Mohammad Jamshidi

Mobile robot navigation and target tracking system

This paper presents the framework for the navigation and target tracking system for a mobile robot. Navigation and target tracking are to be performed using a Microsoft Xbox Kinect sensor which provides RGB color and 3D depth imaging data to an x86 based computer onboard the robot running Ubuntu Linux. A fuzzy logic controller to be implemented on the computer is considered for control of the robot in obstacle avoidance and target following. Data collected by the computer is to be sent to a server for processing with learning-based systems utilizing neural networks for pattern recognition, object tracking, long-term path planning and process improvement. An eventual goal of this work is to create a multi-agent robot system that is able to work autonomously in an outdoor environment.

Prediction of cloud data center networks loads using stochastic and neural models

The increasing demand for cloud computing resources has led to a commensurate increase in the operating power consumption of the systems that comprise the cloud. In this paper, we introduce a novel framework combining load demand prediction and stochastic state transition models. We claim that our model will lead to optimal cloud resource allocation by minimizing energy consumed while maintaining required performance levels. We characterize the ability of neural network and auto-regressive linear prediction algorithms to forecast loads in cloud data center applications. In this paper, the performance of our models against two sets of data at multiple look-ahead times is also presented.

Low-latency software defined network for high performance clouds

Multi-tenant clouds with resource virtualization offer elasticity of resources and elimination of initial cluster setup cost and time for applications. However, poor network performance, performance variation and noisy neighbors are some of the challenges for execution of high performance applications on public clouds. Utilizing these virtualized resources for scientific applications, which have complex communication patterns, require low latency communication mechanisms and rich set of communication constructs. To minimize the virtualization overhead, a novel approach for low latency network for HPC Clouds is proposed and implemented over a multi-technology software defined network. The efficiency of the proposed low-latency Software Defined Networking is analyzed and evaluated for high performance applications. The results of the experiments show that the latest Mellanox FDR InfiniBand interconnect and Mellanox OpenStack plugin gives the best performance for implementing VM-based high performance clouds with large message sizes.

Bilateral haptic teleoperation of an articulated track mobile robot

Teleoperation has been used in many applications, allowing a human operator to remotely control a robotic system in order to perform a particular task. Recently haptic teleoperation has focused mainly on improving performance in remote manipulation tasks, however the haptic approach offers similar advantages for teleoperative control of the motion of a mobile robot. This paper describes a prototype system designed to facilitate haptic teleoperation of an all-terrain, articulated track mobile robot. This system utilizes a multi-modal user interface intended to improve operator immersion, reduce operator overload and improve teleoperative task performance. The system architecture facilitates implementation of an application-specific haptic augmentation algorithm in order to improve operator performance in challenging real-world tasks. The contributions of this work can be categorized as the custom mobile platform, teleoperator interface and haptic augmentation strategy.

Energy efficiency in a smart house with an intelligent neuro-fuzzy lookup table

Demand response has an important role in improving energy efficiency. By using it, we can shift electrical load from peak demand time to other periods which is usually in response to price signal. In residential level and in a dynamic pricing system which modification of energy consumption is unrecognized by a consumer, using an automated Energy Management System (EMS) should be considered. In this paper, a new intelligent EMS in a smart house is presented1. It has two parts, fuzzy part and intelligent lookup table. Fuzzy part based on its fuzzy rules and inputs makes the proper output for intelligent lookup table. The second part which its core is an associative neural network is able to map inputs to desired outputs. It takes two types of inputs which come from fuzzy part and outside sensors. Whatever is trained in this lookup table are different scenarios in different conditions. This system is able to find the best energy efficiency scenario in different situations.

Intelligent Object-Tracking using Sensor Networks

The idea of using sensor networks for monitoring events is to utilize the distributed nature provided by these tiny and low powered devices. Multiple sensors can be used collaboratively to monitor events or space more effectively than a single sensor. Several applications can be envisioned with sensor networks ranging from military to commercial applications to environment and earth sciences, such as, traffic monitoring of vehicles, military reconnaissance and surveillance, cross-border infiltration, habitat monitoring, to name a few. In this paper, we propose an algorithm for tracking a moving object in an environment with densely deployed sensing devices.

Stock market prediction by using artificial neural network

A neural networks based model have been used in predicting of the stock market. One of the methods, as an intelligent data mining, is artificial neural network (ANN). In this paper represents how to predict a NASDAQs stock value using ANNs with a given input parameters of share market. We used real exchange rate value of NASDAQ Stock Market index. This paper makes use generalized feed forward networks. The network was trained using input data of stock market price in between 2012 and 2013. It shows a good performance for NASDAQ stock market prediction.

Fuzzy logic controlled UAV autopilot using C-Mean clustering

The implementation of fuzzy logic control for autonomous UAV autopilots is achieved by having two sets of fuzzy rules, one for controlling the change in heading (horizontal plane controller) and the other for controlling the change in altitude (vertical plane controller) of the aircraft. This paper is a general presentation on the topic of fuzzy logic controlled UAV autopilots as well as a presentation of how the input and output membership functions are chosen for both the horizontal plane and vertical plane controller from Fuzzy C-Mean clustering. This paper also provides a sample implementation of the controllers for verification of process and proof that the use of C-Mean clustering for generation of membership functions is a good method. The understanding established in this paper is critical for the development and implementation of a successful fuzzy logic autopilot.

Thermal imaging in fuzzy condition monitoring

The procedure of monitoring the condition of processes is called condition monitoring. Condition monitoring is one of the most important part of any system which could be managed and controlled by thermal imaging system. This paper attempts to show the capability of thermal imaging in condition monitoring. According to the characteristic of thermal images, the goals of this paper are: (a) introducing a new metric as thermal condition monitoring measurement, (TCMM) (b) detecting of fault location, and (c) define a new concept of thermal image fuzzy condition monitoring system as a priority level classifier to identify type of condition and sending the correspond recommended action. The advantages of the proposed schemes are: (a) thermal imaging condition monitoring system doesnt need to access high-level knowledge about the system and, (b) using the proposed system cause to reduce number of thermal instruments and make the data send/receive protocol more reliable. Experimental results show the effectiveness of the proposed methods on condition monitoring system and control.

Cost effective ROF communication system for CATV channels over WDM network and fuzzy modeling of the system

A radio over fiber (RoF) communication system is considered for cable television (CATV) channels over wavelength division multiplexing (WDM) network using an optical direct modulator (DM). Since the DM bandwidth is limited, increasing bandwidth efficiency of the system using M-ary quadrature amplitude modulation (MQAM) schemes will improve the link symbol error rate (SER) performance. Radio frequency (RF) signals with constellations of 16-64-256 QAM were simulated for CATV channels and the effect of using higher bit per symbol on the link performance was studied in order to reduce the cost of the network through utilizing financially feasible optical modulator. The 64-QAM scheme which is the most appropriate is used for the system of CATV channels. The link performance is studied for different combinations of effective parameters such as AC electrical power and Module to Bias ratio, which are crucial to be set properly, and SER is obtained at the front end of the receiver. The best setting options are proposed for 30 CATV channels with 64-QAM constellation with direct modulation transmitted over the 4-WDM link. Moreover, communication system is modeled by fuzzy logic using data-base obtained from simulation. Fuzzy reverse modeling of the system is also implemented in order to provide reasonable estimate of electrical power required to achieve a desired SER. Characteristics of forward and reverse fuzzy modeling are discussed. Simulation results represent satisfactory performance of the models.