Security is a major threat to institutions that is why there is a need of several specially trained personnel to attain the desired security to overcome the declining security conditions in the country. These personnel, as human beings, make mistakes that might affect the level of security. The need for facial recognition system that is fast and accurate is continuously increasing which can detect intruders and restricts them from restricted or high-security areas in real time and help in minimizing human error. Face recognition is one of the most important biometrics pattern recognition technique which is used in a broad spectrum of applications. The time and accuracy factor is considered as a major problem that specifies the performance of automatic face recognition system in real time environments. Various solutions have been proposed using multicore systems. However, harnessing current advancements is not without difficulties. Motivated by such challenge, this paper provides the architectural design, detailed design and proposes a comparative analysis for a Real Time Face Recognition System with three variant implementations of Real Time Face Recognition algorithms including Local Binary Patterns Histograms (LBP), PCA (Principal Component Analysis) and Fisher face. Finally, this paper concludes the speed obtained for the advanced implementations achieved by integrating embedded system models against the convention implementation.
20 December 2023 in UMT Artificial Intelligence Review
Due to the growing population and the numerous ecological challenges that affect crop yields, the need to modernize the crop production process has become increasingly critical. Swiftly managing potential threats to crops can have a substantial impact on overall crop production. Pests represent a significant menace, capable of causing substantial losses if not effectively controlled in a timely manner. In this study, a deep learning-based method for pest identification is introduced. The approach leverages the YOLO (You Only Look Once) object recognition SSD (single shot detection )algorithm in combination with the pre-trained DARKNET architecture to categorize pests into nine distinct classes. The study utilizes a publicly available dataset sourced from Kaggle, which comprises a total of 7,046 images. The outcomes reveal overall 83% of overall accuracy rate, with a notably low training and validation loss of 0.02%. Moreover, our model exhibits a notable enhancement in localization results, delivering a precision of 0.83, a recall of 0.83, an mAP-0.5 of 0.833, and an mAP-0.5:0.95 of 0.783.
Armed forces are one of the most integral part of any country. Being in one of the most hostile and critical environment they constantly face both mental and physical challenges. Those soldiers are always at risk and when met with an unfortunate incident, they remain isolated from instantaneous medical help. In these situations, it is essential to monitor and track each individual in real-time so that it can be concluded from the accumulated data as which individual requires immediate medical help and which one performs exceptionally well that can be considered a preferred candidate for the up-coming specific missions. In this paper, we present the system of an embedded next generation tactical suit designed for monitoring health statistics/analytics of an armed personnel. The suit has an onboard integrated CPU that extracts data from multiple sensors and send this information using LoRaWAN (Long Range Wide Area Network) technology. This information is recorded into the database, according to each suit and can be viewed in real-time or with respective to each individual. The paper also discusses the advantages of using LoRa and describes the system architecture and the working of the suit.
1 January 2021 in International Journal of Modelling, Identification and Control
This paper proposes an automotive smart black box (SBB) for accident and theft prevention using artificial intelligence (AI). The SBB is a versatile device and can work with any type of vehicle inc...
now a day’s people desire to travel from one city to another city in a convenient way, that save the time and according to their budget. Everyone wants to acquire the best solution within lesseffort. Traditionally, whenever people want to buy bus ticket they have to visit the bus terminal of different passenger carrier and for their turn in a long queue. There are also websites and apps of different passenger carrier for online ticket booking that are running separately people get confused to acquire the best one. Searching ticket from a different websites and apps is time taken. For this argumentation a pro efficient eBus Services System (EBS) is to be proposed in this paper to overcome these issues faced by passengers during transport reservation inside the nation. The system provides web and android application based structure that allows the guest to check eBus accessibility, make reservation and pay charges through online payment gateway. Which is stylish now a days. EBS will help population to reserve tickets of journeys and it also allows passengers to compare estimate fares, services of different service providers. Development of system is based on agile software development approach and Unified Modeling Language(UML). The idea is to gather all conveyor & agent and their services on one platform. So, the tourist can easily appoint and lined up according to them decide on. This entity will also present the functionality of tracking the bus, you can track the bus if your agnate, relatives makes a journey. This paper proposed eBus Services system. eBus Services was developed by using Bootstrap, server side scripting by using PHP, MYSQL, JQuery and JavaScript to make client end responsive and user friendly and AJAX to reduce load from server.
With emerging advancements of technology, we can observe the increasing number of automation technologies that has made life easier and simpler in all aspects. With a swift upturn in the number of internet users over the preceding span has made internet turn into a gist of life. The said automation technology i.e. IoT (Internet of Things), has taken us to anew world of automation. In this new era of Internet Revolution, where we tend to discover approaches to make things inside the range of our fingertips, prompted the advancement of Home Automation Systems. Controlling and monitoring the home has never been so easyand secure until science made thispossible. In this paper, we present a solution, ElectriCare, which is an IoT based home automation and monitoring system that provides the ability to control and conserve electricity with the sense of intelligence. This intelligence feature helps us to design a system that lets user in control of their electronics and allowing them to also automate their liveswith the help of on-board sensors. It uses smart phone application to control the appliances via the internet from anyplace round the globe. It uses Wi-Fi to communicatewith the microcontroller to control as well as it creates a log of the electricity consumption to help save energy as it is destined to conserve the electric and human power.