Intelligent Interface Research Articles

Ontology Application to Construct Inductive Modeling Tools with Intelligent Interface

This paper is devoted to the analysis of sources in the field of development and building intelligent user interfaces. Particular attention is paid to presenting an ontology-based approach to constructing the architecture of the interface, the tasks arising during the development, and ways for solving them. An example of the construction of the intelligent user interface is given for software tools of inductive modeling based on the detailed analysis of knowledge structures in this domain.

Use of Information Technology by Transport Enterprises: Cryptocurrency Mining Mechanism Based on Blockchain Technology

Currently, the migration fact of many transport enterprises to the Internet cloud has been noted, where the use of information technology is one of the factors for the active use of enterprise innovative potential, revealing new opportunity to increase revenue, improve efficiency and achieve better results. New concepts and terms have been developed with the emergence of the digital economy. Thus tariffs for transport services of enterprises engaged in international transport are replenished with new content. Introducing information systems, using an intelligent user interface, auto-indexed technological tools, transport companies strengthen their influence on international markets, increase volume of service export. Working with blockchain technology is not a particularly difficult task for transport enterprises. The use of the blockchain-based cryptocurrency mining mechanism to increase revenues encourages transport enterprises to improve their organizational structure, create IT departments, introduce new management methods and personnel remuneration systems without limitation to traditional approaches developed by practical activities. A topical issue in the study of cryptocurrency mining and closely related to the implementation of blockchain technology in the activities of transport enterprises remains the issue of the peculiarities forming the cost of services for an enterprise using blockchain technology. In the near future, artificial intelligence will become an indispensable tool for transport enterprises and service organizations. The rapid development of the digital eco-nomy and information technologies in the activity of transport enterprises will serve as the basis for formation of prerequisites for a transition to the V technological mode and development of market relations based on innovative technologies.

TRAINING AND GAMING SYSTEM FOR DEVELOPMENT OF LOGIC WITH INTELLIGENT INTERFACE

In today's education, there are problems associated with the development of attention in preschool and primary school children. It is difficult for children to focus on a given task, especially if it is not very interesting and monotonous, their attention is attracted by everything new and bright. For this reason, the gamification of educational processes is one of the most popular modern trends in the development of information systems. Using the game, children in an interesting and simple way can develop the skills of logical thinking, solving certain problems of logic-mathematical games, such as sudoku. Most of the current informational training and gaming systems have a standard interface and are age-specific. The authors propose a modern training and gaming system with an intellectual interface, which will increase the efficiency of teaching children of preschool and primary school age the basics of logical thinking by adapting to each specific child. The article provides a comparative analysis of existing systems for the development of logic, the basic requirements for such a system, the analysis of methods of gesture recognition and the algorithm of work of the intellectual interface based on the use of neural networks, namely the convolutional neural network, which is the logical development of ideas of such architectures neural networks such as cognitron and neocognitron. After that, a conceptual model of training and gaming system was developed, which consists of a game subsystem that interacts with the intellectual interface with the help of a database and a knowledge base. The authors also developed a general scheme of the game subsystem. The innovative training-gaming system offered by the authors not only allows to use the intelligent interface but also adapts to each individual player, depending on the previous results of the game, which leads to an increase in the quality and effectiveness of teaching children of preschool and primary school age. Learning through play is an interesting and simple learning that leads not only to the development of logic but also to the development of sustained attention in children.

Eye-Mind reader: an intelligent reading interface that promotes long-term comprehension by detecting and responding to mind wandering

ABSTRACT We zone out roughly 20-40% of the time during reading – a rate that is concerning given the negative relationship between mind-wandering and comprehension. We tested if Eye-Mind Reader – an intelligent interface that targeted mind-wandering as it occurred – could mitigate its negative impact on reading comprehension. When an eye-gaze-based classifier indicated that a reader was mind-wandering, those in a MW-Intervention condition were asked to self-explain the concept they were reading about. If the self-explanation quality was deemed subpar by an automated scoring mechanism, readers were asked to re-read parts of the text in order to correct their comprehension deficits and improve their self-explanation. Each participant in the MW-Intervention condition was paired with a Yoked-Control counterpart who received the exact same interventions regardless of whether they were mind-wandering. Results indicate that re-reading improved self-explanation quality for the MW-Intervention group, but not the control group. The two conditions performed equally well on textbase (i.e. fact-based) and inference-level comprehension questions immediately after reading. However, after a week-long delay, the MW-Intervention condition significantly outperformed the yoked-control condition on both comprehension assessments (ds = .352 and .307). Our findings suggest that real-time interventions during critical periods of mind-wandering can promote long-term retention and comprehension.

