CSED

Handwriting Recognition enables a person to scribble something on a piece of paper and then convert it into text. If we look into the practical reality there are enumerable styles in which a character may be written. These styles can be self combined to generate more styles. Even if a small child knows the basic styles a character can be written, he would be able to recognize characters written in styles intermediate between them or formed by their mixture. This motivates the use of Genetic Algorithms for the problem. In order to prove this, we made a pool of images of characters. We converted them to graphs. The graph of every character was intermixed to generate styles intermediate between the styles of parent character. Character recognition involved the matching of the graph generated from the unknown character image with the graphs generated by mixing. Using this method we received an accuracy of 98.44%.

Flying ad hoc networks (FANETs) are a collection of unmanned aerial vehicles that communicate without any predefined infrastructure. FANET, being one of the most researched topics nowadays, finds its scope in many complex applications like drones used for military applications, border surveillance systems and other systems like civil applications in traffic monitoring and disaster management. Quality of service (QoS) performance parameters for routing e.g. delay, packet delivery ratio, jitter and throughput in FANETs are quite difficult to improve. Mobility models play an important role in evaluating the performance of the routing protocols. In this paper, the integration of two selected mobility models, i.e. random waypoint and Gauss–Markov model, is implemented. As a result, the random Gauss integrated model is proposed for evaluating the performance of AODV (ad hoc on-demand distance vector), DSR (dynamic source routing) and DSDV (destination-Sequenced distance vector) routing pr...

Road related accidents have always been a nuisance to drivers and pedestrians alike. Every year countless accidents and deaths occur due to potholes which could have been preventable if there had been a prior warning or if the civic authorities were able to repair these potholes in time. This paper proposes a machine learning based pothole detection system called DeepBus for real time identification of surface irregularities on roads using Internet of Things (IoT). DeepBus uses IoT sensors to detect potholes in real time while an end user is driving vehicles on the road. The location of these potholes would be available on a centrally hosted map which can be accessed by both end users and civic authorities. Thus, it would serve as a warning system to all users as well as a database of potholes with thier locations to the authorities for quick repair and action. We have compared the performance of various machine learning models (Logistic Regression, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Naive Bayes, Decision Tree, Random Forest and Ensemble Voting) based on different parameters (Accuracy, F-score, Precision and Recall) and identified that Random Forest is the best model for pothole detection.

Establishing the maturity levels of-Small and Medium Enterprises (SMEs) without Capability Maturity Model Integration (CMMI) certification has always been regarded as an extremely challenging task. Software process improvement (SPI) has targeted to monitor and improve software processes, thereby improving the software business. Although there is scientific interest in SPI, little attention has been specifically given to the exploration of maturity levels for non-CMMI SMEs. The goal is to explore the effect of time on process maturity and maturity levels achieved informally or unofficially by SMEs that are not otherwise CMMI certified. To find out the maturity levels achieved informally, a CMMI-DEV v1.3 based survey questionnaire is administered to Indian software SMEs. Time of establishment of SMEs and follow-up of CMMI-based processes and practices unofficially are used as two important parameters to decide upon process maturity and achievement of specific CMMI level informally. This paper has been successful in ascertaining the effect of time of establishment of SMEs and follow-up of CMMI-based processes on process maturity using proposed RuleML that advocates adoption of more than 70% of CMMI-DEV v1.3 process area-specific practices for an SME to be unofficially ready for CMMI-based SPI initiatives. The findings manifest multidimensional aspects of unofficial readiness of SMEs for CMMI-based SPI that can be used by relevant authorities to select SMEs for funding for SPI initiatives. Finally, the proposed work has been validated statistically using t-test for CMMI Level II and Level III.

Software Processes are the lifeline of any Software Development Model. Software Processes decide the survival of a particular software development model in the market as well as in software organization. The set of processes those proved to be effective and efficient for software development in one organization may or may not be followed in another organization. That is other organization finds another approach for software development more convenient to work with. This paper explains the progression and remarkable change in Software Processes and their respective models. It also summarizes a contrast of classical software processes with Agility and CBSE.

