Abstract: A Blockchain is basically a decentralized, distributed ledger of all the transactions or events which takes place only after involving multiple parties. It ensures high level of security as the transactions which takes place are entirely anonymous. Each transactions or digital events taking place in a Blockchain network is verified, only if it is agreed upon by the consensus of the majority party of the users participating in this process. Blockchain is one of the emerging technologies in today's world and a lot of revolution and research has just began regarding this distributed technology. Bitcoin has been the most popular cryptographic currency since it was invented and it is the best example that uses the Blockchain technology. In this paper, we will discuss about the research being done on this new domain of Computer Science. We will outline the underlining concepts about this new technology. We will try to peek a bit into its applications in the financial and non financial sector. It is not only the most popular topic to discuss about, but is the most technological breakthrough, that is all set to revolutionize the entire world.

Abstract: Clustering is essentially a procedure of grouping a set of objects in such a manner that items within the same clusters are more akin to each other compared with those data point or objects in different amassments or clusters. This paper discusses partition-predicated clustering techniques, such as K-Means, K-Means++ and object predicated Fuzzy C-Means clustering algorithm. This paper proposes a method for getting better clustering results by application of sorted and unsorted data into the algorithms. Elapsed time & total number of iterations are the factors on which, the behavioral patterns are analyzed. The experimental results shows that passing the sorted data instead of unsorted data not only effects the time complexity but withal ameliorates performance of these clustering techniques.

Abstract: Supervised machine learning algorithms have been used extensively in different domains of machine learning like pattern recognition, data mining and machine translation. Similarly, there has been several attempts to apply the various supervised or unsupervised machine learning algorithms to the analysis of air traffic data. However, no attempts have been made to apply Gradient Boosted Decision Tree, one of the famous machine learning tools to analyse those air traffic data. This paper investigates the effectiveness of this successful paradigm in the air traffic delay prediction tasks. By combining this regression model based on the machine learning paradigm, an accurate and sturdy prediction model has been built which enables an elaborated analysis of the patterns in air traffic delays. Gradient Boosted Decision Tree has shown a great accuracy in modeling sequential data. With the help of this model, day-to-day sequences of the departure and arrival flight delays of an individual airport can be predicted efficiently. In this paper, the model has been implemented on the Passenger Flight on-time Performance data taken from U.S. Department of Transportation to predict the arrival and departure delays in flights. It shows better accuracy as compared to other methods.

Abstract: Normalized mutual information (NMI) is a widely used measure to compare community detection methods. Recently, however, the need of adjustment for information theory-based measures has been argued because of the so-called selection bias problem, that is, they show the tendency in choosing clustering solutions with more communities. In this article, an experimental evaluation of these measures is performed to deeply investigate the problem, and an adjustment that scales the values of these measures is proposed. Experiments on synthetic networks, for which the ground-truth division is known, highlight that scaled NMI does not present the selection bias behavior. Moreover, a comparison among some well-known community detection methods on synthetic generated networks shows a fairer behavior of scaled NMI, especially when the network topology does not present a clear community structure. The experimentation also on two real-world networks reveals that the corrected formula allows to choose, among a set, the method finding a network division that better reflects the ground-truth structure.

Abstract: The IoT is in need of an advanced prototype for security, which considers the security issues from a holistic perspective comprising the advanced users and their intercommunication with this technology. In this paper, it has been analyzed and compared how current approaches are ensuring fundamental and basic secu-rity requisites and securing intercommunication of IoT, along with the rolling challenges and scope for research work in this field in the coming future. Cloud Computing is today's generation advanced technology services are made available for customers per utilization basis. Servers are being utilized on cloud to out-source their highly valuable data. Though there are many benefits of cloud computing. However, it has security threads of pivotal confidential data. Users of cloud technology can't count on the cloud service sup-pliers for the safety of the pivotal confidential data. Therefore, a Third-Party Authenticator is required which authenticates the cloud data from the side of users or holders of the data. Security of sensitive data is of questionable nature due to the presence of various entities. Cloud Service Providers along with Data Users are equally in charge for putting the security of the pivotal confidential data at risk. Surveys have sug-gested that huge storage systems cannot be trusted completely; and all of them can be hacked.

