Search

Automatic detection and analysis of rice crop diseases is widely required in the farming industry, which can be utilized to avoid squandering financial and other resources, reduce yield losses, and improve treatment efficiency, resulting in healthier crop output. An automated approach was proposed for accurately detecting and classifying diseases from a supplied photograph. The proposed system for the recognition of rice plant diseases adopts a computer vision-based approach that employs the techniques of image processing, machine learning, and deep learning, reducing the reliance on conventional methods to protect paddy crops from diseases like bacterial leaf blight, false smut, brown leaf spot, rice blast, and sheath rot, the five primary diseases that frequently plague the Indian rice fields. Following image pre-processing, image segmentation is employed to determine the diseased section of the paddy plant, with the diseases listed above being identified purely on the basis of their visual contents. An integration of a support vector machine classifier and convolutional neural networks are used to recognize and classify specific varieties of paddy plant diseases. With ReLU and softmax functions, the suggested deep learning-based strategy attained the highest validation accuracy of 0.9145. Following recognition, a predictive remedy is recommended, which can assist agriculture-related individuals and organizations in taking suitable measures to combat these diseases.

Nowadays, wearable techniques are widely used in the Internet of Things (IoT). The discussed IoT devices are used in various applications such as smart home, security management, education institutions and so on. Among the various application, IoT devices are used widely in health care application for reducing the risk factors. So, in this paper, introduces the wearable sensors based on the Internet of Things (WS-IoT) for sports person continuous health monitoring system. The goal of this paper is to define the health clinics for sports medicine and performance services of the sports team to further the use of the technology to help athletes return to play in different fields of sport. With the help of wearable tracking devices to collect the health details and track the exercise records. To analyze and monitoring sports person health effective optimization machine learning techniques are introduced. The created system efficiency is evaluated using experimental results and discussion.

Incremental learning from non-stationary environments with evolving streaming data is one of the main challenges in streaming data analysis (SDA). The advances in data acquisition technology have ignited the importance of data analysis on streaming data. Analysis on streaming data has to be performed with constrained memory and single pass over the data. The main challenges are in window adjustments, various drift detections, feature selection, dynamic model selection, adaptability of models and it’s real-time processing. The change in characteristics of data stream often make our model obsolete. Such changes are called concept drift. This concept drift mandates model adaptations in SDA. Adaptations are required at the feature selection, parametric adjustments and model selection. Making models with the capability of detecting abrupt, gradual and virtual drift is one of the challenges addressed by the researchers in this field. Upon detecting concept drifts, it is required to make necessary changes to the models for its acceptance. Statistical constraints have to be overcome for developing such adaptive algorithms. The model adaptability can be achieved much faster with good feature selection strategies which in turn reduces resource conception without affecting performance of model. Here the objective is to survey on building an adaptive model which is capable of handling concept drifts occurring in non-stationary data with limited resources without degradation in performance.

Art can be used to spread an inspirational message to encourage people and accomplish great things in life. The art of communication among people can be a mode of communication to concentrate on common issues to improve humankind. The challenging characteristics in art painting include such as degradation, cracking, and flaking is considered an essential factor. In this paper, the Multilevel Based Convolutional Ancient Recognition Neural Network Method (M-CARNNM) has been proposed to incorporate experts’ suggestions, helping artists envisage how the ancient painting may have looked after restoration. Mid-frequency analysis is introduced to reinforce the rough estimation of complete images by adding missing regions and the nearest neighbor pixels to match the maps. A domain-specific pyramid network is used to capture various space context amounts. Experimental results effectively predict the proposed method for large areas of lack of information and produce controllable vector graphics, photographic painting, and high-frequency results.

