Ahmad R. Shahid

Adaptive mesh based routing for efficient multicasting in highly mobile ad hoc networks

Since meshes show much robustness than tree based multicasting and reactive algorithms tend to reduce control overhead in a mobile ad hoc network (MANET). On demand mesh is a strong candidate for efficient multicasting in such a network. While, mesh enables a scoped flooding mechanism among selected nodes, it results in much data overhead. The tradeoff establishment, by efficiently reducing retransmitting mesh members and achieving high packet delivery ratio at the same time is challenging. Likewise, periodic flooding of control packets throughout the network tends to increase control overhead. Some optimized flooding technique needs to be investigated to efficiently reduce periodic broadcast packets. Adapting control packets that refresh mesh members to current mobility/density conditions of the network, was previously addressed by GPS enabled on-demand multicast routing protocol (ODMRP). We propose an alternative for GPS in our case by utilizing mean link duration metric to adapt and reduce refreshing control packets. In addition, we suggest a new reactive multicast mesh construction algorithm, using overhearing technique, which forms a fish bone structure. Motive is to selectively add relevant redundant members to a source based mesh. Each mesh member chooses its forwarding mode independently and entirely in a distributed fashion, based on its own perceived network conditions to provide a tradeoff between reducing data overhead and achieving multicast reliability. Similarly, optimized flooding technique, using multi point relays (MPRs), is also exploited. Thus we propose to solve the problem of limiting control plus data overhead for mesh based multicast routing and that of achieving very high packet delivery ratio at the same time in MANET

Detection and Counting of On-Tree Citrus Fruit for Crop Yield Estimation

In this paper, we present a technique to estimate citrus fruit yield from the tree images. Manually counting the fruit for yield estimation for marketing and other managerial tasks is time consuming and requires human resources, which do not always come cheap. Different approaches have been used for the said purpose, yet separation of fruit from its background poses challenges, and renders the exercise inaccurate. In this paper, we use k-means segmentation for recognition of fruit, which segments the image accurately thus enabling more accurate yield estimation. We created a dataset containing 83 tree images with 4001 citrus fruits from three different fields. We are able to detect the on-tree fruits with an accuracy of 91.3%. In addition, we find a strong correlation between the manual and the automated fruit count by getting coefficients of determination R2 up to 0.99.

Pedestrian detection using HOG, LUV and optical flow as features with AdaBoost as classifier

Pedestrian detection has been used in applications such as car safety, video surveillance, and intelligent vehicles. In this paper, we present a pedestrian detection scheme using HOG, LUV and optical flow features with AdaBoost Decision Stump classifier. Our experiments on Caltech-USA pedestrian dataset show that the proposed scheme achieves promising results of about 16.7% log-average miss rate.

Vehicle Remote Health Monitoring and Prognostic Maintenance System

In many industries inclusive of automotive vehicle industry, predictive maintenance has become more important. It is hard to diagnose failure in advance in the vehicle industry because of the limited availability of sensors and some of the designing exertions. However with the great development in automotive industry, it looks feasible today to analyze sensor’s data along with machine learning techniques for failure prediction. In this article, an approach is presented for fault prediction of four main subsystems of vehicle, fuel system, ignition system, exhaust system, and cooling system. Sensor is collected when vehicle is on the move, both in faulty condition (when any failure in specific system has occurred) and in normal condition. The data is transmitted to the server which analyzes the data. Interesting patterns are learned using four classifiers, Decision Tree, Support Vector Machine, Nearest Neighbor, and Random Forest. These patterns are later used to detect future failures in other vehicles which show the similar behavior. The approach is produced with the end goal of expanding vehicle up-time and was demonstrated on 70 vehicles of Toyota Corolla type. Accuracy comparison of all classifiers is performed on the basis of Receiver Operating Characteristics (ROC) curves.

Outdoor Scene Labeling Using ALE and LSC Superpixels

Scene labeling has been an important and popular area of computer vision and image processing for the past few years. It is the process of assigning pixels to specific predefined categories in an image. A number of techniques have been proposed for scene labeling but all have some limitations regarding accuracy and computational time. Some methods only incorporate the local context of images and ignore the global information of objects in an image. Therefore, accuracy of scene labeling is low for these methods. There is a need to address these issues of scene labeling to improve labeling accuracy. In this paper, we perform outdoor scene labeling using Automatic labeling Environment (ALE). We enhance this framework by incorporating bilateral filter based preprocessing, LSC superpixels and large co-occurrence weight. Experiments on a publicly available MSRC v1 dataset showed promising results with 89.44% pixel-wise accuracy and 78.02% class-wise accuracy.

Significance of machine learning algorithms in professional blogger's classification

Abstract Outreach of internet has opened new horizons for the people who want quick and widespread dissemination of their ideas, and the tool to do so is blogging. Bloggers can broadly be classified into two groups: professional and non-professional bloggers. As for professional bloggers, there are many factors that influence individuals to opt this profession. This study, with the help of an online dataset, attempts to identify such factors. Data analysis was made by using decision tree algorithms, lazy learning algorithms and ensembling methods. Nearest-neighbour classifier (IB1) and RandomForest have results with 85% accuracy and 84.8% precision for classification. The proof of concept is provided for result validation. The causes behind the varying performance of algorithms are elaborated. The factors that influence a blogger to behave professionally are identified based on the classifier with the best results.

Intelligent Pedestrian Detection using Optical Flow and HOG

Pedestrian detection is an important aspect of autonomous vehicle driving as recognizing pedestrians helps in reducing accidents between the vehicles and the pedestrians. In literature, feature based approaches have been mostly used for pedestrian detection. Features from different body portions are extracted and analyzed for interpreting the presence or absence of a person in a particular region in front of car. But these approaches alone are not enough to differentiate humans from non-humans in dynamic environments, where background is continuously changing. We present an automated pedestrian detection system by finding pedestrians’ motion patterns and combing them with HOG features. The proposed scheme achieved 17.7% and 14.22% average miss rate on ETHZ and Caltech datasets, respectively.