Abstract: Detecting emotions in microblogs and social media posts has applications for industry, health, and security. Statistical, supervised automatic methods for emotion detection rely on text that is labeled for emotions, but such data are rare and available for only a handful of basic emotions. In this article, we show that emotion-word hashtags are good manual labels of emotions in tweets. We also propose a method to generate a large lexicon of word-emotion associations from this emotion-labeled tweet corpus. This is the first lexicon with real-valued word-emotion association scores. We begin with experiments for six basic emotions and show that the hashtag annotations are consistent and match with the annotations of trained judges. We also show how the extracted tweet corpus and word-emotion associations can be used to improve emotion classification accuracy in a different nontweet domain.

Abstract: Since the phenomenon of cloud computing was proposed, there is an unceasing interest for research across the globe. Cloud computing has been seen as unitary of the technology that poses the next-generation computing revolution and rapidly becomes the hottest topic in the field of IT. This fast move towards Cloud computing has fuelled concerns on a fundamental point for the success of information systems, communication, virtualization, data availability and integrity, public auditing, scientific application, and information security. Therefore, cloud computing research has attracted tremendous interest in recent years. In this paper, we aim to precise the current open challenges and issues of Cloud computing. We have discussed the paper in three-fold: first we discuss the cloud computing architecture and the numerous services it offered. Secondly we highlight several security issues in cloud computing based on its service layer. Then we identify several open challenges from the Cloud computing adoption perspective and its future implications. Finally, we highlight the available platforms in the current era for cloud research and development.

Abstract: Recommendation system provides the facility to understand a person's taste and find new, desirable content for them automatically based on the pattern between their likes and rating of different items. In this paper, we have proposed a recommendation system for the large amount of data available on the web in the form of ratings, reviews, opinions, complaints, remarks, feedback, and comments about any item (product, event, individual and services) using Hadoop Framework. We have implemented Mahout Interfaces for analyzing the data provided by review and rating site for movies.

Abstract: A 3D Shenzhen city web platform based on WE-BVRGIS is presented. A 3D globe browser is employed to load all kinds of demanded data of the city, such as 3D building model data, residents information, real-time and historical traffic data. Using these data, the 3D analysis and visualization of the concerned city massive information are conducted in the platform. All the presented functions of the platform are extracted from the practical customer demand. The system design has considered some existing Geographic human-computer interaction (GeoHCI) research results.

Abstract: Noise refers to the random variation of intensity of a pixel, which modifies the actual information of the image. As a result, pixels which appear in the image are not the actual pixels. Addition of extraneous values to the image causes the occurrence of noise. Noise is categorized into impulse (salt-and-pepper) noise, uniform noise, Gaussian noise, exponential noise, Erlang (gamma) noise, photon noise, speckle noise, etc. Speckle noise is the noise that arises due to the effect of environmental conditions on the imaging sensor during image acquisition. Speckle noise is mostly detected in case of medical images, active Radar images and Synthetic Aperture Radar (SAR) images. Various researchers have performed experiments to overcome this kind of noise using different filtering techniques based on soft computing approaches, such as Fuzzy Filter, Genetic Algorithm, Particle Swarm Optimization, Artificial Bee Colony Optimization, Neural Networks, etc. In this paper, we present a brief analysis of different techniques used for speckle noise reduction, along with their advantages and disadvantages, in a comparative manner.

Abstract: In this paper, a novel approach towards classification of various human emotions based on statistically weighed autoregressive modeling of Electroencephalogram (EEG) signals is discussed. The proposed algorithm was proven to be superior to many related works, in distinguishing different emotions such as happiness, fear, sadness etc. The findings discussed are based on the results obtained using benchmark emotion based EEG database called DEAP. In this work, epochs were extracted from data using statistical measures such as Shannon Entropy and higher order auto-regressive model was fit to the extracted features. The model was used for classifying human emotions by feeding it into a multi-class Support Vector Machine (MCSVM). The proposed algorithm is proven to be more efficient than existing algorithms as a classification accuracy of 94.097% was obtained.