Abstract: In this paper, we propose an automatic brain tumor segmentation algorithm based on a 22-layers deep, three-dimensional Convolutional Neural Network (CNN) for the challenging problem of gliomas segmentation. To correct the bias field distortion of MRI images, we have added N4ITK method before intensity normalization. The use of several cascaded convolution layers with small kernels allows building a deeper CNN. During training, we add dropout to reduce overfitting, and adapt the batch normalization technique to speed up training. Our proposed method has been validated in the BRATS 2015 databases, the performance for the complete, core and enhancing regions was evaluated by the online evaluation platform with Dice matric of 0.84, 0.79, 0.75, Positive Predictive Value matric of 0.88, 0.86, 0.70 and Sensitivity matric of 0.82, 0.75, 0.86. Due to the GPU acceleration and improvement of the algorithm, our total training time is about 140 min. And through the experiments and results, we can prove that our method is time-saving and efficient.

Abstract: Due to information explosion, huge number of items are present over web which makes it difficult for user to find appropriate item from available set of options. Recommender System (RS) overcomes the problem of information overload and suggests items that interest to a user. It has gained a lot of popularity in past decades and huge amount of work has been done in this field. Collaborative Filtering (CF) is the most popular and widely used approach for RS which tries to analyze the user's interest over the target item on the basis of views expressed by other like-minded users. This paper gives a brief idea of various approaches used for Recommender System and provides an insight of Collaborative Filtering technique. Here, we also discuss well-known methods for CF i.e. Memory-based, Model-based, and hybrid approaches and at last we focus on research challenges that need to be addressed.

Abstract: Internet of Things (IoT) refers to technological advancements in the networking with the help of which real world objects can be connected to communicate with each other over the internet. The objects that are connected are known as ‘things’. This interconnection of various things over the internet with the capability of sending and receiving information has a wide number of applications in almost every field like healthcare, business, transportation, agriculture, management and education. This paper will discuss about the Internet of Things (IoT) in general, some of its applications with particular emphasis on E-learning. Finally the paper gives a model of Smart Learning using the IoT and the gamification technique of E-Learning.

Abstract: It is of great significance to carry out cities' air quality forecasting work for the prevention of the air pollution in urban areas and to the improvement of the living environment of urban residents. The air quality index (AQI) is a dimensionless index that quantitatively describes the state of air quality. In this paper, the data of air quality in Lanzhou released by china air quality online monitoring and analysis platform is dealt with, and then AQI prediction model based on back propagation (BP) neural network, AQI prediction model based on genetic algorithm optimization and AQI prediction model of BP neural network based on genetic simulated annealing algorithm optimization are established. By comparing and analyzing the prediction results, it is found that BP neural network based on genetic simulated annealing algorithm has strong generalization ability and global search ability, and has higher accuracy rate.

Abstract: Multicore architecture of CPU is popular because of its performance; the challenge for the Multicore environment are-writing the effective code that can exploit the parallelism, measuring the performance in terms of CPU individual core utilization. The effective code using multithreading (parallel code) leads to performance speedup. Various multithreading applications are getting developed now days to utilize the CPU cores. In this paper, tools are developed, one by using C# console viz. application for measuring the performance of the CPU cores individually. Performance is measured in terms of load on each core in percentage. Second tool is designed using windows C# viz. application for plotting the graph with respect to time of CPU load in percentage. By both the tools performance is measured while quicksort is getting executed in the serial and parallel for a large number of data elements. Experiment is done on dual core and quad core CPU and results are stored in the table. Comparison graphs are drawn for running time of quicksort as well as CPU individual core utilization. The result shows parallel version of quicksort better utilize the CPU individual cores compared to its sequential version. It exploits more parallelism that leads the better CPU utilization.

Abstract: The recent advances in Deep Learning based Machine Translation and Computer Vision have led to excellent Image Captioning models using advanced techniques like Deep Reinforcement Learning While these models are very accurate, these often rely on the use of expensive computation hardware making it difficult to apply these models in realtime scenarios, where their actual applications can be realised In this paper, we carefully follow some of the core concepts of Image Captioning and its common approaches and present our simplistic encoder and decoder based implementation with significant modifications and optimizations which enable us to run these models on low-end hardware of hand-held devices We also compare our results evaluated using various metrics with state-of-the-art models and analyze why and where our model trained on MSCOCO dataset lacks due to the trade-off between computation speed and quality Using the state-of-the-art TensorFlow framework by Google, we also implement a first of its kind Android application to demonstrate the realtime applicability and optimizations of our approach

Abstract: Wireless sensor networks are spatially distributed sensor nodes that keeps the track of the physical or environmental conditions like sound, stress waves, temperature of surrounding etc, and also send the sensed data back to the sink or base station. WSN are used in many applications like military areas, disaster management in remote areas, in building smart cities etc. Therefore security is an important aspect in WSN. These networks can be prone to various disastrous attacks or hackers that has the motive to disrupt the entire network. In this article, various aspects of security in Wireless Sensor Networks has been observed like secure routing protocols, security at the node level in the network, cryptography etc.

