Volume 10, Number 3

In a recent era of modern technology, there are many problems for storage, retrieval and transmission of data. Data compression is necessary due to rapid growth of digital media and the subsequent need for reduce storage size and transmit the data in an effective and efficient manner over the networks. It reduces the transmission traffic on internet also. Data compression try to reduce the number of bits required to store digitally. The various data and image compression algorithms are widely use to reduce the original data bits into lesser number of bits. Lossless data and image compression is a special class of data compression. This algorithm involves in reducing numbers of bits by identifying and eliminating statistical data redundancy in input data. It is very simple and effective method. It provides good lossless compression of input data. This is useful on data that contains many consecutive runs of the same values. This paper presents the implementation of Run Length Encoding for data compression.

Hide Abstract

One of the most common methods of communication involves the use of e-mail for personal messages or for business purposes. One of the major concerns of using the emails is the problem of e-mail spam. The worst part of the spam emails is that, these are invading the users without their consent and bombarding of these spam mails fills up the whole email space of the user along with that, the issue of the wasting the network capacity and time consumption in checking and deleting the spam mails makes it even more concerning issue.  With the increasing demand of removing the e-mail spams the area has become magnetic to the researchers. This paper intends to present the performance comparison analysis of various pre-existing classification technique. This paper discusses about spam mails in section (I), In section (II) various feature selection methods are discussed , In section (III) classification techniques concept in spam filtering has been elaborated, In section (IV) existing algorithms for classification are discussed and are compared. In section (V) concludes the paper giving brief summary of the work.

Hide Abstract

Agriculture is a gigantic sector of the Indian economy as its share to gross domestic product (GDP) is almost 17 per cent. Over 60 per cent of the population adopts agriculture as main occupation. In spite of a large of Indian economy, agriculture is lagging behind many aspects and characterised by poor connectivity and disintegration of market, unreliable and delayed information to the farmers, small land holdings, non adoption or less adoption of improved technology and so on. It has become indispensable to explore various ways to keep our farmers updated about modern technologies and relevant information. The development and timely dissemination of better personalized technologies specific to different agro-climatic conditions, size of land holding, soil type, type of crops and related pests/diseases is the real issue to brazen out ahead for the agricultural scientists/experts. The timely availability of right information and its proper utilisation is indispensable for agriculture. ICT based initiatives can be taken for propagation of information, transfer of technology, procurement of inputs and selling of outputs in a way so that farmers can be benefitted. The timely information and practical solutions of the agricultural problems helps the farmers to adopt good agricultural practices, make better choices of inputs and to plan the cultivation properly.

Hide Abstract

Maturity checking has become mandatory for the food industries as well as for the farmers so as to ensure that the fruits and vegetables are not diseased and are ripe. However, manual inspection leads to human error, unripe fruits and vegetables may decrease the production [3]. Thus, this study proposes a Tomato Classification system for determining maturity stages of tomato through Machine Learning which involves training of different algorithms like Decision Tree, Logistic Regression, Gradient Boosting, Random Forest, Support Vector Machine, K-NN and XG Boost. This system consists of image collection, feature extraction and training the classifiers on 80% of the total data. Rest 20% of the total data is used for the testing purpose. It is concluded from the results that the performance of the classifier depends on the size and kind of features extracted from the data set. The results are obtained in the form of Learning Curve, Confusion Matrix and Accuracy Score. It is observed that out of seven classifiers, Random Forest is successful with 92.49% accuracy due to its high capability of handling large set of data. Support Vector Machine has shown the least accuracy due to its inability to train large data set.

Hide Abstract

The present research effort analyses various application areas of risk oriented testing and indentifies the gaps from the past .We need risk oriented testing not only for identifying risks in the projects but also for the maximum optimization of resources .Our research stresses on risk oriented testing in pervasive and evolutionary computational areas as due to dynamicity of such computing environment ,the project imbibes risk in great measure and needs to be taken care in early stages of the project .  Risk oriented testing requires concentration in both of these application areas as extremely little work has been done in this regard.