The human mind is an amazing piece of creation that can handle multiple modalities of input seamlessly and help to make sense about the surroundings. When it comes to making sense about speech, 2 main features of input are sound and vision (although there are many other components). Since not every mind is alike, some of them have trouble processing the sound aspect of input therefore vision becomes their primary source to process and understand speech. Lip reading is a skill that is used mainly by people suffering from hearing deformities and it involves large amount of language specific knowledge as well as contextual awareness i.e. using all possible visual clues that help to make sense of what the other person is saying and thus allow them to take part in the conversation. Recent breakthroughs in the field of Deep learning have clearly shown promise with models that have the ability to extract complex, intricate and generalizable patterns both in spatial as well as temporal dimension. In this paper we present FYEO (For Your Eyes Only) an end-to-end deep learning based solution that only uses vision as its single modality of input and generates a single word, character by character. The model is a modified version of the LipNet architecture from Deep Mind, to a subset of words curated from the Oxford-BBC Lip Reading in the Wild (LRW) dataset. Also, as a part of novel work FYEO is extended by adding attention mechanism for further improvement of the model’s contextual awareness and observe the model’s focus while making a prediction. The standard FYEO model achieves a length normalised test CER (character-error-rate) of 25.024%.

Centrality in social network is one of the major research topics in social network analysis. Even though there are more than half a dozen methods to find centrality of a node, each of these methods has some drawbacks in one aspect or the other. This paper analyses different centrality calculation methods and proposes a new swarm based method named Flocking Based Centrality for Social network (FBCS). This new computation technique makes use of parameters that are more realistic and practical in online social networks. The interactions between nodes play a significant role in determining the centrality of node. The new method has been calculated both empirically as well as experimentally. The new method is tested, verified and validated for different sets of random networks and benchmark datasets. The method has been correlated with other state of the art centrality measures. The new centrality measure is found to be realistic and suits well with online social networks. The proposed method can be used in applications such as finding the most prestigious node and for discovering the node which can influence maximum number of users in an online social network. FBCS centrality has higher Kendall’s tau correlation when compared with other state of the art centrality methods. The robustness of the FBCS centrality is found to be better than other centrality measures.

Online Social networks have gained much prominence in the recent years such that it has become an unavoidable means of daily communication. The element of trust in social networks has been studied ever since the inception of online social networks. Trust in online social networks is extremely fragile in nature due to the virtual connections between users in the network. The level of trustworthiness of each user in a social network varies and is usually computed using reputation level of the users. This paper focuses on identifying the features that determine the trust of a user in online social networks using benchmark datasets. We propose a new probabilistic reputation feature model that is better than the raw reputation features. The enhanced trust prediction framework has been tested and validated on three benchmark datasets namely Wikipedia election dataset, Epinions dataset and Slashdot dataset. The proposed probabilistic feature enhances the overall accuracy, F1 score, and area under the ROC for the classifier results significantly. The results have been compared with other state of the art techniques and are found to be efficient.

There has been a surge in the research of complex network analysis in the recent years. This paper engages with online social network, which is the most popular complex network in the modern world. Network communities help to understand the organization of real world networks. Accordingly, this paper proposes and validates a novel algorithm for overlapping community detection in online social networks. We focus on the stability-plasticity problem in complex networks and attempt to solve it using a Fuzzy Adaptive resonance theory inspired algorithm. The algorithm consists of two stages namely prediction stage and comparison stage. The proposed algorithms make use of network measures such as Edge betweenness, Betweenness centrality, and pair betweenness. The algorithm has been tested and compared with other algorithms using benchmark datasets, artificial datasets and real network datasets. The experimental results obtained were better than other overlapping community detection algorithms. The entropy of the proposed model has been evaluated using Overlapping normalized information, omega index, F-score and the cumulative performance value is 2.42 out of 3, which is better than other community detection algorithm.

