Ausif Mahmood

Innovative Algorithms and Techniques in Automation, Industrial Electronics and Telecommunications

Innovative Algorithms and Techniques in Automation, Industrial Electronics and Telecommunications includes a set of rigorously reviewed world-class manuscripts addressing and detailing state-of-the-art research projects in the areas of Industrial Electronics, Technology & Automation, Telecommunications and Networking. Innovative Algorithms and Techniques in Automation, Industrial Electronics and Telecommunications includes selected papers form the conference proceedings of the International Conference on Industrial Electronics, Technology & Automation (IETA 2006) and International Conference on Telecommunications and Networking (TeNe 06) which were part of the International Joint Conferences on Computer, Information and Systems Sciences and Engineering (CISSE 2006). All aspects of the conference were managed on-line; not only the reviewing, submissions and registration processes; but also the actual conference. Conference participants - authors, presenters and attendees - only needed an internet connection and sound available on their computers in order to be able to contribute and participate in this international ground-breaking conference. The on-line structure of this high-quality event allowed academic professionals and industry participants to contribute work and attend world-class technical presentations based on rigorously refereed submissions, live, without the need for investing significant travel funds or time out of the office. Suffice to say that CISSE received submissions from more than 70 countries, for whose researchers, this opportunity presented a much more affordable, dynamic and well-planned event to attend and submit their work to, versus a classic, on-the-ground conference. The CISSE conference audio room provided superb audio even over low speed internet connections, the ability to display PowerPoint presentations, and cross-platform compatibility (the conferencing software runs on Windows, Mac, and any other operating system that supports Java). In addition, the conferencing system allowed for an unlimited number of participants, which in turn granted CISSE the opportunity to allow all participants to attend all presentations, as opposed to limiting the number of available seats for each session.

Improved gait recognition based on specialized deep convolutional neural network

Abstract Gait recognition is a biometric technique used in determining the identity of humans based on the style and the manner of their walk. Its performance is often degraded by covariate factors such as carrying condition changes, clothing condition changes, and viewing angle variations. Recently, machine learning based techniques have produced promising results for challenging classification problems. Since, a deep convolutional neural network (CNN) is one of the most advanced machine learning techniques with the ability to approximate complex non-linear functions, we develop a specialized deep CNN architecture for Gait Recognition. The proposed architecture is less sensitive to several cases of the common variations and occlusions that affect and degrade gait recognition performance. It can also handle relatively small data sets without using any augmentation or fine-tuning techniques. The majority of previous approaches to gait recognition have used subspace learning methods which have several shortcomings that we avoid. Our specialized deep CNN model can obtain competitive performance when tested on the CASIA-B large gait dataset.

Advances in Computer, Information, and Systems Sciences, and Engineering: Proceedings of IETA 2005, TeNe 2005 and EIAE 2005

In this paper, we present an efficient method for supporting wireless video multicast services. The method is based on storing multiple differently encoded versions of the video stream at the server. The corresponding video streams are obtained by encoding the original uncompressed video file as a sequence of I-P(I) frames using different GOP pattern. Mechanisms for controlling the multicast service request are also presented and their effectiveness is assessed through simulations. Wireless multicast video services are supported with considerably reduced additional delay and acceptable visual quality at the wireless client –end.

Deep face liveness detection based on nonlinear diffusion using convolution neural network

A face-spoofing attack occurs when an imposter manipulates a face recognition and verification system to gain access as a legitimate user by presenting a 2D printed image or recorded video to the face sensor. This paper presents an efficient and non-intrusive method to counter face-spoofing attacks that uses a single image to detect spoofing attacks. We apply a nonlinear diffusion based on an additive operator splitting scheme. Additionally, we propose a specialized deep convolution neural network that can extract the discriminative and high-level features of the input diffused image to differentiate between a fake face and a real face. Our proposed method is both efficient and convenient compared with the previously implemented state-of-the-art methods described in the literature review. We achieved the highest reported accuracy of 99% on the widely used NUAA dataset. In addition, we tested our method on the Replay Attack dataset which consists of 1200 short videos of both real access and spoofing attacks. An extensive experimental analysis was conducted that demonstrated better results when compared to previous static algorithms results. However, this result can be improved by applying a sparse autoencoder learning algorithm to obtain a more distinguishable diffused image.

