Papers by Alireza Sadeghian

Neurocomputing, 2015
Detecting faults in electrical power grids is of paramount importance, either from the electricit... more Detecting faults in electrical power grids is of paramount importance, either from the electricity operator and consumer viewpoints. Modern electric power grids (smart grids) are equipped with smart sensors that allow to gather real-time information regarding the physical status of all the component elements belonging to the whole infrastructure (e.g., cables and related insulation, transformers, breakers and so on). In real-world smart grid systems, usually, additional information that are related to the operational status of the grid itself are collected such as meteorological information. Designing a suitable recognition (discrimination) model of faults in a real-world smart grid system is hence a challenging task. This follows from the heterogeneity of the information that actually determine a typical fault condition. The second point is that, for synthesizing a recognition model, in practice only the conditions of observed faults are usually meaningful. Therefore, a suitable recognition model should be synthesized by making use of the observed fault conditions only. In this paper, we deal with the problem of modeling and recognizing faults in a real-world smart grid system, which supplies the entire city of Rome, Italy. Recognition of faults is addressed by following a combined approach of multiple dissimilarity measures customization and one-class classification techniques. We provide here an in-depth study related to the available data and to the models synthesized by the proposed one-class classifier. We offer also a comprehensive analysis of the fault recognition results by exploiting a fuzzy set based reliability decision rule. control, communication, and self-healing technologies in order to (i) facilitate the connection and operation of generators of all sizes and technologies; (ii) allow consumers to play an active role in optimizing the operation of the system; (iii) significantly reduce the environmental impact of the whole electricity supply system; (iv) preserve or improve the level of system reliability, quality of service, and security. SGs can be considered as an "evolution" rather than a "revolution" of the existing energy networks . The evolution is leaded by the symbiotic exchange between power grid technologies and the Information and Communication Technologies (ICT). ICT provide instruments, such as Smart Sensors (SS), to monitor the network status, wired and wireless communication network to collect and transport data, and powerful computational architectures for data processing. A SG can be framed as a complex non-linear and time-varying system , where heterogeneous elements, including exogenous factors, are extremely interconnected through the exchange of both energy and information. Computational Intelligence (CI) techniques offer sound modeling and algorithmic solutions in the SG context . Well-known CI techniques adopted in the SG context include approximate dynamic programming [10], neural networks and fuzzy inference systems for prediction and control , and swarm intelligence and evolutionary computation for optimization problems ].

IFMBE Proceedings, 2009
In this paper, three feed-forward neural networks including Multi-Layer Perceptron (MLP), Radial ... more In this paper, three feed-forward neural networks including Multi-Layer Perceptron (MLP), Radial Basis Function network (RBFN) and Generalized Regression Neural Network (GRNN) are employed to estimate the release profile of betamethasone (BTM) and betamethasone acetate (BTMA). To accomplish this task, three features are extracted from each release profile using the nonlinear principal component analysis (NLPCA) technique, constituting the outputs of the neural network. The drug loaded formulation parameters are the input vectors of the artificial neural networks (ANNs) which include drug concentration, gamma irradiation, additive substance and type of drug (BTMA or BTM). Regarding the drug loaded formulation parameters as the input vectors and the extracted features as the output vectors, leave-one-out cross validation (L.O.O.) approach are used to train each neural network. Several simulations are presented to compare the potential of each neural network. It is demonstrated that the MLP is more reliable and efficient tool and has better performance in estimation of BTM and BTMA release profile than GRNN and RBF networks.
Self-adaptive middleware for the design of context-aware software applications in public transit systems
Ubiquitous software applications can be more responsive if they can adapt to their surrounding si... more Ubiquitous software applications can be more responsive if they can adapt to their surrounding situation without relying on users' continuous commitment. In dynamic environments such as public transit settings, where information is rapidly changing and passengers' demography are not uniform, an adaptive mobile application to navigate passengers based on their profile and context may be a good example of an
iFAST: An Intelligent Fire-Threat Assessment and Size-up Technology for first responders
IEEE Symposium on Computational Intelligence in Dynamic and Uncertain Environments, 2011
Currently, emergency response agencies use simplified "one-size-fits-all" procedures to... more Currently, emergency response agencies use simplified "one-size-fits-all" procedures to decide what quantity and type of resources to dispatch to each fire threat. These procedures are based on principles established decades ago, and are generally static in nature. They then rely on the judgment of the experienced officer who has arrived on-scene to make a dynamic evaluation and request additional units
Chosen Plaintext Attack against Neural Network-Based Symmetric Cipher
International Symposium on Neural Networks, 2007
In this paper the security of neural network-based symmetric ciphers (M. Arvandi et al., 2006) is... more In this paper the security of neural network-based symmetric ciphers (M. Arvandi et al., 2006) is analyzed. The vulnerability of such ciphers against chosen plaintext attacks is studied and a possible attack is mathematically presented.
A theoretic framework for intelligent expert systems in medical encounter evaluation
Expert Systems, 2009
... 1999), a computer program for neural-network-based weaning in intensive ... expert system app... more ... 1999), a computer program for neural-network-based weaning in intensive ... expert system approaches use artificial intelligence tools such as bivalued ifthen rules or fuzzy logic inference in a ... Hence, the main goal of this paper is to develop a novel expert system that mimics the ...
A neural network based surface roughness discrimination algorithm
This paper presents two approaches to surface roughness discrimination based on the use of a sens... more This paper presents two approaches to surface roughness discrimination based on the use of a sensitive whisker system together with frequency spectrum analysis and neural networks classification methods. The key characteristic of the proposed methods is their ability to provide real-time feature classifications to help roboticspsila agents to scan their environmentpsilas properties such as objectpsilas location and textures, by performing
On the use of recurrent neural networks to design symmetric ciphers
IEEE Computational Intelligence Magazine, 2008
In this article, we describe an innovative form of cipher design based on the use of recurrent ne... more In this article, we describe an innovative form of cipher design based on the use of recurrent neural networks. The well-known characteristics of neural networks, such as parallel distributed structure, high computational power, ability to learn and represent knowledge as a black box, are successfully applied to cryptography. The proposed cipher has a relatively simple architecture and, by incorporating neural
IEEE Transactions on Instrumentation and Measurement, 2009
We present an algorithm for the online detection of rotor bar breakage in induction motors throug... more We present an algorithm for the online detection of rotor bar breakage in induction motors through the use of wavelet packet decomposition (WPD) and neural networks. The system provides a feature representation of multiple frequency resolutions for faulty modes and accurately differentiates between healthy and faulty conditions, and its main applicability is to dynamic time-variant signals experienced in induction motors

