scholarly journals Comparing Plan Recognition Algorithms Through Standard Plan Libraries

2022 ◽  
Vol 4 ◽  
Author(s):  
Reuth Mirsky ◽  
Ran Galun ◽  
Kobi Gal ◽  
Gal Kaminka
Keyword(s):  
User Interfaces ◽  
Cyber Security ◽  
Evaluation Criteria ◽  
Computation Time ◽  
Plan Recognition ◽  
Discrete Space ◽  
Standard Representation ◽  
Recognition Process ◽  
Common Representation ◽  
Recognition Algorithms

Plan recognition deals with reasoning about the goals and execution process of an actor, given observations of its actions. It is one of the fundamental problems of AI, applicable to many domains, from user interfaces to cyber-security. Despite the prevalence of these approaches, they lack a standard representation, and have not been compared using a common testbed. This paper provides a first step towards bridging this gap by providing a standard plan library representation that can be used by hierarchical, discrete-space plan recognition and evaluation criteria to consider when comparing plan recognition algorithms. This representation is comprehensive enough to describe a variety of known plan recognition problems and can be easily used by existing algorithms in this class. We use this common representation to thoroughly compare two known approaches, represented by two algorithms, SBR and Probabilistic Hostile Agent Task Tracker (PHATT). We provide meaningful insights about the differences and abilities of these algorithms, and evaluate these insights both theoretically and empirically. We show a tradeoff between expressiveness and efficiency: SBR is usually superior to PHATT in terms of computation time and space, but at the expense of functionality and representational compactness. We also show how different properties of the plan library affect the complexity of the recognition process, regardless of the concrete algorithm used. Lastly, we show how these insights can be used to form a new algorithm that outperforms existing approaches both in terms of expressiveness and efficiency.

On quality assessment of electronic training course interfaces

2021 ◽  
pp. 11-17
Author(s):  
T. B. Larina
Keyword(s):  
User Interface ◽  
User Interfaces ◽  
Evaluation Criteria ◽  
Qualitative Evaluation ◽  
Educational Process ◽  
Educational Resources ◽  
Human Machine Interaction ◽  
Software Products ◽  
E Learning

The development of e-learning, both in distance and mixed forms, becomes especially relevant in the modern educational process. A high-quality e-learning course is developed through the efforts of two parties: the teacher, who creates the methodological content, and the programmer, who creates the electronic shell of the course. The article substantiates the importance of quality issues in the development of a user interface for electronic educational resources, since the user of an electronic course deals with the direct implementation of educational material. The indicators for assessing the quality of software products in accordance with international and Russian standards and their applicability for assessing user interfaces of electronic educational resources are analyzed. The conclusion is made about the importance of the indicator “practicality” in relation to this type of software product as an indicator of an individual evaluation of the use of a product by a certain user or circle of users. The classical methods for assessing the quality of the human-machine interaction interface and the applicability of experimental and formal methods for assessing quality are considered. The analysis of modern approaches to the design of user interfaces based on UX/UI design is given. An assessment of the requirements and criteria for assessing the user interface from the standpoint of modern design is given. The tasks and features of the UX and UI components of the design process are analyzed. The essence of the modern term “usability” as an indicator of the interface evaluation is explained, and the qualitative evaluation criteria for this indicator are considered. The concept of UX testing is given, the main stages of this process are considered. The importance of taking into account the subjective psychological factors of interface perception is substantiated. The indicators for assessing the quality of user interfaces, based on the cognitive factors of its perception by a person, are analyzed.

scholarly journals A Methodology to Evaluate Standards and Platforms within Cyber Threat Intelligence

2020 ◽  
Vol 12 (6) ◽  
pp. 108
Author(s):  
Alessandra de Melo e Silva ◽  
João José Costa Gondim ◽  
Robson de Oliveira Albuquerque ◽  
Luis Javier García Villalba
Keyword(s):  
Cyber Security ◽  
Comprehensive Evaluation ◽  
Evaluation Criteria ◽  
Evaluation Methodology ◽  
Proactive Approach ◽  
The Past ◽  
Threat Intelligence ◽  
Cyber Threat ◽  
Cyber Threat Intelligence ◽  
Selection Of

