Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 3130

World Academy of Science, Engineering and Technology

[Computer and Information Engineering]

Online ISSN : 1307-6892

3130 Adaptive Data Approximations Codec (ADAC) for AI/ML-based Cyber-Physical Systems

Authors: Yong-Kyu Jung

Abstract:

The fast growth in information technology has led to de-mands to access/process data. CPSs heavily depend on the time of hardware/software operations and communication over the network (i.e., real-time/parallel operations in CPSs (e.g., autonomous vehicles). Since data processing is an im-portant means to overcome the issue confronting data management, reducing the gap between the technological-growth and the data-complexity and channel-bandwidth. An adaptive perpetual data approximation method is intro-duced to manage the actual entropy of the digital spectrum. An ADAC implemented as an accelerator and/or apps for servers/smart-connected devices adaptively rescales digital contents (avg.62.8%), data processing/access time/energy, encryption/decryption overheads in AI/ML applications (facial ID/recognition).

Keywords: adaptive codec, AI, ML, HPC, cyber-physical, cybersecurity

Procedia PDF Downloads 2
3129 Detection of Ethereum Eclipse Attack based on Hybrid Method and Dynamic Weighted Entropy

Authors: Dhanasak Bhumichai, Ryan Benton

Abstract:

The growth of Ethereum platforms brings numerous cyber threats to this technology. An Eclipse attack is one of the most dangerous cyber threats generated to attack the network layer of blockchain platforms. Nonetheless, the Detection of Eclipse attacks is a challenging task because of needing an Eclipse attack dataset, knowledge about features of this attack, and imbalanced and overlapping in the samples data among different classes. Therefore, this paper introduces a novel approach to detect Eclipse attacks on the Ethereum network layer by combining iForest and Random Forest to handle imbalanced and overlapped datasets while a Dynamic Weighted Entropy (DWE) is implemented to evaluate and enhance the quality of the overlapping subset.

Keywords: Blockchain, Eclipse Attack, Imbalanced and Overlapped data, Ethereum Blockchain, Anomaly Detection Model

Procedia PDF Downloads 2
3128 Knowledge Elicitation Approach for Formal Ontology Design: An Exploratory Study Applied in Industry for Knowledge Management

Authors: Ouassila Labbani-Narsis, Christophe Nicolle

Abstract:

Building formal ontologies remains a complex process for companies. In the literature, this process is based on the technical knowledge and expertise of domain experts without further details on the used methodologies. Possible problems of disagreements between experts, expression of tacit knowledge related to high level know-how rarely verbalized, qualification of results by using cases, or simply adhesion of the group of experts, remain currently unsolved. This paper proposes a methodological approach based on knowledge elicitation for the conception of formal, consensual, and shared ontologies. The proposed approach is experimentally tested on industrial collaboration projects in the field of manufacturing (associating knowledge sources from multinational companies) and in the field of viticulture (associating explicit knowledge and implicit knowledge acquired through observation).

Keywords: collaborative ontology engineering, knowledge elicitation, knowledge engineering, knowledge management

Procedia PDF Downloads 1
3127 Symmetric Arabic Language Encryption Technique Based on Modified Playfair Algorithm

Authors: Fairouz Beggas

Abstract:

Due to the large number of exchanges in the networks, the security of communications is essential. Most ways of keeping communication secure rely on encryption. In this work, a symmetric encryption technique is offered to encrypt and decrypt simple Arabic scripts based on a multi-level security. A proposed technique uses an idea of Playfair encryption with a larger table size and an additional layer of encryption to ensure more security. The idea of the proposed algorithm aims to generate a dynamic table that depends on a secret key. The same secret key is also used to create other secret keys to over-encrypt the plaintext in three steps. The obtained results show that the proposed algorithm is faster in terms of encryption/decryption speed and can resist to many types of attacks.

Keywords: arabic data, encryption, playfair, symmetric algorithm

Procedia PDF Downloads 3
3126 Block Verifiable Dynamic Searchable Encryption Using Redactable Blockchain

Authors: Ruizhong Du, Na Liu, Mingyue Li, Junfeng Tian

Abstract:

To solve the problems of low efficiency, inflexible updates, and the high storage cost of existing result-verifiable searchable encryption schemes, we propose a dynamic, searchable encryption scheme with block verification using a redactable blockchain. First, the inverted index is divided into blocks, the verification tag corresponding to the block index is uploaded to the redactable blockchain, and smart contracts are used to perform block verification of the query results to improve the query and verification performance. Furthermore, we use blockchain rewriting technology to update the tags in the result checklist, improving the data update performance and scalability of the blockchain and ensuring the constant storage overhead of the blockchain. Security analysis confirms that our proposals guarantee the correctness and completeness of the query results. Experimental results show that our proposed approach can improve query efficiency and result in verification efficiency under the premise of the low-speed growth of the blockchain data scale. In particular, the advantages become more significant as the data collection scale grows.