Microbiological and physicochemical parameters for predicting quality of fat and low-fat raw ground beef during refrigerated aerobic storage.

The aim of the current study was to identify quality indicators of fat (14.50±0.75%) and low-fat (4.79±0.63%) raw ground beef by monitoring changes in physicochemical and microbiological parameters during aerobic refrigerated storage, such as water-holding capacity, pH, thiols, carbonyl compounds, thiobarbituric acid reactive substances (TBARS), metmyoglobin, deoxymyoglobin, oxymyoglobin color indices, pseudomonads, Brochothrix thermosphacta, and total viable counts. Meat packaged in air-permeable polyethylene plastic film was stored under controlled isothermal conditions (0, 5, 10, and 15 °C). A population level of pseudomonads equal to 7.0±0.5 log10 colony forming units (CFU)/g was considered as the potential spoilage level. Using principal component analysis, samples were distinguished on the basis of their microbial load. A significant positive correlation between microbial population and carbonyls, metmyoglobin, TBARS, water-holding capacity, and a negative correlation with thiols and color parameters (L* , chroma) were observed. Two different approaches were followed to estimate the quality status of samples: (i) the partial least square (PLS) regression with R2 of 0.93 and root mean square error prediction of 0.44 for pseudomonads, using the above physicochemical characteristics as the dominant input variables, which allowed prediction of the microbiological status of ground beef regardless of time-temperature storage profile and fat content, and (ii) a square-root-type model (adjusted R2 of 0.952) that satisfactorily predicted the growth of spoilage pseudomonads under isothermal and dynamic conditions, regardless of the above physicochemical changes. The above results suggest that depending on the available input data, the two modeling approaches can accurately (and complementarily) assess quality of aerobically stored ground beef. PRACTICAL APPLICATION: Changes in appearance and quality of fat and low-fat raw ground beef are associated with physicochemical alteration and/or microbial growth. The study provides two different modeling approaches that can be integrated in an intelligent interface of the refrigerator having specific colorimetric and/or temperature sensors, to evaluate in a convenience way the quality of stored meat thus reducing domestic waste: the partial least square model was based on physicochemical parameters (particularly chroma, metmyoglobin, and thiobarbituric acid reactive substances), while the square root model was based on the time-temperature conditions during storage.

Natural Language SQL Query Processing using Fuzzy Matching and Elimination Technique

In Structured Query Language (SQL), complex queries are difficult to write or understand by a user, because every user is not familiar with SQL. A common user can able to retrieve the information from the query databases using natural language is considered as an important research area. To improve the communication between databases application and naive user, an enhanced application with intelligent interface are needed. A fuzzy system with matching and elimination technique is designed in this research study, where SQL queries are formed from the input given by the user through several steps like noise removal, lexicon normalization and query formation. Then, the system uses the Latent Dirichlet Allocation (LDA) to extract the keywords from the input query. Finally, matching and elimination techniques are used to find the data, which is related to the input query given by end-user. When compared with the existing SQL techniques, the proposed fuzzy method achieved 91% and 90.5% accuracy, 95% and 93% precision, and 0.10 and 0.12 error rate for both 28 and 50 queries.

P.333 Multimodal neuroplastic mechanisms of lurasidone treatment in the chronic mild stress model

Today, most handheld devices including smartphones, tablets and notebooks are equipped with Wi-Fi, Bluetooth, LTE/4G radio interfaces that can allow connections to the Internet and other devices. However, given the properties changes of the radio environment and user mobility, an open question still lies in how to select the best access network interface, considering that the availability and characteristics of an access network will change in time. This paper describes a new intelligent interface selection mechanism based on analysis of contextual information obtained from the user, network environment, and device. To select the best available wireless network, the mechanism, named as CANS (Context-Aware Network Selection), allows for dynamic decision-making during the operation of a mobile device, taking into account different metrics such as price, local network capabilities, user preferences, and the mobile terminal capabilities. The evaluation of the proposed mechanism in a real environment shows that the adoption of selection strategies enables the best exploitation of the advantages on multiple access technologies, achieving a reduction in device power consumption and financial cost.