Hide Abstract

In recent years there has been widely increase the use of digital media everywhere. To increase the use of digital media, there is a huge problem of storage, manipulation and transmission of data over the internet. These digital media such as image, audio and video require large memory space. So it is necessary to compress the digital data to require less memory space and less bandwidth to transmission of data over network. Image compressions techniques are used to compress the data for reduce the storage requirement. It plays an important role for transfer of data such as image over the network. Two methods are used in this paper on Barbara image. This compression study is performed by using Set Partitioning In Hierarchical Trees (SPIHT) and Embedded Zero tree Wavelet (EZW) compression techniques. There are many parameters are used to compare this techniques. Mean Square Error (MSE), Pick Signal to Noise Ration (PSNR) and Compression Ratio (CR) are used at different level of decompositions.

Hide Abstract

Two major trends that have an effect on our planet: increase and urbanization. The anticipated increase for the primary one and half this century is discouraging. Betting on the estimate, there'll be nine to ten billion individuals by mid-century. This population is simply beneath seven billion that means that there'll be a couple of fifty percentage increases from the start to the center of this century. One could dialogue the relative accuracy of explicit models, however all of them agree that there'll be several, more mouths to enclose the approaching decades.

IT has reworked several different aspects of human endeavor and has helped produce systems for responding to a good varies of social group wants. Indeed, transportation, communication, national security, and health systems square measure utterly dependent thereon to perform even basic functions. However, data, and its automatic technological embodiment, has not compact agriculture to identical level.

Hide Abstract

In the recent development of IT technology, the capacity of data has surpassed the zettabyte, and improving the efficiency of business is done by increasing the ability of predictive through an efficient analysis on these data which has emerged as an issue in the current society. Now the market needs for methods that are capable of extracting valuable information from large data sets. Recently big data is becoming the focus of attention, and using any of the machine learning techniques to extract the valuable information from the huge data of complex structures has become a concern yet an urgent problem to resolve. The aim of this work is to provide a better understanding of this Machine Learning technique for discovering interesting patterns and introduces some machine learning algorithms to explore the developing trend.

Hide Abstract

Wireless Sensor Networks (WSNs) are developing very fast in the wireless networks. The wireless sensor network has the characteristics of limited memory, small size and limited battery. WSNs are vulnerable to the different types of attacks due to its characteristics. One of the attacks is clone node attack in which attacker capture the nodes from the network and stoles the information from it and replicates it in the network. From the clone nodes, the attacker can easily launch the different type of attacks in the network. To detect the clone node, different methods has been implemented .Each method having advantages and limitations. In the this paper, we explain the different methods to detect the clone nodes in the static wireless sensor network and compare their performance based on the communication cost and memory.

Hide Abstract

Escalating crimes on digital facet alarms the law enforcement bodies to keep a gaze on online activities which involve massive amount of data. This will raise a need to detect suspicious activities on online available social media data by optimizing investigations using data mining tools. This paper intends to throw some light on the data mining techniques which are designed and developed for closely examining social media data for suspicious activities and profiles in different domains. Additionally, this study will categorize the techniques under various groups highlighting their important features, challenges and application realm.

Hide Abstract

A comprehensible Visual Basic (VB) computer program is developed to find out the tractor parameters for an automated steering system. Tractor parameters such as real wheel and front wheel trajectory coordinates, clockwise front and rear wheel angle and corrected front and rear wheel angle can be calculated. Front wheel trajectory data, rear wheel trajectory, distance between front and rear wheel(X₁₃), Tractor velocity vector(V) and Tractor turning angle with center line are input variables for developed software. The tractor parameters are being calculated with the help of mathematical model which are already fed in program. The developed program successfully calculates the tractor parameters on automated steering . This developed software could guide an autonomous agricultural tractor in the field. Furthermore, software navigates agricultural tractor both in straight or curved path at normal field operational speed.

