Accepted Papers

Leveraging Modern Hardware Tools and Utilizing Deep Learning Methods to Create an Assistance Method for Individuals with Visual Disorders

Neeraj Rattehalli¹ and Ishan Jain², ¹Department of Computer Engineering, East Palo Alto, USA, ²Department of Computer Engineering, Fremont, USA

ABSTRACT

Approximately 285 million individuals globally suffer from a visual disorder, rendering them unable to perform tasks and interact with the society around them. Because of such impairments that limit daily activities, disparities in society are prone to occur, causing visually disordered individuals to encounter disadvantages routinely. As a result, the affected population lacks the social and collaboration skills that are vital to an optimal quality of life. The social and psychological impacts of having a visual disorder is troublesome for most individuals. Many people experience bullying and harassment due to their inability to interact with society. With the constant uprising of disadvantages for people with visual disorders, these victims feel left out in society, leading to suicides and depression. Without the help of a sufficient and capable assistant, these individuals can live traumatizing lives. In the current market, there are few to none applications and devices that offer virtual assistance for individuals with visual disorders. Present applications simply involve situations in which victims need real-life human assistance for navigation and assistance. However, this requires various resources, time, and costs. On the contrary, in certain scenarios, if a particular patient does not have access to family members or friends who can assist them in their daily life, then there will be various resulting problems. Another method for patients to receive daily assistance is via a personal medical companion. There are various costs in this method, for the patient has to hire and pay for these services. Many patients do not have access to such resources. In the status quo, there are no efficient methods and services that can provide support for visually disabled individuals. In order to progress in daily activity, one must resort to digital and technological tools to receive access to companionship and assistance during a daily routine. Thus, we present the solution to the need for an artificially intelligent and computational approach for a virtual and self-trained device to provide aid for visually impaired individuals.

KEYWORDS

Machine Learning, Server processing, deep neural networks, gRPC.

A Proposed Framework for Building Semantic Search Engine with Map-reduce

Abeer A. Amer¹, Sarah S. Abulwafa² and Mohamed M. El-Hadi³, ¹Department of Computer and Information Systems, Sadat Academy, Alexandria, Egypt, ²MSc. Candidate of Computer and Information Systems, Sadat Academy, Cairo, Egypt, ³Department of Computer and Information Systems, Sadat Academy, Cairo, Egypt

ABSTRACT

Every daily moment, people shares billion of information all over the world via the Internet, which makes in the other side large database stores for that web-based information. With the massive databases, Search Engines (SE) are increasing, they act as filters to allow users find information they are interested in easily and quickly. As Semantic search engines try to understand what a user is asking in a query by placing it in context through analysis of the query’s terms and language. This analysis is conducted against tightly pre-compiled pools of knowledge, potentially including knowledge about the user. Most of researchers did their best to convert such a traditional search engine to a Semantic one, but without giving any attention for the increasing of the generated indices. This paper proposes a framework for building semantic search engine using MapReduce for speeding up indexing and retrieving big ontological data.

KEYWORDS

Semantic Search Engine, MapReduce, indexing, ontology.

The role of public libraries for promoting reading within the family

Md Solemanpharcy, Pondicherry University, India

ABSTRACT

This paper goals to determine some examples of good practice accepted out in public libraries and their role of promoting reading within the everyday and in particular with parents and children. In this case, the family takes on the accountability of getting the book into the life of the child nearly from the time they are natural. Several libraries hold occasions which aim to bring parents and children, books and reading and ridiculous activities together and therefore inspire early interest in reading on the part of the child. This events effort on many stages, planning to train parents on how to take full benefit of books, to make them more aware of the profits of reading and how to make a good selection of reading material to support family promises and promote an improved and more balanced education for the child.

KEYWORDS

Public library, family, family literacy, emergent literacys.

An Investigation of Modern Foreign Language (MFL) Teachers and their Attitudes to Computer Assisted Language Learning (Call) Amid the Covid-19 Health Pandemic

Louise Hanna, David Barr, Helen Hou and Shauna McGill, School of Education, Ulster University

ABSTRACT

A study was performed with 33 Modern Foreign Language (MFL) teachers to afford insight into how classroom practitioners interact with Computer Assisted Language Learning (CALL) in Second Language (L2) pedagogy. A questionnaire with CALL specific statements was completed by MFL teachers who were recruited via UK based Facebook groups. Significantly, participants acknowledged a gap in practice from the expectation of CALL in the MFL classroom. Overall, respondents were shown to be interested and regular consumers of CALL who perceived its ease and importance in L2 teaching and learning.