The cyber security landscape is fundamentally changing over the past years. While technology is evolving and new sophisticated applications are being developed, a new threat scenario is emerging in alarming proportions. Sophisticated threats with multi-vectored, multi-staged and polymorphic characteristics are performing complex attacks, making the processes of detection and mitigation far more complicated. Thus, organizations were encouraged to change their traditional defense models and to use and to develop new systems with a proactive approach. Such changes are necessary because the old approaches are not effective anymore to detect advanced attacks. Also, the organizations are encouraged to develop the ability to respond to incidents in real-time using complex threat intelligence platforms. However, since the field is growing rapidly, today Cyber Threat Intelligence concept lacks a consistent definition and a heterogeneous market has emerged, including diverse systems and tools, with different capabilities and goals. This work aims to provide a comprehensive evaluation methodology of threat intelligence standards and cyber threat intelligence platforms. The proposed methodology is based on the selection of the most relevant candidates to establish the evaluation criteria. In addition, this work studies the Cyber Threat Intelligence ecosystem and Threat Intelligence standards and platforms existing in state-of-the-art.

scholarly journals Application of Artificial Intelligence in User Interfaces Design for Cyber Security Threat Modeling

2021 ◽  
Author(s):  
Jide Ebenezer Taiwo Akinsola ◽  
Samuel Akinseinde ◽  
Olamide Kalesanwo ◽  
Moruf Adeagbo ◽  
Kayode Oladapo ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
User Interface ◽  
User Interfaces ◽  
Cyber Security ◽  
Security Threat ◽  
Human Machine Interaction ◽  
Daily Lives ◽  
Threat Modeling ◽  
Ui Design ◽  
Intelligent User Interface

In recent years, Cyber Security threat modeling has been discovered to have the capacity of combatting and mitigating against online threats. In order to minimize the associated risk, these threats need to be modelled with appropriate Intelligent User Interface (IUI) design and consequently the development and evaluation of threat metrics. Artificial Intelligence (AI) has revolutionized every facet of our daily lives and building a responsive Cyber Security Threat Model requires an IUI. The current threat models lack IUI, hence they cannot deliver convenience and efficiency. However, as the User Interface (UI) functionalities and User Experience (UX) continue to increase and deliver more astonishing possibilities, the present threat models lack the predictability capacity thus Machine Learning paradigms must be incorporated. Meanwhile, this deficiency can only be handled through AI-enabled UI that utilizes baseline principles in the design of interfaces for effective Human-Machine Interaction (HMI) with lasting UX. IUI helps developers or designers enhance flexibility, usability, and the relevance of the interaction to improving communication between computer and human. Baseline principles must be applied for developing threat models that will ensure fascinating UI-UX. Application of AI in UI design for Cyber Security Threat Modeling brings about reduction in critical design time and ensures the development of better threat modeling applications and solutions.

Communication Model for the User Interface of a Shape Conceptualization System

2001 ◽  
Author(s):  
György Kuczogi ◽  
Imre Horváth ◽  
Joris S. M. Vergeest ◽  
Zoltán Rusák
Keyword(s):  
Information Theory ◽  
User Interfaces ◽  
Hand Movement ◽  
Evaluation Criteria ◽  
Simplified Model ◽  
Communication Model ◽  
Cad Systems ◽  
Pilot Implementation ◽  
Machine Communication ◽  
Future Work

