32 results for Sarrafzadeh, Hossein, Conference paper

  • Large-scale image retrieval using local binary patterns and iterative quantization

    Shakerdonyavi, M.; Shanbehzadeh, J.; Sarrafzadeh, Hossein (2017-05-10T05:38:08Z)

    Conference paper
    Unitec

    Hashing algorithm is an efficient approximate searching algorithm for large-scale image retrieval. Learning binary code is a key step to improve its performance and it is still an ongoing challenge. The inputs of Hashing affects its performance. This paper proposes a method to improve the efficiency of learning binary code by improving the suitableness of the Hashing algorithms inputs by employing local binary patterns in extracting image features. This approach results in more compact code, less memory and computational requirement and higher performance. The reasons behind these achievements are the binary nature and high efficiency in feature generation of local binary pattern. The performance analysis consists of using CIFAR-10 and precision vs. recall rate as dataset and evaluation criteria respectively. The simulations compare the new algorithm with three state of the art and along the line algorithms from three points of view; the hashing code size, memory space and computational cost, and the results demonstrate the effectiveness of the new approach.

    View record details
  • Distributed Incremental wLPSVM Learning

    Zhu, L.; Ban, T.; Ikeda, K.; Pang, P.; Sarrafzadeh, Hossein (2017-05-10T05:38:05Z)

    Conference paper
    Unitec

    Weighted linear proximal support vector machine (wLPSVM) is known as an efficient binary classification algorithm with good accuracy and class-imbalance robustness. In this work, original batch wLPSVM is facilitated with distributed incremental learning capability, which allows simultaneously learning from multiple streaming data sources that are geographically distributed. In our approach, incremental and distributed learning are solved as a merging problem at the same time. A new wLPSVM expression is derived. In the new expression, knowledge from samples are presented as a set of class-wised core matrices, and merging knowledge from two subsets of data can be simply accomplished by matrix addition. With the new expression, we are able to conduct incremental and distributed learning at the same time via merging knowledge from multiple incremental stages and multiple data sources.

    View record details
  • Free and open source intrusion detection systems : a study

    Tirumala, Sreenivas Sremath; Sathu, Hira; Sarrafzadeh, Hossein (2015-07)

    Conference paper
    Unitec

    Importance of cyber security cannot be denied in the current cyber environment. With continuous growth of internet, cyber security has become a necessity for both big and reputed organizations as well as small businesses and individuals. Intrusion detection systems (IDS) are considered to be an efficient way for detecting and preventing cyber security threats. However, there has been not enough attention and awareness on intrusion detection and prevention systems, especially among small businesses and individuals. Due to this, selection and deployment of IDS is significance in regard to this subject being considered highly technical, expensive and time consuming process. To overcome this, it is necessary to create an awareness of IDS tools which forms the basis of this paper. This study is the first phase of an ongoing research. In this phase, we present a detailed study of three free and open source IDS tools which are most popular in their respective categories. The IDS software used for this study are Suricata, a Network based Intrusion Detection System (NIDS), Samhain, a Host Based Intrusion Detection System (HIDS) and Ironbee, a universal web application firewall system. This study of IDS tools at one place will serve as a knowledge source for both technical and non-technical audience, small businesses which may not afford experienced security consultants. Further, this will also help in identifying suitable IDS software for their respective organization.

    View record details
  • Adaptive background modeling for land and water composition scenes

    Zhao, Jing; Pang, Shaoning; Hartill, Bruce; Sarrafzadeh, Hossein (2015-09)

    Conference paper
    Unitec

    In the context of maritime boat ramps surveillance, this paper proposes an Adaptive Background Modeling method for Land and Water composition scenes (ABM-lw) to interpret the traffic of boats passing across boat ramps. We compute an adaptive learning rate to account for changes on land and water composition scenes, in which the portion of water changes over time due to tidal dynamics and other environmental influences. Experimental comparative tests and quantitative performance evaluations of real-world boat-flow monitoring traffic sequences demonstrate the benefits of the proposed algorithm.

    View record details
  • Ensemble learning methods for decision making : status and future prospects

    Ali, Shahid; Tirumala, Sreenivas Sremath; Sarrafzadeh, Hossein (2015-07)

    Conference paper
    Unitec

    In real world situations every model has some weaknesses and will make errors on training data. Given the fact that each model has certain limitations, the aim of ensemble learning is to supervise their strengths and weaknesses, leading to best possible decision in general. Ensemble based machine learning is a solution of minimizing risk in decision making. Bagging, boosting, stacked generalization and mixture of expert methods are the most popular techniques to construct ensemble systems. For the purpose of combining outputs of class labels, weighted majority voting, behaviour knowledge space and border count methods are used to construct independent classifiers and to achieve diversity among the classifiers which is important in ensemble learning. It was found that an ideal ensemble method should work on the principle of achieving six paramount characteristics of ensemble learning; accuracy, scalability, computational cost, usability, compactness and speed of classification. In addition, the ideal ensemble method would be able to handle large huge image size and long term historical data particularly of spatial and temporal. In this paper we reveal that ensemble models have obtained high acceptability in terms of accuracy than single models. Further, we present an analogy of various ensemble techniques, their applicability, measuring the solution diversity, challenges and proposed methods to overcome these challenges without diverting from the original concepts.

