CATA2022: Papers with Abstracts

Abstract. Trigger-Action-Programming (TAP) is a most widely used End User Development (EUD) tool for Internet of Things (IoT). However, end users often cannot differentiate between distinct kinds of triggers and actions. They also make erroneous combinations of those. Consequently, inconsistencies, and bugs are exhibited in behavior of IoT objects. To resolve this issue, end users need to be guided to interpret different triggers, actions and their combinations effectively. In this case, precise representation of temporal and contextual aspects of triggers and actions can assist. Moreover, vast and growing numbers of IoT objects as well as increasing numbers customized rules create scalability issues. To address these drawbacks, this paper has proposed an upper level ontology named as Trigger Action Ontology (TAO) that provides meta rule semantics for TAP. The contribution of proposed ontology specification is to present formal semantics of temporal and contextual aspects of triggers and actions. Further, the ontology is implemented in Protégé. In addition, the expressiveness of the proposed ontology is illustrated using a suitable case study.

Abstract. Artificial intelligence has become the mainstream technology. Automatic vacuum clean- ers or robot vacuums change the field of vacuum cleaners with an involvement of an au- tomation, which is a technology that makes people’s daily life easier and more economical. Robot vacuums were invented by the Massachusetts Institute of Technology in 1990. To- day, robot vacuums are successful and have many users all around the world. More than 2.5 million families live in 60 countries use them. However, a question that is still being asked about robot vacuum is the efficiency of room coverage and the ability to remem- ber the redundant areas that have already been cleaned. The answers to these questions are unclear, as manufacturers do not reveal the algorithms that are learned by robots, or sometimes they just partially did, due to business reasons. This study was proposed in response to the above questions by using our mobile application for tracking and recording actual geolocations of the robot walking across various points of the room by extracting the real geolocation data from satellites consisting of a latitude and a longitude under multiple different room conditions. Once the robot has cleaned throughout the room, the applica- tion reported all areas that the robot has cleaned for analysis purpose. We presented the actual route map, the coverage area map, and the duplicate area map of the robot that potentially led the further understanding of robot vacuum’s effectiveness.

Abstract. Quality human resources are the most important issue for the success of a company as almost all of the companies are today knowledge driven and use information technology to operate their systems. All these companies have HR managers to recruit the people to match their requirements as per required skills, experience etc. In order to meet the requirement of skilled workforce companies recruit fresher candidates across the country from different educational Institutions and obviously it is a very complex process. The complexity is manifold for different rounds of recruitment process, involvement of human resources, travel etc. and incur huge cost too. The traditional methods of recruitment are On-Campus (where the Organization visits the educational Institutes) and Off-campus (Candidates visit the office of the recruiter). Both of these models are costly and have many complexities. This research work proposes a new service based model that will reduce the complexity of the existing recruitment process, dynamic in nature (helps in quick recruitment) and saves the cost drastically. The proposed model analyzes the skill level of the applicants from all possible perspectives that helps the companies to find out suitable resources for them. A real life case study is also shown to depict the cost effectiveness of the proposed model.

Abstract. In recent days, the uses of Internet of Things (IoT) applications have been growing enormously. IoT considers the integration of business process models or process execution with resources of intelligent devices. The concept of process meta store (PMS) [1] optimizes the interactions between IoT devices and business processes. However, the mechanism of PMS highly depends on the meta-information of the system, associated devices, and interactions among them. In this context, a novel semantics of meta- information of process store (MIPS) for IoT-based applications is proposed in this paper. The semantics of various MIPS elements and their relationships are described using a class diagram. Further, a B+ tree-based indexing approach for the MIPS semantic is presented for efficient searching of meta-information. The semantics of MIPS are illustrated using the case study related to the clinical decision support system (CDSS). Moreover, a detailed comparative analysis has been carried out to show the expressiveness of MIPS.

