Welcome to ITCA 2021

9th International Conference of
Information Technology, Control and
Automation (ITCA 2021)

July 10~11, 2021, Toronto, Canada



Accepted Papers
Use of Analogies in Science Education, a Systematic Mapping Study

Hernandez Pedro and Espitia Edinson

ABSTRACT

This systematic mapping study consisted of tracking the scientific literature that addresses the issue of analogies as a didactic strategy in science teaching. An analogy can be understood as comparing an existing knowledge with a new knowledge to achieve a better understanding of the new knowledge as a result of the comparison of similarities; or in other words, use students own concepts to introduce new concepts using comparisons between the two. The purpose of this study was to identify, analyze, synthesize and evaluate research works that touched on this topic, with this, to have knowledge about the models of uses of analogies, most used didactic strategies, research methodologies in this field and how to evaluate the learning effectiveness of working with analogies. The methodology that was used is the systematic mapping study; Five questions were posed that guided the information tracking process. Later, the electronic documents in English for the last twenty years were traced in five databases related to the educational field. Finally, it is concluded by responding to the purpose of the study where it is evident that, broadly speaking, the research methodologies in this field are quantitative as well as qualitative, to implement analogies, resources such as images, illustrations, textual indications and audiovisual aids are used, it is usually evaluated the effectiveness of using analogies with multiple choice tests, oral tests of creating analogies by students.

KEYWORDS

Analogies, science teaching, analog model.


Automatic Computing Communication:A New Perspective Algorithm to Cognition for Automatic Computer Communication Systems

Bita Bayat, Department of Computer Engineering, Azad University, Safadasht, Tehran, Iran

ABSTRACT

The aim of this paper was to optimize the system and the method of identifying communication systems and evaluating the scope of system communication. Algorithmic technique was used to simulate the article. The name of the data set was a Mehr Bank data set in Iran with the number of connection routes of 80 cases and the prediction of 2 models (optimal and distorted). The algorithms used included a combined neural network and genetic algorithm, support vector machine (SVM). In the results of the research, we showed that in relation to the reduction of the cases of distorted route data and the increase of optimal routes, the accuracy of detecting the routes of connection to bank users in optimal routes is increasing. Using a combined neural network and genetic algorithm, the backup vector machine improves the accuracy of detecting connection paths to bank users. By recognizing the information, the system proposed in this paper can transfer less data when transferring data with the same amount. Using two types of algorithms to explain the level of accuracy and power of algorithms in identifying and monitoring the connection paths of inter-system communication. The algorithms used included a combined neural network and genetic algorithm, support vector machine (SVM). Examination of the ability of each of the hybrid algorithms The combined neural network and genetic algorithm and support vector machine (SVM) showed that in the major items of classification and identification of interconnection pathways and their identification, the neural network and genetic hybrid algorithm is more successful. And the percentage of identification and classification of this algorithm in order to identify computer communication systems was higher than the support vector machine (SVM).

KEYWORDS

Combined Neural Network and Genetics Algorithm, Support Vector Machine, Communication Systems, Connection Paths.


Automatic Data Segmentation in Human Activity Recognition

Seyed Modaresi1,2, Aomar Osmani1, Mohammadreza Razzazi2, Abdolghani Chibani3, 1Sorbonne Paris Nord University, 2Amirkabir University of Technology and Institute for Research in Fundamental Sciences (IPM), 3University Paris-Est Creteil

ABSTRACT

Internet of Things (IoT) generates a long and heterogeneous series of data. It is particularly the case with human activity recognition. Segmentation is a common bias used to divide this long (may be infinite) data stream into a set of smaller meaning-full finite segments to have a more straightforward model. It is often defined by researchers using their prior knowledge and therefore adds uncontrollable biases in their models. In this paper, we define the segmentation as a particular case of a general data-decomposition problem. Therefore, we formalise this problem as an hyperparameter in order to control the added biases and to optimize the segmentation process for a given task to solve. The impact of the biases should be described and evaluated in the data decomposition step, the problem resolution (ML) step, and in the composition (the connection between ML results, segments and the global problem results) step. In addition, our formalism leads to select dynamically an appropriate segmentation method independently as an hyper-parameter from the considered application that reduces, by the way, the implicit added biases. Intensive experiments on several public datasets show the effectiveness of this original approach.

KEYWORDS

Activity Recognition, Segmentation, Data-Decomposition, Complex Event Recognition, IoT.


