Search results for: data mining techniques

Authors: Asifa Amara, Prachi Singh, Kanishka, Debargho Pathak, Akshat Kumar, Jayakumar Eravelly

Abstract:

Today's generation is totally dependent on technology that uses data as its fuel. The present study is all about innovations and developments in data science and gives an idea about how efficiently to use the data provided. This study will help to understand the core concepts of data science. The concept of artificial intelligence was introduced by Alan Turing in which the main principle was to create an artificial system that can run independently of human-given programs and can function with the help of analyzing data to understand the requirements of the users. Data science comprises business understanding, analyzing data, ethical concerns, understanding programming languages, various fields and sources of data, skills, etc. The usage of data science has evolved over the years. In this review article, we have covered a part of data science, i.e., machine learning. Machine learning uses data science for its work. Machines learn through their experience, which helps them to do any work more efficiently. This article includes a comparative study image between human understanding and machine understanding, advantages, applications, and real-time examples of machine learning. Data science is an important game changer in the life of human beings. Since the advent of data science, we have found its benefits and how it leads to a better understanding of people, and how it cherishes individual needs. It has improved business strategies, services provided by them, forecasting, the ability to attend sustainable developments, etc. This study also focuses on a better understanding of data science which will help us to create a better world.

Keywords: data science, machine learning, data analytics, artificial intelligence

Procedia PDF Downloads 82

Authors: Yude Wu

Abstract:

Mongolia, grappling with significant socio-economic challenges, faces pressing issues of inequality and poverty, as evidenced by a high Gini coefficient and the highest poverty rate among the top 20 largest Asian countries. Despite government efforts, Mongolia's poverty rate experienced only a slight reduction from 29.6 percent in 2016 to 27.8 percent in 2020. PEER countries, such as South Africa, Botswana, Kazakhstan, and Peru, share characteristics with Mongolia, including reliance on the mining industry and classification as lower middle-income countries. Successful transitions of these countries to upper middle-income status between 1994 and the 2010s provide valuable insights. Drawing on secondary analyses of existing research and PEER country profiles, the study evaluates past policies, identifies gaps in current approaches, and proposes recommendations to combat poverty sustainably. The hypothesis includes a reliance on the mining industry and a transition from lower to upper middle-income status. Policies from these countries, such as the GEAR policy in South Africa and economic diversification in Botswana, offer insights into Mongolia's development. This essay aims to illuminate the multidimensional nature of underdevelopment in Mongolia through a secondary analysis of existing research and PEER country profiles, evaluating past policies, identifying gaps in current approaches, and providing recommendations for sustainable progress. Drawing inspiration from PEER countries, Mongolia can implement policies such as economic diversification to reduce vulnerability and create stable job opportunities. Emphasis on infrastructure, human capital, and strategic partnerships for Foreign Direct Investment (FDI) aligns with successful strategies implemented by PEER countries, providing a roadmap for Mongolia's development objectives.

Keywords: inequality, PEER countries, comparative analysis, nomadic animal husbandry, sustainable growth

Procedia PDF Downloads 63

Authors: Faith Eweluegim Enahoro-Ofagbe

Abstract:

Water is essential for sustaining life. As a limited resource, effective water management is vital. Water scarcity has become more common due to the effects of climate change, land degradation, deforestation, and population growth, especially in rural communities, which are more susceptible to water-related issues such as water shortage, water-borne disease, et c., due to the unsuccessful implementation of water policies and projects in Nigeria. Since rural communities generate the majority of agricultural products, they significantly impact on water management for sustainability. The development of methods to advance this goal for residential and agricultural usage in the present and the future is a challenge for rural residents. This study evaluated rural water supply systems and irrigation management techniques to conserve water in Kwara State, North-Central Nigeria. Suggesting some measures to conserve water resources for sustainability, off-season farming, and socioeconomic security that will remedy water degradation, unemployment which is one of the causes of insecurity in the country, by considering the use of fabricated or locally made irrigation equipment, which are affordable by rural farmers, among other recommendations. Questionnaires were distributed to respondents in the study area for quantitative evaluation of irrigation methods practices. For physicochemical investigation, samples were also gathered from their available water sources. According to the study's findings, 30 percent of farmers adopted intelligent irrigation management techniques to conserve water resources, saving 45% of the water previously used for irrigation. 70 % of farmers practice seasonal farming. Irrigation water is drawn from river channels, streams, and unlined and unprotected wells. 60% of these rural residents rely on private boreholes for their water needs, while 40% rely on government-supplied rural water. Therefore, the government must develop additional water projects, raise awareness, and offer irrigation techniques that are simple to adapt for water management, increasing socio-economic productivity, security, and water sustainability.