Technological Developments in Networking, Education and Automation

Technological Developments in Networking, Education and Automation includes a set of rigorously reviewed world-class manuscripts addressing and detailing state-of-the-art research projects in the following areas: Computer Networks: Access Technologies, Medium Access Control, Network architectures and Equipment, Optical Networks and Switching, Telecommunication Technology, and Ultra Wideband Communications. Engineering Education and Online Learning: including development of courses and systems for engineering, technical and liberal studies programs; online laboratories; intelligent testing using fuzzy logic; taxonomy of e-courses; and evaluation of online courses. Pedagogy: including benchmarking; group-learning; active learning; teaching of multiple subjects together; ontology; and knowledge management. Instruction Technology: including internet textbooks; virtual reality labs, instructional design, virtual models, pedagogy-oriented markup languages; graphic design possibilities; open source classroom management software; automatic email response systems; tablet-pcs; personalization using web mining technology; intelligent digital chalkboards; virtual room concepts for cooperative scientific work; and network technologies, management, and architecture. Coding and Modulation: Modeling and Simulation, OFDM technology , Space-time Coding, Spread Spectrum and CDMA Systems. Wireless technologies: Bluetooth , Cellular Wireless Networks, Cordless Systems and Wireless Local Loop, HIPERLAN, IEEE 802.11, Mobile Network Layer, Mobile Transport Layer, and Spread Spectrum. Network Security and applications: Authentication Applications, Block Ciphers Design Principles, Block Ciphers Modes of Operation, Electronic Mail Security, Encryption & Message Confidentiality, Firewalls, IP Security, Key Cryptography & Message Authentication, and Web Security. Robotics, Control Systems and Automation: Distributed Control Systems, Automation, Expert Systems, Robotics, Factory Automation, Intelligent Control Systems, Man Machine Interaction, Manufacturing Information System, Motion Control, and Process Automation. Vision Systems: for human action sensing, face recognition, and image processing algorithms for smoothing of high speed motion. Electronics and Power Systems: Actuators, Electro-Mechanical Systems, High Frequency Converters, Industrial Electronics, Motors and Drives, Power Converters, Power Devices and Components, and Power Electronics.

Novel Algorithms and Techniques in Telecommunications and Networking

Simulated use of IP applications on hosts spread on the internet is expensive, which leads already in simple use cases to an enormous amount of time for setting up and carrying out an experiment. Complex scenarios are only possible with an additional infrastructure. This document describes a framework with which a needed infrastructure can be implemented. This infrastructure allows an efficient use of the IP applications, even if their hosts are spread all over the WAN. Due to the most different kinds of use cases a general solution is necessary. This solution is to meet any requirements so that all necessary IP applications can be integrated. Integration means that any application has a remote control feature. This feature is accessible from a special host, which also offers a comfortable remote desktop service on the internet. Supported by this remote desktop service an indirect remote control of applications in a test field is possible. Target audience for the IP application test framework, briefly IPAT framework, are groups, institutes or companies engaged in predevelopment research or pre-deployment activities of distributed IP applications. (Abstract)

Deep Learning approach for sentiment analysis of short texts

Unstructured text data produced on the internet grows rapidly, and sentiment analysis for short texts becomes a challenge because of the limit of the contextual information they usually contain. Learning good vector representations for sentences is a challenging task and an ongoing research area. Moreover, learning long-term dependencies with gradient descent is difficult in neural network language model because of the vanishing gradients problem. Natural Language Processing (NLP) systems traditionally treat words as discrete atomic symbols; the model can leverage small amounts of information regarding the relationship between the individual symbols. In this paper, we propose ConvLstm, neural network architecture that employs Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) on top of pre-trained word vectors. In our experiments, ConvLstm exploit LSTM as a substitute of pooling layer in CNN to reduce the loss of detailed local information and capture long term dependencies in sequence of sentences. We validate the proposed model on two sentiment datasets IMDB, and Stanford Sentiment Treebank (SSTb). Empirical results show that ConvLstm achieved comparable performances with less parameters on sentiment analysis tasks.

