M Tech Dissertations

Permanent URI for this collectionhttp://ir.daiict.ac.in/handle/123456789/3

Browse

Filters

20152

Settings

Subject: search.filters.subject.Research

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    ItemOpen Access
    Study of communication schemes for multiple neural processing nodes
    (Dhirubhai Ambani Institute of Information and Communication Technology, 2015) Mehta, Nilay V.; Mazad, Zaveri
    Over the past few years variety of hardware for implementing Artificial Neural Networks (ANN) has been designed. The most basic approach to speed up any ANN algorithm, is to parallelize processing. However, the existing wired strategies are not easily scalable and are also expensive. This thesis aims to provide low cost, easily scalable architecture for implementation of ANN, targeted for microcontrollers and FPGA architectures. With wired strategies, it is difficult to have scalable architecture with multiple Processing Nodes (PNs). Scalability of the same architecture can be improved by enabling wireless communication between the PNs. In this thesis, different strategies for implementation ofANNhave been analyzed, which considers two different types of PNs (Arduino R and Spartan3E R ) and various communication strategies (I2C with different speeds, Zigbee beacon enabled, Zigbee Non-beacon enabled, Zigbee GTS mode and TDMA scheme). Comparison of all these communication protocols have been carried out in terms of performance (speed) and energy. In this thesis, Nearest-Neighbour-Mesh (NNM) structure for the implementation is considered, where an application consists of 1024 neurons and 1024 synapses per neuron. The analysis has been carried out by varying number of PNs available for implementing this application. For simulation of all the wireless strategies, NS2 (Network Simulator) is used. For estimating computation time for Arduino and Spartan3E, Arduino software (Arduino 1.6.2) and Xilinx ISE Design Suite 14.7 R is used, respectively.
  • Thumbnail Image
    ItemOpen Access
    Precision agriculture using wireless sensor network
    (Dhirubhai Ambani Institute of Information and Communication Technology, 2015) Joshi, Nikita Rajeshbhai; Shrivastava, Sanjay
    Farming practices should evolve with the rapid increase in population. Recent growth in wireless sensor network (WSN) has the capability to meet this objective. Better quality in crop production can be achieved using real-time data collected through WSN. Also, greenhouse allows farming in a controlled environment. Hence, a combination of WSN and greenhouse gives better quality crop yield. Greenhouse requires climate control and fertigation management. Fertigation is a combination of irrigation and fertilization. Existing architectures for greenhouse management collect data of various parameters using sensor nodes and control values of parameters using actuators. These architectures have very limited capability to handle faults in sensors and actuators. Deployment of sensor nodes in these architectures is crop dependent. Therefore, while changing crops, modifications in the location of sensor node is needed and details of this modification should be entered manually in the database. Thus, they are not flexible architectures. In our work, a WSN based architecture for controlled environment like greenhouse is designed. This architecture provides for actuator control using crop requirements stored in the database. The architecture provides for deployment strategies for sensor nodes and actuators using the details about bed size, crop requirements etc. Localization algorithm is used to find the exact location of the sensor node. The architecture is flexible such that whenever location of sensors nodes needs to be changed, location of sensor nodes will be automatically detected using the localization algorithm. We have designed an algorithm to detect faults in sensor nodes and actuators. These faults are isolated or reported to the user. The architecture provides for network management strategies to control energy consumption of sensor nodes which eventually helps in increasing network lifetime. WSN algorithms for sleep scheduling and localization are used to support these features.We designed a system for a specific group of crops namely tomato, capsicum and cucumber using the architecture. This system is simulated in NS2 and it is verified that system is working as expected.