Abstract. Ensuring the quality is essential for a successful Software System. Software systems need to be tested in every stage of the Software Development Life Cycle (SDLC) irrespective of the type of software being developed. If a software bug remains undetected in the early phase of the SDLC, it becomes harder to fix it at a later stage and becomes very costly. The application of machine learning in Software Quality Assurance and Testing can help testers in the testing process, including the early detection and prediction of a software bug. However, employing machine learning techniques brings new challenges to testing and quality assurance. Machine Learning (ML) uses Artificial Intelligence (AI) techniques that focus on a given dataset to find any trend present in the data. It has been observed that some software testing activities can, in fact, be represented as a learning problem. Thus, ML can be used as an efficient tool to automate software- testing activities, especially when the software system becomes very complex. This survey aims to study and summarize the application of machine learning on software quality assurance and testing in a chronological manner by selecting from articles published in the last twenty-six years or so.

Abstract. Technological advances have increased the potential for wearable augmented reality (AR) devices. More applications are being ported for this platform with this development, and not all are suited for AR. After the initial novelty fades, users often find the application gimmicky and unwieldy, causing them to become incredulous towards AR’s potential. Developers need to ensure that the application emphasizes elements that are unique to AR for a successful port. This paper analyzes the human- cursor paradigm to derive a set of requirements and integrate them into an application. With this integration, an application that has no exclusive need of the AR platform can be redesigned to take advantage of AR’s capability making it more valuable to the user. This emphasis will promote targeted development of meaningful applications further expanding the augmented reality platform.

Abstract. Anomalies in network traffic are usually detected by measuring unexpected deviation from what constitutes a baseline. Several statistical techniques have been proposed to create baselines and measure deviation. However, simply looking at traffic volume to find anomalous deviation may result in increased false positives. Traffic feature distributions need to be created, and deviations need to be measured for these features. An effective approach to finding anomalous deviations starts with entropy analysis on these features. In this paper, we presented an initial entropy analysis on an industrial control system network using selected features with datasets obtained from an HVAC system. We started with the fundamental question: whether a preliminary entropy analysis on Modbus-over-TCP data using only a few TCP/IP features without going into the Modbus traffic itself gives us information about an anomaly in the network. We acknowledge that the initial entropy analysis provides only a starting point that would lead to several questions and investigating relevant issues resulting in an optimal system design and implementation. *

Abstract. TheThe driver safety is given an utmost importance in the Transportation system. Road safety is mostly dependent on the all driver’s on road and their behavior. Aggressive driving behavior such as speed, braking, accelerations etc are some of the major factors contributing to the safety which can jeopardize human lives if a fatality occurs. To improve the safety of drivers and other road users, we proposed a framework which ranks and re- wards the driver’s behavior for each day in crypto tokens. Existing frameworks emphasizes on analyzing or ranking the behavior, however monetizing driver’s behavior will improve the driver’s discipline. A randomized simulated traffic is used to extract the both friendly and aggressive driving patterns and provide test crypto tokens based on them.

Abstract. There is a lot of uncertain and imprecise information in a real-world scenario. Graph database systems based on the graph model support crisp and precise data. This paper presents a system structure that processes fuzzy quantified queries in the context of a graph database. Fuzzy logic allows decisions to be taken more realistically. A specific form of structural quantified query is designed and demonstrated in this paper, which then can be expressed as an extension to the Neo4j Cypher query language. In addition, this research built an active rule system on top of the graph database that reacts to event occurrences automatically. This paper presents our approach of supporting temporal event handling using fuzzy active rules and fuzzy query processing over Neo4j graph database systems.

Abstract. With the increase in popularity of mobile devices for personal and business reasons, they have become even more attractive targets to malicious actors. There are many vulnerabilities with any mobile device, though some environments, features, and operating systems are at higher risk than others for certain attacks. This paper discusses such vulnerabilities, including the elements that allow them, methods of exploiting them, and one might combat attacks on mobile devices.

