Legand Burge

Implementation of Artificial Neural Network-Based Tracking Controller for High-Performance Stepper Motor Drives

Two distinct multilayer perception neural networks (NNs) are implemented via laboratory experiment to simultaneously identify and adaptively control the trajectory tracking of a hybrid step motor assumed to operate in a high-performance drives environment. That is, a neural network identifier (NNI) which captures the nonlinear dynamics of the stepper motor drive system (SMDS) over any arbitrary time interval in its range of operation, and a neural network controller (NNC) to provide the necessary control actions as to achieve trajectory tracking of the rotor speed. The exact form of the control law is unknown, and must be estimated by the NNC. Consequently, the NNC is constructed as a nonlinear unknown function depending on the current state of the drive system supplies by the NNI and the reference trajectory we wish the outputs to follow. The two NNs are online trained using dynamic back-propagation algorithm. The composite structure is used as a speed controller for the SMDS. Performance of the composite controller is evaluated through a laboratory experiment. Experimental results show the effectiveness of this approach, and demonstrate the usefulness of the proposed controller in high-performance drives

Efficient scheduling of pigeons for a constrained delay tolerant application

Information collection in the disaster area is an important application of pigeon networks—a special type of delay tolerant networks (DTNs) that borrows the ancient idea of using pigeons as the telecommunication method. The aim of this paper is to explore highly efficient scheduling strategies of pigeons for such applications. The upper bound of traffic that can be supported under the deadline constraints for the basic on-demand strategy is given through the analysis. Based on the analysis, a waiting-based packing strategy is introduced. Although the latter strategy could not change the maximum traffic rate that a pigeon can support, it improves the efficiency of a pigeon largely. The analytical results are verified by the simulations.

Hardware implementation of an adaptive network-based fuzzy controller for DC-DC converters

A novel control topology of adaptive network-based fuzzy inference system (ANFIS) for control of the dc-dc converter is developed and presented in this paper. It essentially consists of combining fuzzy inference system and neural networks and implementing within the framework of adaptive networks. The architecture of the ANFIS along with the learning rule, which is used to give an adaptive and learning structure to a fuzzy controller, is also described. The emphasis here is on fuzzy-neural-network control philosophies in designing an intelligent controller for the dc-dc converter that allows the benefits of neural network structure to be realized without sacrificing the intuitive nature of the fuzzy system. Specifically, it permits this type of setup to simultaneously share the benefits of both fuzzy control and neural network capabilities. An experimental test bed is designed and built. The components are tested individually and in various combinations of hardware and software segments. Two categories of tests, namely, load regulation and line regulation, are carried out to evaluate the performance of the proposed control system. Experimental results demonstrate the advantages and flexibilities of ANFIS for the dc-dc converter.

DomSVR: domain boundary prediction with support vector regression from sequence information alone

Protein domains are structural and fundamental functional units of proteins. The information of protein domain boundaries is helpful in understanding the evolution, structures and functions of proteins, and also plays an important role in protein classification. In this paper, we propose a support vector regression-based method to address the problem of protein domain boundary identification based on novel input profiles extracted from AAindex database. As a result, our method achieves an average sensitivity of ∼36.5% and an average specificity of ∼81% for multi-domain protein chains, which is overall better than the performance of published approaches to identify domain boundary. As our method used sequence information alone, our method is simpler and faster.

Modelling the spread of mobile malware

The popularity of mobile phones and the internet makes it more enticing for hackers to write viruses and create malicious code. There are currently over 150 mobile viruses today and the prevalence of mobile viruses in the US is currently at its tipping point. The first known cellular virus in the USA is called Cabir and was discovered in 2004. In this paper, we reveal how cellular phones running the Symbian and Windows Mobile operating systems get infected through various channels, specifically, Bluetooth and 802.11 wireless. We investigated the transmission rate of mobile malware in Washington, DC from 2004 to 2012, focusing our research in the Washington DC metropolitan area being that it has a high risk of cyber terrorism attacks. The goal of our study is to show the impact of mobile malware on cell phones using the SIS epidemic model. We aim to help cell phone users prepare now in the event of a future mobile malware epidemic in the District. We then proposed some preventative measures.

