Golshah Naghdy

University of Wollongong, School of Electrical, Computer and Telecommunications Engineering, Faculty Member

Followers

Following

Co-authors

Public Views

Address: Newport, New South Wales, Australia

less

Judith L Green

University of California, Santa Barbara

E. Wayne Ross

University of British Columbia

David Seamon

Kansas State University

Armando Marques-Guedes

UNL - New University of Lisbon

Amanah Nurish

Stanford University

Roshan Chitrakar

Nepal College of Information Technology

Lev Manovich

Graduate Center of the City University of New York

Benjamin Schewel

University of Groningen

Aida Khairuddin

Universiti Teknologi Malaysia - UTM

Fusun Balik Sanli

Yildiz Technical University

InterestsView All (6)

Uploads

Papers by Golshah Naghdy

Process Improvement by Computer-Aided Load Smoothing in Activated Sludge Treatment

The benefits obtainable from smoothing flow and load to conventional activated sludge treatment u... more The benefits obtainable from smoothing flow and load to conventional activated sludge treatment units were examined in a large twin-stream pilot plant. Forecasting flow and load using ARIMA* models was found to lead to a reduction in the volume of storage required to permit flow and load smoothing. Process improvement, as mirrored in effluent quality, was achieved even when air feed was reduced by 25% to the smoothed stream.

Classification of multiclass imbalanced data using cost-sensitive decision tree C5.0

IAES International Journal of Artificial Intelligence, Mar 1, 2020

The multiclass imbalanced data problems in data mining were interesting cases to study currently.... more The multiclass imbalanced data problems in data mining were interesting cases to study currently. The problems had an influence on the classification process in machine learning processes. Some cases showed that minority class in the dataset had an important information value compared to the majority class. When minority class was misclassification, it would affect the accuracy value and classifier performance. In this research, cost sensitive decision tree C5.0 was used to solve multiclass imbalanced data problems. The first stage, making the decision tree model uses the C5.0 algorithm then the cost sensitive learning uses the metacost method to obtain the minimum cost model. The results of testing the C5.0 algorithm had better performance than C4.5 and ID3 algorithms. The percentage of algorithm performance from C5.0, C4.5 and ID3 were 40.91%, 40, 24% and 19.23%

Download

Computer-aided Load Smoothing with Energy Management (CALSEM) for Activated-sludge Sewage Treatment Plants

Water and Environment Journal, Dec 1, 1987

SYNOPSIS RESEARCH OVER a ten-year period leading up to a set of ten experiments lasting two years... more SYNOPSIS RESEARCH OVER a ten-year period leading up to a set of ten experiments lasting two years on a large two-stream pilot sewage-treatment plant has demonstrated process improvements and potential for considerable energy-saving. A reliable, low-cost, user-friendly computer system is used to control the outflow from balancing storage, using available sensors. The automation system can also control de-sludging and activatedsludge surplusing as well as monitoring and storing data on plant performance. A strategy for forecasting flow and load is effective in minimizing balancing volume. The system shows clear process improvements in reducing the risk of bulking sludge, in nitrification, and in reducing air requirement. Control of storage within the sewerage system, using forecasting, may provide some or all of the storage required. Existing tankage will, in many cases, provide the remainder of storage needed. Abridged version of paper entitled 'CALSEM-Computer-aided Load Smoothing with Energy Management' presented to a meeting of the Metropolitan and Southern Branch of the former IWPC on

Download

Process Improvement by Computer-Aided Load Smoothing in Activated Sludge Treatment

Water Science and Technology, Oct 1, 1989

A lossless hybrid shape-adaptive image coder

Computer and Information Technology, Dec 29, 2015

Download

Clinical effectiveness of combined virtual reality and robot assisted fine hand motion rehabilitation in subacute stroke patients

Robot-assisted therapy is regarded as an effective and reliable method for the delivery of highly... more Robot-assisted therapy is regarded as an effective and reliable method for the delivery of highly repetitive rehabilitation training in restoring motor skills after a stroke. This study focuses on the rehabilitation of fine hand motion skills due to their vital role in performing delicate activities of daily living (ADL) tasks. The proposed rehabilitation system combines an adaptive assist-as-needed (AAN) control algorithm and a Virtual Reality (VR) based rehabilitation gaming system (RGS). The developed system is described and its effectiveness is validated through clinical trials on a group of eight subacute stroke patients for a period of six weeks. The impact of the training is verified through standard clinical evaluation methods and measuring key kinematic parameters. A comparison of the pre- and post-training results indicates that the method proposed in this study can improve fine hand motion rehabilitation training effectiveness.