Keywords: water resource management, sustainability, irrigation, rural water management, irrigation management technique

Procedia PDF Downloads 111

Authors: M. Al-Shamery, R. Young, P. Birch, C. Chatwin

Abstract:

Computer Generated Holography (CGH) is employed to create digitally defined coherent wavefronts. A CGH can be created by using different techniques such as by using a detour-phase technique or by direct phase modulation to create a kinoform. The detour-phase technique was one of the first techniques that was used to generate holograms digitally. The disadvantage of this technique is that the reconstructed image often has poor quality due to the limited dynamic range it is possible to record using a medium with reasonable spatial resolution.. The kinoform (phase-only hologram) is an alternative technique. In this method, the phase of the original wavefront is recorded but the amplitude is constrained to be constant. The original object does not need to exist physically and so the kinoform can be used to reconstruct an almost arbitrary wavefront. However, the image reconstructed by this technique contains high levels of noise and is not identical to the reference image. To improve the reconstruction quality of the kinoform, iterative techniques such as the Gerchberg-Saxton algorithm (GS) are employed. In this paper the GS algorithm is described for the optimisation of a kinoform used for the reconstruction of a complex wavefront. Iterations of the GS algorithm are applied to determine the phase at a plane (with known amplitude distribution which is often taken as uniform), that satisfies given phase and amplitude constraints in a corresponding Fourier plane. The GS algorithm can be used in this way to enhance the reconstruction quality of the kinoform. Different images are employed as the reference object and their kinoform is synthesised using the GS algorithm. The quality of the reconstructed images is quantified to demonstrate the enhanced reconstruction quality achieved by using this method.

Keywords: computer generated holography, digital holography, Gerchberg-Saxton algorithm, kinoform

Procedia PDF Downloads 533

Authors: Nedal N. Marei, Nashaat Nassar

Abstract:

Many treatment techniques have been used to remove the soluble pollutants from wastewater as; dyes and metal ions which could be found in rich amount in the used water of the textile and tanneries industry. The effluents from these industries are complex, containing a wide variety of dyes and other contaminants, such as dispersants, acids, bases, salts, detergents, humectants, oxidants, and others. These techniques can be divided into physical, chemical, and biological methods. Adsorption has been developed as an efficient method for the removal of heavy metals from contaminated water and soil. It is now recognized as an effective method for the removal of both organic and inorganic pollutants from wastewaters. Nanosize materials are new functional materials, which offer high surface area and have come up as effective adsorbents. Nano alumina is one of the most important ceramic materials widely used as an electrical insulator, presenting exceptionally high resistance to chemical agents, as well as giving excellent performance as a catalyst for many chemical reactions, in microelectronic, membrane applications, and water and wastewater treatment. In this study, methylene blue (MB) dye has been used as model dye of textile wastewater in order to synthesize a synthetic MB wastewater. NiO nanoparticles were added in small percentage in the sand packed bed adsorption columns to remove the MB from the synthetic textile wastewater. Moreover, different parameters have been evaluated; flow of the synthetic wastewater, pH, height of the bed, percentage of the NiO to the sand in the packed material. Different mathematical models where employed to find the proper model which describe the experimental data and help to analyze the mechanism of the MB adsorption. This study will provide good understanding of the dyes adsorption using metal oxide nanoparticles in the classical sand bed.

Keywords: adsorption, column, nanoparticles, methylene

Procedia PDF Downloads 269

Authors: Ramzi Rihane, Yassine Benayed

Abstract:

Epilepsy is a chronic neurological disorder characterized by recurrent, unprovoked seizures resulting from abnormal electrical activity in the brain. Timely and accurate detection of these seizures is essential for improving patient care. In this study, we leverage the UK Bonn University open-source EEG dataset and employ advanced deep-learning techniques to automate the detection of epileptic seizures. By extracting key features from both time and frequency domains, as well as Spectrogram features, we enhance the performance of various deep learning models. Our investigation includes architectures such as Long Short-Term Memory (LSTM), Bidirectional LSTM (Bi-LSTM), 1D Convolutional Neural Networks (1D-CNN), and hybrid CNN-LSTM and CNN-BiLSTM models. The models achieved impressive accuracies: LSTM (98.52%), Bi-LSTM (98.61%), CNN-LSTM (98.91%), CNN-BiLSTM (98.83%), and CNN (98.73%). Additionally, we utilized a data augmentation technique called SMOTE, which yielded the following results: CNN (97.36%), LSTM (97.01%), Bi-LSTM (97.23%), CNN-LSTM (97.45%), and CNN-BiLSTM (97.34%). These findings demonstrate the effectiveness of deep learning in capturing complex patterns in EEG signals, providing a reliable and scalable solution for real-time seizure detection in clinical environments.