Abstract: A user-based tourist attraction recommender system is developed in this paper. The recommender system is constructed as an online application which is capable of generating a personalized list of preference attractions for the tourist. Modern technologies of classical recommender system, such as collaborative filtering are considered to be effectively adopted in the tourism domain. On the basis of collaborative filtering principle, the recommendation process of tourist attractions divided into three steps, representation of user (tourist) information, generation of neighbor users (tourists) and the generation of attraction recommendations. In order to calculate the similarities between each user, the Cosine method is adopted during the process of the generation of neighbors. And then the recommendations of attractions are generated according to the visiting history of the user's neighbors. In order to demonstrate the calculation process of the system, a case is demonstrated in detail.

Abstract: In the modern era, with the explosive growth of image databases, huge amount of image and video archive led to rise of a new research and development of efficient method to searching, locating and retrieving of image. For this purpose, an efficient tool for searching, locating and retrieval of image is required. This paper presenting a survey on low level feature description techniques for Content Based Image Retrieval is presented with its various applications.

Abstract: Machine Translation pertains to translation of one natural language to other by using automated computing. The main objective is to fill the language gap between two different languages speaking people, communities or countries. In India, we have multiple and hugely diverse languages and scripts, hence scope and need of language translation is immense. In this paper, we focus on the current scenario of research in machine translation in India. We have reviewed various important Machine Translation Systems (MTS) and presented preliminary comparison of the core methodology as used by them.

Abstract: Vehicular Ad Hoc Network (VANET) is formed by a number of moving vehicles that are equipped with wireless interfaces. It is a kind of Mobile Ad Hoc Network (MANET) in which communication takes place between moving vehicles on the road. VANETs are heterogeneous in nature as they provide wireless communication among moving vehicles (V2V) and vehicle to Road Side Units (RSU). It has become an exciting area of research as it is anticipated to improve Intelligent Transport System (ITS). To exploit effective communication among vehicles, routing is the key factor which needs to be investigated. This paper intends to analyze the performance of AODV and GPSR routing protocols in a VANET in various scenarios under different traffic conditions with respect to Packet Delivery Ratio (PDR) and average End-to-End Delay (E2ED). Simulation is performed using NS-2.35 in combination with Vanet MobiSim. It has been found that AODV performs better with respect to PDR and GPSR outperforms AODV with respect to E2ED. Also, the performance of both the routing protocols varies from one scenario to another and traffic types. The performance of both AODV and GPSR is improved by using IEEE 802.11p instead of IEEE 802.11.

Abstract: An exponential increase in number of vehicles necessitates the use of automated systems to maintain vehicle information. The information is highly required for both management of traffic as well as reduction of crime. Number plate recognition is an effective way for automatic vehicle identification. Some of the existing algorithms based on the principle of learning takes a lot of time and expertise before delivering satisfactory results but even then lacks in accuracy. In the proposed algorithm an efficient method for recognition for Indian vehicle number plates has been devised. The algorithm aims at addressing the problems of scaling and recognition of position of characters with a good accuracy rate of 98.07%.

Abstract: This paper provides a different kind of approach to the dynamic motion planning problems of mobile robots in uncertain dynamic environments based on the behavior dynamics from a control point of view. The conceptual behavior of a mobile robot in motion planning is regarded as a dynamic process of the interaction between the robot and its local environment, and it is modeled and controlled for the purpose of motion planning. Based on behavior dynamics, the dynamic motion planning problem of mobile robots is transformed into a control problem of the integrated planning and control system and the dynamic motion planning problem can be transformed into an optimization problem in the robot's acceleration space. Mobile robot path planning is one of the critical issues in the design of robotic work cells. This paper deals with the design of a battery operated mobile robot and its path planning. Analysis of various robots is conducted and it is found that the robot used in our paper is the best one with high accuracy and had fastest response.

Abstract: Cloud computing is very popular in organizations and institutions because it provides storage and computing services at very low cost. However, it also introduces new challenges for ensuring the confidentiality, integrity and access control of the data. Some approaches are given to ensure these security requirements but they are lacked in some ways such as violation of data confidentiality due to collusion attack and heavy computation (due to large no keys). To address these issues we propose a scheme that uses threshold cryptography in which data owner divides users in groups and gives single key to each user group for decryption of data and, each user in the group shares parts of the key. In this paper, we use capability list to control the access. This scheme not only provides the strong data confidentiality but also reduces the number of keys.