Improved Gait recognition based on specialized deep convolutional neural networks

Gait recognition is a biometric technique that is used in order to determine the identity of humans based on the style and the manner of their walk. Yet, Gait recognition performance is often degraded by some covariate factors such as a viewing angle variation, clothing and carrying condition changes, and a low-image resolution. In general, current tactics to object recognition highly depend on the use of machine learning techniques. Therefore, a deep convolutional neural network (CNN) is one of the most advanced machine learning techniques that has the ability to approximate complex non-linear functions from high-dimensional input data in a hierarchical process. In this paper, we develop a specialized deep CNN architecture, which consists of multilayers of convolutional and subsampling layers. The proposed technique is less sensitive to several cases of the common variations and occlusions that affect and degrade gait recognition performance. We avoided the use of the typical subspace learning methods, along with its shortcomings, that are widely used in gait recognition. When applied the proposed deep CNN model to CASIA-B large gait database, the experimental results show that the deep CNN model developed in this paper outperforms the other state of art gait recognition techniques in several cases.

Fortified Anonymous Communication Protocol for Location Privacy in WSN: A Modular Approach

Wireless sensor network (WSN) consists of many hosts called sensors. These sensors can sense a phenomenon (motion, temperature, humidity, average, max, min, etc.) and represent what they sense in a form of data. There are many applications for WSNs including object tracking and monitoring where in most of the cases these objects need protection. In these applications, data privacy itself might not be as important as the privacy of source location. In addition to the source location privacy, sink location privacy should also be provided. Providing an efficient end-to-end privacy solution would be a challenging task to achieve due to the open nature of the WSN. The key schemes needed for end-to-end location privacy are anonymity, observability, capture likelihood, and safety period. We extend this work to allow for countermeasures against multi-local and global adversaries. We present a network model protected against a sophisticated threat model: passive /active and local/multi-local/global attacks. This work provides a solution for end-to-end anonymity and location privacy as well. We will introduce a framework called fortified anonymous communication (FAC) protocol for WSN.

A Framework for Designing the Architectures of Deep Convolutional Neural Networks

Recent advances in Convolutional Neural Networks (CNNs) have obtained promising results in difficult deep learning tasks. However, the success of a CNN depends on finding an architecture to fit a given problem. A hand-crafted architecture is a challenging, time-consuming process that requires expert knowledge and effort, due to a large number of architectural design choices. In this article, we present an efficient framework that automatically designs a high-performing CNN architecture for a given problem. In this framework, we introduce a new optimization objective function that combines the error rate and the information learnt by a set of feature maps using deconvolutional networks (deconvnet). The new objective function allows the hyperparameters of the CNN architecture to be optimized in a way that enhances the performance by guiding the CNN through better visualization of learnt features via deconvnet. The actual optimization of the objective function is carried out via the Nelder-Mead Method (NMM). Further, our new objective function results in much faster convergence towards a better architecture. The proposed framework has the ability to explore a CNN architecture’s numerous design choices in an efficient way and also allows effective, distributed execution and synchronization via web services. Empirically, we demonstrate that the CNN architecture designed with our approach outperforms several existing approaches in terms of its error rate. Our results are also competitive with state-of-the-art results on the MNIST dataset and perform reasonably against the state-of-the-art results on CIFAR-10 and CIFAR-100 datasets. Our approach has a significant role in increasing the depth, reducing the size of strides, and constraining some convolutional layers not followed by pooling layers in order to find a CNN architecture that produces a high recognition performance.