Improving retention of minority freshmen in engineering by applying the six sigma methodology

In response to the pressing need to increase the pool of future engineers, the engineering academia are focusing on improving the persistence rate of underrepresented minority students in the engineering program. This has led to various studies into the factors which affect the attrition of minority engineering students and which strategies can significantly reduce their attrition. This paper recognizes that addressing most of the factors which affect minority student attrition at freshman level will improve overall retention; and supports that the industry-based six sigma methodology can be adapted to solve or at least alleviate the retention problem. In addition, it identifies the freshman engineering process as a key process improvement effort under the six sigma initiative and recommends the selection of the freshman education process as a key sigma project which will result in a significant increase in the retention rates of the underrepresented minority students enrolled in the engineering program.

The potential benefits of mobile microwork services in developing nations: Research opportunities and challenges

Unemployment is one of the main hindrances to socio-economic development in developing nations. At the same time, the prominent adoption and use of digital technologies, especially mobile devices have changed the status quo in Africa with regard to digital divide, communication, and information access. Nevertheless, most parts of Africa and other developing countries are still lagging behind when it comes to the swiftness of implementing technologies that have the potential of addressing pressing issues such as unemployment. On-demand mobile microwork services, which are a subset of the crowdsourcing paradigm, are some of the initiatives that are under-explored, particularly for dealing with issues of unemployment. This research paper explores the potential benefits of such services as one possible contribution for dealing with joblessness in developing nations where mobile devices are easily accessible and used. Furthermore, the paper presents some of the pertinent research opportunities and challenges that need to be considered when dealing with mobile microwork services.

HMMF: An Hidden Markov Model Based Approach for Motif Finding

Transcriptional factor binding site (TFBS) motifs on DNA genomes play important functional roles in gene expression and regulation. Accurately identifying the motifs is thus an important problem in bioinformatics. However, exhaustively enumerating all possible locations for a motif in a set of sequences is computationally intractable. Many heuristic or approximation algorithms and machine learning based approaches have been developed for this problem. In this paper, we develop a novel approach that can efficiently explore all possible locations of TFBS motifs in a set of sequences with high accuracy. Our approach constructs an ensemble of k Hidden Markov Models (HMM) through local alignments of two sequences in the set and then progressively aligns each HMM in the ensemble to other sequences in the set and update the parameters of the k HMMs. Our experimental results showed that our approach could achieve higher accuracy with satisfying efficiency than previous state-of-art approaches.

Parameterized lower bound and inapproximability of polylogarithmic string barcoding

Abstract String barcoding is a method that can identify microorganisms by analyzing their genome sequences. In this paper, we study the polylogarithmic string barcoding problem, where the lengths of the substrings in the testing set are polylogarithmically bounded. In particular, we show that the polylogarithmic string barcoding problem remains NP-hard and moreover, for a problem instance with n sequences, it is NP-hard to achieve an approximate ratio within dln n in polynomial time, where d is some constant. We then consider the parameterized polylogarithmic string barcoding problem, where the number of substrings in the test set is considered to be a fixed parameter k. We show that, unless W[2]=FPT, there does not exist a 2O(k)nc algorithm that can decide whether a test set of size k exists or not, where c is a constant independent of n and k.

A Graph Approach to Bridge the Gaps in Volumetric Electron Cryo-microscopy Skeletons

Electron Cryo-microscopy is an advanced imaging technique that is able to produce volumetric images of proteins that are large or hard to crystallize. De novo modeling is a process that aims at deriving the structure of the protein using the images produced by Electron Cryo-microscopy. At the medium resolutions (5 to 10A), the location and orientation of the secondary structure elements can be computationally identified on the images. However, there is no registration between the detected secondary structure elements and the protein sequence, and therefore it is challenging to derive the atomic structure from such volume data. The skeleton of the volume image is used to interpret the connections between the secondary structure elements in order to reduce the search space of the registration problem. Unfortunately, not all features of the image can be captured using a single segmentation. Moreover, the skeleton is sensitive to the threshold used which leads to gaps in the skeleton. In this paper, we present a threshold-independent approach to overcome the problem of gaps in the skeletons. The approach uses a novel representation of the image where the image is modeled as a graph and a set of volume trees. A test containing thirteen synthesized images and two authentic images showed that our approach could improve the existent skeletons. The percent of improvement achieved were 117% and 40% for Gorgon and MapEM, respectively.