Search results for: real world data

Authors: Daofan Guo, Dong Yang

Abstract:

For decades, well logging with coiled tubing has relied solely on surface data such as pump pressure, wellhead pressure, depth counter, and weight indicator readings. While this data serves the oil industry well, modern smart logging utilizes real-time downhole information, which automatically increases operational efficiency and optimizes intervention qualities. For example, downhole pressure, temperature, and depth measurement data can be transmitted through the electro-optical hybrid cable in the coiled tubing to surface operators on a real-time base. This paper mainly introduces the unique structural features and various applications of the electro-optical hybrid cables which were deployed into downhole with the help of coiled tubing technology. Fiber optic elements in the cable enable optical communications and distributed measurements, such as distributed temperature and acoustic sensing. The electrical elements provide continuous surface power for downhole tools, eliminating the limitations of traditional batteries, such as temperature, operating time, and safety concerns. The electrical elements also enable cable telemetry operation of cable tools. Both power supply and signal transmission were integrated into an electro-optical hybrid cable, and the downhole information can be captured by downhole electrical sensors and distributed optical sensing technologies, then travels up through an optical fiber to the surface, which greatly improves the accuracy of measurement data transmission.

Keywords: electro-optical hybrid cable, underground photoelectric composite cable, seismic cable, coiled tubing, real-time monitoring

Procedia PDF Downloads 117

Authors: Hankyu Lee, Seoung Bum Kim

Abstract:

The issue with imbalance and overlapping in the class distribution becomes important in various applications of data mining. The imbalanced dataset is a special case in classification problems in which the number of observations of one class (i.e., major class) heavily exceeds the number of observations of the other class (i.e., minor class). Overlapped dataset is the case where many observations are shared together between the two classes. Imbalanced and overlapped data can be frequently found in many real examples including fraud and abuse patients in healthcare, quality prediction in manufacturing, text classification, oil spill detection, remote sensing, and so on. The class imbalance and overlap problem is the challenging issue because this situation degrades the performance of most of the standard classification algorithms. In this study, we propose a classification procedure that can effectively handle imbalanced and overlapped datasets by splitting data space into three parts: nonoverlapping, light overlapping, and severe overlapping and applying the classification algorithm in each part. These three parts were determined based on the Hausdorff distance and the margin of the modified support vector machine. An experiments study was conducted to examine the properties of the proposed method and compared it with other classification algorithms. The results showed that the proposed method outperformed the competitors under various imbalanced and overlapped situations. Moreover, the applicability of the proposed method was demonstrated through the experiment with real data.

Keywords: classification, imbalanced data with class overlap, split data space, support vector machine

Procedia PDF Downloads 289

Authors: Martin Georgiev, Milena Nanova, Damyan Damov

Abstract:

Architects, engineers, and developers need to analyse and implement a wide spectrum of data in different formats, if they want to produce viable residential developments. Usually, this data comes from a number of different sources and is not well structured. The main objective of this research project is to provide parametric tools working with real geodesic data that can generate residential solutions. Various codes, regulations and design constraints are described by variables and prioritized. In this way, we establish a common workflow for architects, geodesists, and other professionals involved in the building and investment process. This collaborative medium ensures that the generated design variants conform to various requirements, contributing to a more streamlined and informed decision-making process. The quantification of distinctive characteristics inherent to typical residential structures allows a systematic evaluation of the generated variants, focusing on factors crucial to designers, such as daylight simulation, circulation analysis, space utilization, view orientation, etc. Integrating real geodesic data offers a holistic view of the built environment, enhancing the accuracy and relevance of the design solutions. The use of generative algorithms and parametric models offers high productivity and flexibility of the design variants. It can be implemented in more conventional CAD and BIM workflow. Experts from different specialties can join their efforts, sharing a common digital workspace. In conclusion, our research demonstrates that a generative parametric approach based on real geodesic data and collaborative decision-making could be introduced in the early phases of the design process. This gives the designers powerful tools to explore diverse design possibilities, significantly improving the qualities of the building investment during its entire lifecycle.

