A5087231010- Speech Recognition and Synthesis
- Music and Audio Processing
- Voice and Speech Disorders
- Speech and Audio Processing
- Emotion and Mood Recognition
- Parkinson's Disease Mechanisms and Treatments
- Phonetics and Phonology Research
- Dementia and Cognitive Impairment Research
- Hearing Loss and Rehabilitation
- Muscle activation and electromyography studies
- Natural Language Processing Techniques
- Balance, Gait, and Falls Prevention
- Neural and Behavioral Psychology Studies
- Neurological disorders and treatments
- Hearing, Cochlea, Tinnitus, Genetics
- Infant Health and Development
- Cognitive Functions and Memory
- Non-Invasive Vital Sign Monitoring
- Neuroscience and Neural Engineering
- Algorithms and Data Compression
- Speech and dialogue systems
- Visual perception and processing mechanisms
- Cerebral Palsy and Movement Disorders
- Noise Effects and Management
- Botulinum Toxin and Related Neurological Disorders
University of the Witwatersrand
2016-2025
University of Nicosia
2023-2025
Afeka College of Engineering
2013-2023
University of Central Lancashire Cyprus
2021-2022
Tel Aviv University
1994-2008
Academic College of Tel Aviv-Yafo
2003
Massachusetts Eye and Ear Infirmary
2003
<i>Background:</i> Many studies have suggested that cognitive training can result in gains healthy older adults. We investigated whether personalized computerized provides greater benefits than those obtained by playing conventional computer games. <i>Methods:</i> This was a randomized double-blind interventional study. Self-referred adults (n = 155, 68 ± 7 years old) were assigned to either personalized, or games group. Cognitive performance assessed at baseline and...
In this paper, we report on classification results for emotional user states (4 classes, German database of children interacting with a pet robot).Six sites computed acoustic and linguistic features independently from each other, following in part different strategies.A total 4244 were pooled together grouped into 12 low level descriptor types 6 functional types.For these groups, using Support Vector Machines Random Forests are reported the full set features, 150 highest individual...
Automated voice-based detection of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) could facilitate the screening for COVID19. A dataset cellular phone recordings from 88 subjects was recently collected. The included vocal utterances, speech and coughs that were self-recorded by in either hospitals or isolation sites. All underwent nasopharyngeal swabbing at time recording labelled as SARS-CoV-2 positives negative controls. present study harnessed deep machine learning...
Tremor in essential tremor and tremor-dominant Parkinson's disease is assessed by subjective observations patients undergoing focused ultrasound thalamotomy, a minimally invasive procedure intended to alleviate these patients. To develop an objective tool for analysis be used before after thalamotomy treatment the treated hand (contralateral ablation) non-treated (ipsilateral ablation). Using image processing signal that utilized images of Archimedes spiral drawing, we created analyze...
Improved interpretation of electroencephalography (EEG) associated with the neural control essential hand movements, including wrist extension (WE) and flexion (WF), could improve performance brain–computer interfaces (BCIs). These BCIs a prosthetic or orthotic to enable motor-impaired individuals regain activities daily living. This study investigated signal patterns kinematic differences between real, regulated, isometric WE WF movements from recorded EEG data. We used 128-channel data 14...
In this paper, we report on classification results for emotional user states (4 classes, German database of children interacting with a pet robot).Starting 5 emotion labels per word, obtained chunks different degrees prototypicality.Six sites computed acoustic and linguistic features independently from each other.A total 4232 were pooled together grouped into 10 low level descriptor types.For these groups separately all taken together, using Support Vector Machines are reported 150 the...
We previously described software that we have developed for use in the evaluation of mild cognitive impairment (MCI). Our previous study included an aged nondemented population with memory complaints (n = 41) was relatively homogenous terms education, clinical history, neurological examination, and Mini-Mental Status Examination (MMSE) scores. Performance patterns computerized tests separated subjects into two groups, hypothesized one group might had incipient dementia.In present report a...
Computerized administration of neuropsychological tests can be an objective, sensitive and efficient way to screen for monitor cognitive changes in the elderly. However, current computer software still suffers from limitations both those interpretation their results, which might severely hamper usability. In this paper qualitative aspects methods use prediction dementia are discussed, guidelines correct design usage computerized suggested a solution that overcomes several methodological is...
Control loop performance monitoring methods to detect problems in PID loops are developed and tested using industrial data sets. The is captured from the process, passed on researcher who tries out new detection diagnosis methods. not generally shared with other researchers working similar problems. authors therefore have implemented a repository categorise store so that it becomes accessible all researchers. Existing can be compared enhanced This paper describes context of CPM as well...
Automatic eye tracking is of interest for interaction with people suffering from amyotrophic lateral sclerosis, using the eyes to control a computer mouse, and controlled radiotherapy uveal melanoma. It has been speculated that gaze estimation accuracy might be improved by vestibulo-ocular reflex. This involuntary reflex results in slow, compensatory movements, opposing direction head motion. We therefore hypothesised leaving move freely during must produce more accurate than keeping fixed,...
A brain–computer interface could control a bionic hand by interpreting electroencephalographic (EEG) signals associated with wrist extension (WE) and flexion (WF) movements. Misinterpretations of the EEG may stem from variations in force, speed range these To address this, we designed, constructed tested novel dynamometer, IsoReg, which regulates WE WF movements during recording experiments. The IsoReg restricts to isometric WF, controlling their motion. It measures movement force using...
Lateralization and just-noticeable difference (jnd) measurements relative to the center were tested in a large group of patients with pontine lesions caused either by stroke or multiple sclerosis. Stimuli included binaural clicks, low- high-frequency narrow-band noise bursts. Two major types abnormalities revealed lateralization performances: perception all stimuli, regardless interaural differences (time and/or level) head (center-oriented), stimuli one side other (side-oriented). The only...