Vladimir Robles-Bykbaev

SPELTRA: A Robotic Assistant for Speech-and-Language Therapy

The Speech and Language Therapy (SLT) is an area focused on the rehabilitation of people suffering from different kinds of disorders and disabilities related with language and communication. According to latest estimates of the World Health Organization, most countries do not have appropriate structures to provide healthcare and rehabilitation services for those people. This problem becomes more complex on developing countries, due the lack of professionals and ICT-based tools to support the several activities that must be performed by the Speech and Language Pathologists (SLPs). On those grounds, this paper presents a robotic assistant with the aim to help SLPs during the therapy activities. This approach is based on an integrative environment that relies on mobile ICT tools, an expert system, a knowledge layer and standardized vocabularies. This proposal has been tested on 26 children suffering from different kind of disabilities, and the results achieved have shown important improvements in some activities related with SLT like reduction of the time required to prepare patients for therapy, and better response of children to perform tasks.

An intelligent system based on ontologies and ICT tools to support the diagnosis and intervention of children with autism

The World Health Organization (WHO) claims that one of each 160 persons in the world are diagnosed with Autism Spectrum Disorders (ASDs). However, in low- and middle-income countries this situation turns more complex, given that the prevalence of ASDs is not adequately estimated, or is unknown. On those grounds, in this paper we present a new approach based on semantic web, ontologies, and intelligent ICT tools (mobile tools and robotic assistants) to provide an effective support during the diagnosis and intervention stages of children with ASDs. Our system has been put to test on a pilot experiment carried in two stages: in the first one 32 children were surveyed about the functionality and appearance of the robot, while in the second stage we have evaluated the system services that are based on ontologies and the semantic web.

Intelligent Nano-Worlds: A New ICT Based Tool for Mental Health Care of Children Living Under Social Vulnerability

The latest estimates of UNICEF and United Nations present a complex picture related with children living under social vulnerability. Approximately, one-half of the estimated 57.4 million people displaced by war around the world are children, most of whom have been separated from their families. In the same line, many countries (especially the developing ones) present a lack of specialized professionals and resources to provide mental care and rehabilitation services. Thus, children who are under institutional care, frequently present some kind of resistance to the psychological intervention. On those grounds, this paper presents a new proposal with the aim of providing support for infant psychotherapy (diagnosis and intervention) focused on this vulnerable population. Our approach relies on the new idea of incorporating the “interactive and ludic nano-worlds” (that are special sceneries inside a micro-world focused on the patient’s profile). Likewise, the developed system uses intelligent ICT tools, and an expert system to generate automatically intervention guidelines. This proposal has been tested with 124 children and has reached encouraging results.

An ontology-based expert system to generate therapy plans for children with disabilities and communication disorders

Nowadays there are no precise estimates about the number of persons (especially children) living with disabilities and communication disorders in the world. This situation becomes more complex in developing countries, where the World Health Organization (WHO) claims that only between 5 and 15% of children and adults with disabilities have the opportunity to access to assistive technologies. In the same way, a Speech-Language Pathologist (SLP) has a work overload, and must carry out several activities related with monitoring patients, designing therapy plans, preparing reports, providing couseling services, among others. On those grounds, in this paper we present an expert system able to automatically infer general intervention guidelines for children with disabilities and communication disorders. The system relies on ontologies and implements a semantic web environment to provide several services related with information querying, reports generation, inference of intervention strategies, etc. In order to populate the ontology and validate the system, we have used the clinical information of 152 real cases of patients of Cuenca, Ecuador and 1,005 speech-language therapy information elements.

An educative environment based on ontologies and e-learning for training on design of speech-language therapy plans for children with disabilities and communication disorders

Nowadays several developing countries must to face several problems related with the lack of personnel, resources or adequate health-care structures to attend children with disabilities and communication disorders. Some studies of the World Health Organization (WHO) and other organizations point that in some countries of Africa exists one Speech-Language Pathologist (SLP) per each 2 to 4 million people, whereas in developed countries like United States or Australia the ratio is much higher: one SLP per each 2500 to 4700 people. For these reasons, in this paper we propose an intelligent educative environment aimed to support the training and development of practice skills of the future SLPs. Our proposal relies on ontologies and several e-learning modules and at the moment is able to support the learning process of designing therapy plans. Currently, the ontology that we have designed contains more than 1,005 instances and two tests to evaluate the articulation, and hearing skills on children.