Hide Abstract

In this paper, we give a framework for integration of patients’ Body Area Network with IoT. We also discuss the enabling technologies that may help with the proliferation of the IoT in healthcare, besides mitigating various interoperability challenges in a healthcare IoT. We use a healthcare use-case of an artificial pancreas for diabetic patients to discuss our framework. We describe the framework as a formal model of a healthcare IoT, which we map onto the components of a proposed end-to-end, closed-loop health-care IoT architecture. In this paper, we also discuss dependability in a healthcare IoT. As such, we describe why certification, standardisation, and dependability should be central for a healthcare IoT.

Hide Abstract

Tree volume is one of the oldest areas of interest and is a crucial task in tree management system. Estimating the woody volume of a live tree is important for economic, scientific purposes and provides a tool to researcher/grower. It provides the useful information about the commercial value of wood to the potential buyer/seller. However, manual methods are being used largely to calculate woody volume of a tree. These methods are based on different log rules, cumbersome and laborious. The present work proposed a digital image processing technique to estimate the woody volume of a live tree. The developed program successfully determines the woody volume of standing tree trunk with MATLAB image processing techniques. In this method three parameters an individual tree were extracted from digital images of the tree. Calibration factor was also calculated to make the method independent of camera distance from the tree. The method was tested on several samples of trees and compared to experimental results. The soft approach generates information about height, diameter and volume of the tree. The percentage error of height, diameter at breast height and volume of standing tree by proposed method and experimental results was found to be less than 6.65%.

Hide Abstract

Complex Word Identification (CWI) is the process of locating difficult words from a given sentence. The aim of automated CWI system is to make non-native English user understand the meaning of target word in the sentence. CWI systems assist second language learners and dyslexic users through simplification of text. This study introduces the CWI process and investigates the performance of twenty systems submitted in the SemEval -2016 for CWI. The G-score measure which is harmonic mean of accuracy and recall is taken for the performance evaluation of systems. This paper explores twenty CWI systems and identifies that why sv000gg system outperformed with highest G-score as 0.773 and 0.774 for the two respective submissions.

Hide Abstract

Evolution of software is cumbersome process and also needs many iterations of software testing for satisfying some quality criteria. Software quality assurance activities must be effectively used for the proper software quality management and to achieve good product quality .Effective quality management is related to Value Engineering and Risk Management. In the present paper we will study relevance of quality assurance tools, strategies and models while doing risk based testing for the proper product function orientation .By analysing risks we can get to know how much we need to do the testing of software and further can assure the software quality.

Hide Abstract

Big Data is defined by 3Vs which stands for variety, volume and velocity. The volume of data is very huge, data exists in variety of file types and data grows very rapidly. Big data storage and processing has always been a big issue. Big data has become even more challenging to handle these days. To handle big data high performance techniques have been introduced. Several frameworks like Apache Hadoop has been introduced to process big data. Apache Hadoop provides map/reduce to process big data. But this map/reduce can be further accelerated. In this paper a survey has been performed for map/reduce acceleration and energy efficient computation in quick time.

Hide Abstract

Mobile ad-hoc Network [MANET] is the collection of mobile nodes deployed with the short-lived purpose. It is the most innovative and useful variety which provide the facility to establish communication without the prerequisite of any infrastructure. Here, wireless communication medium is usually used for communication and connection establishment purpose. Generally, it is deployed with mobile nodes but can be used for stationary design also. Open nature communication makes it vulnerable for several security threats. This paper has considered the simulation of AODV and ODMRP using Qualnet 5.2 simulator.

Hide Abstract

Traffic conditions in infrastructure-less environment are in many ways not ideal for driving. This is due to undefined road curvature, faded and unmaintained lane markings and various obstacles situations cause vital life loses and damage of vehicles in accidents. This paper provides an efficient approach of finding various roadways obstacles situation using our depth learning approach based on the data collected through a Smartphone. The existing methods are suitable for planned or structured roads. The proposed approach is suitable for planed as well as unplanned roads i.e. for infrastructure-less environment. The approach is capable of effectively classifying roadways obstacles into predefined categories using depth learning approach. While compared with other similar approach this approach is a cost effective approach