This paper proposes IoT-based an enterprise health information system called IoTPulse to predict alcohol addiction providing real-time data using machine-learning in fog computing environment. We used data from 300 alcohol addicts from Punjab (India) as a case study to train machine-learning models. The performance of IoTPulse is compared against existing work using various parameters including accuracy, sensitivity, specificity and precision which shows improvement of 7%, 4%, 12% and 12% respectively. Finally, IoTPulse is validated in FogBus-based real fog environment using QoS parameters including latency, network bandwidth, energy and response time which improves performance by 19.56%, 18.36%, 19.53% and 21.56% respectively.

In recent years, healthcare data analysis is becoming one of the most promising research areas. Healthcare includes data in various types such as clinical data, Omics data, and Sensor data. Clinical data includes electronic health records which store patient records collected during ongoing treatment. Omics data is one of the high dimensional data comprising genome, transcriptome and proteome data types. Sensor data is collected from various wearable and wireless sensor devices. To handle this raw data manually is very difficult. For analysis of data, machine learning is emerged as a significant tool. Machine learning uses various statistical techniques and advanced algorithms to predict the results of healthcare data more precisely. In machine learning different types of algorithms like supervised, unsupervised and reinforcement are used for analysis. In this paper, different types of machine learning algorithms are described. Then use of machine learning algorithms for analyzing v...

179 Abstract—The Component Based Software Development (CBSD) approach is becoming the trend for software development which is based on developing the software from existing components instead of developing software from scratch everytime. Measuring software complexity is an important aspect during software development. Because software complexity is an important determinant of software development effort, testing effort , cost, maintainability etc. Researchers have proposed a wide range of complexity metrics for software systems . But the traditional software product and process metrics are neither suitable nor sufficient in measuring the Component and Component Based Software (CBS) complexity. So CBSD provides one of the central problems in measuring component and CBS complexity. Measuring component complexity plays an important role in determining the complexity of CBS system. Because component complexity affects the complexity of whole CBS . Component complexity affects integrati...

Image processing methods are widely used to improvise the quality of an image to extract the hidden information in it. Phenomena of scattering and atmosphere absorption results inhaze smoke and fog. Weather conditions majorly influence the visual system as well as detection and identification of the targets and degrade the picture quality. In the previous year, researchers have been focused on the high-quality images or videos for enhancement as well as to detect objects. In this paper, we have reviewed previous papers and compare based on used techniques and performance parameters.

To investigate how differing amounts of experiential feedback and feedback s availability in an interactive simulation tool influences people s decision-making against landslide risks. Feedback via simulation tools is likely to help people improve their decisions against disasters; however, currently little is known on how differing amounts of experiential feedback and feedback's availability in simulation tools influences people's decisions against landslides. We tested the influence of differing amounts of experiential feedback and feedback's availability on people's decisions against landslide risks in an Interactive Landslide Simulation (ILS) tool. In an experiment, in high-damage conditions, the probabilities of damages to life and property due to landslides were 10-times higher than those in the low-damage conditions. In feedback-present condition, experiential feedback was provided in numeric, text, and graphical formats in ILS. In feedback-absent conditions, the probabilities of damages were described; however, there was no experiential feedback present. Investments were greater in conditions where experiential feedback was present and damages were high compared to conditions where experiential feedback was absent and damages were low. Furthermore, only high-damage feedback produced learning in ILS. Experience gained in ILS enables people to improve their decision-making against landslide risks. Simulation tools seem appropriate for landslide risk communication and for performing what-if analyses. 1 Introduction Landslides cause massive damages to life and property worldwide (Chaturvedi and Dutt, 2015; Margottini et al., 2011). Knowledge about causes-and-consequences of landslides and awareness about landslide disaster mitigation are likely to help people take good mitigation actions that prevent landslides from occurring (Becker et al., 2013; Osuret et al., 2016; Webb and Ronan, 2014). However, to educate people about cause-and-effect relationships concerning landslides, effective landslide risk communication systems (RCSs) are needed (Glade et al., 2005). To be effective, these RCSs should possess five main components (Rogers and Tsirkunov, 2011): monitoring; analyzing; risk communication; warning dissemination; and, capacity building. Among these components, prior research has focused on monitoring and analyzing the occurrence of landslide events (Dai et al., 2002; Montrasio et al., 2011). For example, there exists various statistical and processbased models for predicting landslides (