Abstract: Network security has become a very important issue and attracted a lot of study and practice. To detect or prevent network attacks, a network intrusion detection (NID) system may be equipped with machine learning algorithms to achieve better accuracy and faster detection speed. One of the major advantages of applying machine learning to network intrusion detection is that we don't need expert knowledge as much as the black or white list model. In this paper, we apply the equality constrained-optimization-based extreme learning machine to network intrusion detection. An adaptively incremental learning strategy is proposed to derive the optimal number of hidden neurons. The optimization criteria and a way of adaptively increasing hidden neurons with binary search are developed. The proposed approach is applied to network intrusion detection to examine its capability. Experimental results show our proposed approach is effective in building models with good attack detection rates and fast learning speed.

Abstract: Usage of social network for topic identification has become essential when dealing with event detection, especially when the events impact the society. In order to address this task, machine learning algorithms and natural language processing techniques have been extensively used. In this paper, an approach to obtain meaningful data from Twitter has been discussed. Further, Latent Dirichlet Allocation (LDA) and Non-Negative Matrix Factorization (NMF) have been used in order to detect topics from this textual data obtained from Twitter along with RSS feed of news headlines. The observed results show that both the algorithms perform well in detecting topics from text streams, the results of LDA being more semantically interpretable while NMF being faster of the two.

Abstract: The field of image computing incorporates the crucial subject of character recognition which is gaining significant importance and extensive research in the current wake of digital revolution The goal is to find an effective software tool capable of accurately identifying the characters The variations in a single alphabet itself and the plethora of handwriting varieties make this a challenging task The proposed solution comprises of a series of steps for the purpose of classification System training and testing incorporates hundred instances of handwritten digit images from MNIST Dataset Preprocessing of the image enhances data images prior to computational processing Input image are converted into gray scale and finally into binary This is followed by morphological operations and the images are then converted into Comma Separated Files to be able to be used as Training and Testing Dataset in WEKA Pattern recognition is done by Hoeffding Tree, Decision tree and Random forest methodologies to ultimately compare them on a set of benchmarks to find the most effective tool marked on a set of measures such as efficiency, effectiveness, time to perform the complete process of classification, etc On the basis of the key parameters which include classified instances of the digits, error rate and time taken for the classification, Hoeffding tree is found to be most effective in terms of time taken to build model, precision, recall and confusion matrix The future work requires inclusion of an extensive data set to declare the best among these approaches

Abstract: Vehicular Ad-hoc Networks (VANET) is an unique category of Mobile Ad-hoc Network (MANET), which promises prospect in the future Intelligent Transporting System by providing inter-vehicle communication of road surveillance, traffic information, road condition etc. However, the high nodes mobility, frequent network change topology, unstable network and small coverage issues in the VANET implementation motivates for a stable design of cloud clustering algorithm. This paper propose a system that combines the traditional 802.11p standard VANET networks with LTE networks to form a hybrid Cloud-VANET that provides low network overhead with a high mobility management and high coverage in VANET networks. This approach enables VANET to have high bandwidth along with un-interruptable data connectivity by reducing the data packet loss and SNIR loss ratio over the network. The OMNET++ and SUMO traffic generator has been used to simulate the network scenario. Simulation results indicates that hybrid VANET architecture improve the overall network stability and performance.

Abstract: Spider monkey optimization (SMO) algorithm, which simulates the food searching behavior of a swarm of spider monkeys, is a new addition to the class of swarm intelligent techniques for solving unconstrained optimization problems. The purpose of this article is to study the performance of SMO after incorporating quadratic approximation (QA) operator in it. The proposed version is named as QA-based spider monkey optimization (QASMO). An experimental study has been carried out to check the validity and applicability of QASMO. For validation purpose, the performance of QASMO is tested over a benchmark set of 46 scalable and nonscalable problems, and results are compared with the original SMO algorithm. In order to test the applicability of the proposed algorithm in solving real-life optimization problems, one of the most challenging optimization problems, namely, Lennard–Jones (LJ) problem is considered. LJ clusters containing atoms from three to ten have been taken into consideration, and results are presented. To the best of our knowledge, this is the first attempt to apply SMO and its proposed variant on a real-life problem. The results demonstrate that incorporation of QA in SMO has positive effects on its performance in terms of reliability, efficiency, and accuracy.

