Environmental Engineering and Green Technologies - Applications of Image Processing and Soft Computing Systems in Agriculture ◽

10.4018/978-1-5225-8027-0.ch010 ◽

2019 ◽

pp. 242-271 ◽

Cited By ~ 3

Author(s):

Shradha Verma ◽

Anuradha Chug ◽

Amit Prakash Singh ◽

Shubham Sharma ◽

Puranjay Rajvanshi

Keyword(s):

Machine Learning ◽

Deep Learning ◽

Mobile Application ◽

Plant Disease ◽

Prediction Models ◽

Disease Diagnosis ◽

Tomato Leaf ◽

Plant Diseases ◽

Learning Tools ◽

Class Labels

With the increasing computational power, areas such as machine learning, image processing, deep learning, etc. have been extensively applied in agriculture. This chapter investigates the applications of the said areas and various prediction models in plant pathology for accurate classification, identification, and quantification of plant diseases. The authors aim to automate the plant disease identification process. To accomplish this objective, CNN has been utilized for image classification. Research shows that deep learning architectures outperform other machine learning tools significantly. To this effect, the authors have implemented and trained five CNN models, namely Inception ResNet v2, VGG16, VGG19, ResNet50, and Xception, on PlantVillage dataset for tomato leaf images. The authors analyzed 18,160 tomato leaf images spread across 10 class labels. After comparing their performance measures, ResNet50 proved to be the most accurate prediction tool. It was employed to create a mobile application to classify and identify tomato plant diseases successfully.

Download Full-text

An Augmented-Reality-Based Intelligent Mobile Application for Open Computer Education

Mobile Technologies and Augmented Reality in Open Education - Advances in Educational Technologies and Instructional Design ◽

10.4018/978-1-5225-2110-5.ch008 ◽

2017 ◽

pp. 154-174 ◽

Cited By ~ 1

Author(s):

Utku Köse

Keyword(s):

Artificial Intelligence ◽

Augmented Reality ◽

Mobile Application ◽

Learning Experiences ◽

Computer Education ◽

Dynamic Learning ◽

Common Environment ◽

Application System ◽

Course Materials

Objective of this chapter is to introduce an Augmented Reality based intelligent mobile application (M-Learning application) to support courses of Computer Education. In the study, it was aimed to provide an alternative way of improving M-Learning experiences by employing both Augmented Reality and Artificial Intelligence based approaches in a common environment. Briefly, the application is able to use an intelligent mechanism evaluating students' several dynamic learning parameters to match them with the most appropriate course materials provided over the system. So, each student can encounter with appropriate course materials matching with their states over the application system. The related course materials include both AR based ones and standard ones as uploaded by teachers. An evaluation based flow has been run in the study by using the developed application through courses of Computer Education and the obtained results have shown that the application is effective and successful enough at improving students' learning experiences and achieving a good Open Computer Education.

Download Full-text

Automated Soil Residue Levels Detecting Device With IoT Interface

Advances in Data Mining and Database Management - Challenges and Applications of Data Analytics in Social Perspectives ◽

10.4018/978-1-7998-2566-1.ch007 ◽

2021 ◽

pp. 123-135

Author(s):

Adiraju Prasanth Rao ◽

K. Sudheer Reddy ◽

Sathiyamoorthi V.

Keyword(s):

Machine Learning ◽

Machine Learning Techniques ◽

The Novel ◽

Cloud Environment ◽

Application System ◽

Learning Techniques ◽

Social And Economic Development ◽

Residue Levels ◽

Soil Residue ◽

Agricultural Farm

Cloud computing and internet of things (IoT) are playing a crucial role in the present era of technological, social, and economic development. The novel models where cloud and IoT are integrated together are foreseen as disruptive and enable a number of application scenarios. The e-smart is an application system designed by leveraging cloud, IoT, and several other technology frameworks that are deployed on the agricultural farm to collect the data from the farm fields. The application extracts and collects the information about the residue levels of soil and crop details and the same data will be hosted in the cloud environment. The proposed e-smart application system is to analyze, integrate, and correlate datasets and produce decision-oriented reports to the farmer by using several machine learning techniques.

