Sharif Digital Repository

Many recent studies show that Augmented Reality (AR) and Automatic Speech Recognition (ASR) technologies can be used to help people with disabilities. Many of these studies have been performed only in their specialized field. Audio-Visual Speech Recognition (AVSR) is one of the advances in ASR technology that combines audio, video, and facial expressions to capture a narrator's voice. In this paper, we combine AR and AVSR technologies to make a new system to help deaf and hard-of-hearing people. Our proposed system can take a narrator's speech instantly and convert it into a readable text and show the text directly on an AR display. Therefore, in this system, deaf people can read the... 

Augmented Reality (AR), Automatic Speech Recognition (ASR) and Text-to-Speech Synthesis (TTS) can be used to help people with disabilities. In this paper, we combine these technologies to make a new system for helping deaf people. This system can take the narrator's speech and convert it into a readable text and show it directly on AR display. To improve the accuracy of the system, we use Audio-Visual Speech Recognition (AVSR) as a backup for the ASR engine in noisy environments. In addition, we use the TTS system to make our system more usable for deaf people. The results of testing the system show that its accuracy is over 85 percent on average in different places. Also, the result of a... 

Recently, many researches show Augmented Reality (AR) and Automatic Speech Recognition (ASR) can help people with disabilities. In this paper we implement an innovative system for helping deaf people by combining AR, ASR, and AVSR technologies. This system can instantly take narrator's speech and converts it into readable text and shows it directly on AR display. We show that our system's accuracy becomes over 85 percent on average, by using different ASR engines near using an AVSR engine in different noisy environments. We also show in a survey that more than 90 percent of deaf people on average need such system as assistant in portable devices, near using only text or only sign-language... 

Due to the increasing number of people suffering from physical disabilities in the elbow and wrist, developing an assistive wearable robot seems crucial. These disabilities are mostly common in elderly people and people who are suffering from spinal injury or stroke. In this paper, a wearable assistive robot for rehabilitation of the wrist and elbow is developed. The mechanism has 3 Degree of Freedom (DoF); two active DoF for assisting the exion/extension of the elbow and wrist, and a passive one in order to have unconstrained supination/pronation of the forearm. The motors and sensors were chosen based on kinematic constraints governing the motion of arms and wrists. Finally, with the... 

This paper introduces a novel robotic platform, called RASA (Robot Assistant for Social Aims). This educational social robot is designed and constructed to facilitate teaching Persian Sign Language (PSL) to children with hearing disabilities. There are three predominant characteristics from which design guidelines of the robot are generated. First, the robot is designed as a fully functional interactive social robot with children as its social service recipients. Second, it comes with the ability to perform PSL, which demands a dexterous upper-body of 29 actuated degrees of freedom. Third, it has a relatively low development cost for a robot in its category. This funded project, addresses... 

Today, the Internet is used to offer different services to users. Most of these services are designed for human users, but unfortunately some computer programs are designed which abuse these services. CAPTCHA (Completely Automated Public Turing test to tell Computers and Human Apart) systems are designed to automatically distinguish between human users and computer programs and block such computer programs. Most of current CAPTCHA methods are using visual patterns and hence blind users cannot use them. In this paper, we propose a new CAPTCHA method which is designed for blind people. In this method, a small sound clip is played for the user and he/she is asked to say a word. Then the user... 

This paper introduces a novel robotic platform, called RASA (Robot Assistant for Social Aims). This educational social robot is designed and constructed to facilitate teaching Persian Sign Language (PSL) to children with hearing disabilities. There are three predominant characteristics from which design guidelines of the robot are generated. First, the robot is designed as a fully functional interactive social robot with children as its social service recipients. Second, it comes with the ability to perform PSL, which demands a dexterous upper-body of 29 actuated degrees of freedom. Third, it has a relatively low development cost for a robot in its category. This funded project, addresses... 

Steady State Visual Evoked Potential (SSVEP) based Brain Computer Interfaces (BCI) can be great assistance for people suffering from physical disabilities due to their high accuracy, high speed, an acceptable number of possible targets, etc. Many researchers have managed to design such systems. Most of these BCIs utilize methods for frequency detection which cause the system to need a training phase for each new user, making the system a user-based one. That is why our goal was to design a BCI that not only has accuracy and speed comparable to similar systems, but also does not need any training phase and thus can be used by new users right away. Our final design got a mean accuracy of... 

Classification is the most important part of brain-computer interface (BCI) systems. Because the neural activities of different individuals are not identical, using the ordinary methods of subject-dependent classification, does not lead to high accuracy in betweensubject classification problems. As a result, in this study, we propose a novel method for classification that performs well in between-subject classification. In the proposed method, at first, the subject-dependent classifiers obtained from the train subjects are applied to the test trials to obtain a set of scores and labels for the trials. Using these scores and the real labels of the labeled test trials, linear regression is... 

Importance: Cancer and other noncommunicable diseases (NCDs) are now widely recognized as a threat to global development. The latest United Nations high-level meeting on NCDs reaffirmed this observation and also highlighted the slow progress in meeting the 2011 Political Declaration on the Prevention and Control of Noncommunicable Diseases and the third Sustainable Development Goal. Lack of situational analyses, priority setting, and budgeting have been identified as major obstacles in achieving these goals. All of these have in common that they require information on the local cancer epidemiology. The Global Burden of Disease (GBD) study is uniquely poised to provide these crucial data.... 