Abstract: Injection molded part quality can be improved by precise process adjustment, which could rely on in-situ measurements of part quality. Geometrical and appearance quality (visually and sensory) requirements are increasing. However, direct measurement is often not feasible industrially. Therefore, process control must rely on a prediction of parts quality attributes. This study compares prediction performances of diverse neural networks architectures with “classical” regression algorithms. Dataset comes from inline industrial measurements. Regression was performed on 97 scalar statistical features extracted from multiple acquisitions sources: thermographic images and analog signals. Haralick features were extracted. Convolutional Neural Networks were trained on thermographic images and Long Short Term Memory networks were trained on raw signals. Although the dataset was small, neural networks show better predictions scores than other regression algorithms.

Abstract: Image based or live video feed based face recognition is a very interesting field in research and applications. Various face recognition methods have been devised and applied over the past several years of technological development. Fields like security and surveillance have widely used face recognition over the years as people are very concerned as to identifying and catching criminals or people with mal intentions. Catching them without being able to promptly recognize and their faces has been a major problem. A person's facial features are dynamic and have variable appearances, which makes it a problem to be very accurate and fast in identification of a person. Not only this, security access controls through face recognizers makes it highly difficult for hackers and crackers to use a person's identity or data. The basic objective of this paper hence is to understand several pre-existing face detection and recognition algorithms and then provide a viable solution for live video based facial recognition with better accuracy, higher speed and efficiency so as to help develop a technology such which can help catch criminals promptly and as well as protect people's privacy and identity from hackers. Many facial databases have been considered so as to differentiate them in conditions of changes in poses, illuminations and emotions. Various other conditions to obstruct identification of faces are discussed later.

Abstract: Classification of fruits is traditionally done using manual resources due to which the time and economic involvements increase adversely with number of fruit types and items per class. In recent times computer based automated techniques have been used to alleviate this problem to a certain extent. These techniques utilize image analysis and pattern recognition methodologies to automatically classify fruits based on their visual features like color, texture, and shape. However, challenges of such techniques include the fact that fruit appearances differ due to natural environments, geographical locations, stages of growth, size, orientations and imaging equipments. In this paper, a shape based fruit recognition approach has been proposed which is independent of many of these factors. It involves a pre-processing step to normalize a fruit image with respect to variations in translation, rotation, scaling and utilizes features which do not change due to varying distances, growth stages and surface appearances of fruits. The proposed method has been applied to 210 images of 7 fruit classes. The overall recognition accuracy ranges from 88–95%.

Abstract: In this paper, we have discussed various routing techniques of wireless body area network (WBAN), its challenges and comparison has been done based on various parameters. Due to advancement in wireless technology miniature sensor nodes with low power, lightweight, invasive or non-invasive are placed in, on or around the human body to monitor the health condition. Routing protocols plays an important role to improve the overall performance of network in terms of delay, throughput, network lifetime etc. and to improve the quality of services (QoS) in WBAN. Network lifetime and successfully transmission of data to the sink node are two main factors to design a routing protocol. Routing in WBAN is classified as QoS based, temperature aware, clusters based routing, postural based, cross layer network based routing etc. These categories are further divided into various protocols. This paper provides a review of some of the existing routing protocols of WBAN by describing their techniques, advantages and disadvantages. Also, the comparison of ATTEMPT (Adaptive Threshold based Thermal unaware Energy-efficient Multi-hop Protocol), SIMPLE (Stable Increased-throughput Multihop Protocol for Link Efficiency) and EERDT (Energy Efficient and Reliable Data Transfer) protocol has been done by simulating in MATLAB.

Abstract: The main purpose to push the development towards autonomous maritime operations in shipping and offshore installations, is to increase the performance of maritime activities; by social benefits for staff or other related personal groups; by economic benefits when the ability to increase the cargo or effectuate better space allocation; by environmental benefits that's allow the ship operations to be optimized for routing, speed, etc.; and finally by an increased safety benefit in all these aspects. The increased use of artificial intelligent based benefits is expected to increase the operational performance of all the above aspects in the sense that an overall quality in logical and knowledge based will be consistent. The increased complexity of maritime activities and the offshore business requires more precise and automated solutions to achieve the expectations from staff, stakeholders, and society.

Abstract: Automated valuation model (AVM) is a mathematical program to estimate the market value of real estates based on the analysis of locations, neighborhood characteristics, and relevant property characteristics. The most common AVMs em-ployed by the appraisal industry are based on multiple regression analysis. Other analytic tools such as statistical learning and fuzzy algorithms have become more popular because of the increasing capability of collecting a high volume of data and the advancement of machine learning. The new analytic model thus becomes possible to build a more sophisticated model to exploit the information embedded in the collected data. In this work, we proposed a boosting tree model facilitated with a Recurrent Neural Network (RNN) to forecast the average price of an area. The experimental results indicate that our model outperforms the existing models adopted in the appraisal industry.