Keywords: architectural design, residential buildings, urban development, geodesic data, generative design, parametric models, workflow optimization

Procedia PDF Downloads 31

Authors: Che Z. Zulkifli, Nursyahida M. Noor, Siti N. Semunab, Shafawati A. Malek

Abstract:

Wireless sensors, also known as wireless sensor nodes, have been making a significant impact on human daily life. The Radio Frequency Identification (RFID) and Wireless Sensor Network (WSN) are two complementary technologies; hence, an integrated implementation of these technologies expands the overall functionality in obtaining long-range and real-time information on the location and properties of objects and people. An approach for integrating ZigBee and RFID networks is proposed in this paper, to create an energy-efficient network improved by the benefits of combining ZigBee and RFID architecture. Furthermore, the compatibility and requirements of the ZigBee device and communication links in the typical RFID system which is presented with the real world experiment on the capabilities of the proposed RFID system.

Keywords: mesh network, RFID, wireless sensor network, zigbee

Procedia PDF Downloads 436

Authors: Catarina Maria Neto Da Cruz, Ana Maria Reis D’Azevedo Breda

Abstract:

The world is changing and, consequently, the young people need more sophisticated tools and skills to lead with the world’s complexity. The Organisation for Economic Co-operation and Development Learning Framework 2030 suggests an interdisciplinary knowledge as a principle for the future of education systems. In the curricular document Portuguese about the profile of students leaving compulsory education, the critical thinking and creative thinking are pointed out as skills to be developed, which imply the interconnection of different knowledge, applying it in different contexts and learning areas. Unlike primary school teachers, teachers specialized in a specific area lead to more difficulties in the implementation of interdisciplinary approaches in the classrooms and, despite the effort, the interdisciplinarity is not a common practice in schools. Statement like "Mathematics is everywhere" is unquestionable, however, many math teachers show difficulties in presenting such evidence in their classes. Mathematical modelling and problems in real contexts are promising in the development of interdisciplinary pedagogical practices and in Portugal there is a continuous training offer to contribute to the development of teachers in terms of their pedagogical approaches. But when teachers find themselves in the classroom, without a support, do they feel able to implement interdisciplinary practices? In this communication we will try to approach this issue through a case study involving a group of Mathematics teachers, who attended a training aimed at stimulating interdisciplinary practices in real contexts, namely related to the COVID-19 pandemic.

Keywords: education, mathematics, teacher training, interdisciplinarity

Procedia PDF Downloads 67

Authors: Taha SamadSoltani, Peyman Rezaei Hachesu, Marjan GhaziSaeedi, Maryam Zolnoori

Abstract:

Introduction: Data mining defined as a process to find patterns and relationships along data in the database to build predictive models. Application of data mining extended in vast sectors such as the healthcare services. Medical data mining aims to solve real-world problems in the diagnosis and treatment of diseases. This method applies various techniques and algorithms which have different accuracy and precision. The purpose of this study was to apply knowledge discovery and data mining techniques for the diagnosis of asthma based on patient symptoms and history. Method: Data mining includes several steps and decisions should be made by the user which starts by creation of an understanding of the scope and application of previous knowledge in this area and identifying KD process from the point of view of the stakeholders and finished by acting on discovered knowledge using knowledge conducting, integrating knowledge with other systems and knowledge documenting and reporting.in this study a stepwise methodology followed to achieve a logical outcome. Results: Sensitivity, Specifity and Accuracy of KNN, SVM, Naïve bayes, NN, Classification tree and CN2 algorithms and related similar studies was evaluated and ROC curves were plotted to show the performance of the system. Conclusion: The results show that we can accurately diagnose asthma, approximately ninety percent, based on the demographical and clinical data. The study also showed that the methods based on pattern discovery and data mining have a higher sensitivity compared to expert and knowledge-based systems. On the other hand, medical guidelines and evidence-based medicine should be base of diagnostics methods, therefore recommended to machine learning algorithms used in combination with knowledge-based algorithms.

