Human – Computer Systems Interaction: Backgrounds and Applications 2

A new procedure for combined validation of learning models – built for specifically uncertain data – is briefly described. The procedure, called the

queue validation

, relies on a combination of

resubstitution

with the modified learn-and-test paradigm. In the initial experiment [Burda and Hippe 2010] the developed procedure was checked on doubtful (presumably distorted by creative accounting) data, related to small and medium enterprises (further called

SME

), displaying two concepts:

bankrupt

or

non-bankrupt

. In the current research a new set of learning models was generated for the same data using various types of optimized artificial neural networks. All learning models were evaluated using the

queue validation

methodology. It was found that error rates for

bankrupt

concept are much larger than error rates for the concept

non-bankrupt

. It is assumed that this difference in error rates discovered by the

queue validation

procedure can be probably used as a hint pointing frauds in the investigated

SME

data.

In the paper current results of a project devoted to the development of a software and hardware platform for a holonic based Intelligent Manufacturing System dedicated to small and medium metal component production companies are presented. Recent trends in factory automation which create a promising perspective for industrial implementations of Intelligent Manufacturing Systems including extended Human-System Interfaces, are briefly discussed. It was shown that modern factory automation controllers facilitate implementations of extended Human-System Interface as well as Human-Machine Interface and enable the integration of human operators and manufacturing resources into an Intelligent Manufacturing System. In the paper two industrial testbeds used in daily production processes in two different companies are described and future directions of the system development are discussed.

The aim of this paper is to present some difficulties which can be met when a fuzzy model is built with a domain expert help. The paper discusses methods used at succeeding steps of expert modeling process and also presents some of them on a real example. The main concern of the paper is a high quality of a fuzzy expert model which can be easily missed when not all aspects of expert modeling are carefully tackled. Practical experiments presented in the last part of the paper shown that most popular methods used in the process of interviewing an expert are not always appropriate and can be a reason of creating a completely useless expert model.

The possibility of using MOODLE e-learning platform as an environment for teaching database issues, concerning database objects and users creating, analysis and management of a transaction has been analyzed in the paper. All of the needed extensions were made using PHP scripts and were tested in the chosen database servers: MySQL, SQL Server and Oracle DBMS. Results of these tests were satisfactory, confirming preliminary assumptions.

A concept of computer systems supporting human activity by recommendations for actions leading to desired intermediate and final goals is here presented. The recommendations are given in a standard form of deontological statements specifying the current states, the desired next states and operations transforming the current into the desired states. The quality of recommended actions is by parameters describing various favorable and unfavorable effects assessed. The quality parameters are presented as vectors in semi-ordered linear (Kantorovitsch) space where preferences between vectors is induced by definition of a positive vectors’ cone. It is shown how the positive cone by systems of linear inequalities (without constant terms) can be defined so as to establish a compromise between different quality parameters in order to chose the most preferable actions. Two methods of the above-mentioned methods extension on the paths of actions comparative quality assessment are proposed. The presented basic concepts by simple examples are illustrated.

Chapter reviews the solutions used in diagnostic-advisory system, dedicated to the needs of the foundry industry. Multimedia techniques used in the system were selected to create a comprehensive capabilities of contact between user and computer system. The first part of the considerations apply to work in diagnostic mode, including identification of castings defects and determine the causes of their occurrence, the second part is a look at some of the features of the system implemented in a consultative mode, such as the integration of knowledge or technical and market expertise. Many illustrations was used to illustrate the various forms of contact with the user.

The aim of the paper is to discuss some selected issues related to services merging, partitioning and execution in systems based on service oriented paradigm. The main feature of such systems is that the required services may be efficiently and flexibly composed of available atomic (elementary) services providing certain and well-defined functionalities. It is rather obvious that the flexibility of such a services delivering system may be limited by the amount and cost of communication necessary to support increasing atomic services granularity. It is assumed that the cost of complex service delivery is composed of exchanged data flows processing and communication costs and the services quality depends on delays introduced by available resources for data flows characterizing services requests followed by specified requirements.

Healthcare system is modern complex system that includes four principal components in point of view of reliability engineering. They are hardware, software, human factor and organization component. There are different methods in reliability engineering for analysis and quantification of every of these components. But new tendency in reliability analysis needs methods that evaluate the system as a single whole. In accordance with this tendency one aspect of reliability engineering (importance analysis) is considered in the paper. The importance reliability analysis allows to estimate influence of every healthcare system component to the system reliability and functioning. New algorithms for importance analysis of healthcare system are proposed in this paper.