Hide Abstract

Cryptanalysis is a standout amongst the most vital requesting zones of capable research in the request of the security. An approach of data security is Cryptography. Cryptanalysis is the investigation to break cryptography without the encryption key. Cryptanalysis is breaking or separating cipher text content into its identical plain-content without past data of the secret key or without knowing the real approach to unscramble the cipher text content. Particle Swarm Optimization (PSO) is a population based, self-versatile find improvement of optimization performance motivated by group performance of bird flocking or fish schooling. In this paper discussed with use of PSO in automated cryptanalysis of simple substitution ciphers. In this manner, encrypted data can be sent by any individual utilizing the general puplic key, yet the data can be decoded just by the holder of the secret key.

Hide Abstract

The problem of recursively approximating motion resulting from the Optical Flow (OF) in video thru Total Least Squares (TLS) techniques is addressed. TLS method solves an inconsistent system Gu=z , with G and z in error due to temporal/spatial derivatives, and nonlinearity, while the Ordinary Least Squares (OLS) model has noise only in z. Sources of difficulty involve the non-stationarity of the field, the ill-posedness, and the existence of noise in the data. Three ways of applying the TLS with different noise conjectures to the end problem are observed. First, the classical TLS (cTLS) is introduced, where the entries of the error matrices of each row of the augmented matrix [G;z] have zero mean and the same standard deviation. Next, the Generalized Total Least Squares (GTLS) is defined to provide a more stable solution, but it still has some problems. The Generalized Scaled TLS (GSTLS) has G and z tainted by different sources of additive zero-mean Gaussian noise and scaling [G;z] by nonsingular D and E, that is, D[G;z] E makes the errors iid with zero mean and a diagonal covariance matrix. The scaling is computed from some knowledge on the error distribution to improve the GTLS estimate. For moderate levels of additive noise, GSTLS outperforms the OLS, and the GTLS approaches. Although any TLS variant requires more computations than the OLS, it is still applicable with proper scaling of the data matrix.

Hide Abstract

Vehicle Routing Problem (VRP) is a real life constraint satisfaction problem to find minimal travel distances of vehicles to serve customers. Capacitated VRP (CVRP) is the simplest form of VRP considering vehicle capacity constraint. Constructive and clustering are the two popular approaches to solve CVRP. A constructive approach creates routes and attempts to minimize the cost at the same time. Clarke and Wright’s Savings algorithm is a popular constructive method based on savings heuristic. On the other hand, a clustering based method first assigns nodes into vehicle wise cluster and then generates route for each vehicle. Sweep algorithm and its variants and Fisher and Jaikumar algorithm are popular among clustering methods. Route generation is a traveling salesman problem (TSP) and any TSP optimization method is useful for this purpose. In this study, popular constructive and clustering methods are studied, implemented and compared outcomes in solving a suite of benchmark CVRPs. For route optimization, Genetic Algorithm (GA), Ant Colony Optimization (ACO) and Velocity Tentative Particle Swarm Optimization (VTPSO) are employed in this study which are popular nature inspired optimization techniques for solving TSP. Experimental results revealed that parallel Savings is better than series Savings in constructive method. On the other hand, Sweep Reference Point using every stop (SRE) is the best among clustering based techniques.

Hide Abstract

This paper proposes a novel design for Binary to Gray code encoders and/or counters using multiplexers and flip-flops. The proposed design are modular based, whereby other stages can be added as per the requirement of the desired applications. Moreover, the external clock timing signal drives only the first stage, while all remaining stages are linked to the outputs from preceding stages. The successive stages transitions at half the rate of the preceding stage thereby, makes the design power efficient since the dissipated power is quadratic frequency dependent. The proposed design can be modified to increase the counters duration or increase the counters resolution according to the applications need. Increasing the Gray counters time span by powers of two simply necessitates augmenting the design by more stages, while maintaining a constant clock rate. On the other hand, doubling the time resolution of the Gray counter over a constant time span can be achieved by adding another stage while subsequently doubling the clock rate.

Hide Abstract