Classification of Leaf Disease Based On Multiclass SVM Classifier
India, the country where the main source of income is from agriculture. Farmers grow variety of crops based on their requirement. Since the plants suffer from disease, the production of crop decreases due to infections caused by several types of diseases on its leaf, fruit and stem. Leaf diseases are mainly caused by bacteria, fungi, virus etc. Diseases are often difficult to control. Diagnosis of the disease should be done accurately and proper actions should be taken at the appropriate time. Image Processing is the trending technique in detection and classification of plant leaf disease. This work describes how to automatically detect leaf diseases. The given system will provide fast, spontaneous, precise and very economical method in detecting and classifying leaf diseases. This paper is envisioned to assist in the detecting and classifying leaf diseases using Multiclass SVM classification technique. First the affected region is discovered using segmentation by K-means clustering, then features (color and texture) are extracted. Lastly, classification technique is applied in detecting the type of leaf disease. The proposed system effectively detects and also classify the disease with accuracy of 92%.
Published by: Pooja Kulinavar, Vidya I. Hadimani
Author: Pooja Kulinavar
Paper ID: V3I4-1205
Paper Status: published
Published: July 25, 2017
Analysis of Air Pollution
This research paper is an attempt towards analyzing real time air pollution data collected by PAQS sensor devices from some key locations in Bangalore. Air pollution in most of the metropolitan cities in India is turning out to be a major threat to our environment and hazardous to our health. Many infections and diseases related to lungs and throat are caused by the polluted air we breathe. There is a growing need to conduct regular measurements of air quality data and analyze it.
Published by: Rajeshwari K. Rai
Author: Rajeshwari K. Rai
Paper ID: V3I4-1221
Paper Status: published
Published: July 25, 2017
Non Destructive Method by Penetrant Testing
This paper presents results from a literature review of defect characteristics essential for non-destructive testing (NDT). Most of the major NDT methods are included in the study – Penetrant Testing (PT), The study was performed by means of searching in scientific databases, , etc. Mainly, the following It is concluded that for Penetrant testing, the defect geometry, the defect size and the defect. A number of investigations address the relationships between the defect parameters like roller depth, surface defects Also the phenomena of the electrical contacts between the defect surfaces (for a crack) was studied. Defect parameters that are essential to the quality of Penetrant testing are defect position in the object (includes the depth), orientation, size, crack surface roughness, closure and tip radius. This investigation has been focused on those parameters that are not that easy to reconstruct and only briefly discussed the influence on the signal response due to defect position, orientation and size.
Published by: Shyamji, Dr. Suresh Prasad
Author: Shyamji
Paper ID: V3I4-1219
Paper Status: published
Published: July 25, 2017
Effectively Reconstructing the Routing Paths in Sensor Networks
In wireless sensor networks, sensor nodes are usually self-organized or self sorted, delivering data to a central sink in a multi-hop manner. Reconstructing the per-packet routing path enables fine-grained diagnostic analysis and performance optimizations of the network. The performances of existing path reconstruction approaches like MNT, however, goes down rapidly in large scale networks with loss links or failed links. We present Pathfinder, a vigorous path reconstruction method against packet losses as well as routing dynamics. At the node side, Pathfinder exploits temporal correlation between a set of packet paths and efficiently compresses the path information using path difference. At the sink side, Pathfinder infers packet paths from the compressed information and employs intelligent path speculation to reconstruct the packet paths with high reconstruction ratio. We propose a novel analytical model to analyze the performance of Pathfinder. We further calculate Pathfinder compared with two most related approaches using traces from a large scale deployment and extensive simulations by means of graph. Results show that Pathfinder outperforms existing approaches, achieving both high reconstruction ratio and low transmission cost compared to MNT.
Published by: Mohammad Peer M. Shaikh, Prof. Anand D. Vaidya
Author: Mohammad Peer M. Shaikh
Paper ID: V3I4-1218
Paper Status: published
Published: July 24, 2017
Comparative Research Analysis on LTE Techniques to Reduce PAPR in Multi-Carrier Communication Systems
New technologies emerging day by day and main focus to give a better quality of service at low cost. LTE has adopted DFT-spread OFDMA technique as the uplink multiple access schemes which use single carrier modulation and frequency domain equalization. In our research work, we show the PAPR performance of DFT-spreading technique. The performance of PAPR of DFT spreading technique is dependent on the number of subcarriers assigned to each user. In this thesis, a method for PAPR reduction in LTE system has been introduced, which is based on the DFT spread method. DFT spread method is further classified into two methods known as LFDMA (localized FDMA) and IFDMA (interleaved FDMA). It was shown that an interleaved FDMA and localized FDMA perform better than orthogonal FDMA in the uplink transmission where transmitter power efficiency is of great importance in the uplink. LFDMA and IFDMA result in lower average power values due to the fact that OFDM and OFDMA map their input bits straight to frequency symbols where LFDMA and IFDMA map their input bits to time symbols. We conclude that single carrier-FDMA is a better choice on the uplink transmission for cellular systems. Our conclusion is based on the better efficiency due to low PAPR and on the lower sensitivity to frequency offset since SC-FDMA has a maximum of two adjacent users. From results, it can also be concluded that the performance of IFDMA is far better than the LFDMA.
Published by: Ritu, Tajendar Malik
Author: Ritu
Paper ID: V3I4-1225
Paper Status: published
Published: July 24, 2017
Simulink Model Design for FSO Communication System for Analysing Of Different Parameters
In our dissertation work, an approach has been made to analyze the effect of free space transfer function by considering various parameters like path loss factor, atmospheric turbulence, pointing errors on the performance of free space optical (FSO) communication system. The performance of the proposed free space optical communication system is studied by developing a MATLAB simulator. In our research work two cases are considered for two different probabilities when binary codes are generated by Bernoulli generator with 0.5 and 0.4. Finally, we evaluated the Bit Error Rate (BER) and signal to noise ratio (SNR) performance of the proposed system varying with different system parameters. The BER is highly degraded on severe atmospheric turbulence condition ever for a short distance of free space channel. The effect of path loss factor due to dense fog is also severe on the BER even though the turbulence effect and free space distance is short. After Bernoulli generator spectrum analyser used to see result in frequency domain and later on both signal are convoluted with Hadmard code to achieve orthogonality criterion and the passed through AWGN channel and 10db SNR also added the both signal are processed with FSO circuit with different parameters condition and finally BER is received on display. FSO communication is latest trend technology and during this lot of problem have to face and one important parameter is that range. Signal cannot be transmitted to long distance if we transmit then BER also increased and due to which communication is not reliable so we required to work on distance and power utilized and atmospheric condition so that data can be transmitted successfully for a long distance
Published by: Usha, Manisha
Author: Usha
Paper ID: V3I4-1224
Paper Status: published
Published: July 24, 2017