Keywords: electroencephalogram, epileptic seizure, deep learning, LSTM, CNN, BI-LSTM, seizure detection

Procedia PDF Downloads 14

Authors: Bahram Khan, Anderson Rocha Ramos, Rui R. Paulo, Fernando J. Velez

Abstract:

With the growing demand for a new blend of applications, the users dependency on the internet is increasing day by day. Mobile internet users are giving more attention to their own experiences, especially in terms of communication reliability, high data rates and service stability on move. This increase in the demand is causing saturation of existing radio frequency bands. To address these challenges, researchers are investigating the best approaches, Carrier Aggregation (CA) is one of the newest innovations, which seems to fulfill the demands of the future spectrum, also CA is one the most important feature for Long Term Evolution - Advanced (LTE-Advanced). For this purpose to get the upcoming International Mobile Telecommunication Advanced (IMT-Advanced) mobile requirements (1 Gb/s peak data rate), the CA scheme is presented by 3GPP, which would sustain a high data rate using widespread frequency bandwidth up to 100 MHz. Technical issues such as aggregation structure, its implementations, deployment scenarios, control signal techniques, and challenges for CA technique in LTE-Advanced, with consideration of backward compatibility, are highlighted in this paper. Also, performance evaluation in macro-cellular scenarios through a simulation approach is presented, which shows the benefits of applying CA, low-complexity multi-band schedulers in service quality, system capacity enhancement and concluded that enhanced multi-band scheduler is less complex than the general multi-band scheduler, which performs better for a cell radius longer than 1800 m (and a PLR threshold of 2%).

Keywords: component carrier, carrier aggregation, LTE-advanced, scheduling

Procedia PDF Downloads 199

Authors: Se-Hyuk Park, Hee-Jung Seo

Abstract:

Previous studies have investigated effective coping strategies for excessive stress, positive adaptation, resilience, mental health, and personal growth. However, to the best of the authors' knowledge, little research has been conducted to investigate how Koreans with physical disabilities deal with the COVID-19 pandemic. The purpose of this study was to identify coping strategies and coping resources that Koreans with physical disabilities utilized during the COVID-19 crisis. This study used semi-structured, in-depth interviews with 15 participants. Data were qualitatively analyzed using the constant comparative method with content mapping and content mining questions. We identified three salient themes that were used by participants as coping strategies to deal with various COVID-related challenges: (a) engagement in meaningful activities, (b) improvement of social and emotional support, and (c) experience of resilience. The findings of the present study highlighted that Korean adults with SCI actively engaged in various leisure activities, maintained and developed closer social relationships, and experienced resilience to face COVID-19-related stressors. These coping strategies were noted as a catalyst for physical health as well as psychological well-being of individuals with SCI.

Keywords: spinal cord injury, covid-19 pandemic, coping strategies, coping resources, leisure

Procedia PDF Downloads 43

Authors: Monirah Alkathiry, Hanan Aljarwan

Abstract:

Cloud computing is one of the most significant technologies that the world deals with, in different sectors with different purposes and capabilities. The cloud faces various challenges in securing data from unauthorized access or modification. Consequently, security risks and levels have greatly increased. Therefore, cloud service providers (CSPs) and users need secure mechanisms that ensure that data are kept secret and safe from any disclosures or exploits. For this reason, CSPs need a number of techniques and technologies to manage and secure access to the cloud services to achieve security goals, such as confidentiality, integrity, identity access management (IAM), etc. Therefore, this paper will review and explore various access controls implemented in a cloud environment that achieve different security purposes. The methodology followed in this survey was conducting an assessment, evaluation, and comparison between those access controls mechanisms and technologies based on different factors, such as the security goals it achieves, usability, and cost-effectiveness. This assessment resulted in the fact that the technology used in an access control affects the security goals it achieves as well as there is no one access control method that achieves all security goals. Consequently, such a comparison would help decision-makers to choose properly the access controls that meet their requirements.

Keywords: access controls, cloud computing, confidentiality, identity and access management

Procedia PDF Downloads 131

Authors: Duncan Wallace, M-Tahar Kechadi

Abstract:

In recent years, Machine Learning (ML) approaches have been successfully applied to an analysis of patient symptom data in the context of disease diagnosis, at least where such data is well codified. However, much of the data present in Electronic Health Records (EHR) are unlikely to prove suitable for classic ML approaches. Furthermore, as scores of data are widely spread across both hospitals and individuals, a decentralized, computationally scalable methodology is a priority. The focus of this paper is to develop a method to predict outliers in an out-of-hours healthcare provision center (OOHC). In particular, our research is based upon the early identification of patients who have underlying conditions which will cause them to repeatedly require medical attention. OOHC act as an ad-hoc delivery of triage and treatment, where interactions occur without recourse to a full medical history of the patient in question. Medical histories, relating to patients contacting an OOHC, may reside in several distinct EHR systems in multiple hospitals or surgeries, which are unavailable to the OOHC in question. As such, although a local solution is optimal for this problem, it follows that the data under investigation is incomplete, heterogeneous, and comprised mostly of noisy textual notes compiled during routine OOHC activities. Through the use of Deep Learning methodologies, the aim of this paper is to provide the means to identify patient cases, upon initial contact, which are likely to relate to such outliers. To this end, we compare the performance of Long Short-Term Memory, Gated Recurrent Units, and combinations of both with Convolutional Neural Networks. A further aim of this paper is to elucidate the discovery of such outliers by examining the exact terms which provide a strong indication of positive and negative case entries. While free-text is the principal data extracted from EHRs for classification, EHRs also contain normalized features. Although the specific demographical features treated within our corpus are relatively limited in scope, we examine whether it is beneficial to include such features among the inputs to our neural network, or whether these features are more successfully exploited in conjunction with a different form of a classifier. In this section, we compare the performance of randomly generated regression trees and support vector machines and determine the extent to which our classification program can be improved upon by using either of these machine learning approaches in conjunction with the output of our Recurrent Neural Network application. The output of our neural network is also used to help determine the most significant lexemes present within the corpus for determining high-risk patients. By combining the confidence of our classification program in relation to lexemes within true positive and true negative cases, with an inverse document frequency of the lexemes related to these cases, we can determine what features act as the primary indicators of frequent-attender and non-frequent-attender cases, providing a human interpretable appreciation of how our program classifies cases.