Keywords: searchable encryption, redactable blockchain, block index, result verification, smart contract

Procedia PDF Downloads 1
3125 Cyber and Space: Information Warfare and Joint All Domain Effects in the Youngest Domains

Authors: Joshua Alton Sipper

Abstract:

Cyberspace and space operations are examined here as interdependent, cross-functional, and co-dependent on the electromagnetic spectrum. The research methodologies used here are survey research and comparative analysis leveraging the myriad entanglements between space, cyberspace, and electromagnetic spectrum technologies. To get a closer look at how space and cyber interdisciplinary operations can achieve these effects, cyber and space technological relationships, doctrine, operations, and cross-domain integration will be analyzed and discussed. Through this analysis, it was found that these technologies have the intrinsic potential to affect deep enclaves of the electromagnetic spectrum, critical infrastructure, information infrastructure, information-related capabilities, and joint all-domain operations. These various technological and operational connections suggest various vulnerabilities and consequences if they are not properly secured and managed.

Keywords: cyber, space, information warfare, electromagnetic, intelligence

Procedia PDF Downloads 2
3124 Dual-use UAVs in Armed Conflicts: Opportunities and Risks for Cyber and Electronic Warfare

Authors: Piret Pernik

Abstract:

Based on strategic, operational, and technical analysis of the ongoing armed conflict in Ukraine, this paper will examine the opportunities and risks of using small commercial drones (dual-use unmanned aerial vehicles, UAV) for military purposes. The paper discusses the opportunities and risks in the information domain, encompassing both cyber and electromagnetic interference and attacks. The paper will draw conclusions on a possible strategic impact to the battlefield outcomes in the modern armed conflicts by the widespread use of dual-use UAVs. This article will contribute to filling the gap in the literature by examining based on empirical data cyberattacks and electromagnetic interference. Today, more than one hundred states and non-state actors possess UAVs ranging from low cost commodity models, widely are dual-use, available and affordable to anyone, to high-cost combat UAVs (UCAV) with lethal kinetic strike capabilities, which can be enhanced with Artificial Intelligence (AI) and Machine Learning (ML). Dual-use UAVs have been used by various actors for intelligence, reconnaissance, surveillance, situational awareness, geolocation, and kinetic targeting. Thus they function as force multipliers enabling kinetic and electronic warfare attacks and provide comparative and asymmetric operational and tactical advances. Some go as far as argue that automated (or semi-automated) systems can change the character of warfare, while others observe that the use of small drones has not changed the balance of power or battlefield outcomes. UAVs give considerable opportunities for commanders, for example, because they can be operated without GPS navigation, makes them less vulnerable and dependent on satellite communications. They can and have been used to conduct cyberattacks, electromagnetic interference, and kinetic attacks. However, they are highly vulnerable to those attacks themselves. So far, strategic studies, literature, and expert commentary have overlooked cybersecurity and electronic interference dimension of the use of dual use UAVs. The studies that link technical analysis of opportunities and risks with strategic battlefield outcomes is missing. It is expected that dual use commercial UAV proliferation in armed and hybrid conflicts will continue and accelerate in the future. Therefore, it is important to understand specific opportunities and risks related to the crowdsourced use of dual-use UAVs, which can have kinetic effects. Technical countermeasures to protect UAVs differ depending on a type of UAV (small, midsize, large, stealth combat), and this paper will offer a unique analysis of small UAVs both from the view of opportunities and risks for commanders and other actors in armed conflict.

Keywords: dual-use technology, cyber attacks, electromagnetic warfare, case studies of cyberattacks in armed conflicts

Procedia PDF Downloads 1
3123 Framework for Performance Measure of Super Resolution Imaging

Authors: Varsha Hemant Patil, Swati A. Bhavsar, Abolee H. Patil

Abstract:

This paper aims to present an investigation of classic techniques for image quality assessment, especially in use for super-resolution imaging. Image quality assessment plays an important role in image evaluation. Even though much effort has been made towards the development of both qualitative and quantitative measures, the appropriate measures to assess the super-resolution imaging techniques' performance are still not paid noticeable attention. In this paper, the study report of existing image quality measures is given. The paper classifies reviewed approaches according to functionality and suitability for super-resolution imaging. Probable modifications and improvements of these to suit super-resolution imaging are presented. The prime goal of the paper is to provide a comprehensive reference source for researchers working towards super-resolution imaging and suggest a better framework for measuring the performance of super-resolution imaging techniques.

Keywords: interpolation, MSE, PSNR, SSIM, super resolution

Procedia PDF Downloads 1
3122 Predicting Personality and Psychological Distress Using Natural Language Processing

Authors: Jihee Jang, Seowon Yoon, Gaeun Son, Minjung Kang, Joon Yeon Choeh, Kee-Hong Choi

Abstract:

Background: Self-report multiple choice questionnaires have been widely utilized to quantitatively measure one’s personality and psychological constructs. Despite several strengths (e.g., brevity and utility), self-report multiple-choice questionnaires have considerable limitations in nature. With the rise of machine learning (ML) and Natural language processing (NLP), researchers in the field of psychology are widely adopting NLP to assess psychological constructs to predict human behaviors. However, there is a lack of connections between the work being performed in computer science and that psychology due to small data sets and unvalidated modeling practices. Aims: The current article introduces the study method and procedure of phase II, which includes the interview questions for the five-factor model (FFM) of personality developed in phase I. This study aims to develop the interview (semi-structured) and open-ended questions for the FFM-based personality assessments, specifically designed with experts in the field of clinical and personality psychology (phase 1), and to collect the personality-related text data using the interview questions and self-report measures on personality and psychological distress (phase 2). The purpose of the study includes examining the relationship between natural language data obtained from the interview questions, measuring the FFM personality constructs, and psychological distress to demonstrate the validity of the natural language-based personality prediction. Methods: The phase I (pilot) study was conducted on fifty-nine native Korean adults to acquire the personality-related text data from the interview (semi-structured) and open-ended questions based on the FFM of personality. The interview questions were revised and finalized with the feedback from the external expert committee, consisting of personality and clinical psychologists. Based on the established interview questions, a total of 425 Korean adults were recruited using a convenience sampling method via an online survey. The text data collected from interviews were analyzed using natural language processing. The results of the online survey, including demographic data, depression, anxiety, and personality inventories, were analyzed together in the model to predict individuals’ FFM of personality and the level of psychological distress (phase 2).

Keywords: personality prediction, psychological distress prediction, natural language processing, machine learning, the five-factor model of personality

Procedia PDF Downloads 2
3121 New Machine Learning Optimization Approach Based on Input Variables Disposition Applied for Time Series Prediction

Authors: Hervice Roméo Fogno Fotsoa, Germaine Djuidje Kenmoe, Claude Vidal Aloyem Kazé

Abstract:

One of the main applications of machine learning is the prediction of time series. But a more accurate prediction requires a more optimal model of machine learning. Several optimization techniques have been developed, but without considering the input variables disposition of the system. Thus, this work aims to present a new machine learning architecture optimization technique based on their optimal input variables disposition. The validations are done on the prediction of wind time series, using data collected in Cameroon. The number of possible dispositions with four input variables is determined, i.e., twenty-four. Each of the dispositions is used to perform the prediction, with the main criteria being the training and prediction performances. The results obtained from a static architecture and a dynamic architecture of neural networks have shown that these performances are a function of the input variable's disposition, and this is in a different way from the architectures. This analysis revealed that it is necessary to take into account the input variable's disposition for the development of a more optimal neural network model. Thus, a new neural network training algorithm is proposed by introducing the search for the optimal input variables disposition in the traditional back-propagation algorithm. The results of the application of this new optimization approach on the two single neural network architectures are compared with the previously obtained results step by step. Moreover, this proposed approach is validated in a collaborative optimization method with a single objective optimization technique, i.e., genetic algorithm back-propagation neural networks. From these comparisons, it is concluded that each proposed model outperforms its traditional model in terms of training and prediction performance of time series. Thus the proposed optimization approach can be useful in improving the accuracy of time series forecasts. This proves that the proposed optimization approach can be useful in improving the accuracy of time series prediction based on machine learning.

Keywords: input variable disposition, machine learning, optimization, performance, time series prediction

Procedia PDF Downloads 3
3120 Phishing Attacks Facilitated by Open Source Intelligence

Authors: Urva Maryam

Abstract:

Information has become an important asset to the current cosmos. Globally, various tactics are being observed to confine the spread of information as it makes people vulnerable to security attacks. Open Source Intelligence (OSINT) is a publicly available source that has disseminated information about users or website, companies, and various organizations. This paper focuses on the quantitative method of exploring various OSINT tools that reveal public information of personals. This information could further facilitate the phishing attacks. Phishing attacks can be launched on email addresses, open ports, and unsecured web-surfing. This study allows to analyze information retrieved from OSINT tools i.e., the Harvester, and Maltego, that can be used to send phishing attacks to individuals.

Keywords: OSINT, phishing, spear phishing, email spoofing, the harvester, maltego

Procedia PDF Downloads 2
3119 Emerging Cyber Threats and Cognitive Vulnerabilities: Cyberterrorism

Authors: Oludare Isaac Abiodun, Esther Omolara Abiodun

Abstract:

The purpose of this paper is to demonstrate that cyberterrorism is existing and poses a threat to computer security and national security. Nowadays, people have become excitedly dependent upon computers, phones, the Internet, and the Internet of things systems to share information, communicate, conduct a search, etc. However, these network systems are at risk from a different source that is known and unknown. These network systems risk being caused by some malicious individuals, groups, organizations, or governments, they take advantage of vulnerabilities in the computer system to hawk sensitive information from people, organizations, or governments. In doing so, they are engaging themselves in computer threats, crime, and terrorism, thereby making the use of computers insecure for others. The threat of cyberterrorism is of various forms and ranges from one country to another country. These threats include disrupting communications and information, stealing data, destroying data, leaking, and breaching data, interfering with messages and networks, and in some cases, demanding financial rewards for stolen data. Hence, this study identifies many ways that cyberterrorists utilize the Internet as a tool to advance their malicious mission, which negatively affects computer security and safety. One could identify causes for disparate anomaly behaviors and the theoretical, ideological, and current forms of the likelihood of cyberterrorism. Therefore, for a countermeasure, this paper proposes the use of previous and current computer security models as found in the literature to help in countering cyberterrorism