Enhancing sentient embodied conversational agents with machine learning

Within the area of intelligent User Interfaces, we propose what we call Sentient Embodied Conversational Agents (SECAs): virtual characters able to engage users in complex conversations and to incorporate sentient capabilities similar to the ones humans have. This paper introduces SECAs together with their architecture and a publicly available software library that facilitates their inclusion in applications –such as educational and elder-care– requiring proactive and sensitive agent behaviours. In fact, we illustrate our proposal with a virtual tutor embedded in an educational application for children. The evaluation was performed in two stages: firstly, we tested a version with basic textual processing capabilities; and secondly, we evaluated a SECA with Machine-Learning-enhanced user understanding capabilities. The results show a significant improvement in users’ perception of the agent’s understanding capability. Indeed, the Response Error Rate decreased from 22.31% to 11.46% using ML techniques. Moreover, 99.33% of the participants consider the global experience of talking with the virtual tutor with sentient capabilities to be satisfactory.

Methodology for developing an intelligent user interface for educational publications in the e-learning system

The article analyzes special features and principles of constructing the user interface and substantiates the authors methodical approach to the development of the intellectual user interface of educational publications in the e-learning system. Besides, the “user interface” concept is analyzed and types of user interfaces are considered. For representatives of each representative system, the article gives a list of typical ways of perceiving environmental information that should be considered in developing the user interface of educational publications. The main features of procedurally-oriented and object-oriented types of user interface are considered and their main parameters are presented. The implementation of an innovative component in the development interface of educational publications in the e-learning system is proposed to be implemented by adding the properties of adaptability to the user interface. Provisions are determined that define the user interface concept, on the basis of which the principles of constructing adaptive interfaces are formed. The basic principles of visual design of mental maps of electronic educational publications for the e-learning system are offered. The main features provided by the mental map are presented in the form of a visual diagram. The didactic interface of the developed e-learning edition is considered and the scheme of the user and publication interaction is given. The focus group method evaluates the user interface quality of the created e-learning publication.

Intelligent interaction interface for medical emergencies: Application to mobile hypoglycemia management

Abstract Among the widely available information technologies for remote health care, emergency care, and more specifically self-care in urgent situations (through automated, protocol-based intervention), has not been considered to date. Urgent care is particularly difficult due to the individual transient and dynamic patient context; the design-for-all approach currently being implemented does not consider the varying manifestation of physical states and cognitive disabilities. Therefore, the objective was to design and integrate into a remote health care platform, an intelligent user interface scheme that adapts in real time to the clinically urgent patient condition. The current study presents a mobile implementation, targeting diabetic hypoglycemia treatment. Continuous physiological data from medical-grade wearable sensors, and results from customized cognitive exercises evaluating the corresponding common emergency symptoms are used to define the patient state. This state feeds the adaptation rules and determines the most appropriate interaction interface delivering the intervention instructions. The designed adaptations prioritize the incorporation of multimodal interfaces (including voice and facial recognition and interactions), with the goal of augmenting patient-technology information exchange, thus providing more efficient and effective treatment delivery. This application is being validated with clinical partners in endocrinology.

Модели интеллектуальных интерфейсов поисковых информационных систем

Currently, there are many models of intelligent interfaces of search information systems for search using natural for the user modalities of speech, face, gestures and their recognition. In this article, on the example of the intelligent interface of the unmanned aerial vehicle, two models of user modality recognition will be studied, these are hidden markov models and bayesian network, these models will have to recognize the hand gestures of the operator of the unmanned aerial vehicle.

Special Issue on Highlights of ACM Intelligent User Interface (IUI) 2018

Special Issue on Highlights of ACM Intelligent User Interface (IUI) 2018

MAIA (Medical Artificial Intelligence Assistant) as interface for a new cancer healthcare integrative platform.

