Showing papers in "International Journal of Computer Applications in 2019"

Internet of Things (IoT) of Smart Home: Privacy and Security

Abstract: The smart home is an environment, where heterogeneous electronic devices and appliances are networked together to provide smart services in a ubiquitous manner to the individuals. organization and people are wide accepting and adopting the functionalities offered by the smart home applications. this can be because of the various advantages, in easing users’ everyday life and work, provided by the rising internet of Things (IoT) technologies and devices, equipped with sensors, cameras, or actuators, and able either to accumulate information from the environment or to perform proper tasks. the main features of smart homes embrace realtime monitoring, remote control, safety from intruders, gas/fire alarm, and so on. Since among smart homes, sensitive and personal data are managed, security and privacy solutions should be put in place, to protect users/businesses’ data against violation try still on guarantee the supply of reliable services. As IoT home devices become increasingly ubiquitous, study’s findings and recommendations contribute to the broader understanding of users’ evolving attitudes towards privacy in smart homes.

The Internet of Things (IoT) and its Application Domains

Abstract: There is no suspicion that IoT has added a new dimension to the living being by the link between smart objects. Thus making the link among any media and anything at any place and anytime was appreciable. Under the umbrella of the Internet of Things (IoT) the number of interconnected devices is expected to grow exponentially toward more than 34 billion devices until 2021. IoT will propose the unique identification of the objects and their virtual representation as the basis for autonomously development of applications and services. These will be characterized by enormous and self-governing data capture, incident transfer, network connectivity and interoperability. This technology has a lot of applications in heterogeneous fields. The IoT technology and applications are likely to be major drivers of investment and innovation in the communications sector, over the forthcoming years, delivering the valued advantage to citizens, client and industrial end-users. These will lead to the introduction of many new and modern services. It will permit data to be transmitted between many various types of devices, enhance the safety of transportation, and decrease the consumption of energy and enhance our health. In this paper, we are briefly discussing about the Internet of Things and applications in several fields. The IoT applications are using at the edge of the network sensors accumulate data on a computing and communicating device and actuators to perform distinguished tasks controlled by these devices.

A Detailed Survey on Topic Modeling for Document and Short Text Data

Abstract: Text mining is one of the most significant field in the digital era due to the rapid growth of textual information. Topic models are gaining popularity in the last few years. A topic comprises of a group of words that are often take place together. Topic models are better performing techniques to extract semantic knowledge presented in the data. The various methods used for topic models are, LSA (Latent Semantic Analysis), PLSA (Probabilistic Latent Semantic Analysis), LDA (Latent Dirichlet Allocation). These methods gained popularity in extracting hidden themes from the document (corpus). Various topic modeling algorithms are developed to inquiry, summarize and extract hidden semantic structures of large corpus. In this paper, we present a detailed survey covering the various topic modeling techniques proposed in last decade. Additionally, we focus on different strategies of extracting the topics in social media text, where the goal is to find and aggregate the topic within short texts. Further, we summarize the various applications and quantitative evaluation of the various methods, with statistical and mathematical knowledge to predict the convergence of results.

Intelligent tutoring systems: A comprehensive historical survey with recent developments

Abstract: This paper provides interested beginners with an updated and detailed introduction to the field of Intelligent Tutoring Systems (ITS). ITSs are computer programs that use artificial intelligence techniques to enhance and personalize automation in teaching. This paper is a literature review that provides the following: First, a review of the history of ITS along with a discussion on the interface between human learning and computer tutors and how effective ITSs are in contemporary education. Second, the traditional architectural components of an ITS and their functions are discussed along with approaches taken by various ITSs. Finally, recent innovative ideas in ITS systems are presented. This paper concludes with some of the author's views regarding future work in the field of intelligent tutoring systems.