Keywords: artificial neural networks, data-mining, machine learning, medical informatics

Procedia PDF Downloads 131

Authors: Zulkiflee Abd Latif, Sitinor Atikah Nordin, Alawi Sulaiman

Abstract:

Different tree species possess different and various benefits. Arenga Pinnata tree species own several potential uses that is valuable for the economy and the country. Mapping vegetation using remote sensing technique involves various process, techniques and consideration. Using satellite imagery, this method enables the access of inaccessible area and with the availability of near infra-red band; it is useful in vegetation analysis, especially in identifying tree species. Pixel-based and object-based classification technique is used as a method in this study. Pixel-based classification technique used in this study divided into unsupervised and supervised classification. Object based classification technique becomes more popular another alternative method in classification process. Using spectral, texture, color and other information, to classify the target make object-based classification is a promising technique for classification. Classification of Arenga Pinnata trees is overlaid with elevation, slope and aspect, soil and river data and several other data to give information regarding the tree character and living environment. This paper will present the utilization of remote sensing technique in order to map Arenga Pinnata tree species

Keywords: Arenga Pinnata, pixel-based classification, object-based classification, remote sensing

Procedia PDF Downloads 380

Authors: Meghamala Nugehally

Abstract:

This paper hypothesises and draws inferences on the impact of minimalism in dance education on the development of artistic and aesthetic sensibilities in individuals in the age group of 5-18 yrs of age. This research and conclusions are within the context of Indian Classical Dance, which is based on Indian theories of aesthetics drawn from the Natyashastra, an ancient treatise on Indian dance and drama. The research employs training methods handed down through a strict one-on-one teacher-student tradition known as the Guru-Shishya Parampara. Aesthetic principles used are defined, and basic theories from the Natyashastra are explained to provide background for the research design. The paper also discusses dance curriculum design and training methodology design within the context of these aesthetic theories. The scope of the research is limited to two genres of Indian classical forms: Bharatanatyam and Odissi. A brief description of these dance forms is given as background and dance aesthetics specific to these forms are described. The research design includes individual case studies of subjects studied, independent predetermined attributes for observations and a qualitative scoring methodology devised for the purpose of the study. The study describes the training techniques used and contrasts minimal solo training techniques with the more elaborate group training techniques. Study groups were divided and the basis for the division are discussed. Study observations are recorded and presented as evidences. The results inform the conclusion and set the stage for further research in this area.

Keywords: dance aesthetics, dance education, Indian classical dance, minimalism

Procedia PDF Downloads 228

Authors: Zunaira Zaman, David Bohannon

Abstract:

This study explores the application of machine learning (ML) for detecting security vulnerabilities in source code. The research aims to assist organizations with large application portfolios and limited security testing capabilities in prioritizing security activities. ML-based approaches offer benefits such as increased confidence scores, false positives and negatives tuning, and automated feedback. The initial approach using natural language processing techniques to extract features achieved 86% accuracy during the training phase but suffered from overfitting and performed poorly on unseen datasets during testing. To address these issues, the study proposes using the abstract syntax tree (AST) for Java and C++ codebases to capture code semantics and structure and generate path-context representations for each function. The Code2Vec model architecture is used to learn distributed representations of source code snippets for training a machine-learning classifier for vulnerability prediction. The study evaluates the performance of the proposed methodology using two datasets and compares the results with existing approaches. The Devign dataset yielded 60% accuracy in predicting vulnerable code snippets and helped resist overfitting, while the Juliet Test Suite predicted specific vulnerabilities such as OS-Command Injection, Cryptographic, and Cross-Site Scripting vulnerabilities. The Code2Vec model achieved 75% accuracy and a 98% recall rate in predicting OS-Command Injection vulnerabilities. The study concludes that even partial AST representations of source code can be useful for vulnerability prediction. The approach has the potential for automated intelligent analysis of source code, including vulnerability prediction on unseen source code. State-of-the-art models using natural language processing techniques and CNN models with ensemble modelling techniques did not generalize well on unseen data and faced overfitting issues. However, predicting vulnerabilities in source code using machine learning poses challenges such as high dimensionality and complexity of source code, imbalanced datasets, and identifying specific types of vulnerabilities. Future work will address these challenges and expand the scope of the research.