A System for Supporting Anomaly Detection in Government Data using Multiple Classifiers

Rafael A. Spíndola and Tiago M. U. Araújo, Computer Center, Federal University of Paraiba, João Pessoa, Brazil

ABSTRACT

With increasing amounts of data to be analyzed and interpreted, Anomaly Detection emerges as one of the areas of great impact in the context of Data Mining. Its applications extend to the most diverse fields of human activity, notably in medicine, administration, information science, economics and computing. In this work, we propose a support system for detecting aberrant events in stationary databases from Public Administration. The solution combines multiple supervised and unsupervised detection algorithms (OCSVM, LOF, CBLOF, HBOS, KNN, IForest and Robust Covariance) to classify events as anomalies. The results showed that, of the total events returned by the solution, 91.61% +/- 1.66% of them were correctly identified as outliers. Therefore, there are indications that the proposed solution has the potential to contribute to government audit support activities, as well as to management and decisionmaking processes, these arising from the interpretation of the phenomena present in the data.

KEYWORDS

Anomaly detection, Outlier detection, (un)supervised learning, data mining.


Manufacturers, AI Models and Machine Learning, Value Chains, and 5th Generation Wireless Networks

Robert B. Cohen, Economic Strategy Institute, Washington, D.C, USA

ABSTRACT

When AI models and machine learning are fully interconnected in factories using 5th Generation wireless communications, firms achieve significant gains over what they obtained from their initial, digital efforts. Firms enhance their value chains by building smart factories and connecting nearly all manufacturing processes to machine learning and AI models that analyze data rapidly. Next, they take advantage of network effects to derive even larger benefits inside their production operations and in their supply chains. In both phases, the adoption of 5th Generation wireless in plants ramps up firms’ abilities to interconnect their digital systems. Once the interconnected systems exist, firms exploit network effectsto create“knowledge synthesis” or knowledge platforms to consolidate insights gained from optimizing many machines and processes. Using “knowledge synthesis”, firms can transfer knowledge from one group of equipment to another that is not optimized. Theresult is that firms are far more flexible and scalable.

KEYWORDS

Digital Firms, Value Chains, Smart Factories, Manufacturing Processes, Knowledge Synthesis.


Pseudo examples by noisy decoder and release of UrduMNIST dataset

Wisal Khan1, Teerath Kumar2, Waqas Ahmad1, Bin Luo1, Ali Kashif Basheer3, Ejaz Ahmed4, Waseem Shahzad4, 1School of Computer and Technology, Anhui University, Hefei 230039, Peoples Republic of China, 2Kyung Hee University, South Korea, 3Department of Computing and Mathematics, Manchester Metropolitan University, Manchester, UK & School of Electrical Engineering and Computer Science, National University of Science and Technology (NUST), Islamabad, Pakistan, 4National University of Computer and Emerging Sciences, Islamabad Pakistan

ABSTRACT

Pseudo examples generation has shown an impressive performance on image classification tasks. Pseudo examples generation is useful when we have data in a limited quantity used for semi-supervised learning or few-shot learning. Previous work used autoencoder to improve the classification performance for semi-supervised learning. A Single autoencoder can generate confusing pseudo examples that degrade the performance. To address this issue, we propose a unique way of pseudo examples generation using only generator (decoder) for each class separately, that is effective for both semi-supervised learning and few-shot learning. In our approach, the decoder is trained for each class sample using random noise, and N samples are generated using the trained decoder. Our generator based approach outperforms previous semi-supervised learning and few-shot learning approaches. Secondly, we are the first to release the UrduMNIST dataset consists of 100000 images, including 80000 training and 20000 test images collected through three different methods for diversity purposes. We also check our methods effectiveness on the UrduMNIST dataset by using semi-supervised learning with absolute average improvement of 3.042 accuracy and few-shot learning with absolute average improvement of 1.5 accuracy. Both learning’s are used with a different number of examples.

KEYWORDS

Semi Supervised Learning, Few Shot Learning, Encoder-Decoder, UrduMNIST Dataset.


An Object Detection Navigator to Assist the Visually Impaired using Artificial Intelligence and Computer Vision

Ethan Wu1, Jonathan Sahagun2, Yu Sun3, 1Bellflower, CA 90706, 2California State University, Los Angeles, Los Angeles, CA, 90032, 3California State Polytechnic University, Pomona, CA, 91768

ABSTRACT

The advent and worldwide adoption of smartphones has enriched the lives of many people. However, one particular group--the visually impaired--still need specific apps to help them with their daily lives. Thus, I’m developing this Smart app to specifically help the visually-impaired. Specifically, I hope to integrate the functions of Google Maps into the Smart App. While Google Maps functions well as a GPS for the average person without any impairment, I’m adding additional features to the Smart app so that it would guide the eye-sight impaired. For example, I will use the camera of the Smartphone to guide the user such that it would take the user to the desired destination. Thus, using the inherent functions (camera) of a phone, the Smart app can gently and safely guide any sight-impaired person to a predetermined destination by walking. One can think of Smart app as an improvement upon Google Maps -- for the visually impaired.