This paper aims at contributing to a better understanding of essential concepts of visual design aided by computer. Towards this end, we first present an ontology of conceptual visual design. Then, we define particular components of the formal model paying attention to the role of different kinds of classification during the design process. Moreover, we present two types of logic models used in computer tools supporting the design process. Finally, a formal model of computer-aided visual design is defined. The model is illustrated on examples of designing floor layouts based on a graph-based data structure gathering information for design knowledge and describing two categories of thinking during design process.

The paper discusses the idea and the design of a remote control system for storage management of agricultural products which temperature may rise as the result of biological processes during the storage. An actual potatoes storehouse is discussed as an application for the proposed automation system. Because of existing buildings and infrastructure at the farm, wireless data transfer system has been proposed for communication between sensors, data acquisition module (Storehouse Local Controller) and human-machine interface (HMI) module. Special rod-like temperature and humidity sensors have been designed and built to measure the temperature and humidity inside the potatoes stack at the storehouse. A complete system allows to monitor the storage process and control it on the run maintaining the desired temperature of the stored products. The study is an elaboration of previously proposed control system, including ventilation system working algorithm, further analysis of working range of the wireless data transfer modules and agricultural products temperature changes characteristics.

Outdoor sport practitioners can improve greatly their performance if they train at the right intensity. Nevertheless, in common training systems, performance is only evaluated at the end of the training session, and sensed data are incomplete because only human biometrics are analyzed. These systems do not consider environmental conditions, which may influence athletes’ performance directly during instruction. In this paper, we introduce a decision making method for a multi-step training scenario based on dynamic program optimization and formulated as a Markov Decision Process, which allow athletes to complete heterogeneous training programs with several levels of exercise intensity. This methodology is applied in a pilot experiment of cross-country running. Environment and athletes are monitored by means of a wireless sensor network deployed over the running circuit, and by mobile elements carried by the users themselves, which monitor their heart rate (HR). The goal is to select, for a given user, a running track that optimizes heart rate according to a predefined training program. Results show that the proposal is of practical interest. It achieves a notable success in heart rate control over non-optimal track selection policies. The importance of environmental data is shown as well, since heart rate control improves when those data are taken into account.

This paper introduces a novel vision for further enhanced Internet of Things services. Based on a variety of data (such as location data, ontology-backed search queries, in- and outdoor conditions) the Prometheus framework is intended to support users with helpful recommendations and information preceding a search for context-aware data. Adapted from artificial intelligence concepts, Prometheus proposes user-readjusted answers on umpteen conditions. A number of potential Prometheus framework applications are illustrated. Added value and possible future studies are discussed in the conclusion.

The widespread use of the standard, worldwide and vendor-independent OPC UA specifications in industrial environment introduces many benefits as they allow to keep open the market of the industrial applications. On the other hand, OPC UA adopts a very complex software infrastructure to realise the communication between industrial applications; this complexity may impact on the overall performance of their data exchanges. The aim of this paper is to deal with the performance evaluation of OPC UA. The main features which may influence performance in the client/server exchange of information, will be pointed out; then, the main results of the evaluation of the overhead introduced by these mechanisms onto the OPC UA overall performance will be presented and discussed.

Classic models of distributed processing assume documents to be passive objects, sent to remote recipients as messages, or downloaded from remote sites as files. The paper introduces a concept of documents being implemented as

active

objects that can migrate from the originating host to remote sites, and interact there with local users. Upon completing their mission, documents return to the originating host with a resulting content to be archived or processed further. Such a

document-centric

computing paradigm, involving documents implemented as mobile and interactive agents with embedded functionality, is more flexible and usable for knowledge based organizations than

data-centric

computing, with functionality hard-wired in individual processing nodes. This is particularly important for collaborative computing systems, where human and artificial agents render and use services interchangeably. Moreover, it stimulates mobility of users, as it reduces the need for them to stay on-line during the entire computation process and allows for using less sophisticated personal devices.