Abstract: High calorie intake in the human body on the one hand, has proved harmful in numerous occasions leading to several diseases and on the other hand, a standard amount of calorie intake has been deemed essential by dietitians to maintain the right balance of calorie content in human body. As such, researchers have proposed a variety of automatic tools and systems to assist users measure their calorie in-take. In this paper, we consider the category of those tools that use image processing to recognize the food, and we propose a method for fully automatic and user-friendly calibration of the dimension of the food portion sizes, which is needed in order to measure food portion weight and its ensuing amount of calories. Experimental results show that our method, which uses deep learning, mobile cloud computing, distance estimation and size calibration inside a mobile device, leads to an accuracy improvement to 95 percent on average compared to previous work.

Abstract: This paper proposes two methods, oriented to crop row detection in images from agriculture fields with high weed pressure and to further distinguish between weed and crop. Firstly, for crop row detection the image processing consists of three main processes: image segmentation, double thresholding based on the 3D-Otsu's method, and crop row detection. Secondly, further classification between weed and crop, is carried out by compressing the three dimension vectors of an image to one dimension using the principal component analysis (PCA) method. Finally the combination of Otsu method and the PCA enable us to not only detect weed in crop rows but also classify this weed from crop. Hence it is better suited for the real time applications pertaining to weed detection.

Abstract: Severe acute respiratory syndrome (SARS) was first reported in 2003 and quickly spread around the world. Therefore, many international airport quarantine stations launched fever-based screening to detect infected passengers using infrared (IR) cameras for preventing global pandemics. However, a screening method based on fever alone can be insufficient for detecting infected individuals because many factors, such as antipyretics uptake, can affect it. Our previous studies using compact radar revealed that simultaneous measurement of facial skin temperature and respiratory and heart rates drastically improved the sensitivity of infection screening compared to that achieved by facial skin temperature measurement alone. Using a CMOS camera-equipped IR camera (CMOS-IR camera), which most Japanese International Airports have adopted, we developed an enhanced thermal/RGB image processing method for non-contact measurement of facial skin temperature, and respiratory and heart rates. We conducted the image processing on the thermal/RGB image-fusion mode in real time; we determined the respiratory rate by thermal images of the IR camera and the heart rate by the RGB images of the CMOS camera. Using a CMOS-IR camera, we measured respiratory and heart rates of ten healthy subjects (23 ± 1 years), and compared them with those determined by a contact-type respiratory effort belt and electrocardiograms (ECGs) as references. The respiratory and heart rates obtained from the CMOS-IR camera exhibited strong positive correlations with those derived from the references, a respiratory effort belt: r = 0.99, p < 0.01; ECG: r = 0.96, p < 0.01, whereas the axillary temperature indicated a moderate degree of correlation to facial skin temperature (r = 0.6). Adopting this method into conventional CMOS-IR camera image processing at international airport quarantines will achieve higher infection screening sensitivity.

Abstract: Despite efforts to curb online fraud, there continues to be a significant proliferation of fraud in the online space. In the same vein, Phishing attacks are a significant and growing problem for users, and carrying out certain actions such as mouse hovering, clicking, etc., on malicious URLs may cause unwary users to unwittingly fall victim to identity theft and problems. In this paper, we propose a methodology that could be used towards developing an anti-phishing URL tool to thwart a phishing attack by either masking the potentially phishing URL or by alerting the user about the potential threat.

Abstract: K Nearest Neighbor is one of the simplest method for classification as well as regression problem. That is the reason it is widely adopted. KNN is a supervised method that uses estimation based on values of neighbors. Though KNN came into existence in decade of 1990, it still demands improvements based on domain in which it is being used. Now the researchers have invented methods in which multiple techniques can be combined in some order such that advantages of each technique covers the disability of techniques being combined for example, KNN-Kernel based algorithms are being used for clustering. Though heavy applicability of KNN in classification problems, it is not that much used in function estimation problems. This paper is an attempt in using KNN as function estimation problem. The approach is made for linear as well as nonlinear regression problem. We have made an assumption that supervisor data given is reliable. We have considered here two dimensional data to illustrate the idea which is equally applicable to n-dimensional data for some large but finite n.