KEYWORDS

Computer Assisted Language Learning (CALL), Modern Foreign Languages (MFL), teacher attitudes, digital technologies, Second Language (L2) pedagogy

Prediction of Juvenile Crime Because of Drug Addiction & Prevention Strategies with Data & Analytics

Meherun Nesa¹ and Tumpa Rani Saha², ¹Department of Computer Science & Engineering, Bangabandhu Sheikh Mujibur Rahman Science & Technology University, Gopalgonj, ²Department of Computer Science & Engineering, Bangabandhu Sheikh Mujibur Rahman Science & Technology University, Gopalgonj

ABSTRACT

This paper proffers the concept of predicting juvenile crime because of drug addiction, using machine learning technique. Juvenile crime is the participation in the illegal behavior or committing crime where the age of the criminals are under 18. This research help to find out the causes of addiction to drugs as well as involvement in crimes. This study also proposes some prevention strategies. In this regard, the collection of dataset is of great importance. We have collected raw data from some drug addicted young people who are staying in drug rehabilitation center and some local young people who are not addicted to drugs. We have categorized the dataset into 31 attributes apart from target feature and the experiment is conducted with these factor analysis. The result predicts if there exist any association with crime or not. The Performance of prediction models are evaluated using Decision Tree, K-Nearest Neighbor, Support Vector Machine, Random Forest and XGBoost machine learning techniques. We use different measures for the evaluation of the classification quality and we also compares the result among these algorithms we have used. We also calculate features importance to detect which features are more liable for crime involvement according to this dataset.

KEYWORDS

Decision Tree, K-Nearest Neighbor, Support Vector Machine, Random Forest, XGBoost, Features Importance.

Data Prediction of Deflection Basin Evolution of Asphalt Pavement Structure Based on Multi-level Neural Network

Shaosheng Xu, Jinde Cao and Xiangnan Liu, School of Automation, Southeast University, Nanjing, China, School of Mathematics, Southeast University, Nanjing, China, School of Mathematics, Southeast University, Nanjing, China

ABSTRACT

Aiming at the high cost of test data collection of deflection basins in the structural design of asphalt pavement and the long test time of new structures, this paper innovatively designs a structure coding network based on traditional neural networks to map the pavement structure to an abstract space. Therefore, the generalization ability of the neural network structure is improved, and a new multi-level neural network model is formed to predict the evolution data of the deflection basin of the unknown structure. By testing the experimental data of RIOHTRACK, the network structure is effective for predicting the deflection basin data of unknown pavement structure.

KEYWORDS

multi-level neural network, Encoding converter, structural of asphalt pavement, deflection basins, RIOHTRACK.

Stability analysis of quaternion-valued neural networks with leakage delay and additive time-varying delays

Qun Huanga and Jinde Cao, School of Mathematics, Southeast University, China

ABSTRACT

In this paper, the stability analysis of quaternion-valued neural networks (QVNNs) with both leakage delay and additive time-varying delays is proposed. By employing the Lyapunov-Krasov skii functional method and fully considering the relationship between time-varying delays and upper bounds of delays, some sufficient criteria are derived based on reciprocally convex method and several inequality techniques. The stability criteria are established in two forms: quaternion- valued linear matrix inequalities (QVLMIs) and complex-valued linear matrix inequalities (CV- LMIs), in which CVLMIs can be directly resolved by the Yalmip toolbox in MATLAB. Finally, an illustrative example is presented to demonstrate the validity of the theoretical results.

KEYWORDS

Quaternion-valued neural networks, Stability analysis, Lyapunov-Krasovskii functional, Leakage delay, Additive time-varying delays

Social Humanoid Robot “Ai-gerim”

Zhumadil Baigunchekov^1,2, Zhadyra Zhumasheva², Bekzat Amanov², Yernar Zholdassov², Berik Sagitzhanov², Alibek Tleukhanov², ¹Satbayev University, 22 Satpayev str., Almaty 050013, Republic of Kazakhstan, ²Al-Farabi Kazakh National University, 71 Al-Farabi Ave., Almaty 050040, Republic of Kazakhstan

ABSTRACT

In this paper, a social humanoid robot “Ai-Gerim” is developed, which is remotely controlled and cheap due to the simplified design and control system. On the basis of this robot, the “Qamqor” system is created to provide employment for people with disabilities. This system allows the operator who is a person with disabilities, while at home, to remotely control the robot “Ai-Gerim” via the Internet, which performs service and other work in the user's institutions.

KEYWORDS

Social humanoid robot, Robotic system, Remote control.

Development of Iotbased Automated Irrigation System for Crop Farmers in Namibia

Anton Limbo¹, Ndakolute Set-Sakeus¹, Valerianus Hashiyana¹, Nalina Suresh¹, Titus Haiduwa¹, Martin Mabeifam Ujakpa², ¹School of Computing, University of Namibia, Windhoek, Namibia, ²Faculty of Information and Communication Technology, International University of management, Windhoek, Namibia

ABSTRACT

Namibia is a relatively dry country, characterized by high temperatures and low rainfall through the year. In light of that, the agricultural sector is commonly affected during the dry season which results in food insecurity, loss of jobs, crops and livestock. In Namibia, the agriculture sector accounts for about 70% of food security, 30% of livelihood and contributes about 6% toward Namibia’s gross domestic product (GDP). Hence, there is an urgent need to find remedies to avert the challenges inflicted on farmers during the prolonged dry season. One of the strategies is the application Internet of Things (IoT) in Agriculture. This paper discusses the development of a prototype of an automated irrigation system aimed to continuously monitor the soil moisture level and automatically activate the water pump whenever a certain threshold is met based on predefined criteria.