25 Background: Cancer healthcare systems are an example of inequity and waste in low and middle income countries. Access to high quality cancer pathways focused in early diagnosis, molecular biology, proper staging and evidence based treatments are scarce and the patient`s care experience is dramatic and difficult in a majority of cases. There are no integrative healthcare models based on new technologies that improve outcomes and make more comfortable and expeditious all the patient and physician´s journey in cancer. Methods: Our team developed and trained a talkbot called MAIA (Medical Artificial Intelligence Assistant) using an algorithmic translation of medical language focused in the state or art for non small cell lung cancer. Our clinical team developed decision trees in diagnosis, staging, medical and surgical treatment and molecular biology that were incorporated in a virtual platform and then integrated onto a narrow artificial intelligence bot brain using neural networks with the proposal of generate clinical support to the physician and create a standard text using the verbal information captured in the oncological consultation and integrated images (reports) through a image edition software and then create a unique medical record without using computers by the physician. MAIA also can create medical treatment choices in first line of treatment and create alerts and alarms through an own app (MAIA Hip). Results: Our proof of concept was released in video at this link https://drive.google.com/file/d/12YtiOkhfEmIsL2bFp9T3QyfHHWxBvvKU/view?ts=5ceec096 Due to our decision trees size we can´t upload them, but are available for presentation. Conclusions: A talkbot trained as a narrow artificial intelligence interface for an integrative cancer healthcare platform (HIP) is possible through the clinical and engineer integration of languages using a neural network method and other software tools. MAIA is for now a patient and physician experience improvement, but the real impact will be in the data standarization and acquisition for advanced analytics. The final scope of MAIA HIP will be a blockchain for cancer in low and middle income countries.

Intelligent and Analog CMOS ASIC Development of Angular Rate Error Compensation for MEMS Gyroscope

Background & Objective: MEMS-based gyroscopes are used in angular rate detection where precision is an important parameter; however, gyroscope output is limited by angular rate error. For minimizing these types of non-idealities, conventional external hardware-based analog or digital circuits have limitations for using in compact applications. CMOS analog ASIC for angular rate error compensation is necessary as both MEMS-CMOS technologies are supplementary and compatible. Method: In this paper, the output of MEMS gyroscope is taken as input for the compensation circuit which results in compensated angular rate. ANN is used in intelligent compensation circuit for error reduction in which offline data is trained and minimum optimum error of MSE of 1.72e-4 is achieved. ANN uses tanh sigmoidal activation function and back propagation trained MLP model with three neurons in the hidden layer. The equivalent ANN is implemented by CMOS ASIC where each neuron is implemented using Gilbert multiplier cell, differential analog adder, and differential amplifier as tanh sigmoidal circuit using OrCAD-PSpice 10.5 with 0.35 μ m technology. These blocks consist of differential configuration which has the capability of common mode interference rejection as noise becomes comparable at lower values of input analog signal. The entire ASIC consumes 77.8 mW of power which is far less and compact in size as compared to available external hardware interface circuits. Result and Conclusion: MEMS gyroscope with proposed analog ASIC becomes smart sensor with ANN based intelligent interface circuit. The proposed compensation cum interface circuit gives the average angular rate error of 1.91% in the range of minimum 0% to maximum 27% leading to improved accuracy.

Intelligent user interface design of application programs

The modern software is used in all areas of human activity. Application programs allows users to carry out the professional activity at the new, better level. The most important component of any application is the interface on which not only specialist productivity depends, but also quality of the performed work. As the contingent of modern users is very different, it is reasonable to develop the software and its interface part taking into account features of target audience. Use of elements of artificial intelligence at design of application programs will allow to consider features of training of users as much as possible. Creation of adaptive interfaces is caused by high growth rates of functionality of modern program systems, need of simplification of their operation and also to reduction of requirements to the professional level of users. In article the technique of development of the adaptive interface on the basis of individual characteristics of users and also their emotional status is described. Users were divided into five groups: the beginner, normal, confident, qualified and the administrator. Key parameters of individual users characteristics and also their possible emotional states are revealed. The automated system which can create groups based on the analysis of characteristics of users and their emotional state is developed, each group is provided by the adapted prototype of the interface of the application program.