Background. The Arthritis Impact Measurement Scales 2 (AIMS2) has not been translated and validated for Persian-speaking patients with osteoarthritis of the knee. This was to provide a validated instrument to measure functional disability and health-related quality of life in patients with osteoarthritis of the knee in Iran. The aim of this study was to culturally adapt and validate the AIMS2 for Persian-speaking patients with osteoarthritis of the knee in Iran. Methods. A consecutive sample of patients with knee osteoarthritis were asked to complete the AIMS2, the Short Form Health Survey (SF-36) and four visual analog scales for pain, joint stiffness, patient's and physician's global... 

Although several studies have applied traditional linear measures to evaluate postural control of patients with multiple sclerosis (MS), little is known about the nonlinear dynamics of this patient group. In this study, recurrence quantification analysis (RQA), a well documented nonlinear method, was used to compare the nonlinear dynamical structure of postural sway in two groups consisting of MS patients (. n=. 23) and healthy matched controls (. n=. 23). The study focuses on three levels of postural difficulty consisting of (1) standing on a rigid surface (force platform) with eyes open, (2) standing on a rigid surface with eyes closed, and (3) standing on a foam surface with eyes closed.... 

Rehabilitation is the best approach for patients who suffer physical disability of their upper-limbs. Maintaining the intensity of exercise during treatment is the main factor that makes the robots suitable for rehabilitation since robots do not get tired and do the exercises with constant intensity under supervision of the doctor. Two main categories of rehabilitation robots are End-Effector based robots and wearable robots. According to the fact that most problems occur in need of rehabilitation for hand wrist area, in this paper a wearable rehabilitation robot has been developed for the wrist. Nowadays, wearable robots attract more attention than the other group. Wearable robots are... 

Speech is one of the main communication methods used by humans. So designing speech based interfaces for computer applications can ease the use of them for different users, especially disabled and elderly people. In this project, we want to design and implement a system that can identify user's group from his/her speech. We are working on two main applications: Parental Control and Completely Automated Public Turing test to tell Computers and Human Apart (CAPTCHA). In the Parental Control application, we want to distinguish between child users and adults based on human speech. This can be used to restrict child user access to adult materials such as adult websites. In the CAPTCHA... 

Background Motor control exercise was claimed to improve spinal stability in patients with chronic non-specific back pain, but to investigate the effectiveness of this exercise, other outcome measures have been used rather than spinal stability itself. The aim of our study is to assess motor control exercise effects on spinal stability using a biomechanical model. Methods Fifty-one patients were assigned to either motor control or general exercises. Before and after trainings, participants were tested for spinal stability at seven isometric tasks. Electromyography signals were recorded from ten superficial muscles, and a hybrid EMG-driven musculoskeletal model estimated spinal stability... 

The main objective of this research was to introduce a smart assist-as-needed control system that helps elderly or partially paralyzed individuals. To ensure that a smart and compliant controller, in each cycle of the gait is developed, we adapted the target impedance gains and feed-forward force of the assistive mechanism according to a learning law. A strength metric was defined to determine when the human needs assistance. Then, a cost function was introduced and the gains are modified to reduce the cost function. Applying the proposed controller, the interaction force between patient's limb and robot was reduced in cases wherein user has sufficient strength for task execution and... 

Several studies have investigated postural control in anterior cruciate ligament (ACL) deficient patients; yet the contribution of cognitive processing (attention) in the postural control of these patients is still unclear. A dual-task design was used to determine the effects of a concurrent digit span memory task on standing balance in a group of ACL patients (n = 27) compared with a group of matched, healthy participants (n = 27). In double limb stance, three levels of postural difficulty were studies on a force platform (rigid surface with eyes open, rigid surface with eyes closed, and foam surface with eyes closed). There were three cognitive conditions (no cognitive task, easy cognitive... 

Background: Worldwide, both the incidence and death rates of pancreatic cancer are increasing. Evaluation of pancreatic cancer burden and its global, regional, and national patterns is crucial to policy making and better resource allocation for controlling pancreatic cancer risk factors, developing early detection methods, and providing faster and more effective treatments. Methods: Vital registration, vital registration sample, and cancer registry data were used to generate mortality, incidence, and disability-adjusted life-years (DALYs) estimates. We used the comparative risk assessment framework to estimate the proportion of deaths attributable to risk factors for pancreatic cancer:... 

Feature extraction and classification are the most important parts of BCI systems. The new branch of BCI studies focuses on the design of a classifier that is trained to function properly for each individual. This problem is known as Transfer Learning. In between-subject classification, due to the differences in the neural signals' distribution of different individuals, using the common methods of feature extraction for training the classifier, does not lead to high accuracy for the test subject. As a result, in this study, we present a method for extracting features that perform well in between subjects classifications. The data that we used in this study are EEG signals recorded during... 

Background: Accurate childhood cancer burden data are crucial for resource planning and health policy prioritisation. Model-based estimates are necessary because cancer surveillance data are scarce or non-existent in many countries. Although global incidence and mortality estimates are available, there are no previous analyses of the global burden of childhood cancer represented in disability-adjusted life-years (DALYs). Methods: Using the Global Burden of Diseases, Injuries, and Risk Factors Study (GBD) 2017 methodology, childhood (ages 0–19 years) cancer mortality was estimated by use of vital registration system data, verbal autopsy data, and population-based cancer registry incidence...