Ahmad Akbari Azirani

Iran University of Science and Technology · School of Computer Engineering

A useful strategy to perform outlier detection (OD) in highdimensional data, especially in the presence of multiple classes of outliers, is to decompose the outlier detection problem into a set of relevant subspace selection (RSS) problems. In this approach, one relevant subspace is selected locally for each data point, and then the outlierness of...

The increasing complexity of real-world applications, especially those related to the Internet of Things and cloud computing, highlights the importance of using hybrid batch-stream processing techniques to analyze big data. Hybrid processing combines the accuracy of batch processing and the speed of stream processing. Among the important challenges...

The performance of convolutional neural networks is degraded by noisy data, especially in the test phase. To address this challenge, a new convolutional neural network structure with data indeterminacy handling in the neutrosophic (NS) domain, named as Neutrosophic Convolutional Neural Networks, is proposed for image classification. For this task,...

Nowadays, the trend of evolution of connected devices, communication networks, and cloud services towards the internet of things (IoT) has facilitated the interaction between smart objects with minimal human mediation. Considering IoT, where smart objects can be clients and providers of services for each other, trust between objects is a significan...

End-to-end models are state of the art for Automatic Speech Recognition (ASR) systems. Despite all their advantages, they suffer a significant problem: huge amounts of training data are required to achieve excellent performance. This problem is a serious challenge for low-resource languages such as Persian. Therefore, we need some methods and techn...

Among the novel IT paradigms, Cloud Computing and the Internet of Things (CloudIoT) are two complementary areas designed to support the creation of smart cities and application services. The CloudIoT not only presents ubiquitous services through IoT nodes, but it also provides virtually unlimited resources through services composition. Services com...

Outlier detection in high dimensional data faces the challenge of curse of dimensionality, where irrelevant features may prevent detection of outliers. In this research, we propose a novel efficient unsupervised density-based subspace selection for outlier detection in the projected subspace. First, the Maximum-Relevance-to-Density algorithm(MRD) i...

Batch and stream processing are separately and efficiently applied in many applications. However, some newer data-driven applications such as the Internet of Things and cloud computing call for hybrid processing approaches in order to handle the speed and accuracy required for processing such complex data. In this paper, we propose a Hybrid Distrib...

One rapidly growing application of Internet of Things (IoT) is the protection of public health and well-being through enabling environmental monitoring services. In particular, an IoT-enabled health/accessibility monitoring service can be consulted by its users to query about the status of different areas so as to optimize their trip throughout a g...

Spoken term detection (STD) refers to discovering all occurrences of a given term in a set of speech utterances. One of the well-known approaches for the STD system is the phone lattice search (PLS) that produces a phone-based lattice of speech utterances. Since the accuracy of a phone recognizer affects the accuracy of the STD system, the PLS appr...

Convolutional neural networks are sensitive to unknown noisy condition in the test phase and so their performance degrades for the noisy data classification task including noisy speech recognition. In this research, a new convolutional neural network (CNN) model with data uncertainty handling; referred as NCNN (Neutrosophic Convolutional Neural Net...

One rapidly growing application of Internet of Things (IoT) is the protection of public health and well-being through enabling environmental monitoring services. In particular, an IoT-enabled health/accessibility monitoring service (HAMS) can be consulted by its users to query about the status of different areas so as to optimize their trip through...

Keyword Spotting (KWS) systems can be divided into two main groups: Hidden Markov Model (HMM)-based and Discriminative KWS (DKWS) systems. In this paper, we propose an approach to improve a DKWS system using advantages of HMM-based systems. The proposed DKWS system contains feature extraction and classification (that includes a classifier and a sea...

Cloud computing is the latest answer of technology to meet the computational requirements of users. The notable point in complicated computational works is energy consumption. The integration is one of the elements in the cloud system which can reduce the energy consumption and coordinate the software products. In this article, some solutions have...

Service Discovery is known as one of the fundamental components in vehicular networks. Intelligent Transportation Systems (ITS) performance improves by the availability of efficient service discovery solutions in vehicular networks. Nonetheless, some challenges such as network partitioning and vehicular congestion reduce the efficiency of these com...