Abstract It is commonly recognized that the user interfaces of recent CAD systems do not effectively support creative man-machine communication in the conceptual phase of the design process. At the same time, speech, hand sketching, claying, etc. are appropriate tools for communicating ideas among designers. The inherent vagueness of verbalism and hand movement is both tolerable and requested for the human-computer interaction, as well. However, the natural format of communication may also permit unnecessary uncertainty, which can easily lead to significant failures in the understanding. The aim of the paper is to investigate how we can find those particular formats of natural communication that offer the benefit of communication of vague concepts and help to prevent failures of understanding. We have decided to use a simplified model of Gitt’s [5] information theory. We have selected three evaluation criteria (i.e., effectiveness, efficiency, and comfort) to facilitate the ranking of different ways of communication for a particular purpose. As a future work, we intend to accomplish the evaluation prove the evaluation by pilot implementation.

Automated areas of interest analysis for usability studies of tangible screen-based user interfaces using mobile eye tracking

2020 ◽  
Vol 34 (4) ◽  
pp. 505-514
Author(s):  
M. Batliner ◽  
S. Hess ◽  
C. Ehrlich-Adám ◽  
Q. Lohmeyer ◽  
M. Meboldt
Keyword(s):  
Eye Tracking ◽  
User Interfaces ◽  
Computation Time ◽  
Human Machine Interaction ◽  
Automated Mapping ◽  
Wide Range ◽  
Break Even Point ◽  
Areas Of Interest ◽  
First Time ◽  
Mobile Eye Tracking

AbstractThe user's gaze can provide important information for human–machine interaction, but the analysis of manual gaze data is extremely time-consuming, inhibiting wide adoption in usability studies. Existing methods for automated areas of interest (AOI) analysis cannot be applied to tangible products with a screen-based user interface (UI), which have become ubiquitous in everyday life. The objective of this paper is to present and evaluate a method to automatically map the user's gaze to dynamic AOIs on tangible screen-based UIs based on computer vision and deep learning. This paper presents an algorithm for automated Dynamic AOI Mapping (aDAM), which allows the automated mapping of gaze data recorded with mobile eye tracking to the predefined AOIs on tangible screen-based UIs. The evaluation of the algorithm is performed using two medical devices, which represent two extreme examples of tangible screen-based UIs. The different elements of aDAM are examined for accuracy and robustness, as well as the time saved compared to manual mapping. The break-even point for an analyst's effort for aDAM compared to manual analysis is found to be 8.9 min gaze data time. The accuracy and robustness of both the automated gaze mapping and the screen matching indicate that aDAM can be applied to a wide range of products. aDAM allows, for the first time, automated AOI analysis of tangible screen-based UIs with AOIs that dynamically change over time. The algorithm requires some additional initial input for the setup and training, but analyzed gaze data duration and effort is only determined by computation time and does not require any additional manual work thereafter. The efficiency of the approach has the potential for a broader adoption of mobile eye tracking in usability testing for the development of new products and may contribute to a more data-driven usability engineering process in the future.

scholarly journals Human Activities and Postures Recognition: From Inertial Measurements to Quaternion-Based Approaches

Sensors ◽  
2019 ◽  
Vol 19 (19) ◽  
pp. 4058 ◽  
Author(s):  
Zmitri ◽  
Fourati ◽  
Vuillerme
Keyword(s):  
Inertial Sensors ◽  
Magnetic Measurement ◽  
Recognition Task ◽  
Computation Time ◽  
Left Thigh ◽  
K Nearest Neighbors ◽  
Raw Data ◽  
Recognition Process ◽  
Measurement Units ◽  
Inertial Measurements