KEYWORDS

Object detection, Google Maps, iOS, Android.


Cross-Modal Perception in Kirundi

Emmanuella Ahishakiye, Department of English, Institute for Applied Pedagogy- University of Burundi, Faculty of Languages, Arts and Translation- University of Liège

ABSTRACT

Languages do not always use specific perception words to refer to specific senses. A word from one sense can metaphorically express another physical perception meaning. For Kirundi, findings from a corpus-based analysis revealed a cross-modal polysemy and a bidirectional hierarchy between higher and lower senses. The attested multisensory expression of auditory verb kwûmva ‘hear’ allows us to reduce sense modalities to two –vision and audition. Moreover, the use of synesthetic metaphor (e.g. kwûmva akamōto ‘lit:hear a smell’/ ururirimbo ruryoshe ‘lit:a tasty song’/ururirimbo ruhimbaye ‘lit:a pleasant song) does not only show that lower senses can be used to express higher senses, but also that Kirundi considers feelings and emotions as part of the perception system, i.e., there is a sensation-emotion continuum. Kirundi Speakers can express both internal and external perceptions through auditory experience verb (e.g.; kwûmva inzara ‘lit: hear hunger’, kwûmva umunêzēro ‘lit: hear happiness’, kwûmva ingoma ‘lit: hear beats of drums’).

KEYWORDS

Sense Modality, Kirundi, cross-modal perception, lexical semantics, synaesthetic metaphor.


Aspects of Meaning by Collocation and the Degree of Collocability in Hausa Fixed Expressions

Ali Usman Umar*, Department of Nigerian Languages, Federal University of Lafia and TijjaniShehuAlmajir, PhD., Department of Linguistics and Foreign Languages, Bayero University, Kano

ABSTRACT

This paper provides an account for collocational behaviour of Hausa certain fixed expressions withrespect to their aspects of collocative meaning and degree of collocability. Collocations are ubiquitous in everyday language communication, as a result of which is so substantial that language users need to take their pervasive practice into consideration as they shouldknow when and why to be processing such collocational information. It is obvious that meaning, context and culture are closely intertwinedforegrounding with which the formation for the background knowledge ofhuge collocational information are institutionalized. The research is based on empirical method for data justification and the same data was analysed using J. R. Firth’s (1957a, 1968) contextualism as its theoretical framework. In the final analysis, the paperrationalized that the collocative meaning of the collocating words could be determined in either in abstraction or literal meaning. And also the reason why words collocate is because of their meaning relations, context of use, mutual expectancy, and cultural norms. Another thing which rendered the collocational behaviour in the language more accessible, interesting, and worthwhile is the degree of collocability.

KEYWORDS

Collocations, collocability, fixed expressions, Hausa, Meaning.


Concept of Powerlessness and Cultural Estrangement in the Personal Narratives of the Crimea Inhabitants

Svetlana Kucherenko1 and Tatiana Pavliuk2, 1Department of Psychology V.I. Vernadsky Crimean Federal University, Yalta, Crimea, 2Department of Humanities V.I. Vernadsky Crimean Federal University, Armiansk, Crimea

ABSTRACT

This article studies the theme of social-psychological alienation in personal narratives of inhabitants of the Crimea with emotionally-negative type predomination. Metaphorical narrative of “Adventures of Windock, Cloudette and Plumelet” by T. Pavliuk is analyzed; the metaphors of the futility of efforts (rains in the desert) and helplessness (passivity) are identified through the narrative analysis. Main ecopsychological dispositions in personal narratives of the Crimean people are given according to P.V. Lushin concept: home, family; enemy; indifference of others and the indignation at this. Ways of narratives’ deconstruction are put forward based on the category of multiple possibilities: “can be” instead of “should be”. The presence of the enemy’s ecopsychological disposition in the narratives is unproductive to overcome the existential difficulties associated with the change of the socio-political situation in the Crimea after March 18, 2014. Transition to a new self-conception and the place in society can occur through overcoming indifference to their own fate and to the closest people.

KEYWORDS

narrative analysis, personal narrative, metaphorical narrative, concept of powerlessness, cultural estrangement, social-psychological alienation, narrative’s deconstruction.