Download Full-text

North American Hardwoods Identification Using Machine-Learning

Forests ◽

10.3390/f11030298 ◽

2020 ◽

Vol 11 (3) ◽

pp. 298 ◽

Cited By ~ 2

Author(s):

Dercilio Junior Verly Lopes ◽

Greg W. Burgreen ◽

Edward D. Entsminger

Keyword(s):

Machine Learning ◽

North American ◽

Mobile Application ◽

Cross Validation ◽

Data Augmentation ◽

Technical Note ◽

Machine Learning Method ◽

Training Set ◽

Hardwood Species ◽

Fold Cross Validation

This technical note determines the feasibility of using an InceptionV4_ResNetV2 convolutional neural network (CNN) to correctly identify hardwood species from macroscopic images. The method is composed of a commodity smartphone fitted with a 14× macro lens for photography. The end-grains of ten different North American hardwood species were photographed to create a dataset of 1869 images. The stratified 5-fold cross-validation machine-learning method was used, in which the number of testing samples varied from 341 to 342. Data augmentation was performed on-the-fly for each training set by rotating, zooming, and flipping images. It was found that the CNN could correctly identify hardwood species based on macroscopic images of its end-grain with an adjusted accuracy of 92.60%. With the current growing of machine-learning field, this model can then be readily deployed in a mobile application for field wood identification.

Download Full-text

DESIGN OF INTEGRATED MOBILE APPLICATION SYSTEM IN CORPORATE ENVIRONMENT

Vestnik komp iuternykh i informatsionnykh tekhnologii ◽

10.14489/vkit.2020.06.pp.012-021 ◽

2020 ◽

pp. 12-21

Author(s):

D. V. Titarev ◽

E. A. Borzykin ◽

A. S. Romanov ◽

E. I. Lapkovskaya

Keyword(s):

Mobile Application ◽

Business Processes ◽

Graphical Form ◽

General Description ◽

Corporate Environment ◽

Application System ◽

Cross Platform ◽

Access To Data ◽

The Cost ◽

Server Architecture

The benefits of the BYOD (Bring Your Oun Device) approach is describes. This approach contributes to greater efficiency of business processes and economy of the enterprise budget. The necessity of focusing on the problem of information security is substantiated. As a solution, a mobile application is proposed that allows to identify the user and distribute security policies to the device. The following describes the problems that arise in the process of solution – problems of transferring data from a mobile device to the storage, the problem of centralized storage of incoming data, assignment of geolocations available for working with the application, and a problem of cross-platform. Further, the task is formulated – to design and develop a universal solution to these problems, since there is no single, universally accessible solution that would satisfy all the described requirements. The next part of the article describes the model of the proposed system, gives its general description in a formalized and graphical form. The article also provides an image and description of the system architecture, consisting of three main parts: IOS client, Android client and server. The advantages of the developed client-server architecture are highlighted: security and centralized access to data. The architecture of each individual part is described with a specification and justification for the choice of libraries and technologies used. The following describes the operation of the system, presents a sequence diagram of the client requests during authorization and receiving a set of policies for a new user, and BPMN diagram of the business process for obtaining Android agent data. Thus, the resulting solution will reduce the cost of administration of mobile devices in a corporate environment.

Download Full-text

Analysis Of Functions And Applications Of Siaran Mobile (Reporting And Assignment Application System) As A Communication Facility Of South Tangerang City Towards Smart City

Advances in Social Sciences Research Journal ◽

10.14738/assrj.711.8601 ◽

2020 ◽

Vol 7 (11) ◽

pp. 125-135

Author(s):

Enjang Pera Irawan ◽

Tasya Aulianisa

Keyword(s):

Public Relations ◽

Smart City ◽

Mobile Application ◽

Public Communication ◽

Application System ◽

Technical Problems ◽

The Public ◽

Public Facilities ◽

The Government ◽

Communication Facility

This study entitled analysis of functions and applications of siaran mobile (reporting and assignment application system) as a communication facility of South Tangerang City towards smart city. The purpose of this study was to analyze the functions and benefits of the SIARAN Mobile application as a facility of public communication in supporting South Tangerang City towards smart city. Supporting concepts and theories in this research were communication, public relations government, and smart city. This research method was to use a descriptive qualitative approach. The findings showed that the SIARAN Mobile application was a South Tangerang City reporting media based on the mobile application that was officially launched by the government since March 9th, 2017. The function of this application was to become a reporting application for technical problems such as waste problems, damaged public facilities, actions which was detrimental to the community. The benefit of this application was to make it easier for the public to report various problems in the South Tangerang area, and make it easier for the government in handling various problems that were complained of by the community.

Download Full-text