Information security and permeability in the system is a major concern for cloud computing. Cloud service providers should ensure that user information remains private from other people (external or internal). Deployment of an intrusion detection system (IDS) is a technique to protect the cloud from existing security and intrusion threats. Due to t...

A keyword spotter can be considered as a binary classifier which classifies a set of uttered sentences into two groups on the basis of whether they contain target keywords or not. For this classification task, the keyword spotter needs to identify the target keywords locations based on a fast and accurate search algorithm. In our previous works, we...

Analysis of network traffic, financial transactions, and mobile communications are examples of applications where examining entire samples of a large dataset is computationally expensive, and requires significant memory space. A common approach to address this challenge is to reduce the number of samples without compromising the accuracy of analyzi...

Road side units (RSUs) are considered to be one of the most important components in vehicular networks to send and receive data from other components inside the networks. Regarding the fact that vehicular network performance and vehicular environment coverage are highly related, the maximum coverage via RSUs improves the efficiency of vehicular net...

In this paper, we propose a non-parametric, noise resilient, graph-based classification algorithm. By modifying the training phase of the k-associated optimal graph algorithm, and proposing a new labeling algorithm in the testing phase, we introduce a novel approach that is robust in the presence of different level of noise. In designing the propos...

The efficient send and receive of information in VANET improves the efficiency of the safety and traffic services advertisment and discovery. However, if the V2V is the only communication system used, the restrictions of the urban environment and network drop the performance of VANET. In order to improve the performance of the network, it is necess...

In this paper, we propose a two purpose structure that can do vehicle navigating and packet routing simultaneously in an efficient way. The algorithm suggests the shortest travel time path to the drivers and finds reliable routes for traffic information messages. In order to reduce traveling time, vehicles are directed to the paths with lower car c...

Language modeling has many applications in a large variety of domains. Performance of this model depends on its adaptation to a particular style of data. Accordingly, adaptation methods endeavour to apply syntactic and semantic characteristics of the language for language modeling. The previous adaptation methods such as family of Dirichlet class l...

Evaluating the accuracy of HMM-based and SVM-based spotters in detecting keywords and recognizing the true place of keyword occurrence shows that the HMM-based spotter detects the place of occurrence more precisely than the SVM-based spotter. On the other hand, the SVM-based spotter performs much better in detecting keywords and has higher detectio...

با پیشرفت فناوری اطلاعات نیاز به انجام کارهای محاسباتی سنگین توسط افراد بدون نیاز به سخت افزار ونرم افزارهای گران در همه جا و همه زمان احساس می شودکه رایانش ابری آخرین پاسخ فناوری به این نیازها بوده است. نکته قابل توجه در انجام کارهای محاسباتی سنگین، مصرف انرژی می باشد که باید با استفاده از راهکارهایی به شکل بهینه تعدیل شود .یکی از مواردی که درابر...

In this paper, a two purpose structure to simultaneously determine the shortest travel time path for a moving vehicle and efficient packet dissemination for traffic information messages has been presented. In order to reduce traveling time, vehicles are directed to the paths with lower density. Given that, such paths have a higher risk in radio cov...

Two-microphone binary mask speech enhancement (2mBMSE) has been of particular interest in recent literature and has shown promising results. Current 2mBMSE systems rely on spatial cues of speech and noise sources. Although these cues are helpful for directional noise sources, they lose their efficiency in diffuse noise fields. We propose a new syst...

Recovering the nonlinear low dimensional embedding for the speech signals in the clean environment using the manifold learning techniques has become of substantial interest recently. However, the issue of manifold learning for feature transformation in domains involving noise corrupted speech can be quite different. We tackle this issue by presenti...

The purpose of this paper is to provide a framework for detecting vulnerabilities in SIP (Session Initiation Protocol) networks. We focused our studies on the detection of SIP DoS related vulnerabilities in VoIP infrastructures because of their generalization. We try to find weaknesses in SIP enabled entities that an attacker by exploiting them is...

The performance of kernel-based feature transformation methods depends on the choice of kernel function and its parameters. In addition, most of these methods do not consider the classification information and error for the mapping features. In this paper, we propose to determine a kernel function for kernel principal components analysis (KPCA) and...