Behavioral Malware Detection using Deep Graph Convolutional Neural Networks

Abstract: Malware behavioral graphs provide a rich source of information that can be leveraged for detection and classification tasks. In this paper, we propose a novel behavioral malware detection method based on Deep Graph Convolutional Neural Networks (DGCNNs) to learn directly from API call sequences and their associated behavioral graphs. In order to train and evaluate the models, we created a new public domain dataset of more than 40,000 API call sequences resulting from the execution of malware and goodware instances in a sandboxed environment. Experimental results show that our models achieve similar Area Under the ROC Curve (AUC-ROC) and F1-Score to Long-Short Term Memory (LSTM) networks, widely used as the base architecture for behavioral malware detection methods, thus indicating that the models can effectively learn to distinguish between malicious and benign temporal patterns through convolution operations on graphs. To the best of our knowledge, this is the first paper that investigates the applicability of DGCNN to behavioral malware detection using API call sequences.

Action Research Implementation in Developing an Open Source and Low Cost Robotic Platform for STEM Education

Abstract: The aim of this paper is double: (a) to record the latest theoretical considerations (literature review) in the field of STEM (acronym of Science, Technology, Engineering, Mathematics), Educational Robotics and the Educational Robotic Platforms used in their implementation, and (b) to validate the argumentation on the potential contribution of an Action Research implementation on STEM education with the ultimate goal of designing and developing an “open philosophy”, low-cost, hardware and software educational platform for the implementation of STEM and Educational Robotics. This paper is divided into 7 sections: Introduction, STEM Education, Educational Robotics, Problem statement, Action Research, Methodology, and Conclusion. The Introduction introduces the concept and necessity of STEM education approach. STEM Education section reviews recently published scientific literature related to STEM education (literature review) and summarize the pros and barriers of its use in education. Educational Robotics introduces the robotics as an educational tool and presents empirical evidence on its effectiveness. Educational Robot Platforms subsection presents the most popular -along with their main specseducational robots for STEM and Educational Robotics use. Problem statement section identifies the scientific gap and composes the necessity to implement research (specifically an Action Research) on designing and developing an “open philosophy”, low-cost, hardware and software academic platform for the implementation of STEM and Educational Robotics. Action research section reviews recently published scientific literature related to action research. Research Methodology section presents research’s proposal development phases and finally, Conclusion summarizes paper’s findings.

A Survey of Multi-mobile Robot Formation Control

Abstract: This paper denotes a survey on formation control of multi-mobile robot systems which drawn significant attention for the last years. It is concentrated on the stability of multi mobile robots when they obtained the required formation. Also this paper discusses the approaches of formation control and applications of them in changing and remote environments. Two classifications for the formation control methods are surveyed in this paper: the formation control strategies and the formation control stability. The differences among the surveyed approaches are discussed and the results are summarized.

Audio Enhancement and Synthesis using Generative Adversarial Networks: A Survey

Abstract: Generative adversarial networks (GAN) have become prominent in the field of machine learning. Their premise is based on a minimax game in which a generator and discriminator “compete” against each other until an optimal point is reached. The goal of the generator is to produce synthetic samples that match that of real data. The discriminator tries to classify the real data as real and the generated data as not real. Together, the generator improves to the point where the fake data and real data are identical to the discriminator. GAN has been successfully applied in the image processing field over a large range of GAN variant architectures. Although not as prominent, the audio enhancement and synthesis field has also benefitted from GAN in a variety of different forms. In this survey paper, different techniques involving GAN will be explored relative to speech synthesis, speech enhancement, music generation, and general audio synthesis. Strengths and weaknesses of GAN will be looked at including variants created to combat those weaknesses. Also, a few similar machine learning architectures will be explored that may help achieve promising results.

A Comparative Analysis of Symmetric Algorithms in Cloud Computing: A Survey

Abstract: Introducing Cloud computing to the globe has changed many conceptual and infrastructural bases for today’s and tomorrow’s computing. It has made the global thinking migrates rapidly towards cloud based architecture. Clouds bring out a variety of benefits including computing resources configurability, cost controllability, sustainability, mobility and service flexibility. However, the new concepts that clouds introduce such as outsourcing, multi-tenancy, and resource sharing create new challenges and raise a broad range of security and privacy issues. Cryptography is the art-of-science of protecting data privacy by converting it to unreadable format using standard mathematical techniques. This paper provides a comprehensive study for eight of the most common symmetric cryptographic algorithms, namely, DES, 3DES, Blowfish, Twofish, RC2, RC5, RC6 and AES. A comparative analysis based on the structure of the algorithm, encryption and decryption times, throughput and memory utilization has been performed to examine the performance of each algorithm.