Keywords: cyberterrorism, computer security, information, internet, terrorism, threat, digital forensic solution

Procedia PDF Downloads 3
3118 Factors of Social Network Platform Usage and Privacy Risk: A Unified Theory of Acceptance and Use of Technology2 Model

Authors: Wang Xue

Abstract:

The trust and use of social network platforms by users are instrumental factors that contribute to the platform’s sustainable development. Studying the influential factors of the use of social network platforms is beneficial for developing and maintaining a large user base. This study constructed an extended unified theory of acceptance and use of technology (UTAUT2) moderating model with perceived privacy risks to analyze the factors affecting the trust and use of social network platforms. 444 participants completed our 35 surveys, and we verified the survey results by structural equation model. Empirical results reveal the influencing factors that affect the trust and use of social network platforms, and the extended UTAUT2 model with perceived privacy risks increases the applicability of UTAUT2 in social network scenarios. Social networking platforms can increase their use rate by increasing the economics, functionality, entertainment, and privacy security of the platform.

Keywords: perceived privacy risk, social network, trust, use, UTAUT2 model

Procedia PDF Downloads 2
3117 Generating Insights from Data Using a Hybrid Approach

Authors: Allmin Susaiyah, Aki Härmä, Milan Petković

Abstract:

Automatic generation of insights from data using insight mining systems (IMS) is useful in many applications, such as personal health tracking, patient monitoring, and business process management. Existing IMS face challenges in controlling insight extraction, scaling to large databases, and generalising to unseen domains. In this work, we propose a hybrid approach consisting of rule-based and neural components for generating insights from data while overcoming the aforementioned challenges. Firstly, a rule-based data 2CNL component is used to extract statistically significant insights from data and represent them in a controlled natural language (CNL). Secondly, a BERTSum-based CNL2NL component is used to convert these CNLs into natural language texts. We improve the model using task-specific and domain-specific fine-tuning. Our approach has been evaluated using statistical techniques and standard evaluation metrics. We overcame the aforementioned challenges and observed significant improvement with domain-specific fine-tuning.

Keywords: data mining, insight mining, natural language generation, pre-trained language models

Procedia PDF Downloads 8
3116 The Effects of Mobile Phones in Mitigating Cultural Shock Amongst Refugees: Case of South Africa

Authors: Sarah Vuningoma, Maria Rosa Lorini, Wallace Chigona

Abstract:

Mobile phones have the potential to contribute towards reducing isolation and loneliness and to assist in improving interpersonal relations and fostering assimilation processes. Mobile phones may facilitate the incorporation of refugees into a new place. The purpose of this study is to assess how the use of mobile phones helps refugees to mitigate the effects of culture in the host country. Data for the study were collected using semi-structured interviews. The sample consisted of 27 participants. The participants were refugees living in South Africa. Data were analysed using thematic analysis. The study demonstrates that the refugees face myriad challenges in their host country, including a lack of local cultural skills, separation of family and friends from their home countries, obstacle in obtaining legal documents, and the difficulties of becoming integrated into the new environment. The use of mobile phones offers refugees several benefits, such as developing language and cultural knowledge, integrated in the host country, facilitating communication, and finding many opportunities. At the same time, mobile phones enable refugees in South Africa to navigate culture shock.

Keywords: mobile phones, culture shock, refugees, South Africa

Procedia PDF Downloads 4
3115 Alzheimer’s Disease Detection Based on Features Level Selection for Convolutional Neural Network-Support Vector Machines (SVM) Combination

Authors: Mohamed Amine Zayene, Hend Basly, Fatma Ezahra Sayadi

Abstract:

Alzheimer's disease (AD) is a neurodegenerative disease that causes progressive and irreversible brain disorder loss. Early detection of this disease is essential to limit its progress. Computer-aided approaches such as machine learning provide several techniques to detect AD by extracting features from the Brain images and using them to build a classifier. Recently, a subcategory of machine learning called deep learning has widely been proposed to enhance medical diagnosis by attempting notable performance. In fact, these approaches avoid the tricky manual feature extraction using Convolutional Neural Network (CNN) considered as a reference in the field of computer vision. This paper proposes a combination of CNN-SVM (Support Vector Machines) for early diagnosis of AD using positron emission tomography (PET). We first train our CNN on PET images to extract the most relevant features, then we select the most appropriate CNN level to extract the features, which we feed in a second step as input to a Support Vector Machine based classifier (SVM). The proposed approach predicts 99.25%, 94.24%, 97.62% and 96.98% successively as accuracy for CN vs. AD, CN vs. mild cognitive impairment (MCI), MCI vs. AD and CN vs MCI vs AD classification tasks. It has also exceeded the performance obtained by various existing approaches.