Keywords: code embeddings, neural networks, natural language processing, OS command injection, software security, code properties

Procedia PDF Downloads 107

Authors: Shoumodip Roy, Ankit Singhania, Santanu Mallick, Abhiram Jha, M. K. Agarwal, R. V. Ramna, Uttam Singh

Abstract:

The quality of hot metal at any blast furnace is judged by the silicon content in it. Lower hot metal silicon not only enhances process efficiency at steel melting shops but also reduces hot metal costs. The Hot metal produced at G-Blast furnace Tata Steel Jamshedpur has a significantly higher Si content than Benchmark Blast furnaces. The higher content of hot metal Si is mainly due to inferior raw material quality than those used in benchmark blast furnaces. With minimum control over raw material quality, the only option left to control hot metal Si is via optimizing the furnace parameters. Therefore, in order to identify the levers to reduce hot metal Si, Data mining was carried out, and multiple regression models were developed. The statistical analysis revealed that Slag B3{(CaO+MgO)/SiO2}, Slag Alumina and Hot metal temperature are key controllable parameters affecting hot metal silicon. Contour Plots were used to determine the optimum range of levels identified through statistical analysis. A trial plan was formulated to operate relevant parameters, at G blast furnace, in the identified range to reduce hot metal silicon. This paper details out the process followed and subsequent reduction in hot metal silicon by 15% at G blast furnace.

Keywords: blast furnace, optimization, silicon, statistical tools

Procedia PDF Downloads 223

Authors: Onimisi Ekuh Abdullahi, Lasbat Omoshalewa Akinsemoyin

Abstract:

In Nigeria, over two decades now, there has been a steady increase in the insecurity of human lives and physical properties. In the South-South Nigeria, there is an acute insecurity of militants destroying oil pipe-lines and kidnapping cases; in the Middle-Belt zone, insecurity centers on kidnapping and in a few states crises between Herdsmen and Farmers range like wildfire; in the South-Western zone, kidnapping is vile, in the North-East zone the issue of Boko Haram has become World-wide concern, and in North-west zone, cattle rustlers and religious crisis are of great concern. At the initial stage, the Nigerian Police Force was called upon to quell the crisis. It soon became obvious that the dimension of the crisis was beyond police force. The Nigerian Armed Forces were called to maintain peace and order because the magnitude of the crisis was threatening the national unity and cohesion. The main objective of this paper, was to examine the investigative techniques of criminal by the military in Nigeria. Specifically to examine the physical and psychological force; the abusive techniques and tactics; and suggest modern psychological techniques of interrogating criminals accepted to Human Right Activists and the rule of law. The process is to create room behaviour and practices that carefully monitored the trust and reliability of admissions produced by Psychological manipulative process in Nigeria.

Keywords: military, Nigerian criminal, physical, psychological force

Procedia PDF Downloads 160

Authors: Ashley Venerable, Rosario Tatlonghari

Abstract:

This study identified how college deaf students of Bartimaeus Center for Alternative Learning in Tiaong, Quezon, Philippines view development using visual communication techniques and generating themes from responses. Complete enumeration was employed. Guided by Constructivist Theory of Perception, past experiences and stored information influenced perception. These themes of development emerged: social development; pleasant environment; interpersonal relationships; availability of resources; employment; infrastructure development; values; and peace and security. Using the National Economic and Development Authority development indicators, findings showed the deaf students’ views on development were similar from the mainstream views. Responses also became more meaningful through visual communication techniques.

Keywords: deaf, development, perception, development indicators, visual communication

Procedia PDF Downloads 431

Authors: Sharon Q. Yang, Robert J. Congleton

Abstract:

Information security is a broad concept that covers any issues and concerns about the proper access and use of information on the Internet, including measures and procedures to protect intellectual property and private data from illegal access and online theft; the act of hacking; and any defensive technologies that contest such cybercrimes. As more research and commercial activities are conducted online, cybercrimes have increased significantly, putting sensitive information at risk. Information security has become critically important for organizations and private citizens alike. Hackers scan for network vulnerabilities on the Internet and steal data whenever they can. Cybercrimes disrupt our daily life, cause financial losses, and instigate fear in the public. Since the start of the pandemic, most data related cybercrimes targets have been either financial or health information from companies and organizations. Libraries also should have a high interest in understanding and adopting information security methods to protect their patron data and copyrighted materials. But according to information security professionals, higher education and cultural organizations, including their libraries, are the least prepared entities for cyberattacks. One recent example is that of Steven’s Institute of Technology in New Jersey in the US, which had its network hacked in 2020, with the hackers demanding a ransom. As a result, the network of the college was down for two months, causing serious financial loss. There are other cases where libraries, colleges, and universities have been targeted for data breaches. In order to build an effective defense, we need to understand the most common types of cybercrimes, including phishing, whaling, social engineering, distributed denial of service (DDoS) attacks, malware and ransomware, and hacker profiles. Our research will focus on each hacking technique and related defense measures; and the social background and reasons/purpose of hacker and hacking. Our research shows that hacking techniques will continue to evolve as new applications, housing information, and data on the Internet continue to be developed. Some cybercrimes can be stopped with effective measures, while others present challenges. It is vital that people understand what they face and the consequences when not prepared.