Automatic Detection of Microcalcifications in Mammorgams using a Fuzzy Classifier

Join My Mailing List. Fazel Naghdy. University of Wollongong. ... Automatic Detection of Microcal... more

Automatic Detection of Microcalcifications in Mammograms Using a Fuzzy Classifier

WORLD SCIENTIFIC eBooks, 2001

Join My Mailing List. Fazel Naghdy. University of Wollongong. ... Automatic Detection of Microcal... more

Design of adaptive control and virtual reality-based fine hand motion rehabilitation system and its effects in subacute stroke patients

Computer methods in biomechanics and biomedical engineering. Imaging & visualization, Jul 4, 2017

AbstractRobot-assisted therapy is regarded as an effective and reliable method for the delivery o... more AbstractRobot-assisted therapy is regarded as an effective and reliable method for the delivery of highly repetitive training that is needed to trigger neuroplasticity following a stroke. This study focuses on the pre-defined research gaps by combining adaptive assist-as-needed control and immersive virtual environment (VE) into a rehabilitation system, with special attention on the rehabilitation of fine hand motion skills. The virtual reality-based integrated rehabilitation system using Oculus Rift DK2 head mounted display, featuring rehabilitation gaming system with rendering immersive VE is proposed to strengthen activities of daily living and task-oriented kinematic features such as force, range of motion (ROM) and finger coordination. The effectiveness of the system is examined by conducting clinical trials on a group of 8 subacute stroke patients for a period of six weeks with 18 training sessions. The results are verified through clinical evaluation methods and key kinematic features such as activ...

Body postural sway analysis in older people with different fall histories

Medical & Biological Engineering & Computing, 2018

OBJECTIVES: Vitamin K is thought to be involved in both bone health and maintenance of neuromuscu... more OBJECTIVES: Vitamin K is thought to be involved in both bone health and maintenance of neuromuscular function. We tested the effect of vitamin K2 supplementation on postural sway, falls, healthcare costs, and indices of physical function in older people at risk of falls. DESIGN: Parallel-group double-blind randomized placebocontrolled trial. SETTING: Fourteen primary care practices in Scotland, UK. PARTICIPANTS: A total of 95 community-dwelling participants aged 65 and older with at least two falls, or one injurious fall, in the previous year. INTERVENTION: Once/day placebo, 200 μg or 400 μg of oral vitamin K2 for 1 year. MEASUREMENTS: The primary outcome was anteroposterior sway measured using sway plates at 12 months, adjusted for baseline. Secondary outcomes included the Short Physical Performance Battery, Berg Balance Scale, Timed Up & Go Test, quality of life, health and social care costs, falls, and adverse events. RESULTS: Mean participant age was 75 (standard deviation [SD] = 7) years. Overall, 58 of 95 (61%) were female; 77 of 95 (81%) attended the 12-month visit. No significant effect of either vitamin K2 dose was seen on the primary outcome of anteroposterior sway (200 μg vs placebo: −.19 cm [95% confidence interval [CI] −.68 to .30; P = .44]; 400 μg vs placebo: .17 cm [95% CI −.33 to .66; P = .50]; or 400 μg vs 200 μg: .36 cm [95% CI −.11 to .83; P = .14]). Adjusted falls rates were similar in each group. No significant treatment effects were seen for other measures of sway or secondary outcomes. Costs were higher in both vitamin K2 arms than in the placebo arm. CONCLUSION: Oral vitamin K2 supplementation did not improve postural sway or physical function in older people at risk of falls.

Download

Impact of age on body postural sway

TENCON 2015 - 2015 IEEE Region 10 Conference, 2015

Falls are common in the elderly. Almost 30% of people above 65 years of age fall each year and th... more Falls are common in the elderly. Almost 30% of people above 65 years of age fall each year and this figure increases to 40% for people older than 80 . Postural control plays a key role in fall prediction. Many Studies suggest that falls in the elderly are preceded by balance deficiencies in response to changes in sensory information . Postural control in older people has become an important area of research and it is usually assessed by measuring the amount of postural sway of the human body. In this study, an accurate quantitative method is proposed to evaluate body sway and its relationship with age using inertial sensors. The method is validated through experimental work and results are encouraging.

Addressing ICT curriculum recommendations from surveys of academics, workplace graduates, and employers

PP9–1274, current ALTC Project, 2009

Support for this report has been provided by the Australian Learning and Teaching Council Ltd, an... more Support for this report has been provided by the Australian Learning and Teaching Council Ltd, an initiative of the Australian Government Department of Education, Employment and Workplace Relations. The views expressed in this report do not necessarily reflect the views of the Australian Learning and Teaching Council or the Australian Government. This work is published under the terms of the Creative Commons Attribution-Noncommercial-ShareAlike 3.0 Australia Licence. Under this Licence you are free to copy, distribute, display and perform the work and to make derivative works. Attribution: You must attribute the work to the original authors and include the following statement: Support for the original work was provided by the Australian Learning and Teaching Council Ltd, an initiative of the Australian Government Department of Education, Employment and Workplace Relations. Noncommercial: You may not use this work for commercial purposes.

