Panagiotis Moschonas

3-D Model Search and Retrieval From Range Images Using Salient Features

This paper presents a novel framework for partial matching and retrieval of 3-D models based on a query-by-range-image approach. Initially, salient features are extracted for both the query range image and the 3-D target model. The concept behind the proposed algorithm is that, for a 3-D object and a corresponding query range image, there should be a virtual camera with such intrinsic and extrinsic parameters that would generate an optimum range image, in terms of minimizing an error function that takes into account the salient features of the objects, when compared to other parameter sets or other target 3-D models. In the context of the developed framework, a novel method is also proposed to hierarchically search in the parameter space for the optimum solution. Experimental results illustrate the efficiency of the proposed approach even in the presence of noise or occlusion.

Virtual user models for the elderly and disabled for automatic simulated accessibility and ergonomy evaluation of designs

This paper presents a framework for automatic simulated accessibility and ergonomy testing of virtual prototypes of products using virtual user models. The proposed virtual user modeling framework describes virtual humans focusing on the elderly and people with disabilities. Geometric, kinematic, physical, behavioral and cognitive aspects of the user affected by possible disabilities are examined, in order to create virtual user models able to represent people with various functional limitations. Hierarchical task and interaction models are introduced, in order to describe the user’s capabilities at multiple levels of abstraction. The use of alternative ways of a user task’s execution, exploiting different modalities and assistive devices, is supported by the proposed task analysis. Experimental results on the accessibility and ergonomy evaluation of different workplace designs for the use of a telephone and a stapler show how the proposed framework can be put into practice and demonstrate its significant potential.

HapticRiaMaps: towards interactive exploration of web world maps for the visually impaired

Existing information on the Web and especially maps are graphically-orientated and in most cases visually impaired users have very restricted access and find it difficult to recognize this kind of visual representation. For visually impaired people and especially for blind users alternative information presentation ways must be found, which would replace visual information. We investigate the potential role of haptics in augmenting the visualization of maps exist on the Web. HapticRiaMaps is a free open source web application enforces the accessibility of maps for the visually impaired users. Issues of multimodal interaction, relevant sonifications, and haptic technologies enable efficient map exploration of preferable and well known 2D maps (retrieves maps from OpenStreetMap web application).

Novel human factors for ergonomy evaluation in virtual environments using virtual user models

The present paper introduces a set of ergonomic factors which are evaluated by a framework that performs automatic, simulated ergonomic analysis of virtual environments. The proposed framework uses virtual user models describing users with or without physical deficiencies and evaluates the ergonomy of virtual environments for the specific users. Two novel ergonomic factors regarding comfort are introduced and compared to known physical metrics, such as torque, impulse and energy. The factors used are described in detail, according to their theoretical basis as well as their practical meaning. Experimental results illustrate the use of the proposed framework in two realistic application scenarios: a common car interior and a typical workplace design.

Simulation and Visual Analysis of Neuromusculoskeletal Models and Data

This work presents a novel medical decision support system for diseases related to the upper body neuromusculature. The backbone of the system is a simulation engine able to perform both forward and inverse simulation of upper limb motions. In forward mode neural signals are fed to the muscles that perform the corresponding motion. In the inverse mode, a specified motion trajectory is used as input and the neural signals that are the root cause of this particular motion are estimated and investigated. Due to the vast amount of information that results from even simple simulations, the results are presented to the expert using visual analytics metaphors and in particular both embodied and symbolic visualizations. Several use cases are presented so as to demonstrate the analytics potential of the proposed system.

Designing accessible ICT products and services: the VERITAS accessibility testing platform

Among the key components of designing accessible products and services for disabled users is accessibility testing and support. The VERITAS FP7 project has developed a platform that consists of several tools that provide automatic simulation feedback and reporting for built-in accessibility support at all stages of ICT product development. In this explorative pilot study, we evaluated the usability and technology acceptance of using three of these tools in the design of accessible GUI-based ICT products in five application domains. A sample of 80 designers/developers (12 female; 68 male) evaluated the three tools by filling in the standard SUS and TAM questionnaires. Results revealed good usability and technology acceptance for all three tools as a novel accessibility testing method. The VERITAS platform can offer an intuitive solution in accessibility design and can ensure that ICT products are designed for all.

A framework for automatic simulated accessibility assessment in virtual environments

The present paper introduces a framework that enforces the accessibility of products and services by enabling automatic simulated accessibility assessment at all the stages of the development. The proposed framework is based on a new virtual user modelling technique describing in detail all the physical parameters of a user with disability(ies). The proposed user modelling methodology generates a dynamic and parameterizable virtual user model that is used by a simulation framework to assess the accessibility of virtual prototypes. Experimental results illustrate the use of the proposed framework in a realistic application scenario.

Discovering the Discriminating Power in Patient Test Features Using Visual Analytics: A Case Study in Parkinson’s Disease

This paper presents a novel methodology for selecting the most representative features for identifying the presence of the Parkinson’s Disease (PD). The proposed methodology is based on interactive visual analytic based on multi-objective optimisation. The implemented tool processes and visualises the information extracted via performing a typical line-tracking test using a tablet device. Such output information includes several modalities, such as position, velocity, dynamics, etc. Preliminary results depict that the implemented visual analytics technique has a very high potential in discriminating the PD patients from healthy individuals and thus, it can be used for the identification of the best feature type which is representative of the disease presence.

Parkinson’s Disease Patients Classification Based on a Motion Tracking Methodology

This study demonstrates how a computer based methodology for tracking motor abilities of Parkinson’s disease can be utilized for patient classification and assessment of the Parkinson’s disease severity. The Line Test methodology evaluates the impaired voluntary movement and generates a set of features that describe the motion. A total cohort of 6 control subjects and 37 Parkinson’s disease subjects were recruited and assessed for the test. During the test, a vertical line appears on the screen and the device evaluates patient’s performance by producing features that correlate the motion to the last medication dosage, the line-test position, the line-test reaction time and the line-test total error. A common cohort of 24 Parkinson’s disease subjects (patients that carried out the Line Test more than once) was formed to track the features alterations between repetitions in time. Results evaluation was performed in both cohorts based on information visualization methodology, optimized for the multi-objective dataset. The line-test position and the time from the last medication dosage features were proved to present the major relation to patients’ group formation. Additionally, line-test reaction time and the line-test total error features proved significant between patients’ performance in the common cohort. Study limitations are correlated to the size of the cohort and the time frame of the study. In general, the current practice supports further investigation into using Line Test methodology for addressing Parkinson’s disease severity.

3D Protein-Structure-Oriented Discovery of Clinical Relation Across Chronic Lymphocytic Leukemia Patients

Chronic lymphocytic leukemia (CLL) is the most common adult leukemia with still unclear etiology. Indications of antigenic pressure have been hinted, using sequence and structure-based reasoning. The accuracy of such approaches, and in particular of the ones derived from 3D models obtained from the patients’ antibody amino acid sequences, is intimately connected to both the reliability of the models and the quality of the methods used to compare and group them. The proposed work provides a sophisticated method for the classification of CLL patients based on clustering the amino acid sequences of the clonotypic B-cell receptor immunoglobulin, which is the ideal clone-specific marker, critical for clonal behavior and patient outcome. A novel CLL patient clustering method is hereby proposed, combining bioinformatics methods with the extraction of 3D object descriptors, used in machine learning applications. The proposed methodology achieved an efficient and highly informative grouping of CLL patients in accordance to their biological and clinical properties.