Crop yield prediction is affected by many factors such as weather, soil, crop cultivation and management practices, climate change and impact of different factors vary based on the different crops and regions. Crop growth can be captured by analyzing satellite images collected over a period using deep learning methods. To recognize the influence of weather on the crop growth, we applied convolution neural network (CNN)-long short term memory (LSTM) and convolution neural network(CNN)-recurrent neural network (RNN) based models on the satellite images. To capture robust growth over the duration, we had taken fusion of MODIS and LANDSAT-7 images along with weather data and observed results. The forecasting results of CNN-LSMT model shows more than 5% of performance improvement with weather data compared to without it. Other model also shown better results when applied with weather data. It exhibits strong correlation of weather with the crop growth.

Decision Tree is a state-of-the-art classification and prediction algorithm in machine learning which constructs tree-structured set of attributes. Its distributed implementation, i.e. Distributed Decision Tree generates a specified number of trees (depending upon number of partitions of input dataset) and at the end collects votes or averages the prediction or classification. Here, the overall idea of achieving parallelism depends upon number of partitions. Parallelism can be achived by proper tuning of number of partitions. However, this kind of setup in-turn leads to a problem of compromise in accuracy, because there is always a tradeoff between accuracy and size of partition. Therefore, in this paper, we have proposed an improved Distributed Decision Tree algorithm to achieve true parallelism without loss in accuracy. The improved Distributed Decision Tree is implemented using open-source distributed frameworks Hadoop and Spark. We measure learning time, size of tree and accuracy to set up benchmarking using medium to large datasets.

Voluminous and variety of disparate information is generated and consumed in agriculture domain at a higher velocity. In agriculture, information is available in the form of weather and soil conditions reports, GPS mapping, water resources, fertilizer/ pesticide use, field characteristics, and commodity market conditions. Big data technology has a huge potential to refer these information and produce comprehensive insight via Geo-spatial processing, remote sensing, advance analytics algorithms, cloud resources, and advance storage systems. The paper, proposes a spark based information management system for agriculture and intend to reduce the technological gap between agro users and information. The system is proposed to collect, query, analyze, and visualize heterogeneous and distributed data including Geo-spatial data at scale using open source. The implementation is done on big data open source architectures by developing various web based analytical and visualization services for cotton crop in Gujarat state, India. The analytical results are explored through interactive maps and Restful ad-hoc APIs.

The primary focus of this paper is to detect disease and estimate its stage for a cotton plant using images. Most disease symptoms are reflected on the cotton leaf. Unlike earlier approaches, the novelty of the proposal lies in processing images captured under uncontrolled conditions in the field using normal or a mobile phone camera by an untrained person. Such field images have a cluttered background making leaf segmentation very challenging. The proposed work use two cascaded classifiers. Using local statistical features, first classifier segments leaf from the background. Then using hue and luminance from HSV colour space another classifier is trained to detect disease and find its stage. The developed algorithm is a generalised as it can be applied for any disease. However as a showcase, we detect Grey Mildew, widely prevalent fungal disease in North Gujarat, India.

In Indian, canal irrigation sector is one of the most important sources of water for the farmers which accounts to 21.7 percent of the total irrigated area of the country. According to the planning commission about 300000 crores rupees have been invested till 2011 into the infrastructure development. Even after such huge investments into the sector, the service provision is in complete disarray. Water distribution has been a major concern, with unequal distribution patterns in the command area. There is a huge communication gap between the irrigation department, Water User Associations and the farmers, about issues such as time of release of water to the quantity that will be made available to them. There are hardly any mechanisms in place to get feedback from the farmers on whether water is being delivered to them or not. This has led to a complete lack of accountability in the sector and has made farmers lose trust from the sector, and has forced farmers to look for irrigation from other private sources in turn has increased the cost of cultivation. The paper looks at how ICT can be used to build back the lost trust into the system by developing a farmer centric water governance system and use of crowd sourcing techniques to improve the communication and accountability of the irrigation department with the farmers.

