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





Published By Inventive Research Organization

Updated Friday, 23 July 2021

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.

Joy Iong-Zong Chen ◽  
Kong-Long Lai

The design of an analogue IC layout is a time-consuming and manual process. Despite several studies in the sector, some geometric restrictions have resulted in disadvantages in the process of automated analogue IC layout design. As a result, analogue design has a performance lag when compared to manual design. This prevents the deployment of a large range of automated tools. With the recent technical developments, this challenge is resolved using machine learning techniques. This study investigates performance-driven placement in the VLSI IC design process, as well as analogue IC performance prediction by utilizing various machine learning approaches. Further, several amplifier designs are simulated. From the simulation results, it is evident that, when compared to the manual layout, an improved performance is obtained by using the proposed approach.

S Thivaharan ◽  
G Srivatsun

The amount of data generated by modern communication devices is enormous, reaching petabytes. The rate of data generation is also increasing at an unprecedented rate. Though modern technology supports storage in massive amounts, the industry is reluctant in retaining the data, which includes the following characteristics: redundancy in data, unformatted records with outdated information, data that misleads the prediction and data with no impact on the class prediction. Out of all of this data, social media plays a significant role in data generation. As compared to other data generators, the ratio at which the social media generates the data is comparatively higher. Industry and governments are both worried about the circulation of mischievous or malcontents, as they are extremely susceptible and are used by criminals. So it is high time to develop a model to classify the social media contents as fair and unfair. The developed model should have higher accuracy in predicting the class of contents. In this article, tensor flow based deep neural networks are deployed with a fixed Epoch count of 15, in order to attain 25% more accuracy over the other existing models. Activation methods like “Relu” and “Sigmoid”, which are specific for Tensor flow platforms support to attain the improved prediction accuracy.

Subarna Shakya

Smart city is a quickly developing approach that is powered by Internet of Things (IoTs), providing a number of services such as collaborative diagnosis and intelligent transportation. In general, in a smart city, the terminals have certain limitations that crib their capability of processing cross application and diversified services. Due to insufficient availability of resources that can be used to develop a collaborative smart city services, a novel methodology that is highly recommended is edge computing which holds facility with high processing ability in the city terminals. However, the threat of privacy and safety of information in the collaborative services is crucial in order to ensure a safer environment of edge computing. To address this privacy issue, we have proposed an offloading method that can be used in smarty city to strengthen the privacy, promote edge utility and improve offloading efficiency. In order to establish balance between the collaborative service and privacy preservation, edge computing is integrated with information entropy. The performance is further verified using simulation analysis in appropriate environment.

Jennifer S. Raj

Edge computing is a new computing paradigm that is rapidly emerging in various fields. Task completion is performed by various edge devices with distributed cloud computing in several conventional applications. Resource limitation, transmission efficiency, functionality and other edge network based circumstantial factors make this system more complex when compared to cloud computing. During cooperation between the edge devices, an instability occurs that cannot be ignored. The edge cooperative network is optimized with a novel framework proposed in this paper. This helps in improving the efficiency of edge computing tasks. The cooperation evaluation metrics are defined in the initial stage. Further, the performance of specific tasks are improved by optimizing the edge network cooperation. Real datasets obtained from elderly people and their wearable sensors is used for demonstrating the performance of the proposed framework. The extensive experimentation also helps in validating the efficiency of the proposed optimization algorithm.

Kong-Long Lai ◽  
Joy Iong Zong Chen

In construction of smart cities, Internet of Things and Fog computing have a crucial role to play which requires the need for management and exchange of large amount of information. Both Internet of Things as well as Fog computing are two predominant fields that have emerged in recent years to enable the development of transportation, tourism, industries as well as business in a proficient manner. Hence the introduction of a smart city will require proper study as well as ways to improve the strength’s of the city using technological advancement. This will also enhance the strength of city in many fronts. In this paper, we have examined the positive aspects of fog computing using an IoT architecture that is integrated with fog computing in order to address the issues of network scalability and big data processing. Accordingly, the architecture of the IoT system is built such that the smart city will be able to function in a more efficient manner by means of network transmission, information processing and intelligent perceptions.

Export Citation Format

Share Document