2008 3rd International Symposium on Communications, Control and Signal Processing, 2008
Efficient pattern matching algorithms in ad hoc networks can have significant benefits in generat... more Efficient pattern matching algorithms in ad hoc networks can have significant benefits in generating real-time context and eliminate the need for a centralized arbiter. In our paper we demonstrate a generic and customizable architecture for achieving efficient pattern matching in mobile ad hoc networks. A major limitation of current ad hoc matching algorithms is that they are tailored for a specific design scenario and are unable to adapt to new scenarios. In this paper we present a novel architecture for the development of an ad hoc generic matching engine which is customizable to varying scenarios through a web service. We show how customizable semantics can play an important role in decision making, selection of a desired attribute and notifying a message in a volatile network. We also show how our system is adaptable to various scenarios, and focus on social interaction to verify our results.

2008 IEEE International Conference on Fuzzy Systems (IEEE World Congress on Computational Intelligence), 2008
An evolutionary system for derivation of fuzzy classification rules is presented. This system use... more An evolutionary system for derivation of fuzzy classification rules is presented. This system uses two populations: one of fuzzy classification rules, and one of membership function definitions. A constrained-syntax genetic programming evolves the first population and a mutation-based evolutionary algorithm evolves the second population. These two populations co-evolve to better classify the underlying dataset. Unlike other approaches that use fuzzification of continuous attributes of the dataset for discovering fuzzy classification rules, the system presented here fuzzifies the relational operators "greater than" and "less than" using evolutionary methods. For testing our system, the system is applied to the Iris dataset. Our experimental results show that our system outperforms previous evolutionary and non-evolutionary systems on accuracy of classification and derivation of interrelation between the attributes of the Iris dataset. The resulting fuzzy rules of the system can be directly used in knowledge-based systems.
On Efficient Tuning of LS-SVM Hyper-Parameters in Short-Term Load Forecasting: A Comparative Study
2007 IEEE Power Engineering Society General Meeting, 2007
Power load forecasting is essential in the task scheduling of every electricity production and di... more Power load forecasting is essential in the task scheduling of every electricity production and distribution facility. This paper studies the application of a variety of tuning techniques for optimizing the least squares support vector machines (LS-SVM) hyper-parameters in a short-term load forecasting problem. Clearly, the construction of any effective and accurate LS-SVM model depends on carefully setting the associated hyper-parameters.

