Alex Frid

Bio: Alex Frid is an academic researcher from Technion – Israel Institute of Technology. The author has contributed to research in topics: Feature extraction & Feature vector. The author has an hindex of 7, co-authored 29 publications receiving 211 citations. Previous affiliations of Alex Frid include Tel-Hai Academic College & University of Haifa.

Computational Diagnosis of Parkinson's Disease Directly from Natural Speech Using Machine Learning Techniques

Abstract: The human voice signal carries much information in addition to direct linguistic semantic information. This information can be perceived by computational systems. In this work, we show that early diagnosis of Parkinson's disease is possible solely from the voice signal. This is in contrast to earlier work in which we showed that this can be done using hand-calculated features of the speech (such as formants) as annotated by professional speech therapists. In this paper, we review that work and show that a differential diagnosis can be produced directly from the analog speech signal itself. In addition, differentiation can be made between seven different degrees of progression of the disease (including healthy). Such a system can act as an additional stage (or another building block) in a bigger system of natural speech processing. For example it could be used in automatic speech recognition systems that are used as personal assistants (such as Iphones' Siri, Google Voice), or as natural man-machine interfaces. We also conjecture that such systems can be extended to monitoring and classifying additional neurological diseases and speech pathologies. The methods presented here use a combination of signal processing features and machine learning techniques.

Fusing enacted and expected mimicry generates a winning strategy that promotes the evolution of cooperation

Abstract: Although cooperation and trust are essential features for the development of prosperous populations, they also put cooperating individuals at risk for exploitation and abuse. Empirical and theoretical evidence suggests that the solution to the problem resides in the practice of mimicry and imitation, the expectation of opponent’s mimicry and the reliance on similarity indices. Here we fuse the principles of enacted and expected mimicry and condition their application on two similarity indices to produce a model of mimicry and relative similarity. Testing the model in computer simulations of behavioral niches, populated with agents that enact various strategies and learning algorithms, shows how mimicry and relative similarity outperforms all the opponent strategies it was tested against, pushes noncooperative opponents toward extinction, and promotes the development of cooperative populations. The proposed model sheds light on the evolution of cooperation and provides a blueprint for intentional induction of cooperation within and among populations. It is suggested that reducing conflict intensities among human populations necessitates (i) instigation of social initiatives that increase the perception of similarity among opponents and (ii) efficient lowering of the similarity threshold of the interaction, the minimal level of similarity that makes cooperation advisable.

Diagnosis of Parkinson's disease from continuous speech using deep convolutional networks without manual selection of features

Abstract: Parkinson's Disease (PD) is a relatively common neurodegenerative disabling disease. It affects central nervous system with profound effect on the motor system. The most common symptoms include slowness, rigidity and tremor during motion. It has been suggested that the vocal cords are among the first one to be affected and thus the speech is affected at very early stage of the disease and continues to deteriorate as the disease progress. In this work, we focus on automating the process of diagnosis from continuous native speech by removing the necessity of a trained personal from the diagnosis process. This is done by using an adaptation of Convolutional Neural Network (CNN) architecture for one-dimensional signal processing (i.e. raw speech signal) on a relatively small training set. This is a continuation to previous works where we showed (i) that this task can be achieved by using manually-extracted features of the speech (such as formants and their ratios) and (ii) by using an automatic process of auditory features extraction, where the features were selected by signal processing specialist.

Automatic assessment of Parkinson's Disease from natural hands movements using 3D depth sensor

Abstract: Parkinson's Disease (PD) is a degenerative disease of the central nervous system with a profound effect on the motor system. Symptoms include slowness of movement, rigidity of motion and in some patients, tremor. The severity of the disease is quantified using the Unified Parkinson Disease Rating Scale (UPDRS) which is a subjective scale performed and scored by physicians. In this work, we present an automated, objective quantitative analysis of four UPDRS motor examinations of Hand Movement and Finger Taps. For this purpose, a non-invasive system for recording and analysis of fine motor skills of hands was developed. The system is based on a simple low-cost depth acquisition sensor, similar to the second generation of Microsoft's Kinect sensor, and novel recursive self-correcting hand tracking algorithm. The system allows patients to perform test tasks in a natural and unhindered manner. The evaluation of the system was carried out on PD patients and controls. Machine Learning based classification was performed on the acquired data, followed by a decision making scheme.

An SVM based algorithm for analysis and discrimination of dyslexic readers from regular readers using ERPs

Abstract: Dyslexia is a learning disability that impairs a person's ability to decode words accurately and fluently. This deficit can manifest itself in the language-related domain as difficulties in phonological and orthographic working memory, brain systems asynchrony, poor executive function skills and/or poor rapid naming processing. However it is not clear yet whether the dyslexia phenomenon is only related to language or if it can also be seen as a non-language deficit. Moreover, if it is also related to non-language activity, it is important to verify if it is possible to identify dyslexic readers at the earliest stage of information processing for better and effective remediation. Based on this, an effective algorithm was developed for analysis and classification of subjects as either Regular Readers or Dyslexic Readers, by using EEG recorded channels with Event Related Potentials (ERP) methodology during an auditory, short non-linguistic, simple, sub-phonetic choices reaction time task.

Statistical Parametric Mapping The Analysis Of Functional Brain Images

Abstract: Thank you very much for reading statistical parametric mapping the analysis of functional brain images. As you may know, people have search numerous times for their chosen novels like this statistical parametric mapping the analysis of functional brain images, but end up in malicious downloads. Rather than enjoying a good book with a cup of coffee in the afternoon, instead they cope with some infectious bugs inside their desktop computer.

Is this a practical approach

Abstract: 1. Health care is a human right. 2. The care of the individual is at the center of health care, but the whole system needs to work to improve the health of populations. 3. The health care system must treat illness, alleviate suffering and disability, and promote health. 4. Cooperation with each other, those served, and those in other sectors is essential for all who work in health care. 5. All who provide health care must work to improve it. 6. Do no harm.

PhysioBank

Abstract: PhysioBank是一个大型的逐渐扩增的生理学信号和相关数据的数字化记录文档。目前包含多参数的心肺、神经和其他生物医学信号，尤以心电图（ECG）为主。信号来自健康受试者和各种疾病的患者。涉及的疾病包括心脏猝死、充血性心力衰竭、癫痫、步态不稳、睡眠呼吸暂停和衰老等。