    View record details
  • Taxonomy of malware detection techniques

    Mohaddes Deylami, H.; Muniyandi, R. C.; Ardekani, Iman; Sarrafzadeh, Hossein (2017-05-23T14:30:04Z)

    Conference paper
    Unitec

    Malware is an international software disease. Research shows that the effect of malware is becoming chronic. To protect against malware detectors are fundamental to the industry. The effectiveness of such detectors depends on the technology used. Therefore, it is paramount that the advantages and disadvantages of each type of technology are scrutinized analytically. This study’s aim is to scrutinize existing publications on this subject and to follow the trend that has taken place in the advancement and development with reference to the amount of information and sources of such literature. Many of the malware programs are huge and complicated and it is not easy to comprehend the details. Dissemination of malware information among users of the Internet and also training them to correctly use anti-malware products are crucial to protecting users from the malware onslaught. This paper will provide an exhaustive bibliography of methods to assist in combating malware.

    View record details
  • Human action recognition by conceptual features

    Shamsipour, G.; Shanbehzadeh, J.; Sarrafzadeh, Hossein (2017-06-01T14:30:08Z)

    Conference paper
    Unitec

    Human action recognition is the process of labeling a video according to human behavior. This process requires a large set of labeled video and analyzing all the frames of a video. The consequence is high computation and memory requirement. This paper solves these problems by focusing on a limited set rather than all the human action and considering the human-object interaction. This paper employs three randomly selected video frames instead of employing all the frames and, Convolutional Neural Network extracts conceptual features and recognize the video objects. Finally, support vector machine determines the relation between these objects and labels the video. The proposed method have been tested on two popular datasets ; UCF Sports Action and Olympic Sports. The results show improvements over state-of-the-art algorithms. This work is the outcome of Shamsipour's M.Sc thesis at Kharazmi University.

    View record details
  • A survey on Internet usage and cybersecurity awareness in students

    Tirumala, S.; Sarrafzadeh, Hossein (2017-06-01T14:30:09Z)

    Conference paper
    Unitec

    There has been an exponential increase in the usage of the internet, particularly among students since the introduction of e-learning and Bring Your Own Device (BYO) initiatives into the education system. In New Zealand the percentage of the population using the internet is now 93.8% and this increase in internet usage has increased the risk of cybersecurity attacks This makes it necessary to provide awareness and education on cybersecurity to students who are potential targets for exploitation. However, to provide this awareness it is necessary to understand what their current knowledge on cybersecurity is which forms the basis of this paper. This paper presents the results of a survey conducted on internet usage and cybersecurity awareness among three age groups between 8 years and 21 years. A questionnaire consisting of various questions on internet usage and cybersecurity concepts was prepared. For this survey, we considered both computers (desktops & laptops) and mobile devices (tablets & smartphones). The results of the survey showed that cybersecurity awareness among the surveyed students was generally low with the lowest level in the 8- 12-year age group. The students of 8-12 age group were able to answer only 19% of survey questions. Furthermore, most of the students were not familiar with common cybersecurity terms and did not demonstrate enough awareness of common threats such as phishing. The results further show that the majority of the students were not aware of cybersecurity tools for tablets and smartphones which are frequently used devices for BYOD. The key contribution of this paper is to emphasize the necessity to create cybersecurity awareness among students.

    View record details
  • Bionic voice (pilot study) : natural speech restoration for voice impaired individuals

    Sharifzadeh, Hamid; Allen, Jacqui; Sarrafzadeh, Hossein; Ardekani, Iman (2016-11)

    Conference paper
    Unitec

    The human voice is the most magnificent instrument for communication, capable of expressing deep emotions, conveying oral history through generations, or of starting a war. However, those who suffer from aphonia (no voice) and dysphonia (voice disorders) are unable to make use of this critical form of communication. They are typically unable to project anything more than hoarse whispers. Epidemiologic studies of the prevalence of voice disorders in the general adult population are rare. Nevertheless, information from a number of studies suggests that one third of the population have suffered from a temporary vocal impairment at some point in their life and that voice disorders can affect any age group and either sex. In some cases, vocal change is temporary however in those treated for malignant disease or with severe trauma there may be long term disturbance of phonation. This may affect occupation, social function and quality of life. Within a speech processing framework, we have worked on a novel method to return natural voice to laryngectomised people. This method leverages on recent advances in speech synthesis to deliver aworld-first technology. As a pilot study, this project has assessed the acoustic features of laryngectomised speech and has developed required enhancement for natural speech regeneration.