There has been lot of research endeavours in detecting overlapping community structures in complex networks. This paper concentrates on one of the most popular complex networks of recent times—online social networks. Some of the existing methodologies in community detection for online social networks are discussed. The goal of the proposed algorithm is to solve the stability–plasticity dilemma and to suggest a new technique for detecting modular and granular overlaps in community detection. The stability–plasticity dilemma is solved using a Fuzzy ART-inspired algorithm for overlapping community detection for detecting modular and granular overlaps. The algorithm is designed by making use of network measures such as vertex betweenness, betweenness centrality, and split betweenness. The validation metrics used for testing the algorithm were sensitivity, specificity, accuracy and normalized mutual information. The algorithm has been tested and validated using benchmark datasets and real network datasets and gives a cumulative performance of 3.1/4.0.

Big Data and parallel computing are used extensively for processing large quantities of data, structured, semi structured or totally unstructured. MapReduce and Hadoop are used for the parallel data processing of these kinds of data. Various scheduling policies are used for MapReduce scheduling which is discussed in detail and a new scheduling technique Two Phase Scheduling Policy (TPSP) based resource allocation for MapReduce is implemented and the efficiency is verified.

Cloud computing is the most utilized and evolving technology in the past few years and has taken computing to a whole new level such that even common man is receiving the benefits. The end user in cloud computing always prefers a cloud service provider which is efficient, reliable and best quality of service at the lowest possible price. A cloud based gaming system relieves the player from the burden of possessing high end processing and graphic units. The storage of games hosted in clouds using the latest technologies in cloud has been discussed in detail. The Quality of service of games hosted in cloud is the main focus of this chapter and we have proposed a mathematical model for the same. The various factors in dealing with the quality of service on cloud based games have been analyzed in detail. The quality of experience of cloud based games and its relation with quality of service has been derived. This chapter focuses on the various storage techniques, quality of experience factors and correlates the same with QoS in cloud based games.

The Cluster-head Gateway Switch Routing protocol (CGSR) uses a hierarchical network topology. CGSR organizes nodes into clusters, with coordination among the members of each cluster entrusted to a special node named cluster-head. The cluster head selection is done with the help of any of the algorithm for cluster head selection. Energy is the primary constraint on designing any Wireless Networks practically. This leads to limited network lifetime of network. Low-Energy Adaptive Clustering Hierarchy (LEACH) and LEACH with deterministic cluster head selection are some of the cluster head algorithms that enable to optimize power consumption of WSN. There are various factors like density & distance, threshold based, power efficient. Load balancing and scalability are the other factors which plays important role in the selection of Cluster head. Algorithms based on load balancing reduce communication cost to a great extent. The algorithms that this study is focused are A Density and Distance based Cluster Head, An Energy Efficient Algorithm for Cluster-Head Selection in WSNs, Consumed Energy as a Factor for Cluster Head. These three algorithms are analyzed and studied in this paper. The analysis of these algorithms gave birth to a new algorithm called EDRLEACH, which is proposed through this paper. Keywords-Cluster head,energy efficient algorithms,selection head algorithms, wireless sensor,networks.

Scalability and on-demand features of cloud computing have revolutionised IT industry in a large scale. Cloud service providers takes the entire burdens of computing, especially managing resources and file storage. Securing the file stored in cloud storage from internal and external attacks has become a primary concern for cloud storage providers as well as cloud users. In this paper, the threats involved in file storage and a secure way of protecting the stored files using a novel ensemble of security strategies is presented. This proposed strategy helps service providers as well as users to secure the file in cloud storage more efficiently.

Twitter has become one of the most widely used social networks, and its popularity is increasing day by day as the number of tweets grows exponentially each day in the order of millions. The twitter data is used widely for personal, academic, and business purpose. In this paper, we collected real-time tweets from Indian Cricket Team fans during the eight matches of ICC Cricket World Cup (CWC) 2015 (here 8 matches means the total number of games India played in CWC) using the social media twitter. We performed sentiment analysis on the tweets to test emotions of Indian Cricket Lovers. The analysis is based on the fact that the emotions of fans change frequently with each event such that when home country is batting and scoring runs, they will be happy, and for every loss of wicket they will be sad. When the team is bowling, they will be sad for ‘six’ and happy for Wickets. So when Fans are happy, they react with positive tweets and accordingly when they are sad they react with negative tweets. We analyzed that, when India is batting, people use fear, anger, nervousness, and tension which are the most frequently used negative words and words like awesome, happy, and love are the most used positive words. All emotions are entirely dependent on team India’s performance. All negative emotions are increased when opponent team hit runs or when they achieve HIGH SCORE” and is decreased when the Indian team hit runs or when they take wickets’. This paper uses tweets and captures emotions for big data analytics and analyzes emotional quotient.