Remote Sensing Image Segmentation using OTSU Algorithm

Abstract: In recent years, extraction of information from remote sensing images is an active topic of research. Feature extraction from an image is performed by image segmentation by dividing the image into distinct and self-seminar pixel groups. In remote sensing images, large quantity of texture information is present. So, it is difficult and time consuming process to segment objects from the background in remote sensing images. Many algorithms have been proposed for the purpose of segmentation of remote sensing images. Thresholding is a simple technique but effective method to separate objects from the background. A commonly used method, the Otsu method, improves the image segmentation effectively. It is the most referenced thresholding methods, as it directly operates on the gray level histogram. In this project, Otsu thresholding algorithm is used to segment the roads and residential areas from the vegetation areas in remote sensing images.

Toward Mitigating Adversarial Texts

Abstract: Neural networks are frequently used for text classification, but can be vulnerable to misclassification caused by adversarial examples: input produced by introducing small perturbations that cause the neural network to output an incorrect classification. Previous attempts to generate black-box adversarial texts have included variations of generating nonword misspellings, natural noise, synthetic noise, along with lexical substitutions. This paper proposes a defense against black-box adversarial attacks using a spell-checking system that utilizes frequency and contextual information for correction of nonword misspellings. The proposed defense is evaluated on the Yelp Reviews Polarity and the Yelp Reviews Full datasets using adversarial texts generated by a variety of recent attacks. After detecting and recovering the adversarial texts, the proposed defense increases the classification accuracy by an average of 26.56% on the Yelp Reviews Polarity dataset and 16.27% on the Yelp Reviews Full dataset. This approach further outperforms six of the publicly available, state-of-the-art spelling correction tools by at least 25.56% in terms of average correction accuracy.

Grapes Leaf Disease Detection using Convolutional Neural Network

Abstract: Grapes (Vitis Vinifera) is basically a sub-tropical plant having excellent pulp content, rich color and is highly beneficial to health. Generally, it is very time-consuming and laborious for farmers of remote areas to identify grapes leaf diseases due to unavailability of experts. Though experts are available in some areas, disease detection is performed by naked eye which causes inappropriate recognition. An automated system can minimize these problems. The disease on the grape plant usually starts on the leaf and then moves onto the stem, root and the fruit. Once the disease reaches the fruit the whole plant gets destroyed. The approach is to detect the disease on the leaf itself in order to save the fruit. In our proposed system we have used a Deep Learning model named Convolutional Neural Network. Feature extraction and model training of the leaf images is performed using pre-defined AlexNet architecture. The image Dataset is taken from “National Research Centre for Grapes” (ICAR). It consists of images of diseases named Powdery mildew, Downy mildew, Rust, Bacterial Spots and Anthracnose. Image of the leaf is captured using the built-in camera module of a mobile phone. The accuracy achieved is 98.23% for powdery mildew vs bacterial spots.

Exploring the Recent Trends of Paraphrase Detection

Abstract: This study is to examine paraphrase detection (PD) for diagnostic purposes. Which is defined as the capability to find and discover the similarity between sentences that are written in a natural language? Where detecting similar sentences written in natural language is extreme importance and it is very essential for computer software used in plagiarism detection, Q and A automated systems, text mining, authorship authentication and text recapitulation. The goal of paraphrase detection is to detect whether two statements have the identical semantic or not. There is hundreds of empirical research in this direction. This study will focus on the discussion of recent studies of the PD methods and will categorize them in two categories, supervised learning and unsupervised learning. Also will give an idea about text similarity, machine learning and deep learning approaches. The performance of the selected researches is assessed by how accurate the F-measures are in detecting paraphrase in Microsoft Research Paraphrase Corpus (MSPR).