    View record details
  • Noise removal and binarization of scanned document images using clustering of features

    Farahmand, A.; Sarrafzadeh, Hossein; Shanbehzadeh, J. (2017-06-01T14:30:13Z)

    Conference paper
    Unitec

    Old documents are in printed form. Their archiving and retrieval is expensive according in terms of space requirement and physical search. One solution is to convert these documents into electronic form using scanners. The outputs of scanners are images contaminated with noise. The outcomes are more storage requirement and low OCR accuracy. A solution is noise reduction. This paper employs KFCM algorithm to cluster pixels into text, background and noise according to their features. As a result, noise removal and binarization is done simultaneously.

    View record details
  • Engaging children in diabetes education through mobile games

    Baghaei, Nilufar; Casey, John; Nandigam, D.; Sarrafzadeh, Hossein; Maddison, R. (2017-05-17T14:30:01Z)

    Conference paper
    Unitec

    Traditional methods for diabetic education rely heavily on written materials and there is only a limited amount of resources targeted at educating diabetic children. Mobile games can be effective, evidence-based, and motivating tools for the promotion of children's health. In our earlier work, we proposed a novel approach for designing computer games aimed for educating children with diabetes and applied our design strategy to a mobile Android game (Mario Brothers). In this paper, we report the findings of a preliminary evaluation study (n = 12) conducted over 1 week. The initial results showed that the children found the game engaging and improved their knowledge of healthy diet and lifestyle.

    View record details
  • Adaptive document image skew estimation

    Rezaei, S.B.; Shanbehzadeh, J.; Sarrafzadeh, Hossein (2017-05-12T14:30:02Z)

    Conference paper
    Unitec

    The skew of the scanned document image is inevitable, and its correction improves the performance of document recognition systems. Skew specifies the text lines deviation from the horizontal or vertical axes. To date, skew estimation algorithms have employed specific features in a repetitive process. We can improve these algorithms by simply using an adaptive algorithm. This approach is suitable when we have large number of similar documents. This paper proposes adaptive document image skew estimation algorithm using the features of existing methods and supervised learning. This approach significantly improves the skew estimation time and accuracy. The time improvement comes from the training that need be performed only once on the training images rather than the repetitive process for each image of previous algorithms. The accuracy improvement comes from the appropriate selection of features, learning algorithm and image adaptively. This method works well in all skew ranges up to 0.1°.

    View record details
  • An Overview of the Challenges and Progress in PeEn-SMT: First Large Scale Persian-English SMT System

    Mohaghegh, Mahsa; Sarrafzadeh, Hossein (2011)

    Conference paper
    Unitec

    This paper documents recent work carried out for PeEn-SMT, our Statistical Machine Translation system for translation between the English-Persian language pair. We give details of our previous SMT system, and present our current development of significantly larger corpora. We explain how recent tests using much larger corpora helped to evaluate problems in parallel corpus alignment, corpus content, and how matching the domains of PeEn-SMT’s components affect translation outcome. We then focus on combining corpora and approaches to improve test data, showing details of experimental setup, together with a number of experiment results and comparisons between them. We show how one combination of corpora gave us a metric score outperforming Google Translate for the English-to-Persian translation. Finally, we outline areas of our intended future work, and how we plan to improve the performance of our system to achieve higher metric scores, and ultimately to provide accurate, reliable language translation.

    View record details
  • Multilingual Information Service System for Tourists

    Mohaghegh, Mahsa; Sarrafzadeh, Hossein (2011)

    Conference paper
    Unitec

    Globalization and the continued increase in international travel and commerce have made automatic speech-to-speech translation systems an attractive area of research and development. With handheld devices becoming more powerful, the idea of speech to speech translators on PDAs is becoming a practical proposition. New Zealand welcomes a number of tourists from all over the world and tourism is a very important industry for New Zealand. New Zealand, a wealthy Pacific nation is dominated by two cultural groups New Zealanders of European descent, and the minority Maori, but Migration patterns have changed, with most incomers coming from Asia and Pacific island states, rather than from the UK and Australia. Officials estimate that Asians will make up 13% of the population by 2021. Developing a handheld speech to speech translator is therefore not only of economic significance but also of considerable social and cultural importance.