Keywords: asthma, datamining, classification, machine learning

Procedia PDF Downloads 427

Authors: Loai AbdAllah, Mahmoud Kaiyal

Abstract:

Missing values in real-world datasets are a common problem. Many algorithms were developed to deal with this problem, most of them replace the missing values with a fixed value that was computed based on the observed values. In our work, we used a distance function based on Bhattacharyya distance to measure the distance between objects with missing values. Bhattacharyya distance, which measures the similarity of two probability distributions. The proposed distance distinguishes between known and unknown values. Where the distance between two known values is the Mahalanobis distance. When, on the other hand, one of them is missing the distance is computed based on the distribution of the known values, for the coordinate that contains the missing value. This method was integrated with Wikaya, a digital health company developing a platform that helps to improve prevention of chronic diseases such as diabetes and cancer. In order for Wikaya’s recommendation system to work distance between users need to be measured. Since there are missing values in the collected data, there is a need to develop a distance function distances between incomplete users profiles. To evaluate the accuracy of the proposed distance function in reflecting the actual similarity between different objects, when some of them contain missing values, we integrated it within the framework of k nearest neighbors (kNN) classifier, since its computation is based only on the similarity between objects. To validate this, we ran the algorithm over diabetes and breast cancer datasets, standard benchmark datasets from the UCI repository. Our experiments show that kNN classifier using our proposed distance function outperforms the kNN using other existing methods.

Keywords: missing values, incomplete data, distance, incomplete diabetes data

Procedia PDF Downloads 200

Authors: Batatunde Kolawole

Abstract:

Documentary filmmaking stands as a distinctive medium within the cinematic realm, commanding a unique responsibility the portrayal of real-life events and subjects. This research delves into the profound ethical considerations and responsibilities that documentary filmmakers shoulder as they embark on the quest to unveil truth and weave compelling narratives. In the exploration, they embark on a comprehensive review of ethical frameworks and real-world case studies, illuminating the intricate web of challenges that documentarians confront. These challenges encompass an array of ethical intricacies, from securing informed consent to safeguarding privacy, maintaining unwavering objectivity, and sidestepping the snares of narrative manipulation when crafting stories from reality. Furthermore, they dissect the contemporary ethical terrain, acknowledging the emergence of novel dilemmas in the digital age, such as deepfakes and digital alterations. Through a meticulous analysis of ethical quandaries faced by distinguished documentary filmmakers and their strategies for ethical navigation, this study offers invaluable insights into the evolving role of documentaries in molding public discourse. They underscore the indispensable significance of transparency, integrity, and an indomitable commitment to encapsulating the intricacies of reality within the realm of ethical documentary filmmaking. In a world increasingly reliant on visual narratives, an understanding of the subtle ethical dimensions of documentary filmmaking holds relevance not only for those behind the camera but also for the diverse audiences who engage with and interpret the realities unveiled on screen. This research stands as a rigorous examination of the moral compass that steers this potent form of cinematic expression. It emphasizes the capacity of ethical documentary filmmaking to enlighten, challenge, and inspire, all while unwaveringly upholding the core principles of truthfulness and respect for the human subjects under scrutiny. Through this holistic analysis, they illuminate the enduring significance of upholding ethical integrity while uncovering the truths that shape our world. Ethical documentary filmmaking, as exemplified by "Rape" and countless other powerful narratives, serves as a testament to the enduring potential of cinema to inform, challenge, and drive meaningful societal discourse.

Keywords: filmmaking, documentary, human right, film

Procedia PDF Downloads 43

Authors: Jiao Sun, Li Pan, Shijun Liu

Abstract:

Recommender systems have been widely used in contemporary industry, and plenty of work has been done in this field to help users to identify items of interest. Collaborative Filtering (CF, for short) algorithm is an important technology in recommender systems. However, less work has been done in automobile recommendation system with the sharp increase of the amount of automobiles. What’s more, the computational speed is a major weakness for collaborative filtering technology. Therefore, using MapReduce framework to optimize the CF algorithm is a vital solution to this performance problem. In this paper, we present a recommendation of the users’ comment on industrial automobiles with various properties based on real world industrial datasets of user-automobile comment data collection, and provide recommendation for automobile providers and help them predict users’ comment on automobiles with new-coming property. Firstly, we solve the sparseness of matrix using previous construction of score matrix. Secondly, we solve the data normalization problem by removing dimensional effects from the raw data of automobiles, where different dimensions of automobile properties bring great error to the calculation of CF. Finally, we use the MapReduce framework to optimize the CF algorithm, and the computational speed has been improved times. UV decomposition used in this paper is an often used matrix factorization technology in CF algorithm, without calculating the interpolation weight of neighbors, which will be more convenient in industry.