Personalized learning environments requiring the elicitation of a student’s knowledge state have inspired researchers to propose distinct models to understand that knowledge state. Recently, the spotlight has shone on comparisons between traditional, interpretable models such as Bayesian Knowledge Tracing (BKT) and complex, opaque neural network models such as Deep Knowledge Tracing (DKT). Although DKT appears to be a powerful predictive model, little effort has been expended to dissect the source of its strength. We begin with the observation that DKT differs from BKT along three dimensions: (1) DKT is a neural network with many free parameters, whereas BKT is a probabilistic model with few free parameters; (2) a single instance of DKT is used to model all skills in a domain, whereas a separate instance of BKT is constructed for each skill; and (3) the input to DKT interlaces practice from multiple skills, whereas the input to BKT is separated by skill. We tease apart these three d...

We propose a energy efficient resource allocation framework suitable for multicast service delivery over 3GPP's LTE-A SFN-eMBMS networks. A key aspect of the considered system model is that multicast communications are delivered according to the RLNC principle. The proposed optimization framework aims at minimizing the transmission energy associated with the delivery of a set of multicast flows. The goal is achieved by jointly optimizing the transmission power and RLNC scheme of each flow. Furthermore, we present an heuristic strategy that can efficiently find a good quality feasible solution of the presented resource allocation model.

This paper presents design and implementation of dual arrowhead slotted multi-band microstrip patch antenna for mobile (1.9 GHz-IEEE 802.11b/g), WLAN (5.8 GHz-IEEE 802.11a) and other personal wireless applications.The radiating element of the proposed antenna consists of dual arrowhead slot on rectangular patch operating at multi-bands in the range from1.9 to 5.8 GHz..The antenna is probe feeded and it is simulated on IE3D Zeland software.The result of the antenna is analyzed by changing their flair angles (45,60,and 75 degree). The proposed antenna have directivity upto 11.5 dBi,Gain upto 7.5 dB and efficiency upto 80%.The software simulation results shows that the antenna can realize multiband characters with each band having good impedance bandwidth (VSWR≤2) for all the resonant frequencies. The proposed antenna is also tested and verified through VNA network Analyzer and approximately appropriate matching is achieved between the simulated and measured results.

Over the last few years, interference has been a major hurdle for successfully implementing various end-user applications in the fifth-generation (5G) of wireless networks. During this era, several communication protocols and standards have been developed and used by the community. However, interference persists, keeping given quality of service (QoS) provision to end-users for different 5G applications. To mitigate the issues mentioned above, in this paper, we present an in-depth survey of state-of-the-art non-orthogonal multiple access (NOMA) variants having power and code domains as the backbone for interference mitigation, resource allocations, and QoS management in the 5G environment. These are future smart communication and supported by device-to-device (D2D), cooperative communication (CC), multiple-input and multiple-output (MIMO), and heterogeneous networks (HetNets). From the existing literature, it has been observed that NOMA can resolve most of the issues in the existing proposals to provide contention-based grant-free transmissions between different devices. The key differences between the orthogonal multiple access (OMA) and NOMA in 5G are also discussed in detail. Moreover, several open issues and research challenges of NOMA-based applications are analyzed. Finally, a comparative analysis of different existing proposals is also discussed to provide deep insights to the readers. INDEX TERMS NOMA, OMA, uplink, downlink, device-to-device, machine-to-machine. • We present a comprehensive review on the PD-NOMA and CD-NOMA to study the various challenges associated with them. The basic principle of NOMA and its standards, advantages, challenges, and solutions are studied.