Search

Computer vision is the science that aims to contribute a similar, if not better, capability to a machine or computer. It is also interested with the idea and technology for building artificial systems that secure information from images. The digital image processing, image analysis and computer vision have become a principle part of artificial intelligence and the interface between the human and the machine grounded theory and enforced technologies. Implementing machine learning such as deep neural networks on agricultural data as immense attention in recent times. Convolution Neural Networks (CNN) are most commonly used in pattern and image detection problems as they have a number of advantages compared to other techniques. This paper proposes CNN architecture to segregate different plant images from the sequences collected. Following the preprocessing steps that will be including the elimination of blurriness or introducing the illumination change; CNN architecture is employed to extract the traits of the images that are present in the dataset that is created. Image classification using CNN involves dataset creation, training CNN, validating, testing CNN, prediction and at last classification. Here we use Keras software with backend as Theano and Tensor flow and we are able to predict the overall classification report with the accuracy of 43.98% for one cast of field photographs.

Engineers are increasingly acting as “boundary spanners” who coordinate, collaborate, and communicate across many different kinds of boundaries. The research project described in this work-in-progress paper is shedding additional light on this trend by responding to two main research questions: 1) What specific boundary spanning roles, activities, and competencies are most important and prevalent for early career engineers, and 2) How do early career engineers experience boundary spanning challenges? One major goal of this project is to generate a typology of boundary spanning roles, activities, and competencies for multiple engineering fields. This paper more specifically describes methods and reports preliminary findings for the initial phases of our research. The first phase involves a systematic review of more than 80 journal articles and book chapters on boundary spanning and related concepts using established procedures for literature meta-analysis. In this paper we summarize the major themes and categories emerging from this process. The second phase of the project involves semi-structured interviews with engineering students and early career engineers. In this paper we focus on our interview methods, including development and use of a “primer” document to familiarize subjects with boundary spanning. We conclude by discussing the implications of our work, especially in relation to leading-edge approaches for instruction and assessment.

An enabling superjunction device technology, which is fully integrated on the Partial Silicon on Insulator (PSOI) platform using the bulk silicon substrate, is proposed and fabricated. The proposed technology has the potential to eliminate the substrate assisted depletion. It enables the implementation of lateral superjunction power MOSFET (SJ LDMOS) on bulk silicon substrate without sacrificing its thermal performance. In this paper, the approach was demonstrated successfully on both p-i-n diode and planar gate SJ LDMOS devices. The proposed technology has enabled the fabrication of SJ Power Integrated Circuits (PIC) on the bulk silicon substrate for future automotive power electronics applications.

The lateral superjunction power MOSFET device fabricated on the bulk silicon substrate suffers from the substrate-assisted depletion effect, which causes charge imbalance and thus limits the sustainable voltage rating. An enabling device technology, which is fully integrated on the partial silicon on insulator (PSOI) platform using the bulk silicon substrate, is described in this paper. The new technology has the potential to eliminate the substrate-assisted depletion. It enables the implementation of lateral superjunction power MOSFET (SJ LDMOS) on bulk silicon substrate without sacrificing its electrical and thermal performance. The approach was demonstrated successfully on both planar and trench gate SJ LDMOS devices. At the given breakdown voltage rating, the drift region doping concentration can be raised to one order higher than that of the conventional LDMOS. The proposed technology has enabled the fabrication of SJ power integrated circuits on the bulk silicon substrate for future automotive power electronics applications.

Superjunction power LDMOS device implemented on the bulk Si substrate suffers from the substrate-assisted depletion (SAD) effect, which causes the charge imbalance, and thus limits the device performance. A new SJ-LDMOS structure integrated on the partial SOI (PSOI) platform is proposed in this paper, which eliminates the SAD completely and enables the making of SJ-LDMOS on bulk silicon substrate without sacrificing its electrical and thermal performance. The PSOI SJ-LDMOS was fabricated and characterized. The tested PSOI SJ-LDMOS exhibits a specific on-state resistance of 1.01mOmegamiddotcm2 while the breakdown voltage is 72.3 V.