Nona Helmi

Bio: Nona Helmi is an academic researcher from Islamic Azad University. The author has contributed to research in topics: Speaker recognition & Lemke–Howson algorithm. The author has an hindex of 3, co-authored 5 publications receiving 30 citations. Previous affiliations of Nona Helmi include Islamic Azad University of Mashhad.

Applying a neuro-fuzzy classifier for gesture-based control using a single wrist-mounted accelerometer

Abstract: Gestures, due to their natural modality, can be normally used in human-computer interaction (HCI) domains such as robotics, design environments and handheld devices. In this paper, a single wrist-mounted triaxial accelerometer is used to collect the acceleration data generated by hand movements forming 36 different gestures. This study intends to find the gestures which are capable of controlling an appliance with a maximum accuracy. A neuro-fuzzy classifier is devised for gestures detection to improve the classification rate in relative terms. The neuro-fuzzy system also selects the best features which yield the highest rate of classification. It reduces the dimensionality of feature set in two phases; the first phase is before carrying out the classification and the second phase is after selecting the most suitable gestures. The feature selection process finally reduces the number of features from 120 to 19. Our neuro-fuzzy system detects 25 gestures that can be classified with an accuracy of 100%, which is the highest rate among other classifiers. So, since the gesture-based control is accurately performed, it can be a proper method for HCI applications.

Speech Recognition with Fuzzy Neural Network for Discrete Words

Abstract: In this paper we study the feasibility of speech recognition with fuzzy neural Networks for discrete words, dependent or not dependent on speaker. Different Technical methods are used for speech recognition. Most of these methods are based on transfiguration of the speech signals for phonemes and syllables of the words. We use the expression "word Recognition" (because in our proposed method there is no need to catch the phonemes of words.). In our proposed method, Kohonen and LVQ networks are used for compaction and learning the data and then the output is sent to a fuzzy system and a neuro fuzzy system for classifying the conclusion. The experimental results show good precisions. The recognition precision of our proposed method with fuzzy conclusion is 95 percent and with ANFIS conclusion is 96 percent for good data and for all data is 58 percent.

A Novel Approach to Satisfaction Framework for Social Issues Via E-Services

Abstract: There are many social issues in Iran which affect citizens on multiple levels that government e-services attempt to address. However, these services could be improved. This paper addresses this need by proposing the Iranian citizen’s satisfaction Indexes for using e-government services. It proposes a comprehensive satisfaction index to evaluate the various e-government services in Iran. In order to achieve this assessment, we have designed a novel adaptive approach to citizen satisfaction framework concerning reliable performances and measures. In this paper we considered emotional dimension measures, capturing constructs such as utility, efficiency, and customization. Since no earlier study has been conducted based on the Iranian government websites, this model can certainly be beneficial to such websites which are responsible for supplying services to the citizens. Hence, the new method based on a Model for Adaptive Quality Measurement (MAQM), can enhance the e-government services in Iran as well as raising the efficiency and effectiveness of such services. According to this approach to the e-government portal of Iran, e-service’s capabilities can lead to more governmental profitability and success through improving significant services to citizens.

A Multi-Modal Coevolutionary Algorithm for Finding All Nash Equilibria of a Multi-Player Normal Form Game

Abstract: Nash’s theorem says that every game that has a finite strategic form has at least one Nash point. The problem of finding one Nash point is a well studied problem, and there exist a number of different methods for numerically computing a sample Nash equilibrium. But the problem of finding all equilibria has been addressed only recently. Literature review shows that many of the existing methods for detecting all equilibria are computationally intensive and error prone. In this paper we present a multi-modal coevolutionary algorithm that is able to detect all Nash points of a multi-player normal form game at the same time. We formulate the problem of solving a matrix game as a multi- modal optimization problem. Then a coevolutionary algorithm decomposes the problem and solves it in a parallel form. It associates one population to each player’s strategies. So various components of the problem will coevolve and better results may be produced at lower computational costs.

Comparative study of automatic speech recognition techniques

Abstract: Over the past decades, extensive research has been carried out on various possible implementations of automatic speech recognition (ASR) systems. The most renowned algorithms in the field of ASR are the mel-frequency cepstral coefficients and the hidden Markov models. However, there are also other methods, such as wavelet-based transforms, artificial neural networks and support vector machines, which are becoming more popular. This review article presents a comparative study on different approaches that were proposed for the task of ASR, and which are widely used nowadays.

Stability Consideration and Implementation of a Robust Hybrid Feedback Active Noise Cancellation Headset

Abstract: This paper investigates the robustness of a hybrid analog/digital feedback active noise cancellation (ANC) headset system. The digital ANC systems with the filtered-x least-mean-square (FXLMS) algorithm require accurate estimation of the secondary path for the stability and convergence of the algorithm. This demands a great challenge for the ANC headset design because the secondary path may fluctuate dramatically such as when the user adjusts the position of the ear-cup. In this paper, we analytically show that adding an analog feedback loop into the digital ANC systems can effectively reduce the plant fluctuation, thus achieving a more robust system. The method for designing the analog controller is highlighted. A practical hybrid analog/digital feedback ANC headset has been built and used to conduct experiments, and the experimental results show that the hybrid headset system is more robust under large plant fluctuation, and has achieved satisfactory noise cancellation for both narrowband and broadband noises.

Automatic speech recognition: a survey

Abstract: Recently great strides have been made in the field of automatic speech recognition (ASR) by using various deep learning techniques. In this study, we present a thorough comparison between cutting-edged techniques currently being used in this area, with a special focus on the various deep learning methods. This study explores different feature extraction methods, state-of-the-art classification models, and vis-a-vis their impact on an ASR. As deep learning techniques are very data-dependent different speech datasets that are available online are also discussed in detail. In the end, the various online toolkits, resources, and language models that can be helpful in the formulation of an ASR are also proffered. In this study, we captured every aspect that can impact the performance of an ASR. Hence, we speculate that this work is a good starting point for academics interested in ASR research.

Unifying interaction across distributed controls in a smart environment using anthropology-based computing to make human-computer interaction "Calm"

Abstract: Rather than adapt human behavior to suit a life surrounded by computerized systems, is it possible to adapt the systems to suit humans? Mark Weiser called for this fundamental change to the design and engineering of computer systems nearly twenty years ago. We believe it is possible and offer a series of related theoretical developments and practical experiments designed in an attempt to build a system that can meet his challenge without resorting to black box design principles or Wizard of Oz protocols. This culminated in a trial involving 32 participants, each of whom used two different multimodal interactive techniques, based on our novel interaction paradigm, to intuitively control nine distributed devices in a smart home setting. The theoretical work and practical developments have led to our proposal of seven contributions to the state of the art.

Isolated Digit Speech Recognition in Malay Language Using Neuro-Fuzzy Approach

Abstract: In this paper we discuss the development and implementation of an automated speaker-independent isolated Malay digit speech recognition system. The system is developed using Neuro-Fuzzy approach that combines the human-like reasoning style of fuzzy systems and the learning and connectionist structure of neural networks. To recognize the Malay speech digits, the endpoint detection algorithm is used to trim the silent duration in speech sample, the Mel Frequency Cepstral Coefficient technique is used to extract speech features, the subtractive clustering algorithm is applied to identify the fuzzy inference system, and the Adaptive Neuro Fuzzy Inference System (ANFIS) is used as a modern classification technique to train in identifying the features of speech. The performance of the system was evaluated by using 630 speech samples for training and testing, and experimental results showed that an overall 85.24% recognition rate was achieved.