Keywords: cybercrimes, hacking technologies, higher education, information security, libraries

Procedia PDF Downloads 134

Authors: Ali Kazemi

Abstract:

The digital evolution of financial services, while offering unprecedented convenience and accessibility, has also escalated the vulnerabilities to fraudulent activities. In this study, we introduce a distinct approach to real-time anomaly detection in financial transactions, aiming to fortify the defenses of banking and financial institutions against such threats. Utilizing unsupervised machine learning algorithms, specifically autoencoders and isolation forests, our research focuses on identifying irregular patterns indicative of fraud within transactional data, thus enabling immediate action to prevent financial loss. The data we used in this study included the monetary value of each transaction. This is a crucial feature as fraudulent transactions may have distributions of different amounts than legitimate ones, such as timestamps indicating when transactions occurred. Analyzing transactions' temporal patterns can reveal anomalies (e.g., unusual activity in the middle of the night). Also, the sector or category of the merchant where the transaction occurred, such as retail, groceries, online services, etc. Specific categories may be more prone to fraud. Moreover, the type of payment used (e.g., credit, debit, online payment systems). Different payment methods have varying risk levels associated with fraud. This dataset, anonymized to ensure privacy, reflects a wide array of transactions typical of a global banking institution, ranging from small-scale retail purchases to large wire transfers, embodying the diverse nature of potentially fraudulent activities. By engineering features that capture the essence of transactions, including normalized amounts and encoded categorical variables, we tailor our data to enhance model sensitivity to anomalies. The autoencoder model leverages its reconstruction error mechanism to flag transactions that deviate significantly from the learned normal pattern, while the isolation forest identifies anomalies based on their susceptibility to isolation from the dataset's majority. Our experimental results, validated through techniques such as k-fold cross-validation, are evaluated using precision, recall, and the F1 score alongside the area under the receiver operating characteristic (ROC) curve. Our models achieved an F1 score of 0.85 and a ROC AUC of 0.93, indicating high accuracy in detecting fraudulent transactions without excessive false positives. This study contributes to the academic discourse on financial fraud detection and provides a practical framework for banking institutions seeking to implement real-time anomaly detection systems. By demonstrating the effectiveness of unsupervised learning techniques in a real-world context, our research offers a pathway to significantly reduce the incidence of financial fraud, thereby enhancing the security and trustworthiness of digital financial services.

Keywords: anomaly detection, financial fraud, machine learning, autoencoders, isolation forest, transactional data analysis

Procedia PDF Downloads 57

Authors: Christopher Muhawe, Masooda Bashir

Abstract:

With increased Internet Communication Technology(ICT), the virtual world has become the new normal. At the same time, there is an unprecedented collection of massive amounts of data by both private and public entities. Unfortunately, this increase in data collection has been in tandem with an increase in data misuse and data breach. Regrettably, the majority of data breach and data misuse claims have been unsuccessful in the United States courts for the failure of proof of direct injury to physical or economic interests. The requirement to express data privacy harms from an economic or physical stance negates the fact that not all data harms are physical or economic in nature. The challenge is compounded by the fact that data breach harms and risks do not attach immediately. This research will use a descriptive and normative approach to show that not all data harms can be expressed in economic or physical terms. Expressing privacy harms purely from an economic or physical harm perspective negates the fact that data insecurity may result into harms which run counter the functions of privacy in our lives. The promotion of liberty, selfhood, autonomy, promotion of human social relations and the furtherance of the existence of a free society. There is no economic value that can be placed on these functions of privacy. The proposed approach addresses data harms from a psychological and social perspective.

Keywords: data breach and misuse, economic harms, privacy harms, psychological harms

Procedia PDF Downloads 195

Authors: V. S. Binu, Amitha Puranik, Sintomon Mathew, Sebin Thomas

Abstract:

Globally, women are more vulnerable to various forms of crimes than males. The crimes that are directed specifically towards women are classified as crime against women. Crime against women in India is observed to increase year after year and according to the National Crime Records Bureau (NCRB) report, in 2014 there was an increase of 9.2% cases of crime against women compared to the previous year. The violence in a population depends on socio-demographic factors, unemployment, poverty, number of police officials etc. There are very few studies that explored to identify hotspots of various types of crime against women in India. Hotspots are geographical regions where the number of observed cases is more than the expected number for that region. It is important to identify the hotspots of crime against women in India in order to control and prevent violence against women in that region. The goal of this study is to identify the hotspots of crime against women in India using spatial data analysis techniques. For the present study, we used the district level data of various types of crime against women in India in the year 2011 published by NCRB and the 2011 Census population in each of these districts. The study used spatial scan statistic to identify the hotspots using SaTScan software.