Recommendation system filters the information and shows only the data that are relevant to the user. In this paper, we have considered external factors in recommendation such as scrutability, algorithm accuracy and user interface as well as internal factors such as similarity, diversity, negative similarity, serendipity. The characteristics of each factor in similarity based recommendation system have been clearly examined and a model Fuzzy Inference System has been developed. Factors that influence in determining the recommendation are discussed and evaluated using rule based fuzzy inference model.

Online social networks have gained importance in the past few years and have become an inseparable form of communication. People use online social networks for making friends, gaining knowledge, for entertainment and to review products. This increased influence of social networks has led to the emergence of a research area named online social network analysis. In this paper we propose a model fuzzy inference system that analyze and quantify the network measures used in the analysis of online social networks. We have divided the network measures into two classes namely connection based measures and network structure based measure. We have linked the connection based measures with the network structure based measure and have produced a fuzzy inference system for online social network analysis.

The rapid growth of huge data has become a challenge to the data analysts in recent time. As the data is growing exponentially many techniques are on the rise, for processing the real time data. Many data processing models like Hadoop, Apache YARN, Mapreduce, Storm,and Akka are leading the Big Data domain. This paper analyses and compares all the data processing models stated above. Researchers are trying to increase the efficiency of the algorithms used in the data processing. In this paper, we propose two algorithms namely JATS and SD, which will enhance the efficiency of the storm data processing architecture.

Hadoop has become the most used framework for data intensive processes such as mapreduce. Business intelligence and technology forecasting has played a big part in enhancing the popularity of Hadoop framework. In this paper we have proposed an improvement for apache Hadoop yarn (also known as Hadoop 2.0) architecture. Container nodes, application master, resource manager and the pool of resources are arranged and used in a more efficient way in this framework. We are proposing two new algorithms for selection of application master and for selection of container nodes.

Cloud computing has become the cutting-edge technology for information technology processing and high-end computational tasks. Cloud has started playing its part in almost all business processes. Big data in cloud has become the buzzword. The business impact of cloud has deepened with the growth of big data analytics. Current trends such as green cloud computing, mobile cloud computing, and big data have created social as well as business impact. In this chapter, the authors analyze the field of cloud computing and perform an intense literature survey augmented with mathematical analysis. The forecast on the future of cloud and analysis of the current trends shows that cloud computing is a promising technology that will evolve further in years to come.

There has been a surge in the usage and spread of online social networks in the past few years. This paper focuses on online social networks, which is the most prominent complex network in the modern world. People use online social networks for making friendships, learning, for entertainment and to review product items. This expanded impact of online social networks has prompted the rise of a research area named online social network analysis. This paper reflects the research aspects in the detection of influential nodes in online social networks with respect to topological properties, network generation models and analytical measures in online social networks. We have clearly presented the concepts, issues and future research directions in the influential node detection in online social network analysis. The factors and conditions for the evolution and growth of online social networks and the pre-requisites for generating a random graph for simulation of online social networks have been discussed. The paper gives a clear direction on the relation between computation of influential users and the properties, models and measures in online social networks.

Social networking generates a huge amount of data which can throw useful insights if processed at the right time. Social computing is another emerging technique where social networking is made use for computational purpose. Cloud storage plays an important role in social computing. Privacy in social computing is still a debated issue. The privacy concerns and possible loopholes are discussed in detail. In this paper we are proposing some mathematical models to compute the probability of staying in social network and proposing an algorithm named firefly inspired algorithm for establishing connections FIAEC.