Download

Local Image Feature Extraction using Stacked-Autoencoder in the Bag-of-Visual Word modelling of Images

2019 IEEE 5th International Conference on Computer and Communications (ICCC), 2019

The Bag-of-Visual Words has been recognised as an effective mean of representing images for image... more The Bag-of-Visual Words has been recognised as an effective mean of representing images for image classification. However, its reliance on hand crafted image feature extraction algorithms often results in significant computational overhead, and poor classification accuracies. Therefore, this paper presents a Bag-of-Visual Word Modelling in which Image Feature Extraction is achieved using Deep Feature Learning via Stacked-Autoencoder. The proposed method is tested using three image collections constituted from the Caltech 101 image collection and the results confirm the ability of deep feature learning to yield optimum image categorisation performance.

Effect of Post-Stroke Motor Training on EEG Movement-Related Cortical Potentials

BackgroundRehabilitation of post-stroke patients with motor impairments promotes re-learning of l... more BackgroundRehabilitation of post-stroke patients with motor impairments promotes re-learning of lost motor functions through the brain neuroplasticity. Monitoring of electroencephalogram (EEG) signals has the potential to show neuroplasticity changes that take place during motor training.MethodsIn this study, an EEG-derived time-domain pattern namely movement-related cortical potential (MRCP) was deployed to assess the effect of motor training in seven post-stroke patients. Patients were divided into two groups; group A comprising four subjects with supratentorial lesions and group B consisting of three subjects with infratentorial lesions. Both groups participated in motor training with an AMADEO hand rehabilitation device. During pre and post-training periods, EEG signals at eight selected electrodes were recorded. In addition, hand-kinematic parameters, and clinical tests were measured at the beginning and the end of all training sessions.ResultsThe negative peak of the MRCP sign...

Download

Assessment of Neuroplasticity Using EEG Signal in Rehabilitation of Brain Stem Stroke Patients

2020 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE)

Robot-assisted motor training provides an efficient alternative to conventional rehabilitation me... more Robot-assisted motor training provides an efficient alternative to conventional rehabilitation methods used for poststroke patients. The re-learning of lost motor functions happens through neuroplasticity in the brain. Electroencephalogram (EEG) provides an effective method for assessing neuroplasticity. Movement-related cortical potential (MRCP), an EEG-derived time-domain pattern, indicates changes due to motor skills gained as a result of the training. This study aims to perform a two-stage robot-assisted rehabilitation program on brain stem stroke patients consisting of a total of 24 training sessions and to assess whether significant motor recovery and neuroplasticity induction are achieved after the first stage or after completing both stages of the designed rehabilitation program. Three brain stem stroke patients were recruited for hand motor training on AMADEO rehabilitation robot for 8 weeks consisting of two stages of 4 weeks each. Three assessments methods which include standard clinical tests, hand strength and range of movement measurements using AMADEO assessment tool, as well as EEG signal acquisition, were performed at the beginning of all the training sessions (week 0), after completion of the first stage of rehabilitation (week 4) and after completion of both stages of the training sessions (week 8). The experimental results demonstrate that all brain stem stroke patients show significant functional hand motor recovery, as indicated by clinical tests, hand strength, and range of movement measurements, after completing 8 weeks of the training. Moreover, MRCP signal negative peak showed a significant decrease in its amplitude when the patients completed two phases of rehabilitation training, indicating neuroplasticity induction.

Quantitative Frailty Assessment Based on Kinematic Parameters of Daily Living Activities

2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 2020

Frailty is a prevailing phenomena in older people. It is an age related syndrome that can increas... more Frailty is a prevailing phenomena in older people. It is an age related syndrome that can increase the risk of fall in elderly. The people with age above 65 suffers from various functional decline and cognitive impairments. Such deficiencies are conventionally measured subjectively by geriatrics using questionnaire-based methods and clinical tests. Activities of daily living are also assessed in clinical settings by analysing simple tasks performed by the subject such as sit to stand and walking some distances. The clinical methods used to assess frailty and analyse the activity of daily living are subjective in nature and prone to human error. An objective method is proposed to quantitatively measure frailty using inertial sensor mounted on healthy, frail and nonfrail subjects while performing the sit to stand test (SiSt). An artificial neural networks based algorithm is developed to classify the frailty by extracting a unique set of features from 2D -Centre of Mass (CoM) trajectories derived from SiSt clinical test. The results indicate that the proposed algorithms provides an objective assessment of frailty that can be used by geriatrics in turn to make a more objective judgement of frailty status of older people.