This paper presents two approaches to assess the effect of the number of inertial sensors and their location placements on recognition of human postures and activities. Inertial and Magnetic Measurement Units (IMMUs)—which consist of a triad of three-axis accelerometer, three-axis gyroscope, and three-axis magnetometer sensors—are used in this work. Five IMMUs are initially used and attached to different body segments. Placements of up to three IMMUs are then considered: back, left foot, and left thigh. The subspace k-nearest neighbors (KNN) classifier is used to achieve the supervised learning process and the recognition task. In a first approach, we feed raw data from three-axis accelerometer and three-axis gyroscope into the classifier without any filtering or pre-processing, unlike what is usually reported in the state-of-the-art where statistical features were computed instead. Results show the efficiency of this method for the recognition of the studied activities and postures. With the proposed algorithm, more than 80% of the activities and postures are correctly classified using one IMMU, placed on the lower back, left thigh, or left foot location, and more than 90% when combining all three placements. In a second approach, we extract attitude, in term of quaternion, from IMMUs in order to more precisely achieve the recognition process. The obtained accuracy results are compared to those obtained when only raw data is exploited. Results show that the use of attitude significantly improves the performance of the classifier, especially for certain specific activities. In that case, it was further shown that using a smaller number of features, with quaternion, in the recognition process leads to a lower computation time and better accuracy.

scholarly journals The Impact of Information Technology on Industrial Automation – A Critical Evaluation

2018 ◽  
Vol 12 (2) ◽  
pp. 142
Author(s):  
Joshy George ◽  
Stanislaw Paul MAJ
Keyword(s):  
Information Technology ◽  
Integrated Circuits ◽  
User Interfaces ◽  
Cyber Security ◽  
First Generation ◽  
Critical Evaluation ◽  
Modern Society ◽  
Industrial Automation ◽  
Technical Developments ◽  
The Impact

Information Technology (IT) now impacts on all aspects of modern society (personal, commercial and industrial). The advances in IT may broadly be categorized into the following subsets of technologies: integrated circuits, communications, software engineering and Graphical User Interfaces. In the context of Industrial Automation (IA) it can be seen that some communication protocols, for example Modbus which was first introduced in the 1970’s, has under gone numerous updates driven by IT developments with associated considerable improvements in performance and capability. By contrast some, for example HART which was first introduced in the 1980’s, whilst it has undergone revisions it does not fully utilize the capabilities that IT can provide. For higher level IA systems they can be divided into four generations which can each be associated with specific IT developments. The first generation IA system is based on simple Proportional, Integral and Derivative (PID) controllers and ruggedized microprocessor based Programmable Logic Controllers (PLC). IA systems expanded in both complexity and scope through these generations to include Distributed Control Systems (DCS’s) and Supervisory Control and Data Acquisition (SCADA). The fifth generation of IA systems may be associated with IT developments both on and over the horizon that include: Cloud Computing, Cyber Security and Internet of Things. Responses to these technologies include: General Electric (GE) Predix and Siemens MindSphere. Regardless of how IA is categorized there can be no doubt that IT is responsible for major technical developments – a process that is likely to continue. 

Zone-Wise Segmentation and Lexicon-Driven Recognition for Printed Myanmar Characters

2018 ◽  
pp. 162-180 ◽  
Author(s):  
Chit San Lwin ◽  
Xiangqian Wu
Keyword(s):  
Markov Model ◽  
Hidden Markov Model ◽  
Hidden Markov ◽  
Nearest Neighbors ◽  
Structural Features ◽  
The Other ◽  
Self Organization ◽  
K Nearest Neighbors ◽  
Recognition Process ◽  
Recognition Algorithms

This paper presents a new segmentation and recognition algorithms for Myanmar script inputted from offline printed images. Zone segmentation considers horizontal and vertical zones; it is applied to segment letters according to their roles such as primary or peripheral characters. In doing so, statistical and structural features of segmented characters are explored and exploited in recognition process. Hidden Markov model is used for recognition of primary characters while Kohonen self-organization map is used for peripheral characters. The recognized characters by each model are then combined, and finally are recognized by k-nearest neighbors algorithm with the help of lexicon is composed of all common Myanmar characters. Our OCR system for Myanmar characters tested on a dataset that approximately contains 7560 compounded characters. From the results, our system achieves higher significant results both segmentation and recognition compared to the other contemporary Myanmar OCR’s approaches.

Sign in / Sign up

Export Citation Format

Share Document