Abstract: In traditional text sentiment analysis methods, text feature vector has the problem of high dimensionality and high sparseness. In view of this situation, we can cluster the similar words together and use the generated clusters to fit into a new dimension so that the text feature vector dimension will be decreased. By using Word2Vec tool and K-means clustering algorithm, this task can be completed. However, clustering result of K-means clustering algorithm is sensitive to initial number of clusters. Therefore, we propose a text feature vector representation method based on Word2Vec and ISODATA clustering algorithm. This method can solve the problem that word clustering result is sensitive to the initial number of clusters. By using this method, text feature vector can be represented better, moreover, accuracy of text sentiment classification will be improved. The experimental results show that, under different initial number of clusters, the accuracy of our method is about 0.25% higher than that of text feature vector representation based on Word2Vec and K-means clustering method in hotel reviews sentiment analysis, and the AUC value is increased by about 0.31% on average.

Abstract: Occupational accident is a grave issue for any industry Therefore, proper analysis of accident data should be carried out to find out the accident patterns so that precautionary measures could be undertaken beforehand Association rule mining (ARM) technique is mostly used in this scenario to find out the association (ie, rules) causing accidents But, among the rules generated by ARM, all are not useful To handle this kind of problem, a new model ARM and genetic algorithm (GA) has been proposed in this study The model automatically selects the optimal Support and Confidence value to generate useful rules Out of 1285 data obtained from a steel industry in India, eleven useful rules are generated using this proposed method The findings from this study have the potential to help the management take the better decisions to mitigate the occurrence of accidents

Abstract: Diabetes is one of the most frightful diseases that is creating a terror in peoples mind all over the globe and all of them are putting tremendous efforts to search for various methods to prevent this disease at the budding stage by predicting the symptoms of diabetes. In this paper, our main aim is to predict the onset of diabetes amongst women aged at least 21 years using Two-class Neural Network and tabulate and compare our results with others results. This approach has been tested with the Pima Indians Diabetes Data Set downloaded from the UCI Machine Learning data repository. The performance of our predictive model has been measured and compared in terms of accuracy and recall. Endocrinologists, dietitians, ophthalmologists and podiatrists can use this model to predict how likely a patient is to suffer from diabetes.

Abstract: Yield curve forecasting is an important problem in finance. In this work we explore the use of Gaussian Processes in conjunction with a dynamic modeling strategy, much like the Kalman Filter, to model the yield curve. Gaussian Processes have been successfully applied to model functional data in a variety of applications. A Gaussian Process is used to model the yield curve. The hyper-parameters of the Gaussian Process model are updated as the algorithm receives yield curve data. Yield curve data is typically available as a time series with a frequency of one day. We compare existing methods to forecast the yield curve with the proposed method. The results of this study showed that while a competing method (a multivariate time series method) performed well in forecasting the yields at the short term structure region of the yield curve, Gaussian Processes perform well in the medium and long term structure regions of the yield curve. Accuracy in the long term structure region of the yield curve has important practical implications. The Gaussian Process framework yields uncertainty and probability estimates directly in contrast to other competing methods. Analysts are frequently interested in this information. In this study the proposed method has been applied to yield curve forecasting, however it can be applied to model high frequency time series data or data streams in other domains.

Abstract: In Ad hoc Network of Nanosensors for Wastage detection, clustering assist in nodal communication and in organization of the data fetched by the nanosensors in the network The attempt of traditional cluster formation techniques degraded the formation of cluster in a precise manner The data from the nanosensors which act as the nodes of the network have to be distinctively added into the clusters The dynamic path selection cluster would achieve this distinct addition by dynamically creating a path to the data as an initial process and then redirecting the data to their appropriate cluster based to the readied scheme The formation of clusters is evaluated on the bases of the time taken in formation of cluster and the relevance in information clustering In this paper the dynamic path selection clustering algorithm is deployed to the cluster formation in data from sensor set for the detection of wastage from industries Based on the data accumulated from the nanosensors the assignment of fetched information is clustered appropriately The analyses of the resultant obtain on evaluation process shows the cluster formation life time and relevancy in cluster formation has been more feasible than that of the existing approaches

Abstract: In recent times the identification and parking of vehicle has become a difficult task because of the increase in the number of automobiles. In the existing surveillance system the maintenance of incoming and outgoing vehicles is difficult. To resolve this problem a number of techniques can be used out of which Optical Character Recognition (OCR) is most the suitable technology. OCR has been the subject of research for more than decades. OCR is defined as the conversion of scanned images into machine encoded text. The proposed system is implementing the OCR technology to park the vehicles in smart way and keep the track of the vehicles which are entering and leaving. The system will capture the image of number plate of the vehicle using the OCR process and will instantly update the database.