The dramatic growth of Internet and network technologies, etc leads to different perspectives of computing methodologies as well as changes of software business model. If the traditional business model for software is one-time payment for a license for one machine with unlimited use, the development of Internet and network technologies, etc makes it possible for users to pay on their consumption as they pay for water, gas and electricity. With advanced technology all computing and storing process can be centralized on the infrastructure of service providers. With this new model, users don’t have to concern about deploying their infrastructure, security, etc which will be responsible by service providers. This new trend grows extremely fast in last couple years and attracts a lot of researches from scholars such as Grid Computing model, Client Server model and especially Cloud Computing model with its scalability. In this paper we do not analyze differences between these utility computing models and what model will be the main field in the future. Instead we present how to use computer networks as a mean of computing and simulation and how computer networks are considered as a solution to boost technology development. Two software applications through computer networks were developed and applied successfully in teaching and learning courses in Auburn University and Bradley University are presented in this paper. It is a typical example of enhanced interaction between human and CAD tools while computer networks play a role as a human system interface.

The paper presents a new method of improving the human-machine communication in distributed systems and computer networks, in which a substantial portion of traffic is a multimedia traffic. The method bases on priority processing of short and multimedia services packets. The choice of service time as a parameter evaluating the effectiveness of proposed solutions and an appropriate mathematical model is justified. Simulation studies are used to determine the intensity range of information flow, for which the method is appropriate.

This paper describes proposal for the application modified Ant Colony Optimization Algorithm in the task for recruitment and selection of employees. After analyzing the combinatorial problem involving multicriterial process of recruitment and selection model proposed non-compensating its solution using the modified ACO heuristic strategy, showing a lack of opportunities to receive appropriate the resulting matrix, related to the accurate prediction of the decision at an acceptable as satisfactory for implementation only available deterministic algorithms.

This article presents a specific part of the idea of distributed virtual museum. The intention of the authors is to fulfill one of the scenarios for Future Internet and to give a set of requirements for future properties of the global network. A progressive mesh is a lossless approximation of the original mesh model at any, smoothly adjusted, level of detail. The main part of this work is devoted to the extension of progressive meshes for hierarchical representation associated the position of observation. This allows the selective adjustment of the level of detail, measured in the number of triangles that appear in any fragment of the model, independently from the rest. Sample solution was presented, as well as the method of construction and the main criteria for the refinement.

The influence of the control plane architecture on the quality of services offered by the GMPLS network is considered in this paper. Several simulation experiments are prepared to verify this influence. The simulations assume separation of the functional planes of GMPLS and two typical topologies ring and mesh. The GMPLS control plane simulator, prepared by authors, simulate most of the control plane behavior by including OSPF-TE, RSVP-TE, protection and restoration procedures. The simulation results confirm quality of services improvement by providing additional interconnection in the control plane.

Social tagging is an innovative and powerful mechanism introduced by social Web: it shifts the task of classifying resources from a reduced set of knowledge engineers to the wide set of Web users. However, due to the lack of rules for managing the tagging process and of predefined schemas or structures for inserting metadata and relationships among tags, current user generated classifications do not produce sound taxonomies. This is a strong limitation which prevents an effective and informed resource sharing; for this reason the most recent research in this area is dedicated to empower the social perspective applying semantic approaches in order to support tagging, browsing, searching, and adaptive personalization in innovative recommender systems. This paper proposes a survey on existing recommender systems, discussing how they extract social semantic relations (i.e. relations among users, resources and tags of a folksonomy), and how they utilize this knowledge for recommending tags and resources.

Detection of malicious activity in the network still is a challenge. The self-similarity feature of traffic can be used in an anomaly detection method. The influence of traffic generated by intruder who performs access attack is analyzed. In the other hands the simulation of threads is useful in designing and testing processes of a network. For this purpose a multi-layer ‘on-off’ model of traffic source is developed and a traffic generator is implemented according this model. Finally the real traffic including attacker flow is compared to the traffic generated by generator. This comparison proves that it is possible to simulate traffic similar to malicious one.

Uniform Resource Locator (URL) ordering algorithms are used by Web crawlers to determine the order in which to download pages from the Web. The current approaches for URL ordering based on link structure are expensive and/or miss many good pages, particularly in social network environments. In this paper, we present a novel URL ordering system that relies on a cooperative approach between crawlers and web servers based on file system and Web log information. In particular, we develop algorithms based on file timestamps and Web log internal and external counts. By using this change and popularity information for URL ordering, we are able to retrieve high quality pages earlier in the crawl while avoiding requests for pages that are unchanged or no longer available. We perform our experiments on two data sets using the Web logs from university and CiteSeer websites. On these data sets, we achieve a statistically significant improvement in the ordering of the high quality pages (as indicated by Google’s PageRank) of 57.2% and 65.7% over that of a breadth-first search crawl while increasing the number of unique pages gathered by skipping unchanged or deleted pages.