Detection and Prevention of DDoS attacks on Software Defined Networks Controllers for Smart Grid

Abstract: With the evolution of smart grid, the operations, planning and maintenance of an electric grid have improved. On the contrary, smart grid totally relies on the computer network so there is a need of complex and efficient network management. Software defined networks (SDN) is a completely new modern architecture that allows the network to be centrally controlled or explicitly programmed using software applications. Traditionally in computer networks, the routing and switching decisions are implemented on a dedicated hardware. This hardware can be a switch or a router. But with the evolution of Software defined networks, the routing and switching function has been separated and is classified in Control and data planes respectively. Generally, in SDN, the control plane is centralized and is responsible to make a decision on what to do with the incoming packet. Once the decision is made, it is saved in the forwarding table of a switch on the data plane. While Software Defined Network (SDN) has its advantages of central management, programmability, agility and vendor neutrality, they carry a high risk of Distributed Denial of Service attack (DDoS). Centralized nature of the control plane in SDN is a huge risk factor because the attacker may bombard the control plane with malicious packets resulting in a single point of failure of the control plane. If the control plane fails, the entire smart grid network will collapse resulting in a massive outage and financial loss to the stakeholders. In this paper, we have devised a distributed approach, using blockchains, to detect and prevent DDoS attacks on the centralized control plane of SDN. We have simulated our approach using AnyLogic simulator and the results show that the proposed approach is more efficient as compared the existing techniques as it substantially reduces the risk of DDoS attacks and SDN controller overhead.

A Review on Edge detection Technique “Canny Edge Detection”

Abstract: The traditional Canny edge detection method is widely used in gray image processing. However, this traditional algorithm is unable to deal with color images and the parameters in the algorithm are difficult to be determined adaptively. In this paper, an improved Canny algorithm is proposed to detect edges in color image. The proposed algorithm is composed of the following steps: quaternion weighted average filter, vector Sobel gradient computation, non-maxima suppression based on interpolation, edge detection and connection. Experimental results show that the proposed algorithm outperforms other color image edge detection methods and can be widely used in color image processing. This project we present a two dimensional edge detector which gives the edge position in an image with sub-pixel accuracy. The method presented here gives an excellent accuracy (the position bias mean is almost zero and the standard deviation is less than one tenth of a pixel) with a low computational cost’ and its simple since it is derivated from the well known Non-Maxima Suppression method in Matlab[1].

A Proposed Routing Protocol for Mobile Ad Hoc Networks

Abstract: Routing in wireless mobile ad hoc networks (MANETs) is a challenging task. Geographic routing protocols offer promising solutions for routing in MANETs. Their advantages are eliminating the need of topology storage and the associated costs. A disadvantage is that all nodes must be equipped with GPS receivers to be aware of their own positions which consume money and energy. Besides, GPS receivers may not work in areas that are mostly concentrated with computing devices. This work proposes a new routing algorithm that is suitable for network where some nodes may be aware of their position through GPS while others are not. In the proposed algorithm, routing decision is made by the combination of greedy forwarding mechanism and on-demand routing one. Packets are forwarded in greedy mode when position information is available and routed using a reactive on demand procedure when this information is missed. Simulation results show that the proposal achieves better performance compared to GPSR and the DSR protocols concerning end-to-end delay, throughput and packet delivery ratio

Multiprocessing Stemming: A Case Study of Indonesian Stemming

Abstract: Research in the field of Natural Language Processing (NLP) is currently increasing especially with the arrival of a new term that is "big data". The needs of the programming library that ready-touse becomes very important to speed up the phases of research. Some libraries that have already been mature is available but generally for English language and its dependently. So, it can't be used for other languages. Stemming is one of the basic processes that exist in NLP.Indonesian stemming algorithm that often used is ECS (Enhanced Confix Stripping). One of the libraries that already implemented the algorithm is Sastrawi. Results from the experiment show that the time of stemming processing by Sastrawi is still slow. Therefore, this research will optimize the speed of stemming processing using multiprocessing (MP). The data test are used in this research has manually taken form Wikipedia.The experiment results show that the MP technique can decrease the average time of stemming processing about 98.45%.