Features of operation of photovoltaic plants as a supplementary source of electricity for non-traction consumers of railway electric mains

Purpose. To determine the features of operation of photovoltaic stations as а supplementary source of electricity for non-traction consumers of railway power grids. The research methodology is based on modern methods of computational mathematics, statistics and information analysis using modern computer technology. Findings. The authors analyze the current prerequisites for the use of electricity obtained from non-traditional sources (photovoltaic stations) to supply non-traction consumers of railway power grids. The nature of the intensity of solar radiation was clarified due to meteorological observations for 2018, recorded using a SMIR pyranometer from KIRP & ZONEN, which is specially designed to record the flow of solar energy falling on a flat surface from the sun and sky in the wavelength range from 300 to 3000 nanometers (Nm), which has an intelligent interface, in the city of Vasylivka, Zaporizhia region with an interval of minutes. The total number of values was about 25,000. The data obtained are as follows: the lowest intensity of solar radiation during 2018 was 400 W / m2, and the highest - 1000 W / m2. The calculation of the choice of photovoltaic panels type PV-MLV 250 NS with a maximum power of 250 W for the completion of a specific photovoltaic station for installation in the specified region. The authors conclude that in order to provide reliable energy supply to non-traction consumers of railway power grids during the day from autonomous solar power plants, the latter must be provided with electricity (storage batteries) in quantities exceeding the required load by about 1.7 times. The originality is that the use of renewable energy sources in the power supply systems of non-traction consumers of railway transport, in particular photovoltaic installations, is proposed. Practical implications. Introduction of photovoltaic stations as a supplementary source of electricity for non-traction consumers of railway power grids in order to minimize electricity costs. Keywords: renewable energy sources, quality of electric energy, photovoltaic plant, power supply networks of railway transport, non-traction consumers of railway electric networks, electricity production, solar radiation intensity, storage batteries.

Segmented convolutional gated recurrent neural networks for human activity recognition in ultra-wideband radar

The automatic detection and recognition of human activities are valuable for physical security, gaming, and intelligent interface. Compared to an optical recognition system, radar is more robust to variations in lighting conditions and occlusions. The centimeter-wave ultra-wideband radar can even track human motion when the target is fully occluded from it. In this work, we propose a neural network architecture, namely segmented convolutional gated recurrent neural network (SCGRNN), to recognize human activities based on micro-Doppler spectrograms measured by the ultra-wideband radar. Unlike most existing approaches which treat the micro-Doppler spectrograms the same way as natural images, we extract segmented features of spectrograms via convolution operation and encode the feature maps along the time axis with gated recurrent units. Taking advantage of regularities in both the time and Doppler frequency domains in this way, our model can detect activities with arbitrary lengths. The experiments show that our method outperforms existing models in fine temporal resolution, noise robustness, and generalization performance. The radar system can thus recognize human behavior when visible light is blocked by opaque objects.

Intelligent control interfaces developed on versatile portable intelligent platform in order to improving autonomous navigation robots performances

The paper presents Intelligent Control Interfaces (ICIs) for real-time control for terrestrial mobile robots or unmanned aerial robots in order to improve the navigation performances. Intelligent control interfaces using advanced control strategies adapted to robot environment are presented, implemented through IT & C techniques with fast processing and real-time communications in order to develop a versatile, intelligent and portable VIPRO Platform with behavior of e-learning platform, which allows achievement inter-academic research networks and building new intelligent vectors robots. Implementation of ICIs laws in the intelligent real time control interfaces depends on the particular circumstances of the characteristics model used and the exact definition of optimization problem. The results led to the development of the ICI interfaces through image analysis using Images Operation Sampling & Quantization (IOSQ).

Special Issue on Highlights of ACM Intelligent User Interface (IUI) 2017

Special Issue on Highlights of ACM Intelligent User Interface (IUI) 2017

Human-computer interaction and artificial intelligence: from competition to integration

Human-computer interaction and artificial intelligence (AI) are the two most important information technologies in the era of intelligent information. Through the developing histories of human computer interaction and AI, it was found that the relation between human-computer interaction and AI has changed from a competitive (in the past) to mutual promotion (in the present) state. Some intelligent user interface combining both human-computer interaction and AI techniques has gradually become commercial application from the research perspective, such as natural gesture interaction, emotional computing, and voice dialog system. This paper reviews the development process of human-computer interaction and summarizes its relation with AI. Human-computer interaction provides research ideas for AI; moreover, human intelligence drives the development of human-computer interaction and human-machine interaction. In the future, we anticipate that the present mutual promotion and driving relation existing between AI and human-machine interaction will continue, and will even increase.