Investigating Electrode Sites for Intention Detection During Robot Based Hand Movement Using EEG-BCI System

2018 IEEE 18th International Conference on Bioinformatics and Bioengineering (BIBE), 2018

Detection of motor intention from brain signals combined with robot assistive technologies has po... more Detection of motor intention from brain signals combined with robot assistive technologies has potential to be used as an effective rehabilitation process for post-stroke patients. The work conducted on the deployment of AMADEO hand rehabilitation robotic device and Electroencephalogram based Brain Computer Interference (EEG-BCI) system to explore the technical feasibility of the approach in hand motor recovery of post-stroke patients is presented. Two different protocols consisting of simple visual cues and a 2D interactive game are presented to healthy subjects when performing hand movement. The motor intent signals produced during each protocol are detected using Support Vector Machine (SVM) algorithm. Moreover, the signals produced by different single electrodes are analyzed to identify the electrode making the highest contribution to the intent signal and the performance of SVM with respect to each protocol. Overall, an average True Positive Rate (TPR) of 71.72% and True Negative Rate (TNR) of 63.33% for visual cue protocol and an average TPR of 88.56% and TNR of 70.81% for game protocol are obtained.

Temporal Difference (TD) Based Critic-Actor Adaptive Control for a Fine Hand Motion Rehabilitation Robot

Robot assisted post-stroke rehabilitation training is an effective approach in delivering the hig... more Robot assisted post-stroke rehabilitation training is an effective approach in delivering the highly intensive repetitive training, aiming to retrain the neural pathways in the brain thus to restore and improve the affected mobility skills. The adaptive control of robotic devices, especially assist-as-needed control providing exact assistive force intensity along the intended motion trajectory for fine motion, can be a complex but effective method. A temporal difference based critic-actor reinforcement learning control method is explored in this study. The effectiveness of the method is verified through Matlab simulation and implemented on a hand rehabilitation robotic device. Results suggest that the control system can fulfil the control task with high performance and reliability, thus holding the promise of improving the fine hand motion rehabilitation training efficiency.

Reinforcement learning neural network (RLNN) based adaptive control of fine hand motion rehabilitation robot

2015 IEEE Conference on Control Applications (CCA), 2015

Recent neural science research suggests that a robotic device can be an effective tool to deliver... more Recent neural science research suggests that a robotic device can be an effective tool to deliver the repetitive movement training that is needed to trigger neuroplasticity in the brain following neurologic injuries such as stroke and spinal cord injury (SCI). In such scenario, adaptive control of the robotic device to provide assistance as needed along the intended motion trajectory with exact amount of force intensity, though complex, is a more effective approach. A critic-actor based reinforcement learning neural network (RLNN) control method is explored to provide adaptive control during post-stroke fine hand motion rehabilitation training. The effectiveness of the method is verified through computer simulation and implementation on a hand rehabilitation robotic device. Results suggest that the control system can fulfil the assist-as-needed (AAN) control with high performance and reliability. The method demonstrates potential to encourage active participation of the patient in the rehabilitation process and to improve the efficiency of the process.

3D Geometric and Haptic Modeling of Hand-Woven Textile Artifacts

IFIP Advances in Information and Communication Technology, 2010

Haptic Modeling of textile has attracted significant interest over the last decade. In spite of e... more Haptic Modeling of textile has attracted significant interest over the last decade. In spite of extensive research, no generic system has been proposed. The previous work mainly assumes that textile has a 2D planar structure. They also require time-consuming objective measurement of textile properties in mechanical/physical model construction. A novel approach for haptic modeling of textile is proposed to overcome the existing shortcomings. The method is generic, assumes a 3D structure textile artifact, and deploys computational intelligence to estimate textile mechanical and physical properties. The approach is designed primarily for display of textile artifacts in museums. The haptic model is constructed by superimposing the mechanical model of textile over its 3D geometrical model. Digital image processing is applied to the still image of textile to identify its pattern and structure. In order to deal with the nonlinearities associated with the textile, a fuzzy rule-based expert system is deployed. This information is then used to generate a 3D geometric model of the artifact in VRML. Selected mechanical and physical properties of the textile are estimated by an artificial neural network with the textile geometric characteristics and yarn properties as inputs. The neural network learning and verification and validation processes are carried out by a sample data set. The mechanical properties are used in the construction of the textile mechanical model. The haptic rendered model is generated by superimposing the physical/mechanical model over the 3D geometric model. This model has been implemented and rendered in Reachin environment, provided an interactive Virtual Reality environment where the user can navigate the graphic 3D presentation of the textile and touch it by a haptic device. Different samples have been modeled and the whole approach has been validated. The interface can be provided in both in the physical environment and through the cyberspace. The validation of method indicates the feasibility of the approach and its superiority to other haptic modeling algorithms.