Keywords: crime, hotspots, India, Satscan, Women

Procedia PDF Downloads 413

Authors: I. V. Pinto, M. R. Sooriyarachchi

Abstract:

It can be frequently observed that the data arising in our environment have a hierarchical or a nested structure attached with the data. Multilevel modelling is a modern approach to handle this kind of data. When multilevel modelling is combined with a binary response, the estimation methods get complex in nature and the usual techniques are derived from quasi-likelihood method. The estimation methods which are compared in this study are, marginal quasi-likelihood (order 1 & order 2) (MQL1, MQL2) and penalized quasi-likelihood (order 1 & order 2) (PQL1, PQL2). A statistical model is of no use if it does not reflect the given dataset. Therefore, checking the adequacy of the fitted model through a goodness-of-fit (GOF) test is an essential stage in any modelling procedure. However, prior to usage, it is also equally important to confirm that the GOF test performs well and is suitable for the given model. This study assesses the suitability of the GOF test developed for binary response multilevel models with respect to the method used in model estimation. An extensive set of simulations was conducted using MLwiN (v 2.19) with varying number of clusters, cluster sizes and intra cluster correlations. The test maintained the desirable Type-I error for models estimated using PQL2 and it failed for almost all the combinations of MQL. Power of the test was adequate for most of the combinations in all estimation methods except MQL1. Moreover, models were fitted using the four methods to a real-life dataset and performance of the test was compared for each model.

Keywords: goodness-of-fit test, marginal quasi-likelihood, multilevel modelling, penalized quasi-likelihood, power, quasi-likelihood, type-I error

Procedia PDF Downloads 142

Authors: K. K. Soundra Pandian, Bhupendra Gupta

Abstract:

In the modern era, as the application data’s are massive and complex, it needs to be secured from the adversary attack. In this context, a non-recursive key based integrated spritz stream cipher with the circulant hash function using delayed feedback with carry shift register (d-FCSR) is proposed in this paper. The novelty of this proposed stream cipher algorithm is to engender the improved keystream using d-FCSR. The proposed algorithm is coded using Verilog HDL to produce dynamic binary key stream and implemented on commercially available FPGA device Virtex 5 xc5vlx110t-2ff1136. The implementation of stream cipher using d-FCSR on the FPGA device operates at a maximum frequency of 60.62 MHz. It achieved the data throughput of 492 Mbps and improved in terms of efficiency (throughput/area) compared to existing techniques. This paper also briefs the cryptanalysis of proposed circulant hash value based spritz stream cipher using d-FCSR is against the adversary attack on a hardware platform for the hardware based cryptography applications.

Keywords: cryptography, circulant function, field programmable gated array, hash value, spritz stream cipher

Procedia PDF Downloads 250

Authors: Ali El Ksimi

Abstract:

In today's digital academic environment, secure authentication methods are essential for managing sensitive user data, including that of students and faculty. The rise in cyber threats and data breaches has exposed the vulnerabilities of traditional authentication systems used in universities. Passwords, often the first line of defense, are particularly susceptible to hacking, phishing, and brute-force attacks. While multi-factor authentication (MFA) provides an additional layer of security, it can still be compromised and often adds complexity and inconvenience for users. As universities seek more robust security measures, blockchain technology emerges as a promising solution. Renowned for its decentralization, immutability, and transparency, blockchain has the potential to transform how user management is conducted in academic institutions. In this article, we explore a system that leverages blockchain technology specifically for managing user accounts within a university setting. The system enables the secure creation and management of accounts for different roles, such as administrators, teachers, and students. Each user is authenticated through a decentralized application (DApp) that ensures their data is securely stored and managed on the blockchain. By eliminating single points of failure and utilizing cryptographic techniques, the system enhances the security and integrity of user management processes. We will delve into the technical architecture, security benefits, and implementation considerations of this approach. By integrating blockchain into user management, we aim to address the limitations of traditional systems and pave the way for the future of digital security in education.

Keywords: blockchain, university, authentication, decentralization, cybersecurity, user management, privacy

Procedia PDF Downloads 24

Authors: Baris Sezer

Abstract:

A great number of projects have been implemented by Turkey in order to integrate technologies into education. The FATİH Project is intended to integrate technology into all levels of education in Turkey. As part of the FATİH Project that is aimed to complete in 2016, it is intended to initially deliver a tablet PC to every student and teacher. We aimed to detect grade 9 students’ acceptance perception level of tablet PCs during the 2014 – 2015 school year in this study where quantitative and qualitative data collection techniques were used in combination. The study group consisted of 228 grade 9 students of high schools in Istanbul, Ankara, Zonguldak and Bursa in Turkey. Study data was obtained through the “Tablet PC Acceptance Scale” and structured interview forms. Given the results obtained from the study, the mean overall score was 70.08 (3.72 out of 5), which was derived from all the dimensions of the acceptance perception level of tablet PCs in the students’ view. Findings of the study indicate that mean scores for students’ acceptance perception level of tablet PCs did not differ by their gender and their level of use of Information and Communication Technology (ICT). Focus group interviews with students suggest that students did not effectively and actively use the tablet PCs; instead they used the interactive board during classes.

