Journal of Ubiquitous Computing and Communication Technologies - September 2019
Latest Publications





Published By Inventive Research Organization

Updated Friday, 22 October 2021

I. Jeena Jacob ◽  
P. Ebby Darney

A blood bank is the organisation responsible for storing blood to transfuse it to the patients in need. The primary goal of a blood bank is to be reliable and ensure that patients get the relevant non-toxic blood to avoid transfusion-related complications since blood is a critical medicinal resource. It is difficult for the blood banks to offer high levels of precision, dependability, and automation in the blood storage and transfusion process if blood bank administration includes many human processes. This research framework is proposing to maintain blood bank records using CNN model classification method. In the pre-processing of CNN method, the datasets are tokenized and set the donor’s eligibility. It will make it easier for regular blood donors to donate regularly to charitable people and organizations. A few machine learning techniques offer the automated website updation. Jupyter note book has been used to analyze the dataset of blood donors using decision trees, neural networks, and von Bays techniques. The proposed method operates online through a website. Moreover, the donor's eligibility status with gender, body mass index, blood pressure level, and frequency of blood donations is also maintained. Finally, the comparison of different machine learning algorithms with the suggested framework is tabulated.

R. Rajesh Sharma

It's well-known that industrial safety is now a top concern. Nowadays, accidents caused by flammable gases occur frequently in our everyday lives. Gas cylinders, which are used for household purposes, wide range of businesses, and vehicles are often reported to be on the verge of exploding. Explosions have left a large number of individuals seriously wounded or could also be lethal in certain cases. This project's goal is to use a HOG features for SVM classifier which is used to identify pipeline gas leaks and keep tabs on them. In addition, the system utilises an image processing technique to identify pipeline fractures. Early detection and identification of pipeline flaws is a predominant aspect of this study. According to the suggested design, the robot capture the image down the pipe, looking for any signs of gas leakage by the Eddy Current method. This type of recognition has proved superior to other traditional methods. The methods with efficiency parameters and the results were compared and are tabulated in the results section. In the future, the data in the course of detection could be sent through GSM to a mobile application.

R. Asokan ◽  
T. Vijayakumar

Recently, the use of different social media platforms such as Twitter, Facebook, and WhatsApp have increased significantly. A vast number of static images and motion frame pictures posted on such platforms get stored in the device folder making it critical to identify the social network of the downloaded images in the android domain. This is a multimedia forensic job with major cyber security consequences and is said to be accomplished using unique traces contained in picture material (SNs). Therefore, this proposal has been endeavoured to construct a new framework called FusionNet to combine two well-established single shared Convolutional Neural Networks (CNN) to accelerate the search. Moreover, the FusionNet has been found to improve classification accuracy. Image searching is one of the challenging issues in the android domain besides being a time-consuming process. The goal of the proposed network's architecture and training is to enhance the forensic information included in the digital pictures shared on social media. Furthermore, several network designs for the categorization of WhatsApp pictures have been compared and this suggested method has shown better performance in the comparison. The proposed framework's overall performance was measured using the performance metrics.

Haoxiang Wang

In recent times Automation is emerging every day and bloomed in every sector. Intelligent Transportation System (ITS) is one of the important branches of Automation. The major constrain in the transportation system is traffic congestion. This slurps the individual’s time and consequently pollutes the environment. A centralized management is required for optimizing the transportation system. The current traffic condition is predicted by evaluating the historical data and thereby it reduces the traffic congestion. The periodic update of traffic condition in each and every street of the city is obtained and the data is transferred to the autonomous vehicle. These data are obtained from the simulation results of transportation prediction tool SUMO. It is proved that our proposed work reduces the traffic congestion and maintains ease traffic flow and preserves the fleet management.

P. P. Joby

At present, the traditional healthcare system is completely replaced by the revolutionary technique, the Internet of Medical Things (IoMT). Internet of Medical Things is the IoT hub that comprises of medical devices and applications which are interconnected through online computer networks. The basic principle of IoMT is machine-to-machine communication that takes place online. The major goal of IoMT is to reduce frequent or unwanted visits to the hospitals which makes it comfortable and is also highly preferred by the older people. Another advantage of this methodology is that the interpreted or collected data is stored in cloud modules unlike amazon and Mhealth, making it accessible remotely. Although there are countless advantages in IoMT, the critical factor lies in data security or encryption. A surplus number of threat related to devices, connectivity, and cloud might occur under unforeseen or threatening circumstances which makes the person in the situation helpless. Yet, with the help of data security techniques designed especially for Internet of Medical Things, it is possible to address these challenges. In this paper, a review on data securing techniques for the internet of medical things is made along with a discussion on related concepts.