Student Academic Performance Prediction using Artificial Neural Networks: A Case Study

Abstract: Students dropout and delay in graduation are significant problems at Katsina State Institute of Technology and Management (KSITM). There are various reasons for that, students’ performances during first year is one of the major contributing factors. This study aims at predicting poor students’ performances that might lead to dropout or delay in graduation so as to allow the institution to develop strategic programs that will help improve student performance and enable the student to graduate in time without any problem. This study presents a neural network model capable of predicting student’s GPA using students’ personal information, academic information, and place of residence. A sample of 61 Computer Networking students’ dataset was used to train and test the model in WEKA software tool. The accuracy of the model was measured using well-known evaluation criteria. The model correctly predicts 73.68% of students’ performance and, specifically, 66.67% of students that are likely to dropout or experience delay before graduating.

Mann-Kendall, and Sen’s Slope Estimators for Precipitation Trend Analysis in North-Eastern States of India

Abstract: The cause of climate change detection is very tedious and complex phenomenon. For the purpose, the behaviour identification of climatic variable using long term historical database is very important. In present study, highlights the climatic variability has been identified using the nonparametric Mann-Kendall, and Sen’s slope estimators over north-eastern region of India. In this study long term precipitation data has been considered during 1901-2015. The non-parametric tests have been tested at the 5% level of significance. The non-parametric tests were applied at eight north-eastern states i.e., Arunachal Pradesh, Assam, Manipur, Meghalaya, Mizoram, Nagaland, Tripura and West-Bengal of India. This type of study is very necessary for long-term agricultural and water resources planning of the states.

Critical Challenges for Requirement Implementation in Global Software Development: A Systematic Literature Review Protocol with Preliminary Results

Abstract: Context: Successful requirement engineering (RE) leads to successful delivery of software. There exist a lot of challenges during RE process especially in Global Software Development (GSD). The aim of this study is to find challenges during RE in context of GSD. Objective: The objective is to find and analyze the challenges in RE process. Method: Systematic Literature Review (SLR) is used as research method to achieve the goals. Result: SLR protocol is developed. Expected output of this study is to list out all challenges which the stakeholders are facing in implementing RE in the context of GSD through SLR. As a result of SLR protocol, 71 papers are identified.

Sentiment Analysis of Movie Reviews using Machine Learning Classifiers

Abstract: In today’s world, it has become customary to collect opinions and reviews from people through various surveys, polls, social media platform and analyse them in order to understand the preferences of customers. So, in order to understand the sentiments of customers and their view on the services offered by producers, there comes the need for an accurate and canonical mechanism for speculating and anticipating sentiments which possess the ability to fabricate a positive or negative impact in the market and thus making this kind of analysis important for the pair of producers and consumers. In this paper, the main focus is to anatomize the reviews conveyed by viewers on various movies and to use this analysis to understand the customers’ sentiments and market behaviour for better customer experience.

Knowledge based Recommendation System in Semantic Web - A Survey

Abstract: Knowledge based recommendation systems use knowledge about users and products to make recommendations. Knowledge-based recommendations are not dependent on the rating, nor do they have to gather information about a particular user to give recommendations. Knowledge acquisition is the most important task for constructing knowledge-based recommendation system. Acquired knowledge must be represented in some structured machine-readable form, e.g., as ontology to support reasoning about what products meets the user’s requirements. In Semantic Web, knowledge is represented in the form of ontology. Representation of knowledge in structured form of ontology in Semantic Web makes the application of knowledge based recommendations system on Semantic Web very easy, as there is no need to construct knowledge base from scratch. Performance of knowledge based recommendations systems can be enhanced by exploiting ontology reasoning characteristics. This paper explores different techniques used to generate knowledge-based recommendations highlighting the advantages of knowledge based recommendation system over other recommendation techniques.