The Session Initiation Protocol (SIP) is a text-based protocol, which defines the messaging between the SIP entities to establish, maintain, and terminate a multimedia session. Because of the text- and transaction-based nature of the SIP protocol, it encounters various types of malformed message and resource depletion attacks. In this paper, we stu...

Classification of the test samples using positive selection is computationally expensive, as it requires comparisons with large number of detectors. In this paper, we propose an enhanced positive selection algorithm with variable-size detectors to reduce the number of detectors required to cover the training sample space while resolving the issues...

In this paper, we propose a new cluster-based sample reduction method which is unsupervised, geometric, and density-based. The original data is initially divided into clusters, and each cluster is divided into “portions” defined as the areas between two concentric circles. Then, using the proposed geometric-based formulas, the membership value of e...

A keyword spotter is considered as a binary classifier that separates a class of utterances containing a target keyword from utterances without the keyword. These two classes are not inherently linearly separable. Thus, linear classifiers are not completely suitable for such cases. In this paper, we extend a kernel-based classification approach to...

This paper presents a novel method for modeling the one-way quality prediction of VoIP, non-intrusively. Intrusive measures of voice quality su�er from common de�ciency that is the need of reference signal for eval- uating the quality of voice. Owing to this lack, a great deal of e�ort has been recently devoted for modeling voice quality prediction...

In this paper, we propose anomaly based intrusion detection algorithms in computer networks using artificial immune systems, capable of learning new attacks. Unique characteristics and observations specific to computer networks are considered in developing faster algorithms while achieving high performance. Although these characteristics play a key...

In this paper, we propose a non-parametric and noise resilient graph-based classification algorithm. In designing the proposed method, we represent each class of dataset as a set of sub-graphs. The main part of the training phase is how to build the classification graph based on the non-parametric k-associated optimal graph algorithm which is an ex...

In this paper, we present the results of evaluating the robustness to language change of a previously proposed keyword spotting system. We assessed the robustness of this system when trained on clean English dataset and tested on telephony Persian speech. To have better recognition rate on telephony data, we used Cepstral mean and variance normaliz...

Attack graphs are efficient tools for detecting possible attacks in the network and their causes. By analyzing attack graphs and eliminating causes of attacks in the networks, we can immune networks against known intrusions. The main shortcoming of attack graphs is that they give no information about the damages of the possible attacks in the netwo...

Keyword spotting refers to detection of all occurrences of any given keyword in input speech utterances. In this paper, we define a keyword spotter as a binary classifier that separates a class of sentences containing a target keyword from a class of sentences which do not include the target keyword. In order to discriminate the mentioned classes,...

Nowadays mainstream of evolution towards next generation networks extends SIP application as a simple and efficient protocol for management of multimedia communications. Simplicity of SIP increases security concerns for service providers about various kinds of misuse including Denial of Service (DoS) attacks. The target of DoS attacks in SIP can be...

The feature transformation is a very important step in pattern recognition systems. A feature transformation matrix can be obtained using different criteria such as discrimination between classes or feature independence or mutual information between features and classes. The obtained matrix can also be used for feature reduction. In this paper, we...

Language model plays an important role in automatic speech recognition (ASR) systems. Performance of this model depends on its adaptation to the linguistic features. Accordingly, adaptation methods endeavour to apply syntactic and semantic characteristics of the language for language modeling. The previous adaptation methods such as family of Diric...

The purpose of this paper is to provide a framework for detecting vulnerabilities in SIP (Session Initiation Protocol) networks. In other words, we try to find weaknesses in SIP enabled entities that an attacker by exploiting them is able to attack the system and affect it. This framework is provided by the concept of penetration testing and is des...

Language model (LM) is essential for speech recognition systems. Efficiency of this model depends on its adaptation to the linguistic characteristics. According to this, adaptation methods attempt to use syntactic and semantic features for language modelling. The previous adaptation methods such as family of Dirichlet class language model (DCLM) ex...