Keywords: collaborative filtering, recommendation, data normalization, mapreduce

Procedia PDF Downloads 200

Authors: Muhammad Ali

Abstract:

Cyber-attacks and anomaly detection on the Internet of Things (IoT) infrastructure is emerging concern in the domain of data-driven intrusion. Rapidly increasing IoT risk is now making headlines around the world. denial of service, malicious control, data type probing, malicious operation, DDos, scan, spying, and wrong setup are attacks and anomalies that can affect an IoT system failure. Everyone talks about cyber security, connectivity, smart devices, and real-time data extraction. IoT devices expose a wide variety of new cyber security attack vectors in network traffic. For further than IoT development, and mainly for smart and IoT applications, there is a necessity for intelligent processing and analysis of data. So, our approach is too secure. We train several machine learning models that have been compared to accurately predicting attacks and anomalies on IoT systems, considering IoT applications, with ANOVA-based feature selection with fewer prediction models to evaluate network traffic to help prevent IoT devices. The machine learning (ML) algorithms that have been used here are KNN, SVM, NB, D.T., and R.F., with the most satisfactory test accuracy with fast detection. The evaluation of ML metrics includes precision, recall, F1 score, FPR, NPV, G.M., MCC, and AUC & ROC. The Random Forest algorithm achieved the best results with less prediction time, with an accuracy of 99.98%.

Keywords: machine learning, analysis of variance, Internet of Thing, network security, intrusion detection

Procedia PDF Downloads 97

Authors: L. Angiuli, L. Trizio, R. Giua, A. Digilio, M. Tutino, P. Dambruoso, F. Mazzone, C. M. Placentino

Abstract:

In the winter of 2014 a series of measurements were performed to evaluate the behavior of real-time PAHs and black carbon analyzers in a coke oven plant located in Taranto, a city of Southern Italy. Data were collected both insides than outside the plant, at air quality monitoring sites. Contemporary measures of PM2.5 and PM1 were performed. Particle-bound PAHs were measured by two methods: (1) aerosol photoionization using an Ecochem PAS 2000 analyzer, (2) PM2.5 and PM1 quartz filter collection and analysis by gas chromatography/mass spectrometry (GC/MS). Black carbon was determined both in real-time by Magee Aethalometer AE22 analyzer than by semi-continuous Sunset Lab EC/OC instrument. Detected PM2.5 and PM1 levels were higher inside than outside the plant while PAHs real-time values were higher outside than inside. As regards PAHs, inside the plant Ecochem PAS 2000 revealed concentrations not significantly different from those determined on the filter during low polluted days, but at increasing concentrations the automated instrument underestimated PAHs levels. At the external site, Ecochem PAS 2000 real-time concentrations were steadily higher than those on the filter. In the same way, real-time black carbon values were constantly lower than EC concentrations obtained by Sunset EC/OC in the inner site, while outside the plant real-time values were comparable to Sunset EC values. Results showed that in a coke plant real-time analyzers of PAHs and black carbon in the factory configuration provide qualitative information, with no accuracy and leading to the underestimation of the concentration. A site specific calibration is needed for these instruments before their installation in high polluted sites.