A Study on Multiple Barcode Detection from an Image in Business System

Abstract: The pillar of automatic identification is Barcode technology which is used comprehensively in real time applications with various types of codes. The different types of codes and applications sometimes faces special problems, so the improvement of the effectiveness must be done persistently. This paper’s proposal mainly deals with multiple product’s barcode to be detected simultaneously. The proposed algorithm which will have implementation for supershop billing system and inventory management. The method will recognize the barcodes using image processing. Images will be taken using mobile camera sensor. It will detect 1D barcodes such as EAN-13 barcodes, Code-128 barcodes, 2D barcodes such as QR codes. Moreover, it will be angle invariant, requires less user interaction than usual and can be executed on available computers. This model helps consumers to minimize the time for the billing system in shopping. We have implemented this in Python IDE using OpenCV library.

Lung CT Parenchyma Segmentation using VGG-16 based SegNet Model

Abstract: Lung parenchyma segmentation is a very important stage in every CAD system for lung cancer detection. In this paper, we propose a new method for CT lung Parenchyma segmentation using the deep SegNet neural network with VGG-16 model. Firstly, 120 CT lung images were collected for the training phase and their ground truth maps were obtained using manual segmentation. Secondly, the training images alongside their corresponding ground truth label images were used as input to the VGG-16 based SegNet model. Finally, 60 CT lung images were collected to validate the performance of the model. The experimental results showed that an accurate segmentation with an average dice similarity index equal to 0.9586 is achieved.

Improved Round Robin Scheduling Algorithm with Progressive Time Quantum

Abstract: Process management is considered as an important function in the operating system where several scheduling algorithms are used to maintain it. Round Robin is one of the most conventional CPU scheduling algorithms which is frequently used in operating system. The performance of round robin algorithm differs on the choice of time quantum which is clarified by the researchers. In this paper, a new round robin scheduling algorithm has been proposed where time quantum is selected dynamically. An experimental evaluation has been conducted to evaluate the performance of the proposed algorithm. Also a comparative analysis has been performed where the obtained result of this proposed algorithm has been compared with some existing algorithms. The experimental result shows that the performance of the proposed algorithm performs much better than some mentioned algorithms in terms of average waiting time and average turnaround time. General Terms Scheduling Algorithm. Round Robin Scheduling

Nepali Speech Recognition using RNN-CTC Model

Abstract: This paper presents a Neural Network based Nepali Speech Recognition model. RNN (Recurrent Neural Networks) is used for processing sequential audio data. CTC (Connectionist Temporal Classification) [1] technique is applied allowing RNN to train over audio data. CTC is a probabilistic approach of maximizing the occurrence probability of the desired labels from RNN output. After processing through RNN and CTC layers, Nepali text is obtained as output. This paper also defines a character set of 67 Nepali characters required for transcription of Nepali speech to text.

Naïve Bayes Approach for the Crime Prediction in Data Mining

Abstract: Prediction analysis is the analysis in which future trends and outcomes are predicted on the basis of assumption. It is the analysis in which future trends and outcomes are predicted on the basis of assumption. Machine learning techniques and regression techniques are the two approaches that have been utilized in order to conduct predictive analytics. In the conducting predictive analytics, machine learning techniques are widely utilized and become popular as large scale datasets handled by it is effective manner and provide high performance. It provides the results with uniform characteristics and noisy data. The KNN is the popular technique which is applied in the prediction analysis. To improve accuracy of crime prediction technique of Naïve Bayes is applied in this research work. It is evaluated that Naïve Bayes give higher accuracy as compared to KNN for the crime prediction.

Arabic Question Answering: A Study on Challenges, Systems, and Techniques

Abstract: The enormous increase of the amount of information available on the web creates the need for systems like Question Answering to bridge the gap between general end users and the web with its different data representations. A considerable portion of the available data on the web is written in Arabic for and by Arabic users. This paper provides a review of the Arabic Question Answering Systems building processes and the challenges met by the researchers in this topic due to the Arabic language special characteristics. A general architecture is represented for the Question Answering task on both structured and unstructured data. Then, an overview of the work done in Arabic Question Answering Systems is presented. Finally, a number of tools and linguistic resources are recommended for researchers to develop Arabic question answering systems. General Terms Question Answering, Question Answering Systems, Natural Language Processing, Information Retrieval