Keywords: machine learning, deep learning, neurodegenerative disease, Alzheimer's disease

Procedia PDF Downloads 6
3114 Adopting Cloud-Based Techniques to Reduce Energy Consumption: Toward a Greener Cloud

Authors: Sandesh Achar

Abstract:

The cloud computing industry has set new goals for better service delivery and deployment, so anyone can access services such as computation, application, and storage anytime. Cloud computing promises new possibilities for approaching sustainable solutions to deploy and advance their services in this distributed environment. This work explores energy-efficient approaches and how cloud-based architecture can reduce energy consumption levels amongst enterprises leveraging cloud computing services. Adopting cloud-based networking, database, and server machines provide a comprehensive means of achieving the potential gains in energy efficiency that cloud computing offers. In energy-efficient cloud computing, virtualization is one aspect that can integrate several technologies to achieve consolidation and better resource utilization. Moreover, the Green Cloud Architecture for cloud data centers is discussed in terms of cost, performance, and energy consumption, and appropriate solutions for various application areas are provided.

Keywords: greener cloud, cloud computing, energy efficiency, energy consumption, metadata tags, green cloud advisor

Procedia PDF Downloads 6
3113 Max-Pooled B-CUBED Clustering Quality Evaluation Metric

Authors: Felip Guimerà Cuevas, Helmut Schmid

Abstract:

Evaluating the quality of results from clustering algorithms is a complex open problem. B-CUBED (B³) has emerged as a strong measure that meets the four intuitive formal constraints of homogeneity, completeness, rag bag, and size vs. quantity, and it has sparked much attention since. However, this work argues that the constraint "completeness" -items belonging to the same category should be in the same cluster- may be problematic, unfair, and mislead the evaluative assessment in some circumstances and for finer clustering algorithms that identify sub-clusters inside clusters. This paper draws focus on the issue and proposes a modified Max-pooled B³ evaluation method that regroups clusters based on the most frequent label into corresponding super-sets and then considers those during evaluation using an adapted B³-based metric to address the completeness issues faced during subgroup- and information retrieval evaluation. It takes a formal approach to the problem and proposes a solution that, just like B³, works with imbalanced data sets but now further allows to manually determine the desired degree of completeness vs. sub-group extraction trade-off.

Keywords: clustering, evaluation metric, supervised quality assessment, sub-clustering, coarse labels

Procedia PDF Downloads 4
3112 Adaptive Wasserstein Tanh-Normalization of Feature Values

Authors: Felip Guimerà Cuevas, Helmut Schmid

Abstract:

Machine learning models typically require feature scaling (FS) to be the most effective. Conventional FS methods, however, do not protect well against outliers in contaminated data sets. Outliers should be avoided since they may violate statistical assumptions, exacerbate unpredictability and decrease model effectiveness. Tanh-estimators (TE) have been shown to offer robust feature normalization; nevertheless, they utilize a fixed scaling factor for all features, raising the question of whether this is genuinely reasonable given the infinite number of different feature value distributions. This work presents a TE refinement that uses the Wasserstein distance to adaptively estimate the ideal scaling factor against a specified target distribution for each feature individually. The results show that such an adaptive approach can clearly outperform the currently established method in the literature in terms of convergence speed by allowing for better initial training starts by reducing or eliminating the need to re-adjust model weights during early training phases due to inadequately scaled features. Thus, the paper draws attention to, examines, and offers an analytical perspective on the basic issue of utilizing a single fixed spread value. Common toy computer vision sets and synthetic data are used to empirically evaluate the proposed solution.

Keywords: feature normalization, feature pre-processing, deep learning, machine learning.

Procedia PDF Downloads 2
3111 The Effect of Iran's Internet Filtering on Active Digital Marketing Businesses

Authors: Maryam Sheikhzadeh Noshabadi

Abstract:

There is no doubt that the Internet has connected the entire world. As a result of this flexible environment, virtual businesses have grown in importance and become one of the most important types of businesses. Although many governments use the internet and have free access to it, some are not happy with the free space and wide accessibility. As a result of recent events and civil protests in Iran, the country's government leaders have decided to once again cut off and filter its free and global Internet. Several issues were impacted by this decision; this includes the lives of businesses that were formed in virtual spaces platform. In this study, we explored the definitive impact of the Internet in Iran in September 1401, using semi-structured interviews with 20 digital marketing activists. This group was discussed in detail in terms of their financial and psychological damages. As a result of these conditions, this group has experienced a crisis of livelihood.

Keywords: internet, Iran, filtering, digital marketing.

Procedia PDF Downloads 2
3110 Development of Star Image Simulator for Star Tracker Algorithm Validation

Authors: Zoubida Mahi

Abstract:

A successful satellite mission in space requires a reliable attitude and orbit control system to command, control and position the satellite in appropriate orbits. Several sensors are used for attitude control, such as magnetic sensors, earth sensors, horizon sensors, gyroscopes, and solar sensors. The star tracker is the most accurate sensor compared to other sensors, and it is able to offer high-accuracy attitude control without the need for prior attitude information. There are mainly three approaches in star sensor research: digital simulation, hardware in the loop simulation, and field test of star observation. In the digital simulation approach, all of the processes are done in software, including star image simulation. Hence, it is necessary to develop star image simulation software that could simulate real space environments and various star sensor configurations. In this paper, we present a new stellar image simulation tool that is used to test and validate the stellar sensor algorithms; the developed tool allows to simulate of stellar images with several types of noise, such as background noise, gaussian noise, Poisson noise, multiplicative noise, and several scenarios that exist in space such as the presence of the moon, the presence of optical system problem, illumination and false objects. On the other hand, we present in this paper a new star extraction algorithm based on a new centroid calculation method. We compared our algorithm with other star extraction algorithms from the literature, and the results obtained show the star extraction capability of the proposed algorithm.