B Vivekanandam

Data pre-processing is critical for handling classification issues in the field of machine learning and model identification. The processing of big data sets increases the computer processing time and space complexity while decreasing classification model precision. As a result, it is necessary to develop an appropriate method for selecting attributes. This article describes a machine learning technique to solve functional selection by safeguarding the selection and mutation operators of genetic algorithms. During population calculations in the training set, the proposed method is adaptable. Furthermore, for various population sizes, the proposed method gives the best possible probability of resolving function selection difficulties during training process. Furthermore, the proposed work is combined with a better classifier in order to detect the different malware categories. The proposed approach is compared and validated with current techniques by using different datasets. In addition to the test results, this research work utilizes the algorithm for solving a real challenge in Android categorization, and the results show that, the proposed approach is superior. Besides, the proposed algorithm provides a better mean and standard deviation value in the optimization process for leveraging model effectiveness at different datasets.

C Anand

Several intelligent data mining approaches, including neural networks, have been widely employed by academics during the last decade. In today's rapidly evolving economy, stock market data prediction and analysis play a significant role. Several non-linear models like neural network, generalized autoregressive conditional heteroskedasticity (GARCH) and autoregressive conditional heteroscedasticity (ARCH) as well as linear models like Auto-Regressive Integrated Moving Average (ARIMA), Moving Average (MA) and Auto Regressive (AR) may be used for stock forecasting. The deep learning architectures inclusive of Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Recurrent Neural Networks (RNN), Multilayer Perceptron (MLP) and Support Vector Machine (SVM) are used in this paper for stock price prediction of an organization by using the previously available stock prices. The National Stock Exchange (NSE) of India dataset is used for training the model with day-wise closing price. Data prediction is performed for a few sample companies selected on a random basis. Based on the comparison results, it is evident that the existing models are outperformed by CNN. The network can also perform stock predictions for other stock markets despite being trained with single market data as a common inner dynamics that has been shared between certain stock markets. When compared to the existing linear models, the neural network model outperforms them in a significant manner, which can be observed from the comparison results.

R Dhaya

The World Health Organization (WHO) considers the COVID-19 Coronavirus to be a global pandemic. The most effective form of protection is to wear a face mask in public places. Moreover, the COVID-19 pandemic prompted all the countries to set up a lockdown to prevent viral transmission. According to a survey study, the use of facemasks at work decreases the chances of fast transmission. If the facemasks are not used or are worn incorrectly, it contributes to the third and fourth waves of the corona virus spreading throughout the world. This motivates us to conduct an efficient investigation of the face mask identification system and monitor people, who use suitable face mask in public places. Deep learning is the most effective approach for detecting whether or not a person is wearing a face mask in a crowded area. Using a multiclass deep learning technique, this research study proposes an efficient two stage identification (ETSI) for face mask detection. Whereas, the binary classification does not offer information about face mask detection and error. The proposed approach employs CNN's "ReLU" activation function to detect the face mask. Furthermore, in the current pandemic crisis, this research article offers a very efficient and precise approach for identifying COVID-19. Precision has increased as a result of the employment of a multi-class abbreviation in the final output.

Jennifer S. Raj

The advent of autonomous vehicles is indeed a potential field of research in today's situation. Connected Vehicles (CV) have received a lot of attention in the last decade, which has resulted in CV as a Service (CVaaS). With the advent of taxi services, there is a need for or demand for robust, seamless, and secure information transmission between the vehicles connected to a vehicular network. Thus, the concept of vehicular networking is transformed into novel concept of autonomous and connected vehicles. These autonomous vehicles will serve as a better experience by providing instant information from the vehicles via congestion reduction. The significant drawback faced by the invention of autonomous vehicles is the malicious floor of intruders, who tend to mislead the communication between the vehicles resulting in the compromised smart devices. To address these concerns, the best methodology that will protect and secure the control system of the autonomous vehicle in real time is blockchain. This research work proposes a blockchain framework in order to address the security challenges in autonomous vehicles. This research work enhances the security of smart vehicles thereby preventing intruders from accessing the vehicular network. To validate the suggested technique, money security criteria such as changing stored user ratings, probabilistic authentication scenarios, smart device compromise, and bogus user requests were employed. The observed findings have been documented and analysed, revealing an 82% success rate.

Sign in / Sign up

Export Citation Format

Share Document