Keywords: acceptance of technology, student’s view, FATIH project, tablet PCs

Procedia PDF Downloads 293

Authors: Chandra Prayaga, Aaron Wade, Lakshmi Prayaga, Gopi Shankar Mallu

Abstract:

This paper presents the use of machine learning algorithms to predict the success of students in an introductory physics course. Data having 140 rows pertaining to the performance of two batches of students was used. The lack of sufficient data to train robust machine learning models was compensated for by generating synthetic data similar to the real data. CTGAN and CTGAN with Gaussian Copula (Gaussian) were used to generate synthetic data, with the real data as input. To check the similarity between the real data and each synthetic dataset, pair plots were made. The synthetic data was used to train machine learning models using the PyCaret package. For the CTGAN data, the Ada Boost Classifier (ADA) was found to be the ML model with the best fit, whereas the CTGAN with Gaussian Copula yielded Logistic Regression (LR) as the best model. Both models were then tested for accuracy with the real data. ROC-AUC analysis was performed for all the ten classes of the target variable (Grades A, A-, B+, B, B-, C+, C, C-, D, F). The ADA model with CTGAN data showed a mean AUC score of 0.4377, but the LR model with the Gaussian data showed a mean AUC score of 0.6149. ROC-AUC plots were obtained for each Grade value separately. The LR model with Gaussian data showed consistently better AUC scores compared to the ADA model with CTGAN data, except in two cases of the Grade value, C- and A-.

Keywords: machine learning, student success, physics course, grades, synthetic data, CTGAN, gaussian copula CTGAN

Procedia PDF Downloads 44

Authors: Adewoyin O. Olusegun, Emmanuel O. Joshua, Marvel L. Akinyemi

Abstract:

The heterogeneous nature of the subsurface requires the use of factual information to deal with rather than assumptions or generalized equations. Therefore, there is need to determine the actual rate of settlement possible in the soil before structures are built on it. This information will help in determining the type of foundation design and the kind of reinforcement that will be necessary in constructions. This paper presents a simplified and a faster approach for determining foundation settlement in any type of soil using real field data acquired from seismic refraction techniques and cone penetration tests. This approach was also able to determine the depth of settlement of each strata of soil. The results obtained revealed the different settlement time and depth of settlement possible.

Keywords: heterogeneous, settlement, foundation, seismic, technique

Procedia PDF Downloads 445

Authors: Diego Aguirre, Olac Fuentes

Abstract:

In this paper, we present a taxonomy of weight initialization schemes used in deep learning. We survey the most representative techniques in each class and compare them in terms of overhead cost, convergence rate, and applicability. We also introduce a new weight initialization scheme. In this technique, we perform an initial feedforward pass through the network using an initialization mini-batch. Using statistics obtained from this pass, we initialize the weights of the network, so the following properties are met: 1) weight matrices are orthogonal; 2) ReLU layers produce a predetermined number of non-zero activations; 3) the output produced by each internal layer has a unit variance; 4) weights in the last layer are chosen to minimize the error in the initial mini-batch. We evaluate our method on three popular architectures, and a faster converge rates are achieved on the MNIST, CIFAR-10/100, and ImageNet datasets when compared to state-of-the-art initialization techniques.

Keywords: deep learning, image classification, supervised learning, weight initialization

Procedia PDF Downloads 135

Authors: Chuping Lo

Abstract:

This paper presents a simple model demonstrating that ceteris paribus countries with lower barriers to accessing global data tend to earn higher incomes than other countries. Therefore, large countries that inherently have greater data resources tend to have higher incomes than smaller countries, such that the former may be more hesitant than the latter to liberalize cross-border data flows to maintain this advantage. Furthermore, countries with higher artificial intelligence (AI) intensity in production technologies tend to benefit more from economies of scale in data aggregation, leading to higher income and more trade as they are better able to utilize global data.

Keywords: digital intensity, digital divide, international trade, scale of economics

Procedia PDF Downloads 68

Authors: G. R. Navaneesh, E. Nagarajan, C. H. Rajam Raju

Abstract:

Nowadays the multimedia data are used to store some secure information. All previous methods allocate a space in image for data embedding purpose after encryption. In this paper, we propose a novel method by reserving space in image with a boundary surrounded before encryption with a traditional RDH algorithm, which makes it easy for the data hider to reversibly embed data in the encrypted images. The proposed method can achieve real time performance, that is, data extraction and image recovery are free of any error. A secure transmission process is also discussed in this paper, which improves the efficiency by ten times compared to other processes as discussed.

Keywords: secure communication, reserving room before encryption, least significant bits, image encryption, reversible data hiding

Procedia PDF Downloads 412

Authors: Fuad M. Alkoot

Abstract:

DNA data have been used in forensics for decades. However, current research looks at using the DNA as a biometric identity verification modality. The goal is to improve the speed of identification. We aim at using gene data that was initially used for autism detection to find if and how accurate is this data for identification applications. Mainly our goal is to find if our data preprocessing technique yields data useful as a biometric identification tool. We experiment with using the nearest neighbor classifier to identify subjects. Results show that optimal classification rate is achieved when the test set is corrupted by normally distributed noise with zero mean and standard deviation of 1. The classification rate is close to optimal at higher noise standard deviation reaching 3. This shows that the data can be used for identity verification with high accuracy using a simple classifier such as the k-nearest neighbor (k-NN). 

Keywords: biometrics, genetic data, identity verification, k nearest neighbor

Procedia PDF Downloads 258