    View record details
  • A Hierarchical Phrase-Based Model for English-Persian Statistical Machine Translation

    Mohaghegh, Mahsa; Sarrafzadeh, Hossein (2012)

    Conference paper
    Unitec

    In this paper we show that a hierarchical phrasebased translation system will outperform a classical (nonhierarchical) phrase-based system in the English-to-Persian translation direction, yet for the Persian-to-English direction, the classical phrase-based system is preferable. We seek to explain why this is so, and detail a series of translation experiments with our SMT system using various bilingual corpora each with both toolkits Moses (non-hierarchical) and Joshua (hierarchical).

    View record details
  • Cross-layer Optimisation for Quality of Service Support in Wireless Sensor Networks

    Mohaghegh, Mahsa; Manford, Chris; Sarrafzadeh, Hossein (2011)

    Conference paper
    Unitec

    Wireless sensor networks need to deliver real-time services such as video, audio and traditional data services therefore providing efficient quality of services (QoS) support is essential. In this paper we aim to address the time-delay parameter of QoS this is implemented using a new cross-layer framework design. The concept of cross-layer design is based on architecture where different layers can exchange information in order to improve the overall network performance. Promising results achieved by cross-layer optimization initiated significant research activity in this area. We present results from simulations of the new cross layer design and traditional OSI model using the OMNET++ software. We show that the cross layer design provides a feasible and flexible approach to solving the conflict between different layers in a standard OSI model. We demonstrate that the cross layer optimization is a promising solution and that enhances the quality of service in wireless sensor network applications.

    View record details
  • A Text Localization Algorithm in Color Image via New Projection Profile

    Sarrafzadeh, Hossein; Aghajari, G; Shanbehzadeh, Jamshid (2010)

    Conference paper
    Unitec

    Text data in image present useful information for automatic annotation, indexing and structuring of images. In this paper, we propose an approach to automatically localize horizontally texts appearing in color and complex images. First, an edge detection method using a wavelet transform is used to finding text in image. Second, the image is binarized. Third, a new filter is applying for removing disperses pixels and non text area. After that, a new projection profile is applying for estimating text regions. The experimental results show that the proposed method achieves a much higher accuracy than existing methods. The advantage of this algorithm is low computation for finding text.

    View record details
  • Melanoma Diagnosis by the Use of Wavelet Analysis based on Morphological Operators

    Fassihi, Nima; Shanbehzadeh, Jamshid; Sarrafzadeh, Hossein; Ghasemi, Elham (2011-03)

    Conference paper
    Unitec

    Skin melanoma is the most dangerous type of skin cancer which is curable if diagnosed at the right time.. Drawing distinction between melanoma and mole is a difficult task and needs detailed laboratory tests. Utilizing morphologic operators in segmenting and wavelet analysis in order to extract the features has culminated in better result in melanoma diagnosis. This paper employs coefficients of wavelet decomposition to extract image's features. Melanoma classification is carried out by using the variance and mean of wavelet coefficients of images as the inputs of neural network. Results show 90% ability In distinction between benign and malignant lesions.

    View record details
  • Interfaces that adapt like humans

    Alexander, Samuel T.V.; Sarrafzadeh, Hossein (2004)

    Conference paper
    Unitec

    Whenever people talk to each other, non-verbal behaviour plays a very important role in regulating their interaction. However, almost all human-computer interactions take place using a keyboard or mouse – computers are completely oblivious to the non-verbal behaviour of their users. This paper outlines the plan for an interface that aims to adapt like a human to the non-verbal behaviour of users. An Intelligent Tutoring System (ITS) for counting and addition is being implemented in conjunction with the New Zealand Numeracy Project. The system’s interface will detect the student’s non-verbal behaviour using in-house image processing software, enabling it to adapt to the student’s non-verbal behaviour in similar ways to a human tutor. We have conducted a video study of how human tutors interpret the non-verbal behaviour of students, which has laid the foundation for this research.

    View record details
  • An Alternative Approach for Developing Socially Assistive Robots

    Jayawardena, Chandimal; Kuo, I-Han; Sarrafzadeh, Hossein (2014)

    Conference paper
    Unitec

    This paper presents the design of the socially assistive companion robotic wheelchair named RoboChair. Unlike in most current companion robotics projects, the approach of RoboChair is not to build a completely new robotic device. Instead, the focus of the RoboChair project is to convert an already useful device (i.e. wheelchair) to a socially assistive companion robot. The authors argue that there are number of advantages in this approach. The proposed robotic chair is a mobile robot that can carry a person. It is equipped with several measuring devices for measuring vital signs. The robot chair is capable of engaging users with interactive dialogs through a touch screen and by using human-robot interaction techniques. It has a scalable modular software architecture so that adding new hardware and software modules is straightforward. The software frame- work is based on Robot Operating System (ROS) open source robotic middleware.

    View record details