Abstract: Hierarchical multilabel classification is a complex classification problem where an instance can be assigned to more than one class simultaneously, and these classes are hierarchically organized with superclasses and subclasses, that is, an instance can be classified as belonging to more than one path in the hierarchical structure. This article experimentally analyses the behavior of different decision tree-based hierarchical multilabel classification methods based on the local and global classification approaches. The approaches are compared using distinct hierarchy-based and distance-based evaluation measures, when they are applied to a variation of real multilabel and hierarchical datasets' characteristics. Also, the different evaluation measures investigated are compared according to their degrees of consistency, discriminancy, and indifferency. As a result of the experimental analysis, we recommend the use of the global classification approach and suggest the use of the Hierarchical Precision and Hierarchical Recall evaluation measures.

Abstract: Marine wireless channel modeling is significant to construct a maritime communication system. Three dimensional contour data of Diaoyu Islands is collected and analyzed. Then a three dimensional scene combined with sea surface is rebuilt through Matlab. Ray tracing based on angle searching and the deterministic channel modeling are used to model the wireless channels of the main scenes by air platforms(Unmanned Aerial Vehicle (UAV) or hot-air balloons) which carrying the wireless transceivers. A simulation considering relevant parameters like path loss, time delay and arrival angle are carried out. The results show that the pass loss is interrelated with the rough sea surface which also lead to an uncertain multipath effect.

Abstract: This paper presents a comparative study of beam forming techniques using least mean square (LMS) algorithm and its variants, like, normalized least mean square (NLMS) algorithm and sign least mean square (SLMS) algorithm. The accuracy of beam generation toward the direction of arrival (DoA) and null generation toward the interferer, depends on the value of step size parameter used in the algorithm. Beam width and side lobe levels (SLL) are also compared for these three algorithms.

Abstract: Secure and reliable group communication is an active area of research. Its popularity is fuelled by the growing importance of group-oriented and collaborative properties. The central research challenge is secure and efficient group key management. In this paper, we propose an efficient many-to-many group key management protocol in distributed group communication. This protocol is based on Elliptic Curve Cryptography and decrease the key length while providing securities at the same level as that of other cryptosystems provides. The main issue in secure group communication is group dynamics and key management. A scalable secure group communication model ensures that whenever there is a membership change, a new group key is computed and distributed to the group members with minimal communication and computation cost. This paper explores the use of batching of group membership changes to reduce the time and key re-distribution operations. The features of ECC protocol are that, no keys are exchanged between existing members at join, and only one key, the group key, is delivered to remaining members at leave. In the security analysis, our proposed algorithm takes less time when users join or leave the group in comparison to existing one. In ECC, there is only 1 key generation and key encryption overhead at join and leave operation. At join the communication overhead is key size of a node and at leave operation is 2 log2 n -- 2 × key size of a node.

Abstract: Fractal Dimension (FD) is an important feature of fractal geometry that finds the significant application in different fields including texture segmentation, shape classification and image analysis. Various methods were proposed to estimate the fractal dimension of gray scale images. In this paper we found out a uniform fractal dimension for both Color and Grey Scale images using differential box counting (DBC) method.

Abstract: Delay/Disruption Tolerant Networks make communication possible in networks that enable an end user to send/receive data on small, robust networked processing devices distributed in day to day life. Delay/Disruption Tolerant Networks having numerous constraints like frequent movement, low energy devices, limited storage that certainly require different routing paradigm. The uncertain delay in the process involved may cater to undesired results. The problems faced by such network are more complex than existing underlying networks of network. For such different class of networks, designing an innovative protocol considering various limitations makes it definite/obvious to vigorously switch to multicasting approach of forwarding/flooding data packets in DTN environment. In this paper, Researchers have simulated multicasting for routing protocols in DTNs. In the previous work node connectivity is done using synthetic data traces. Researcher proposes the use of real world data traces and analyzes the impact of Multicasting approach on different routing protocol in DTN. Researchers have performed extensive evaluations of the proposed methods using simulation environment. The comparative result critically synthesizes strength and weakness of Message Multicasting approach. Also with Epidemic Oracle having oracle of past contact, it is possible to achieve high delivery ratio.