KEYWORDS

Smart Irrigation system, Water Management, Internet of Things, Sensors, Arduino Uno.

GDPR Compliance for Blockchain Applications in Healthcare

Anton Hasselgren, Paul Kengfai Wan, Margareth Horn, Katina Kralevska, Danilo Gligoroski and Arild Faxvaag, NTNU, Norwegian University of Science and Technology, Trondheim, Norway

ABSTRACT

The transparent and decentralized characteristics associated with blockchain can be both appealing and problematic when applied to a healthcare use-case. As health data is highly sensitive, it is also highly regulated to ensure the privacy of patients. At the same time, access to health data and interoperability is in high demand. Regulatory frameworks such as GDPR and HIPAA are, amongst other objectives, meant to contribute to mitigating the risk of privacy violations in health data. Blockchain features can likely improve interoperability and access control to health data, and at the same time, preserve or even increase, the privacy of patients. Blockchain applications should address compliance with the current regulatory framework to increase real-world feasibility. This exploratory work indicates that published proof-of-concepts in the health domain comply with GDRP, to an extent. Blockchain developers need to make design choices to be compliant with GDPR since currently, none available blockchain platform can show compliance out of the box.

KEYWORDS

Blockchain, DTL, health data, GDPR, privacy regulations.

The Temtum Consensus Algorithm – A Low Energy Replacement to Proof of Work

Richard Dennis and Gareth Owenson, Department of Computing, University of Portsmouth, Portsmouth, United Kingdome

ABSTRACT

This paper presents a novel consensus algorithm deployed within the Temtum cryptocurrency network. An overview of the proof of work consensus algorithm is presented, and gaps in the research are outlined. The Temtum consensus algorithm's unique components, including the Node Participation Document (NPD) and the use of the NIST randomness beacon, are outlined and explained. Comparisons on the cost to attack the consensus algorithm and energy consumption between the Temtum consensus algorithm and Bitcoin’s proof of work is presented and evaluated. We conclude this paper summarising the findings of the research and presenting future work to be conducted.

KEYWORDS

Blockchain, Peer-to-Peer Networks, Cryptocurrencies, Consensus, Byzantine Fault Tolerance

Holochain-based Framework for Securing Communication in Teleradiology

Amine Fayeta, Samir Belfkih and Habiba Chaoui, Systems Engineering Laboratory, ENSA Ibn Tofail University, Kenitra, Morocco

ABSTRACT

Teleradiology, an essential element of telemedicine and it is probably the most successful eHealth service available nowadays, functional for many years in several countries, it is based on the remote transmission of radiological images (e.g. X-ray and CT-images) over electronic networks. In order to enable them to receive appropriate diagnostic and curative care as quickly as possible, while reducing the number of unnecessary transfers for patients who do not have anything to gain from their transport, therefore, maintaining the security of data transmission is crucial Thus, we made us think about implementing the latest technologies which is Holochain on Teleradiology that will reduce Blockchain technology problems.

KEYWORDS

Teleradiology, Holochain, Blockchain, X-Ray, CT-images

Holochain-based Digital Forensics Investigation Framework for Evidence Preservation

Mouad Ben’nali¹, Chaimae Saadi², Habiba Chaoui¹, ¹Systems Engineering Laboratory, ²Systems Analysis Laboratory,Information Processing and Industrial Management

ABSTRACT

The primary key to solve any crime, whether it is physical or a digital one lies in presenting authentic and unaltered evidence in front of court of law, this can only be achieved if the whole procedure meets legal standards defined by high entities. Maintaining a proper Chain of Custody will help demonstrate to the court that the investigation process followed the legal requirement in a way that protects the evidence's integrity and authenticity, otherwise the evidence will be inadmissible. Existing work on evidence preservation tends to rely on blockchain as a distributed ledger. to store the seized evidence, we all agree that blockchain has solved many issues of centralized architectures, even so , it is still not the best model to adopt when it comes to build a large-scale peer-to-peer distributed network due to its drawbacks such as transaction speed, scalability, and network overload. This paper proposes a fully distributed peer to peer forensic investigation framework based on a new approach called Holochain. The limitations of some related work have been addressed, furthermore the necessity of applying Holochain to ensure evidence’s integrity has been elaborated.

KEYWORDS

Digital Forensic, Investigation, Blockchain, Holochain, Validation Rules, Integrity, evidence.