Article is an attempt of formulating of synergy in IT system, synergic IT system definition and synergic intranet, relying on a design, construction, modification and maintenance of the cost effective solutions for practical problems in the field of the Information Society development within the Internet, with the use of scientific and technological knowledge. Authors introduce term of synergy in IT system, synergy types and methods of classification. They present also synergy image in Intranet. Article has to be start for formalizing new domain of informatics, called synergy in IT.

The problem of out-door mobility of the visually impaired and a review of key assistive technologies aiding the blind in independent travel are discussed in this paper. Space perception abilities important for mobility of the visually impaired are outlined and basic concepts such as: cognitive mapping, wayfinding and navigation are explained. Sensory substitution methods and interfaces for non-visual presentation of the obstacles and communicating navigational data are addressed. Current projects under way and available technologies aiding the blind in key mobility tasks such as: obstacle avoidance, orientation, navigation and travel in urban environments are reviewed and discussed. Special attention is paid to a class of teleassistance systems in which an operator at a remote site is capable of guiding the visually impaired. Finally, results of trials of the teleassistance system with participation of blind volunteers are reported.

The paper demonstrates how to transform (using a combination of techniques reported in our previous papers) a collection of random images gathered in an unknown environment into a limited-scale visual model of that environment. The model generally consists of the template images of the typical “visual objects” identified in the explored world. Both the concepts of objects and their templates are formed without any assumptions about the content of acquired images, i.e. the semantics is built using the pictorial data only (although users may subsequently identify the real-world semantics of the formed objects). From the image processing perspective, the method consists in detecting near-duplicate (i.e. photometric/geometric distortions and partial occlusions are allowed) fragments in random images. It is envisaged that such a proposal can be instrumental in assisting both autonomous agents and visually impaired humans (including both blind people and people unable to understand perceived visual data) facing unfamiliar worlds. The paper focuses on the practical aspects of the problem (exemplary results, computational efficiency, etc.) although a substantial amount of theoretical background is also included.

We present problem of recognizing gestures and signs executed by hands. Hand posture recognition is either the process by which gestures formed by a user interact with the computer or is the element of the special signs language to convey meaning. We propose methods for the recognition of hand gestures using Gabor wavelets (GW), Radon transform (RT) and texture features for gesture recognition. We compare these features and propose the fusion features to obtain high recognition rate.

People affected by serious motor disabilities need proper ways to interact with the computer, which is for them an essential communication means. Thanks to recent technological advances in the field of eye tracking, it is now possible to exploit unobtrusive devices to detect the user’s gaze on a screen and employ it to control graphical interfaces. In this paper we present some of the eye tracking projects we have recently developed at the University of Pavia, all aimed at providing the (disabled) user with reliable gaze-driven input modalities.

This paper describes an algorithm for a visual human-machine interface that infers a person’s intention from the motion of the hand. The context for which this solution is intended is that of wheelchair bound individuals whose intentions of interest are the direction and speed variation of the wheelchair indicated by a video sequence of the hand in rotation and in vertical motion respectively. For speed variation recognition, a symmetry based approach is used where the center of gravity of the resulting symmetry curve indicates the progressive position of the hand. For direction recognition, non-linear classification methods are used on the statistics of the symmetry curve. Results show that the symmetry property of the hand in both motions can serve as an intent indicator when a sequence of fifteen consecutive frames is used for recognition. This paper also shows less satisfactory results when fewer frames are used as an attempt to achieve faster recognition, and proposes a Brute force extrapolation algorithm to better the results.

Dichromacy is a serious color vision problem, where people can see and recognize only a limited number of colors. In this article we propose computerized methods and systems for processing of WWW images and pictures obtained using a camera phone. Image simulation, transformation and color vision difference visualization methods are presented as a part of two computerized systems. The paper presents also color recognition and labelling method. The results of experiments obtained by means of simulation and control group showed that both systems can be efficiently used to obtain a color name for indicated real world objects or for the image object contained on the Web.