Abstract. Ethical hacking education prepares future information security professionals with the tools and skills to fight and prevent cybersecurity threats. Businesses, schools, governments, and individuals have an increasing concern to keep their systems, networks, and data secure from outside threats. Most information security technologies use a defensive approach to keep client’s data safe; however, ethical hacking provides one of the only proactive/aggressive methods for information security professionals to utilize. Teaching inexperienced information security professionals these aggressive tactics can be viewed as a double- edged sword. Since they are the same methods used by malicious hackers, educating new security professionals will undoubtedly educate more malicious hackers.

Abstract. Currently, many short texts are published online, especially on social media platforms. High impact events, for example, are highly commented on by users. Understanding the subjects and patterns hidden in online discussions is a very important task for contexts such as elections, natural disasters or major sporting events. However, many works of this nature use techniques that, despite showing satisfactory results, are not the most suitable when it comes to the short texts on social media and may suffer a loss in their results. Therefore, this paper presents a text mining method for messages published on social media, with a data pre-processing step and topic modeling for short texts. For this paper, we created a data set from real world tweets related to COVID-19 that is openly available1 for research purposes.

Abstract. Data security is an increasing concern, not only in cloud storage data centers but also in personal computing and memory devices. It is important to maintain the confidentiality of data at rest against ransom and theft attacks. However, securing data, in runtime, into the drives is associated with performance penalties. In this paper, a study of the performance impact for software-based self-encrypting solid-state drives is presented. This performance evaluation is conducted on the NVMe subsystem which supports encryption and decryption of the user data on an I/O command basis. Additionally, this paper demonstrates the potential of encryption and decryption acceleration for data storage in self-encrypting drives.

Abstract. We are in the golden age of AI. Developing AI software for computer games is one of the most exciting trends of today’s day and age. Recently games like Hearthstone Bat- tlegrounds have captivated millions of players due to it’s sophistication, with an infinite number of unique interactions that can occur in the game. In this research, a Monte-Carlo simulation was built to help players achieve higher ranks. This was achieved through a learned simulation which was trained against a top Hearthstone Battleground player’s historic win. In our experiment, we collected 3 data sets from strategic Hearthstone Bat- tleground games. Each data set includes 6 turns of battle phases, 42 minions for battle boards, and 22 minions for Bob’s tavern. The evaluation demonstrated that the AI assis- tant achieved better performance — loosing on average only 9.56% of turns vs 26.26% for the experienced Hearthstone Battleground players, and winning 56% vs 46.91%.

Abstract. Virtual reality (VR) is a relatively new and rapidly growing field which is becoming accessible by the larger research community as well as being commercially available for en- tertainment. Relatively cheap and commercially available head mounted displays (HMDs) are the largest reason for this increase in availability. This work uses Unity and an HMD to create a VR environment to display a 360◦video of a pre-recorded patient handoff be- tween a nurse and doctor. The VR environment went through different designs while in development. This works discusses each stage of it’s design and the unique challenges we encountered during development. This work also discusses the implementation of the user study and the visualization of collected eye tracking data.

Abstract. We present a Fourier-based machine learning technique that characterizes and detects facial emotions. The main challenging task in the development of machine learning (ML) models for classifying facial emotions is the detection of accurate emotional features from a set of training samples, and the generation of feature vectors for constructing a meaningful feature space and building ML models. In this paper, we hypothesis that the emotional features are hidden in the frequency domain; hence, they can be captured by leveraging the frequency domain and masking techniques. We also make use of the conjecture that a facial emotions are convoluted with the normal facial features and the other emotional features; however, they carry linearly separable spatial frequencies (we call computational emotional frequencies). Hence, we propose a technique by leveraging fast Fourier transform (FFT) and rectangular narrow-band frequency kernels, and the widely used Yale-Faces image dataset. We test the hypothesis using the performance scores of the random forest (RF) and the artificial neural network (ANN) classifiers as the measures to validate the effectiveness of the captured emotional frequencies. Our finding is that the computational emotional frequencies discovered by the proposed approach provides meaningful emotional features that help RF and ANN achieve a high precision scores above 93%, on average.