An approach based on Fourier descriptors and decision trees to perform presumptive diagnosis of esophagitis for educational purposes

According to World Cancer Research Fund International the esophageal cancer is the eighth most common malignancy and the sixth most common cause of cancer-related death in the world. This disease can be originated by various causes, being the Barretts esophagus his previous stage. The Barretts esophagus is present in several cases of patients suffering from gastric reflux. Therefore, it is fundamental to have tools able to detect the earlier stages of esophageal cancer (esophagitis). On those grounds, in this paper we propose a method that allows detecting the esophagitis using an approach based on the analysis of esophageal irregularities (the Z-line). In order to analyze these irregularities, we have applied the Fourier transform on shape signature of the Z-line. With the aim of validate the proposed method, we have used K Nearest Neighbor criterion and Random Forest on a database consisting on 26 real cases of patients (10 healthy and 16 suffering from the disease). The results are promising in terms of precision, sensitivity, and specificity (0.81, 0.86 and 0.72, respectively).

Fuzzy controller for automatic microphone gain control in an autonomous support system for elderly

A fuzzy controller to support older adults should be robust and respond effectively to real-life situations such as illumination changes, ambient noise, and decision-making in critical situations. Following this approach, this paper presents the general design of “SA3M”, an autonomous support system for older adults that implements facial recognition, voice response and the use of various sensors to prevent or alert dangerous situations (gas leaks, fires, etc.). Furthermore, this paper addresses the problem of automatic microphone sensitivity control (Automatic Gain Control) in the processing of voice commands. To validate the proposed approach, the fuzzy controller was tested with a wide range of ambient noise levels and produced promising results.

Preprocessing the Structural Optimization of the SPELTRA Robotic Assistant by Numerical Simulation Based on Finite Elements

This project will structurally optimize the robotic assistant SPELTRA (Robotic Assistant for Speech and Language Therapy) that serves as pedagogical support to children with and without disabilities who are benefiting through the UNESCO Chair and Assistance Technologies (GI-IATa) of the UPS. This process would be carrying out through the study of different geometries and materials considering certain aspects technical and economic that will help to define by weighting parameters the optimal geometry and two possible materials for the design and creation of the new structure of the robot. After, will be defined all the variables and restrictions affecting the SPELTRA during the manipulation to which it is subjected in the robot-human interaction, thus establishing the structural model. For its analysis, CAD-CAE computational tools based on finite elements will be using and it will can to observe the possible deformations, efforts and safety factor to which would be subjected.

An Intelligent System to Automatically Generate Video-Summaries for Accessible Learning Objects for People with Hearing Loss

The latest estimates of the World Health Organization point that approximately 5% of world’s population presents disabling hearing loss (328 million adults and 32 million children). This situation becomes very complex in developing countries, where children with hearing loss and deafness rarely have access to schooling. On those grounds, in this paper we present an intelligent system to automatically generating video-summaries and captioning in sign language with the aim of creating accessible learning objects for children and youth with disabling hearing loss. Through our intelligent system, we propose a methodology that allows performing agile consumption of educational content (Learning Accessible Objects) that use videos. With the aim of determining the real feasibility of our proposal, we have performed a preliminary experiment with 7 educational videos of history, natural sciences and mathematics for deaf children and youth from 8 to 12 years. A team of 6 experts in sign language has evaluated several aspects our proposal (coherence of the summaries and captions, quality of the synchronization between the explicative elements in sign language and video execution, possible lost keywords/meanings, …).

SPELTA-Miner: An expert system based on data mining and multilabel classification to design therapy plans for communication disorders

The ability to express feelings and needs, to share ideas or to establish relations is fundamental in different stages of human life. During language acquisition, a child develops several intellectual, psychological and emotional skills that support many other brain functions. On those grounds, speech-language therapy is a fundamental process for those people who suffer from communication disorders. However, currently in several developing countries there is a lack of rehabilitation services, and personnel of many centers overwork. In this paper, we present an expert system able to design therapy plans for patients suffering from disabilities related with communication. The system uses an approach based on natural language processing and multi-label classification to determine which strategies must be carried out in a therapy session. This approach has been tested on a database consisting on 1,345 strategies and 53 real cases of children with disabilities. In order to evaluate the generated plans we have measured accuracy and quality, obtaining encouraging results.