Keywords: star tracker, star simulation, star detection, centroid, noise, scenario

Procedia PDF Downloads 5
3109 Flood Early Warning and Management System

Authors: Yogesh Kumar Singh, T. S. Murugesh Prabhu, Upasana Dutta, Girishchandra Yendargaye, Rahul Yadav, Rohini Gopinath Kale, Binay Kumar, Manoj Khare

Abstract:

The Indian subcontinent is severely affected by floods that cause intense irreversible devastation to crops and livelihoods. With increased incidences of floods and their related catastrophes, an Early Warning System for Flood Prediction and an efficient Flood Management System for the river basins of India is a must. Accurately modeled hydrological conditions and a web-based early warning system may significantly reduce economic losses incurred due to floods and enable end users to issue advisories with better lead time. This study describes the design and development of an EWS-FP using advanced computational tools/methods, viz. High-Performance Computing (HPC), Remote Sensing, GIS technologies, and open-source tools for the Mahanadi River Basin of India. The flood prediction is based on a robust 2D hydrodynamic model, which solves shallow water equations using the finite volume method. Considering the complexity of the hydrological modeling and the size of the basins in India, it is always a tug of war between better forecast lead time and optimal resolution at which the simulations are to be run. High-performance computing technology provides a good computational means to overcome this issue for the construction of national-level or basin-level flash flood warning systems having a high resolution at local-level warning analysis with a better lead time. High-performance computers with capacities at the order of teraflops and petaflops prove useful while running simulations on such big areas at optimum resolutions. In this study, a free and open-source, HPC-based 2-D hydrodynamic model, with the capability to simulate rainfall run-off, river routing, and tidal forcing, is used. The model was tested for a part of the Mahanadi River Basin (Mahanadi Delta) with actual and predicted discharge, rainfall, and tide data. The simulation time was reduced from 8 hrs to 3 hrs by increasing CPU nodes from 45 to 135, which shows good scalability and performance enhancement. The simulated flood inundation spread and stage were compared with SAR data and CWC Observed Gauge data, respectively. The system shows good accuracy and better lead time suitable for flood forecasting in near-real-time. To disseminate warning to the end user, a network-enabled solution is developed using open-source software. The system has query-based flood damage assessment modules with outputs in the form of spatial maps and statistical databases. System effectively facilitates the management of post-disaster activities caused due to floods, like displaying spatial maps of the area affected, inundated roads, etc., and maintains a steady flow of information at all levels with different access rights depending upon the criticality of the information. It is designed to facilitate users in managing information related to flooding during critical flood seasons and analyzing the extent of the damage.

Keywords: flood, modeling, HPC, FOSS

Procedia PDF Downloads 7
3108 A Hybrid Supervised Machine Learning Approach for Covid-19 Prediction

Authors: Chitesh Khandelwal, Anita Singhrova

Abstract:

COVID-19 pandemic is surfacing around the globe: Corona Virus Disease 2019 (COVID-19), a transmissible disease triggered via the SARS-CoV-2 virus. The stats concerning this pandemic are a long way from addressing the genuine circumstance and the degree of infection. As COVID-19 infection figures continue to escalate, it has become highly crucial to distinguish cases as soon as viable to constrain the infection transmission. Lack of prognosis and asymptomatic patients or even missed identification give rise to a threat to the community. Currently, there is no fool proof treatment or solution for COVID-19, and living with the contamination and its incidental effects is unavoidable. This reality has put a colossal load on confined clinical consideration systems, especially in developing nations. Utilizing non-remedial methodologies can diminish the colossal load on medical services frameworks while giving the best analytics and strategies for tackling COVID-19. One such methodology is machine learning, which is fully capable of digital diagnosis and has proven its biomedical capabilities. This work proposes a hybrid methodology for effective screening of COVID-19 individuals using supervised machine learning. Various ML tools, namely SMOTE has been used to reduce the imbalance and mutual information, along with feature filtering method to reduce the dimensionality and complexity of the proposed framework. Six different supervised algorithms have been implemented and analyzed.

Keywords: classification techniques, Coronavirus, machine learning, prediction, supervised learning

Procedia PDF Downloads 15
3107 Prediction of Distillation Curve and Reid Vapor Pressure of Dual-Alcohol Gasoline Blends Using Artificial Neural Network for the Determination of Fuel Performance

Authors: Leonard D. Agana, Wendell Ace Dela Cruz, Arjan C. Lingaya, Bonifacio T. Doma Jr.