Internet of Things (IoT) application development is technically challenging and complex due to several factors such as the presence of different IoT protocols, interoperability issues, lack of industry standards and dealing with the heterogeneity that exists both in Physical and Internet worlds. Furthermore, developers involved in the IoT application development have to address issues pertaining to different life-cycles ranging from design, implementation to deployment (deployment complexities due to the possibilities of wide range of devices). Manual effort involved in all above three phases for heterogeneous devices is a time-consuming and error-prone process. We demonstrate IoTSuite which is an application development platform consisting of a suite of tools motivated by the need to simplify IoT application development. The IoTSuite supports several features such as automatic code generation and integration with a set of modeling languages. It takes high-level specification as input that abstract heterogeneity related complexity. It integrates compiler and deployment module to provide automation at different phases of application development process.

This article introduces Postfix Genetic Programming (GP), a postfix notation-based GP, approach to symbolic regression for solving empirical modeling problems. The main features of Postfix-GP are presented. These features include (1) postfix-based, variable-length individual-representation and its stack-based evaluation and (2) subtree crossover operator and semantic-aware subtree crossover operator. The article also presents two different constant creation approaches to evolve useful numeric constants for symbolic regression problems. The first approach uses an explicit list of constants and the second allows the Postfix-GP algorithm to evolve constants. Use of Postfix-GP as a solution modeling tool is demonstrated by solving two function identification problems and two deterministic chaotic time series modeling problems. Effectiveness of the evolved models is tested by statistically analyzing their performance on training and out-of-sample datasets of the problems. Experimental results on test problems suggest that Postfix-GP offers a new possibility for solving empirical modeling problems. We also compared the performance of Postfix-GP with the lil-GP system for all four problems. The results suggest that the quality of solutions found by Postfix-GP was better than that found by lil-GP, for the tested problems.

Modern data centers use virtual machine based implementation for numerous advantages like resource isolation, hardware utilization, security and easy management. Applications are generally hosted on different virtual machines on a same physical machine. Virtual machine monitor like Xen is a popular tool to manage virtual machines by scheduling them to use resources such as CPU, memory and network. Performance isolation is the desirable thing in virtual machine based infrastructure to meet service level objectives. Many experiments in this area measure the performance of applications while running the applications in different domains, which gives an insight into the problem of isolation. In this paper we run different kind of benchmarks simultaneously in Xen environment to evaluate the isolation strategy provided by Xen. Results are presented and discussed for different combinations and a case of I/O intensive applications with low response latency has been presented.

Service-oriented computing enables service providers to publish their business functionalities in the form of abstract contracts, which can be discovered by service consumers based on open and standard protocols. Enterprise may be running a number of multiple business processes in parallel, which may require different services to fulfill the functionality. To provide better search, query, composition, and management, we need a mechanism to group these services based on the requirements of clients and business processes. In this paper, we have proposed context and location based approach for service grouping and group notification. Context and location provide powerful mechanism for better search, query, grouping and grouping notification to the services. It allows customization based on user preferences, role, and location to improve personalization. This paper proposes context and location driven grid business process to aggregate information from multiple sources according to the preferences of clients. We have used policy based service grouping approach to aggregate services.

Long running business processes require composition of services for task accomplishment. BPEL provide a mechanism to model business workflow among collaborating Web Services distributed across organizations. For effective execution and consistent outcomes from such composite services in a loosely coupled environment, management of state, transaction, notification and execution monitoring are the key requirements. After the emergence of WS-RF, stateful Web services have become integral part of Grid environment. Grid supports execution monitoring, resource sharing, integration and management of large-scale applications. Such capabilities are the backbone for any large-scale enterprise applications. Process oriented workflow execution in a grid environment with the support to manage state, transaction and notification is a challenging issue. In this paper we have proposed architecture to achieve integration of stateful services for a grid workflow. Development of stateful services is based on WS-RF specification to build services to support state management, transaction, notification and execution monitoring of a business process in a large-scale grid environment.

As a joint effect of advancements in electronics and telecommunication manufacturing segments and ease in usage of mobile devices, there is a tremendous increase in the demand for a new class of services from mobile devices by users. Middleware technologies can empower mobile devices by providing a significant platform for many services. Object-oriented middleware are not inherently designed to support wireless environment behavior. The aim of this research is to investigate the issues of the object management group's common object request broker architecture (CORBA) to facilitate application-to-application communication in a wireless environment. This paper discusses the issues in the design and implementation of an architecture where CORBA objects and the hosting devices both have mobile behavior.