Abstract: Recent years have seen the arising recognition of community detection in complex networks. Artificial immune systems, owing to their inherent properties, have been thoroughly studied and well applied to practical use. In this article, one of the well-known artificial immune system models, named clonal selection algorithm, is introduced to reveal community structures in complex networks. By introducing a novel antibody population initialization mechanism and a novel hypermutation strategy, the proposed approach could be applied to moderate-scale network. Besides, by optimizing an objective function called modularity density, the proposed algorithm is also capable of detecting community structure at multiple resolution levels. Experiments on both synthetic and real-world networks demonstrate the effectiveness of the proposed method.

Abstract: In recent years, chaos-based image cipher has been widely studied and a growing number of schemes based on permutation-diffusion architecture have been proposed. However, recent studies have indicated that those approaches based on low-dimensional chaotic maps/systems have the drawbacks of small key space and weak security. In this paper, a security improved image cipher which utilizes cat map and hyper chaotic Lorenz system is reported. Compared with ordinary chaotic systems, hyper chaotic systems have more complex dynamical behaviors and number of system variables, which demonstrate a greater potential for constructing a secure cryptosystem. In diffusion stage, a plaintext related key stream generation strategy is introduced, which further improves the security against known/chosen-plaintext attack. Extensive security analysis has been performed on the proposed scheme, including the most important ones like key space analysis, key sensitivity analysis and various statistical analyses, which has demonstrated the satisfactory security of the proposed scheme.

Abstract: The advent and prosperity of the GPS equipped devices and reliable location technologies has resulted in a wide growth of location based service. As a certain type of geo-spatial application, moving objects on fixed networks must sustain high update rate for millions of devices, and provide efficient real-time querying on multi-attributes such as time-period and arbitrary spatial dimension. Traditional DBMSs support complex index structures which can effectively cope with spatio-temporal data. However, current relational databases have encountered the ever-increasing scale of datasets, which make a claim for scalability of data manage system. Meanwhile, key-value store databases are designed to be scalable, available and distributed, without much support for data organization including management of spatio-temporal data. In this paper, we present a novel hybrid index structure to organize data, combining a statistical based R-tree for indexing space and applying Hilbert curve for traversing approaching space. With key-value store, which insures effective querying response time and high insert rates, we propose rules for generating target row key which take skewed data handing into account. The cluster of HBase consists 8 nodes, with data volume in a level of millions. Our implementation proves that range queries and k-NN queries sustain response time in hundreds of milliseconds.

Abstract: The increasing volume and unstructured nature of data available on the World Wide Web (WWW) makes information retrieval a tedious and mechanical task. Lots of this information is not semantic driven, and hence not machine process able, but its only in human readable form. The WWW is designed to builds up a source of reference for web of meaning. Ontology information on different subjects spread globally is made available at one place. The Semantic Web (SW), moreover as an extension of WWW is designed to build as a foundation of vocabularies and effective communication of Semantics. The promising area of Semantic Web is logical and lexical semantics. Ontology plays a major role to represent information more meaningfully for humans and machines for its later effective retrieval. This paper constitutes the requisite with a unique approach for a representation and reasoning with ontology for semantic analysis of various type of document and also surveys multiple approaches for ontology learning that enables reasoning with uncertain, incomplete and contradictory information in a domain context.

Abstract: Due to the continuous development of high quality multimedia technologies and rapid growth in the computational power along with availability of huge sized storage devices, digital image archives of very large size are being created day by day on the ever growing WWW through many commercial, research a development and academic web sites. The bulk of digitized images over the Internet are attracting significant research efforts for the development of tools to manage the visual data with their fast and effective retrieval. Towards the beginning of the previous decade, the breakthrough techniques called content based image retrieval has emerged in image retrieval field. This technique uses the contents of the image data for segmenting, indexing, retrieval and searching of relevant images from image repository. This paper mainly concentrates on the indexing phase of the image retrieval system for development of an efficient indexing algorithm of CBIR systems.