• Data mining driven computational analysis of stock markets, methods and strategies 

      Lai, Anthony; Phang, Shaoning; Holmes, Wayne (Academic Fora (Kuala Lumpur, Malaysia), 2015-12)
      The stock market is a complex, dynamic and non-linear environment. The prediction of any future market reaction is further complicated by huge amounts of often unstructured financial data and uncertainty due to the effects ...
    • Defence mechanisms evaluation against RA flood attacks for Linux Victim Node 

      Kolahi, Samad; Barmada,Bashar; Mudaliar, Keysha (Asia-Pacific Signal and Information Processing Association (APSIPA), 2017-12)
      This research evaluates the performance of different defence mechanisms used in IPv6 networks to protect against router advertisement (RA) flood attacks that rely in ICMPv6 Router Advertisement messages to flood the network. ...
    • Designing a memory-aid and reminder system for dementia patients and older adults 

      Airehrour, David; Madanian, S.; Abraham, A. M. (2018-05)
      The United Nations statistics show that our society is rapidly aging, and this has led to the surge in the development of assisted living technologies. Of note is the minimal attention given to the assisted living technologies ...
    • Designing a novel educational game for teaching C# programming 

      Hinds, M.; Baghaei, Nilufar; Ragon, P.; Lambert, J.; Dajakaruna, T.; Houghton, T.; Dacey, Simon; Casey, John (Computer Supported Education (CSEDU Secretariat), 2017-04)
      Learning to code can be a daunting experience for a lot of students. RunJumpCode is a novel 2D platformer video game, designed and developed in Unity, to teach players the fundamental concepts of C# programming. The game ...
    • Designing a socially assistive companion robotic wheel chair: RoboChair 

      Jayawardena, Chandimal; Baghaei, Nilufar; Ganeshan, Kathiravelu; Sarrafzadeh, Hossein (IEEE Computer Society, 2013)
      Developing socially assistive robots is an emerging interdisciplinary research area, which requires collaboration between a wide range of disciplines. Among recent research projects, there have been attempts to develop ...
    • Designing mobile applications for smoking cessation in New Zealand 

      Baghaei, Nilufar; Wu, Lian; Casey, John; Biddle, TeUrikore (International Conference on Medical Information Processing and Analysis, 2016-06)
      Tobacco is a leading cause of preventable death in New Zealand. The smoking rate for New Zealand Māori was 44 percent in 2009, still significantly higher than for non-Māori (18 percent) for both males and females. In this ...
    • The development of a peer marking system for group assignments 

      Comins, Neil; Fitzgibbon, Peter; Boersen, Raewyn (1998-07)
      Group assignments and the fair allocation of assessment marks has led to the development of this easy to administer system. The system involves two forms that have to be completed by the students as a part of their ...
    • Development of unified and dynamic geometric framework for modelling plant leaf spots 

      Alshadli, Duaa; Borna, Kambiz; Lador, Cesar (2020-11)
      The use of computer vision and image processing techniques have proven to be effective in detecting and classifying plant diseases from symptoms, such as leaf spots or mosaic leaf patterns caused by pathogens. To identify ...
    • Distributed Incremental wLPSVM Learning 

      Zhu, Lei; Ban, Tao; Ikeda, K.; Pang, P.; Sarrafzadeh, Hossein (Institute of Electrical and Electronics Engineers (IEEE), 2016-12)
      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 ...
    • Document image noises and removal methods 

      Farahmand, Atena; Sarrafzadeh, Hossein; Shanbehzadeh, Jamshid (Newswood Ltd., 2013)
      Document images may be contaminated with noise during transmission, scanning or conversion to digital form. We can categorize noises by identifying their features and can search for similar patterns in a document image to ...
    • Effect of channel impairments on radiometric fingerprinting 

      Rehman, Saeed; Sowerby, K.W.; Shafiq, Alam; Ardekani, Iman; Komosny, Dan (IEEE Communications Society, 2015-12)
      To increase network security and mitigate identity theft attacks, much of the research is focused on traditional bit-level algorithmic. In conventional wireless networks, security issues are primarily considered above the ...
    • Effect of channel impairments on the performance of RF Fingerprinting using low-end receivers 

      Sowerby, K.W.; Rehman, Saeed; Coghill, Colin (2013)
      Radio Frequency (RF) Fingerprinting Problem definition Objective Experiment setup Results Conclusion Radio fingerprinting is the process of identifying a radio transmitter by the unique characteristics present in its ...
    • Effect of quantization on competitive co-evolution algorithm - QCCEA versus CCEA 

      Tirumala, Sreenivas Sremath; Nandigam, David; Ali, Shahid; Li, Zuojin (International Institute of Engineers and Researchers (IIER), 2015-02-15)
      Quantum inspired Evolutionary Algorithm (QEA) which uses qubits has been the basis for the development of many Quantum Inspired algorithms. Di- verging from this, a new Quantum Inspired Competitive Co-evolution algorithm ...
    • Effect of WPA2 Security on IEEE 802.11n bandwidth and round trip time in peer-peer wireless local area networks 

      Li, Peng; Kolahi, Samad; Safdari, Mustafa; Argawe, Mulugeta (IEEE, 2011-03-22)
      In this paper 802.11 wireless peer-peer network is evaluated for both IPv4 and IPv6 in Windows 7 and Fedora 12 operating systems. IPv4 has higher throughput than IPv6 for all packet sizes for both Windows 7 and Fedora 12 ...
    • Efficient FXLMS algorithm with simplified secondary path models. 

      Ardekani, Iman; Sharifzadeh, Hamid Reza; Rehman, Saeed; Abdulla, W. H. (IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2015)
      his paper extends the existing work on the root locus analysis of FxLMS algorithm by considering secondary path modeling errors. Rules for sketching FxLMS root locus are set out. An analytic convergence condition is then ...
    • An efficient programming framework for socially assistive robots based on separation of robot behavior description from execution 

      Jayawardena, Chandimal; Kuo, I-Han; MacDonald, B.A. (IEEE Computer Society, 2013)
      One of the main challenges in socially assistive robotics is providing flexible and easy-to-use programming tools for users. Unlike other robots, designing socially assistive robots includes the subject-matter-experts ...
    • Engaging children in diabetes education through mobile games 

      Baghaei, Nilufar; Casey, John; Nandigam, David; Sarrafzadeh, Hossein; Maddison, R. (International Association for the Development of the Information Society (IADIS), 2017-04)
      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 ...
    • Enhancing customers’ knowledge and decision making using augmented reality 

      Boonrat, W.; Vaidya, V.; Baghaei, N.; Sharifzadeh, Hamid; Ahmed, A.; Casey, John (Asia-Pacific Society for Computers in Education (APSCE), 2020-11)
      Augmented reality has seen massive success in recent years as it provides an opportunity for a seamless and rich user interaction with the real world. Recent studies have shown augmented and virtual reality can play a ...
    • Enhancing engagement and collaborative learning skills in multi-touch software for UML diagramming 

      Basheri, Mohammed; Burd, Liz; Munro, Malcolm; Baghaei, Nilufar (The International Society of the Learning Sciences, 2013)
      The use of Multi-touch interfaces for collaborative learning has received significant attention. Their ability to synchronously accommodate multiple users is an advantage in co-located collaborative design tasks. This paper ...
    • Ensemble learning methods for decision making : status and future prospects 

      Ali, Shahid; Tirumala, Sreenivas Sremath; Sarrafzadeh, Hossein (Institute of Electrical and Electronics Engineers (IEEE), 2015-07)
      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 ...

      © Unitec Institute of Technology, Private Bag 92025, Victoria Street West, Auckland 1142