Abstract:

The purpose of this paper is to study the predict the fuel performance parameters, which include drivability index (DI), vapor lock index (VLI), and vapor lock potential using distillation curve and Reid vapor pressure (RVP) of dual alcohol-gasoline fuel blends. Distillation curve and Reid vapor pressure were predicted using artificial neural networks (ANN) with macroscopic properties such as boiling points, RVP, and molecular weights as the input layers. The ANN consists of 5 hidden layers and was trained using Bayesian regularization. The training mean square error (MSE) and R-value for the ANN of RVP are 91.4113 and 0.9151, respectively, while the training MSE and R-value for the distillation curve are 33.4867 and 0.9927. Fuel performance analysis of the dual alcohol–gasoline blends indicated that highly volatile gasoline blended with dual alcohols results in non-compliant fuel blends with D4814 standard. Mixtures of low-volatile gasoline and 10% methanol or 10% ethanol can still be blended with up to 10% C3 and C4 alcohols. Intermediate volatile gasoline containing 10% methanol or 10% ethanol can still be blended with C3 and C4 alcohols that have low RVPs, such as 1-propanol, 1-butanol, 2-butanol, and i-butanol. Biography: Graduate School of Chemical, Biological, and Materials Engineering and Sciences, Mapua University, Muralla St., Intramuros, Manila, 1002, Philippines

Keywords: dual alcohol-gasoline blends, distillation curve, machine learning, reid vapor pressure

Procedia PDF Downloads 14
3106 Assisting Dating of Greek Papyri Images with Deep Learning

Authors: Asimina Paparrigopoulou, John Pavlopoulos, Maria Konstantinidou

Abstract:

Dating papyri accurately is crucial not only to editing their texts but also for our understanding of palaeography and the history of writing, ancient scholarship, material culture, networks in antiquity, etc. Most ancient manuscripts offer little evidence regarding the time of their production, forcing papyrologists to date them on palaeographical grounds, a method often criticized for its subjectivity. By experimenting with data obtained from the Collaborative Database of Dateable Greek Bookhands and the PapPal online collections of objectively dated Greek papyri, this study shows that deep learning dating models, pre-trained on generic images, can achieve accurate chronological estimates for a test subset (67,97% accuracy for bookhands and 55,25% for documents). To compare the estimates of these models with those of humans, experts were asked to complete a questionnaire with samples of literary and documentary hands that had to be sorted chronologically by century. The same samples were dated by the models in question. The results are presented and analysed.

Keywords: dating papyri images, deep neural image models, handwritten text image classification, transfer learning

Procedia PDF Downloads 14
3105 Enhanced Multi-Scale Feature Extraction Using a DCNN by Proposing Dynamic Soft Margin SoftMax for Face Emotion Detection

Authors: Armin Nabaei, M. Omair Ahmad, M. N. S. Swamy

Abstract:

Many facial expression and emotion recognition methods in the traditional approaches of using LDA, PCA, and EBGM have been proposed. In recent years deep learning models have provided a unique platform addressing by automatically extracting the features for the detection of facial expression and emotions. However, deep networks require large training datasets to extract automatic features effectively. In this work, we propose an efficient emotion detection algorithm using face images when only small datasets are available for training. We design a deep network whose feature extraction capability is enhanced by utilizing several parallel modules between the input and output of the network, each focusing on the extraction of different types of coarse features with fined grained details to break the symmetry of produced information. In fact, we leverage long range dependencies, which is one of the main drawback of CNNs. We develop this work by introducing a Dynamic Soft-Margin SoftMax.The conventional SoftMax suffers from reaching to gold labels very soon, which take the model to over-fitting. Because it’s not able to determine adequately discriminant feature vectors for some variant class labels. We reduced the risk of over-fitting by using a dynamic shape of input tensor instead of static in SoftMax layer with specifying a desired Soft- Margin. In fact, it acts as a controller to how hard the model should work to push dissimilar embedding vectors apart. For the proposed Categorical Loss, by the objective of compacting the same class labels and separating different class labels in the normalized log domain.We select penalty for those predictions with high divergence from ground-truth labels.So, we shorten correct feature vectors and enlarge false prediction tensors, it means we assign more weights for those classes with conjunction to each other (namely, “hard labels to learn”). By doing this work, we constrain the model to generate more discriminate feature vectors for variant class labels. Finally, for the proposed optimizer, our focus is on solving weak convergence of Adam optimizer for a non-convex problem. Our noteworthy optimizer is working by an alternative updating gradient procedure with an exponential weighted moving average function for faster convergence and exploiting a weight decay method to help drastically reducing the learning rate near optima to reach the dominant local minimum. We demonstrate the superiority of our proposed work by surpassing the first rank of three widely used Facial Expression Recognition datasets with 93.30% on FER-2013, and 16% improvement compare to the first rank after 10 years, reaching to 90.73% on RAF-DB, and 100% k-fold average accuracy for CK+ dataset, and shown to provide a top performance to that provided by other networks, which require much larger training datasets.

