An android based sign language recognition system for selected English vocabularies was developed with the explicit objective to examine the specific characteristics that are responsible for gestures recognition. Also, a recognition model for the process was designed, implemented, and evaluated on 230 samples of hand gestures. The collected samples were pre-processed and rescaled from 3024 ×4032 pixels to 245 ×350 pixels. The samples were examined for the specific characteristics using Oriented FAST and Rotated BRIEF, and the Principal Component Analysis used for feature extraction. The model was implemented in Android Studio using the template matching algorithm as its classifier. The performance of the system was evaluated using precision, recall, and accuracy as metrics. It was observed that the system obtained an average classification rate of 87%, an average precision value of 88% and 91% for the average recall rate on the test data of hand gestures. The study, therefore, has successfully classified hand gestures for selected English vocabularies. The developed system will enhance the communication skills between hearing and hearing-impaired people, and also aid their teaching and learning processes. Future work include exploring state-of-the-art machining learning techniques such Generative Adversarial Networks (GANs) for large dataset to improve the accuracy of results. Keywords— Feature extraction; Gestures Recognition; Sign Language; Vocabulary, Android device.
This article developed a framework for trust management in mobile ambient home network with a view to secure the home devices and channel against attacks. The framework was design using mobile ad hoc network and social networking concept. The trust management, global reputation aggregation which considered the direct and indirect communication of home devices and remote devices was employed to shield home devices from attacks. While real time dynamic source routing protocol was employed to prevent the channel from attacks by selfish and malicious nodes. The prototype of the framework was implemented using C# programming language. The framework will enhance the activities in the home by securing the home network against unforeseen network disruption and node misbehavior due to the distributed nature of the environment.
In ambient intelligence home networks, attacks can be on the home devices or the communication channel. This paper focuses on the channel attacks prevention by proposing Real Time Dynamic Source Routing (RTDSR) protocol. The protocol adopted the observation based cooperation enforcement in ad hoc networks (oceans) and collaborative reputation mechanism built on Dynamic Source Routing (DSR) protocol. The RTDSR introduced lookup table on the source, destination and intermediate nodes. It also ensures that data path with high reputation are used for data routing and a monitoring watchdog was introduced to ensure that the next node forward the packet properly. The RTDSR protocol was simulated and benchmarked with DSR protocol considering network throughput, average delay, routing overhead and response time as performance metrics. Simulation result revealed a better performance of RTDSR protocol over existing DSR protocol.
The study formulated and evaluated a model for effective management of malicious nodes in mobile Ad-hoc network based on Ad-Hoc on-demand distance vector routing protocol. A collaborative injection model called Collaborative Injection Deterrence Model (CIDM) was formulated using stochastic theory.The definition of the model was presented using graph theory. CIDM was simulated using three different scenarios. The three scenarios were then compared using packets delivery ratio (PDR), routing load, throughput and delay as performance metrics. The simulation result showed that CIDM reduce considerably the rate of packets dropped caused by malicious nodes in MANET network. CIDM did not introduce additional load to the network and yet with produce higher throughput. Lastly, the access delay with CIDM is minimal compared with convectional OADV. The study developed a model to mete out a punitive measure to rogue nodes as a form of intrusion deterrence without degrading the overall performance of the network. The well known CRAWDAD dataset was used in the simulation.
This study designed, simulated and evaluated the performance of a conceptual framework for ambient ad hoc home network. This was with a view to detecting malicious nodes and securing the home devices against attacks. The proposed framework, called mobile ambient social trust consists of mobile devices and mobile ad hoc network as communication channel. The trust model for the device attacks is Adaptive Neuro Fuzzy (ANF) that considered global reputation of the direct and indirect communication of home devices and remote devices. The model was simulated using Matlab 7.0. In the simulation, NSL-KDD dataset was used as input packets, the artificial neural network for packet classification and ANF system for the global trust computation. The proposed model was benchmarked with an existing Eigen Trust (ET) model using detection accuracy and convergence time as performance metrics. The simulation results using the above parameters revealed a better performance of the ANF over ET model. The framework will secure the home network against unforeseen network disruption and node misbehavior.
Channel estimation is an important and necessary function performed by modern wireless receivers. The goal of channel estimation is to measure the effects of the channel on known or partially known transmission. The usual practice in acquiring knowledge about a channel is to model the channel and then acquire the parameters involved in the model. This paper proposes a variable partial update model for adaptive communication channel estimation with a view to improving signal error at the receiver station. The proposed model is composed of finite impulse response transversal adaptive filter and least mean square adaptation algorithm. The performance of the proposed model was compared with the full update model. The evaluation results indicated that the proposed model performed better than the full update model in terms of computational complexity, memory load, and convergence rate.
Interpersonal violence is one of the causes of death globally. Getting help depends on timely response from responders. Development in personal safety technologies have been improved over the years due to the increase in the use of mobile technologies and the miniaturization of electronic sensors. However, existing technologies for communicating distress usually require active user interventions in alerting emergencies. Hence, this study proposes a system for the automatic detection and alert of distress situations arising from violent attacks through smartphone sensors. A fuzzy logic approach was adopted to classify levels of distress situation using input data values from tri-axial accelerometer, gyroscope, sound and proximity sensors. A prototype of the distress detection and alert process was implemented using Java programming language. The system prototype was implemented as an android based real-time application that detects and alerts distress using values from mobile device sensors. Testing the prototype showed that the system can automatically detect and send alert to responders using smartphone.
The advent and use of mobile phones have added a lot to the world's social lives as technology keeps evolving on a daily basis but also face a bit of challenges such as info theft, misrepresentation, impersonation etc. with a view to causing mayhem; a scenario that calls for a more secured mode of phone access for protection sake. A unit of functionality provided by the system was demonstrated with the aid of a Use-Case diagram and the procedural flow of control between the various class objects involved was illustrated using the Activity diagram. The code was written in JAVA on a platform called "Android Visual Studio" and the required tools and Texts were built with the aid of the Android In-built Controls; which generate their own codes when utilized thus providing the needed field for entering E-mail and some other required parameters. The design was made in such a way that security info was sent to a designated Email for necessary action whenever an illegal attempt is noticed on the mobile phone. The expected intruder's face captured and the registered phone location due to the provision of incorrect security codes (while attempting to log in on the phone) were sent to the phone's rightful owner inform of alert via a preset Email. This research guaranteed privacy in addition to exposing intruders no matter their motives. It also educates the masses with the basic knowledge of privacy, protection from unauthorized access and the core importance of mobile phones security.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
334 Leonard St
Brooklyn, NY 11211
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.