In our current research, we are developing a robotic walker system with standing, walking and seating assistance function. Our developing system is based on a walker which is popular assistance device for aged person in normal daily life and realizes the standing and seating motion using the support pad which is actuated by the novel assistance manipulator mechanism with four parallel linkages. In this paper, we develop the control scheme which realizes the natural seating motion with fewer loads to the patient. For developing control scheme, we investigate the seating motion of aged people who requires to power support and typical seating motion by healthy young people. Comparing with two motions, we set the reference of seating motion with our system and we discuss the required assistance condition during seating motion. Our key ideas are two topics. One topic is analysis of condition which realizes the seating motion as young healthy people. The other topic is combination of force and position control. According to the patient’s posture during seating motion, our control system select more appropriate control method from them. Using proposed control, our system reduces the patient’s load and maintains his posture stably when it is necessary.

Mobile navigation uses smart mobile devices, such as PDAs, mobile phones or dedicated devices. In order to help the user to navigate, they receive updated data through wireless Internet, GPS, cellular phones and specialized sensors. Car navigation systems are the most known and advanced implementation of data navigation systems. They are embedded in cars or in distinct devices. Pedestrian navigation systems were less approached. This paper presents a PNS for finding a car. It was thought to be included in the car’s key and to guide the user from its starting point, which is in delimited area around the car, to his/her car.

As a result of demographic change the average age of many western populations increases, accompanied with age-related disease patterns. Especially tremor symptoms rise accordingly, aggravating a barrier free interaction with information systems. In order to maintain a self determined lifestyle at home, new technologies and methods need to be introduced, especially for application in health care and telemedical scenarios. Hence, a new direct input technique based on wiping movements on touch screens has been developed. The combination of a new input concept and applying regular commercially available technologies helps to avoid high costs for acquisition and therefore makes it marketable. While making an input on the touch screen the precise characteristics of every wiping movement can be tracked and is used for computation of the desired entry. The efficacy of this approach was evaluated within a clinical study with n=15 subjects. The results show that the error ratio for inputs by tremor patients can be significantly reduced in comparison to a virtual keyboard, depending on tremor strength and form. The learning curve for first time users is very steep and tends to result in inputs that are only slightly steady than purposeful movements to standard buttons and keys.

This paper presents the concept and prototype of a compound infrastructure for ubiquitous human health monitoring. Growing range of mobile health care applications raises the question of their possible interference and cooperation. Particular benefit is expected from integration of personal and residential solutions, because of their complementary features. Consideration of various cooperation scenarios lead us to a specification of three cooperation levels depending on required integration of software. The paper presents details and experimental results of cooperation of two prototype surveillance systems lying in best result selection and conditional use of communication resources of the residential system as a carrier of messages from the personal system over the wired channel. This approach provides a cheap broadband data transfer minimizing the monitoring delays without limiting the subject mobility.

The paper presents a prototype of a system which can be used as a therapeutic and educational tool for children with developmental problems. Natural body movements and gestures are used in the system to interact with virtual objects displayed on the screen. Nowadays such systems can be built with the use of widely available free software tools for both graphical and vision applications. Such tools are also shortly presented in the paper.

This chapter describes the structure of an EEG biofeedback platform focused on an efficient way for its user to learn how to self regulate cortical activity. A longitudinal study of how voluntary training of specific electro cortical activity produces any stable changes in the electroencephalogram is also presented. Correlations of these changes with short term memory are also hypothesized. The results from this study showed that it is possible to learn to change some rhythmical activity in the EEG, in this case the alpha activity, after a few feedback sessions. A positive relation between this frequency band and cognitive processes was also observed. A new technique based on the Hilbert Huang Transform is proposed for the analysis of EEG signals in biofeedback protocols. Initial observations of the results of this technique are presented.

In this article we offer a communication system to people who undergo a severe loss of motor function as a result of various accidents and/or diseases so that they can control and interact better with the environment, for which a brain-computer interface has been implemented through the acquisition of EEG signals by electrodes and implementation of algorithms to extract characteristics and execute a method of classification that would interpret these signals and execute corresponding actions The first objective is to design and construct a system of communication and control based on the thought, able to catch and measure EEG signals. The second objective is to implement the system of data acquisition including a digital filter in real time that allows us to eliminate the noise. The third objective is to analyze the variation of the EEG signals in front of the different tasks under study and of implementing an algorithm of extraction of characteristics. The fourth objective is to work on the basis of the characteristics of the EEG signals, to implement a classification system that can discriminate between the two tasks under study on the basis of the corresponding battles.