Most of intrusion detection systems use primary and raw input features which are extracted from network connection without any preprocessing on the extracted features. In this paper, we propose a new feature transformation method based on class dependent approach for improving the accuracy of intrusion detection systems. In usual class dependent fe...

Nowadays computer networks face with multi-step attacks, during which, intruder exploits multiple vulnerabilities in a specific manner to attack his victim. So for assessing network security it is essential to understand which vulnerabilities and how must be exploited by the attacker to reach his goal. Such information can be obtained by modeling t...

Artificial Immune System (AIS)-based evolutionary algorithms combine rules and randomness to solve optimization and classification problems. Due to their capability in identifying self and non self samples, they have also gained attention in intrusion detection systems. In this paper, we propose a real-time AIS-based anomoly detection algorithm for...

The Session Initiation Protocol (SIP) has gained momentum and is being widely used both in the Internet and Next Generation Telecommunications networks as the core signaling protocol. SIP operation relies on SIP servers which are responsible for routing SIP messages. It has been shown that the performance of SIP servers is largely degraded during o...

Ideal binary mask speech enhancement is shown to increase the speech quality as well as speech intelligibility. But, this property depends highly on the accurate separation of speech and masker time-frequency units of the input spectrum, which is a difficult task in real situations. Ordinary binary mask methods are single-microphone methods and so,...

Accent classification technologies directly influence the performance of automatic speech recognition (ASR) systems. In this paper, we evaluate three accent classification approaches: Phone Recognition followed by Language Modeling (PRLM) as a phonotactic approach; accent modeling using Gaussian Mixture Models (GMM) then selecting the most similar...

Keyword spotting systems can be divided into two main groups: HMM-based and discriminative-based systems. Some of these systems apply a phonetic search algorithm to the sequence of recognized phones to find position of target keyword in a set of speech utterances. Thus, they need a fast and accurate phonetic search algorithm to find the position of...

Keyword spotting (KWS) refers to finding of all occurrences of the chosen words in speech utterances. One of known methods for KWS problem is phone lattice search (PLS). In this method, accuracy and speed of lattice search are most important aspects. One method used in PLS, is Minimum Edit Distance (MED) measure. While this measure increases detect...

Mapping techniques based on the linear discriminant analysis face challenges when the class distribution is not Gaussian. While using evolutionary algorithms may resolve some of the issues associated with non-Gaussian distribution, the solutions provided by evolutionary algorithms may get trapped in local optimum. In this paper, we propose a hybrid...

One of the main goals of employing Next Generation Networks (NGN) is an integrated access to the multimedia services like Voice over IP (VoIP), and IPTV. The primary signaling protocol in these multimedia services is Session Initiation Protocol (SIP). This protocol, however, is vulnerable to attacks, which may impact the Quality of Service (QoS), w...

This paper considers the problem of rapid and robust speaker adaptation in automatic speech recognition (ASR) systems. We propose an approach using combination of eigenspace-based maximum likelihood linear regression (EMLLR) and evolutionary algorithms. To find the best solution for the coefficients estimation problem, we suggest using genetic algo...

Keyword spotting refers to the detection of a limited number of given keywords in speech utterances. In this paper, first we review one of the large margin based keyword spotting approach that uses a discriminative method for training the keyword spotter. Then, we evaluate the robustness of this approach in different noisy conditions. In addition;...

In this paper, a cost-aware framework for intrusion prevention has been presented. The inputs of this framework are the attack graph of the specified network and also the important assets of it (target of attacker). We have defined some graph based security metrics and aggregated their effects for prioritizing attack scenarios. The scenarios are or...

Filtering approaches in spectral domain and features domain have been shown their effectiveness for robust speech recognition. In this paper, we propose a two step filtering method. In the first step, spectral subtraction filter is applied to speech spectrum. In the second step, we design a temporal structure normalization filter in order to apply...

Feature extraction is an important step in pattern classification and speech recognition. Extracted features should discriminate classes from each other while being robust to the environmental conditions such as noise. For this purpose, some transformations are applied to features. In this paper, we propose a framework to improve independent featur...