Keywords: computer vision, facial expression recognition, machine learning, algorithms, depp learning, neural networks

Procedia PDF Downloads 14
3104 In-Game Business and the Problem of Gambling: Legal Analysis of Loot Boxes from the Perspective of Iranian Law

Authors: Vesali Naseh Morteza, Najafi Mohammad Hosein

Abstract:

The possibility of trading in-game items for real money provides a high economic capacity for online games and turns them into a business model. Nowadays, the market for in-game item purchases and microtransactions or micropayments has been growing increasingly. Since the market should be legal, lawyers and lawmakers around the world have expressed concerns over the legality of online gaming and in-game transactions. The issue is highlighted by the recent emergence of an in-game business model in the name of loot boxes. Similarities between loot boxes gaming and gambling features activities have started a legal debate as to whether loot boxes constitute a form of gambling or whether the game’s use of loot boxes should be considered gambling. Hence, based on the relationship between loot boxes purchasing and problem gambling, the paper investigates the legal effect of the newly emergent phenomenon of loot boxes on online games from the perspective of Iranian law.

Keywords: serious games, loot boxes, online gambling, in-game purchase, virtual items

Procedia PDF Downloads 16
3103 LuMee: A Centralized Smart Protector for School Children who are Using Online Education

Authors: Lumindu Dilumka, Ranaweera I. D., Sudusinghe S. P., Sanduni Kanchana A. M. K.

Abstract:

This study was motivated by the challenges experienced by parents and guardians in ensuring the safety of children in cyberspace. In the last two or three years, online education has become very popular all over the world due to the Covid 19 pandemic. Therefore, parents, guardians and teachers must ensure the safety of children in cyberspace. Children are more likely to go astray and there are plenty of online programs are waiting to get them on the wrong track and also, children who are engaging in the online education can be distracted at any moment. Therefore, parents should keep a close check on their children's online activity. Apart from that, due to the unawareness of children, they tempt to share their sensitive information, causing a chance of being a victim of phishing attacks from outsiders. These problems can be overcome through the proposed web-based system. We use feature extraction, web tracking and analysis mechanisms, image processing and name entity recognition to implement this web-based system.

Keywords: online education, cyber bullying, social media, face recognition, web tracker, privacy data

Procedia PDF Downloads 16
3102 Addressing Security and Privacy Issues in a Smart Environment by Using Block-Chain as a Preemptive Technique

Authors: Shahbaz Pervez, Aljawharah Almuhana, Zahida Parveen, Samina Naz, Hira Tariq, Seyed Hosseini, Muhammad Awais Azam

Abstract:

With the latest development in the field of cutting-edge technologies, there is a rapid increase in the use of technology-oriented gadgets. In a recent scenario of the tech era, there is increasing demand to fulfill our day-to-day routine tasks with the help of technological gadgets. We are living in an era of technology where trends have been changing, and a race to introduce a new technology gadget has already begun. Smart cities are getting more popular with every passing day; city councils and governments are under enormous pressure to provide the latest services for their citizens and equip them with all the latest facilities. Thus, ultimately, they are going more into smart cities infrastructure building, providing services to their inhabitants with a single click from their smart devices. This trend is very exciting, but on the other hand, if some incident of security breach happens due to any weaker link, the results would be catastrophic. This paper addresses potential security and privacy breaches with a possible solution by using Blockchain technology in IoT enabled environment.

Keywords: blockchain, cybersecurity, DDOS, intrusion detection, IoT, RFID, smart devices security, smart services

Procedia PDF Downloads 21
3101 Survey of Communication Technologies for IoT Deployments in Developing Regions

Authors: Namugenyi Ephrance Eunice, Julianne Sansa Otim, Marco Zennaro, Stephen D. Wolthusen

Abstract:

The Internet of Things (IoT) is a network of connected data processing devices, mechanical and digital machinery, items, animals, or people that may send data across a network without requiring human-to-human or human-to-computer interaction. Each component has sensors that can pick up on specific phenomena, as well as processing software and other technologies that can link to and communicate with other systems and/or devices over the Internet or other communication networks and exchange data with them. IoT is increasingly being used in fields other than consumer electronics, such as public safety, emergency response, industrial automation, autonomous vehicles, the Internet of Medical Things (IoMT), and general environmental monitoring. Consumer-based IoT applications, like smart home gadgets and wearables, are also becoming more prevalent. This paper presents the main IoT deployment areas for environmental monitoring in developing regions and the backhaul options suitable for them. A detailed review of each of the list of papers selected for the study is included in section III of this document. The study includes an overview of existing IoT deployments, the underlying communication architectures, protocols, and technologies that support them. This overview shows that Low Power Wireless Area Networks (LPWANs), as summarized in Table 1, are very well suited for monitoring environment architectures designed for remote locations. LoRa technology, particularly the LoRaWAN protocol, has an advantage over other technologies due to its low power consumption, adaptability, and suitable communication range. The prevailing challenges of the different architectures are discussed and summarized in Table 3 of the IV section, where the main problem is the obstruction of communication paths by buildings, trees, hills, etc.

Keywords: communication technologies, environmental monitoring, Internet of Things, IoT deployment challenges

Procedia PDF Downloads 15