Translational Oncology, 2015
Three-dimensional quantitative ultrasound spectroscopic imaging of prostate was investigated clin... more Three-dimensional quantitative ultrasound spectroscopic imaging of prostate was investigated clinically for the noninvasive detection and extent characterization of disease in cancer patients and compared to whole-mount, whole-gland histopathology of radical prostatectomy specimens. Fifteen patients with prostate cancer underwent a volumetric transrectal ultrasound scan before radical prostatectomy. Conventional-frequency (~5 MHz) ultrasound images and radiofrequency data were collected from patients. Normalized power spectra were used as the basis of quantitative ultrasound spectroscopy. Specifically, color-coded parametric maps of 0-MHz intercept, midband fit, and spectral slope were computed and used to characterize prostate tissue in ultrasound images. Areas of cancer were identified in whole-mount histopathology specimens, and disease extent was correlated to that estimated from quantitative ultrasound parametric images. Midband fit and 0-MHz intercept parameters were found to be best associated with the presence of disease as located on histopathology wholemount sections. Obtained results indicated a correlation between disease extent estimated noninvasively based on midband fit parametric images and that identified histopathologically on prostatectomy specimens, with an r 2 value of 0.71 (P b .0001). The 0-MHz intercept parameter demonstrated a lower level of correlation with histopathology. Spectral slope parametric maps offered no discrimination of disease. Multiple regression analysis produced a hybrid disease characterization model (r 2 = 0.764, P b .05), implying that the midband fit biomarker www.transonc.com
Survivability in Existing ATM-Based Mesh Networks
2009 International Conference on Advanced Information Networking and Applications, 2009
Page 1. Survivability in Existing ATM-Based Mesh Networks Isaac Woungang1, Guangyan Ma1, Mieso K.... more Page 1. Survivability in Existing ATM-Based Mesh Networks Isaac Woungang1, Guangyan Ma1, Mieso K. Denko2, Alireza Sadeghian1, Sudip Misra3, Alexander Ferworn1 1Department of Computer Science, Ryerson University ...
A review of applications of artificial neural networks in cryptosystems
This paper presents a review of the literature on the use of artificial neutral networks in crypt... more This paper presents a review of the literature on the use of artificial neutral networks in cryptography. Different neural network based approaches have been categorized based on their applications to different components of cryptosystems such as secret key protocols, visual cryptography, design of random generators, digital watermarking, and steganalysis.

Power losses reduction is one of the main targets for any electrical energy distribution company.... more Power losses reduction is one of the main targets for any electrical energy distribution company. In this paper, we face the problem of joint optimization of both topology and network parameters in a real smart grid. We consider a portion of the Italian electric distribution network managed by the ACEA Distribuzione S.p.A. located in Rome. We perform both the power factor correction (PFC) for tuning the generators and the distributed feeder reconfiguration (DFR) to set the state of the breakers. This joint optimization problem is faced considering a suitable objective function and by adopting genetic algorithms as global optimization strategy. We analyze admissible network configurations, showing that some of these violate constraints on * Corresponding Author current and voltage at branches and nodes. Such violations depend only on pure topological properties of the configurations. We perform tests by feeding the simulation environment with real data concerning hourly samples of dissipated and generated active and reactive power values of the ACEA smart grid. Results show that removing the configurations violating the electrical constraints from the solution space leads to interesting improvements in terms of power loss reduction. To conclude, we provide also an electrical interpretation of the phenomenon using graph-based pattern analysis techniques.
Conference of the North American Fuzzy Information Processing Society, 2010
Increasing number of vehicles, as the natural consequence of population growth, has caused a sign... more Increasing number of vehicles, as the natural consequence of population growth, has caused a significant bottle-neck in transportation network and consequently major delays at intersections. Hence, in this paper we study a hybrid adaptive model, based on combination of Coloured Petri Nets, Fuzzy Logic and Learning Automata to efficiently control traffic signals. We show that in comparison with the results
Modeling linguistic label perception in tourism e-satisfaction with type-2 fuzzy sets
2010 Annual Meeting of the North American Fuzzy Information Processing Society, 2010
I. INTRODUCTION NCERTAINTY, as the result of some information deficiency like incomplete, impre... more I. INTRODUCTION NCERTAINTY, as the result of some information deficiency like incomplete, imprecise, fragmentary, vague and contradictory information and so on may be decomposed into three levels of empirical, cognitive and social. Measurement errors and ...
Applying Model-Driven Development Techniques to the Development of Search and Rescue Systems
IEEE International Conference on System of Systems Engineering, 2007
This paper describes our work of applying modem software engineering methodologies such as model-... more This paper describes our work of applying modem software engineering methodologies such as model-driven development and product-line engineering to the development and maintenance of technical supporting systems in the domain of search and rescue. We propose an extensible, domain-specific, graphical modeling language and toolset that allow software developers of search and rescue systems to rapidly compose and generate their applications
Genetic and Evolutionary Computation Conference, 2009
This work presents an evolutionary algorithm for automatic ontology mapping, which attempts to ma... more This work presents an evolutionary algorithm for automatic ontology mapping, which attempts to map similar objects based on their hierarchical structures from an unclassified to a classified ontology. Alignment is performed by swapping branches between the two ontologies and comparing their similarities to find possible missing terms in the unclassified ontology. Our algorithm is a stochastic implementation of the expectation
Uploads
Papers by Alireza Sadeghian