In this paper, we propose a hybrid approach using genetic algorithm and neural networks to classify Peer-to-Peer (P2P) traffic in IP networks. We first compute the minimum classification error (MCE) matrix using genetic algorithm. The MCE matrix is then used during the pre-processing step to map the original dataset into a new space. The mapped dat...

Keyword spotting refers to detection of all occurrences of any given word in a speech utterance. In this paper, we define the keyword spotting problem as a binary classification problem and propose a discriminative approach for solving it. Our approach exploits evolutionary algorithm to determine the separating hyper plane between two classes: clas...

Feature extraction is an important component of pattern classification and speech recognition. Extracted features should discriminate classes from each other while being robust to environmental conditions such as noise. For this purpose, several feature transformations are proposed which can be divided into two main categories: data-dependent trans...

Keyword spotting (KWS) refers to detection of a limited number of given keywords in speech utterances. In this paper, we evaluate a robust keyword spotting system based on hidden markov models for speaker independent Persian conversational telephone speech. Performance of base line keyword spotter is improved by means of normalizing features using...

One of the main goals of moving to Next Generation Networks (NGN) is an integrated access to multimedia services like VoIP, and IPTV. The primary signaling protocol in these multimedia services is Session Initiation Protocol (SIP). This protocol, however, is vulnerable against attacks, which may reduce the Quality of Service (QoS), an important fea...

Dimension reduction is crucial when it is applied on intrusion detection systems. Many data mining algorithms have been used for this purpose. For example, manifold learning algorithms, especially Isometric feature mapping (Isomap) have been investigated. Researchers successfully applied Isomap on intrusion detection system as a nonlinear dimension...

The performance of SIP servers is largely degraded during overload conditions due to the built in message re-transmission mechanism of SIP. In this paper we propose a distributed and end-to-end adaptive window based overload control algorithm, by which upstream SIP servers control the amount of calls that are forwarded to a downstream SIP server in...

The Mel-frequency cepstral coefficients (MFCC) are commonly used in speech recognition systems. But, they are highly sensitive to presence of external noise. In this paper, we propose a two-step method to compensate noise effects on MFCC. In the first step, we propose a sub-band SNR-dependent compression function for Mel sub-band energies to give h...

This paper considers the problem of rapid and robust speaker adaptation in Automatic Speech Recognition (ASR) systems. We propose an approach using combination of eigenspace-based maximum likelihood linear regression (EMLLR) and Minimum Classification Error (MCE). MCE is used to estimate the coefficients of eigenvoices as an alternative to maximum...

The Session Initiation Protocol (SIP) has gained momentum and is being widely used both in the Internet and Next Generation Telecommunications network as the core signaling protocol. SIP operation relies on SIP servers which are responsible for forwarding of SIP messages. It has been shown that the performance of SIP servers is largely degraded dur...

Hidden Markov Model (HMM) is a well-known classification approach which its parameters are conventionally learned using maximum likelihood (ML) criterion based on expectation maximization algorithm. Improving of parameter learning beyond ML has been performed based on the concept of discrimination among classes in contrast to maximizing likelihood...

Automatic speech recognition (ASR) systems work well when trained for a number of specific speakers. However, in most applications there are multiple speakers and they are unknown to the system; performance of ASR system may be degraded because of such speaker variations. This paper examines the use of minimum classification error (MCE) as a prepro...

In this contribution, a novel dual-channel speech enhancement technique is introduced. The proposed approach uses the dissimilarity between the power of received signals in the two channels as a criterion for speech enhancement and noise reduction. We claim that in near field conditions, where the distances between microphones and sound source are...

In this paper, we present a new measure for evaluating similarity changes in a multiagent system. The similarity measure of the agents changes during the learning process. The similarity differences are because of any composition or decomposition of some agent sets. The presented measure, defines the changes of homogeneity of agents by composition...

In this paper, we propose a new noise estimation algorithm based on tracking the minima of an adaptively smoothed noisy short-time power spectrum (STPS). The heart of the proposed algorithm is a constrained variance smoothing (CVS) filter, which smoothes the noisy STPS independently of the noise level. The proposed smoothing procedure is capable of...

Performance of wavelet thresholding methods for speech enhancement is dependent on estimating an exact threshold value in the wavelet sub-ba