Keywords: black carbon, coke oven plant, PAH, PAS, aethalometer

Procedia PDF Downloads 321

Authors: Niousha Bagheri Khulenjani, Mohammad Saniee Abadeh

Abstract:

Learning from very big datasets is a significant problem for most present data mining and machine learning algorithms. MicroRNA (miRNA) is one of the important big genomic and non-coding datasets presenting the genome sequences. In this paper, a hybrid method for the classification of the miRNA data is proposed. Due to the variety of cancers and high number of genes, analyzing the miRNA dataset has been a challenging problem for researchers. The number of features corresponding to the number of samples is high and the data suffer from being imbalanced. The feature selection method has been used to select features having more ability to distinguish classes and eliminating obscures features. Afterward, a Convolutional Neural Network (CNN) classifier for classification of cancer types is utilized, which employs a Genetic Algorithm to highlight optimized hyper-parameters of CNN. In order to make the process of classification by CNN faster, Graphics Processing Unit (GPU) is recommended for calculating the mathematic equation in a parallel way. The proposed method is tested on a real-world dataset with 8,129 patients, 29 different types of tumors, and 1,046 miRNA biomarkers, taken from The Cancer Genome Atlas (TCGA) database.

Keywords: cancer classification, feature selection, deep learning, genetic algorithm

Procedia PDF Downloads 93

Authors: Luis Fonseca, Filipe Cabral Pinto, Susana Sargento

Abstract:

The increase of the world population, especially in large urban centers, has resulted in new challenges particularly with the control and optimization of public safety. Thus, in the present work, a solution is proposed for the prediction of criminal occurrences in a city based on historical data of incidents and demographic information. The entire research and implementation will be presented start with the data collection from its original source, the treatment and transformations applied to them, choice and the evaluation and implementation of the Machine Learning model up to the application layer. Classification models will be implemented to predict criminal risk for a given time interval and location. Machine Learning algorithms such as Random Forest, Neural Networks, K-Nearest Neighbors and Logistic Regression will be used to predict occurrences, and their performance will be compared according to the data processing and transformation used. The results show that the use of Machine Learning techniques helps to anticipate criminal occurrences, which contributed to the reinforcement of public security. Finally, the models were implemented on a platform that will provide an API to enable other entities to make requests for predictions in real-time. An application will also be presented where it is possible to show criminal predictions visually.

Keywords: crime prediction, machine learning, public safety, smart city

Procedia PDF Downloads 89

Authors: Shilpa Balan

Abstract:

Radio Frequency Identification, also popularly known as RFID is used to automatically identify and track tags attached to items. This study focuses on the application of RFID in healthcare. The adoption of RFID in healthcare is a crucial technology to patient safety and inventory management. Data from RFID tags are used to identify the locations of patients and inventory in real time. Medical errors are thought to be a prominent cause of loss of life and injury. The major advantage of RFID application in healthcare industry is the reduction of medical errors. The healthcare industry has generated huge amounts of data. By discovering patterns and trends within the data, big data analytics can help improve patient care and lower healthcare costs. The number of increasing research publications leading to innovations in RFID applications shows the importance of this technology. This study explores the current state of research of RFID in healthcare using a text mining approach. No study has been performed yet on examining the current state of RFID research in healthcare using a data mining approach. In this study, related articles were collected on RFID from healthcare journal and news articles. Articles collected were from the year 2000 to 2015. Significant keywords on the topic of focus are identified and analyzed using open source data analytics software such as Rapid Miner. These analytical tools help extract pertinent information from massive volumes of data. It is seen that the main benefits of adopting RFID technology in healthcare include tracking medicines and equipment, upholding patient safety, and security improvement. The real-time tracking features of RFID allows for enhanced supply chain management. By productively using big data, healthcare organizations can gain significant benefits. Big data analytics in healthcare enables improved decisions by extracting insights from large volumes of data.

Keywords: RFID, data mining, data analysis, healthcare

Procedia PDF Downloads 207

Authors: Sylvester Akpah, Selasi Vondee

Abstract:

Unmanned Aerial Vehicles (UAV) as they are also known, drones have attracted increasing attention in recent years due to their ubiquitous nature and boundless applications in the areas of communication, surveying, aerial photography, weather forecasting, medical delivery, surveillance amongst others. Operated remotely in real-time or pre-programmed, drones can fly autonomously or on pre-defined routes. The application of these aerial vehicles has successfully penetrated the world due to technological evolution, thus a lot more businesses are utilizing their capabilities. Unfortunately, while drones are replete with the benefits stated supra, they are riddled with some problems, mainly attributed to the complexities in learning how to master drone flights, collision avoidance and enterprise security. Additional challenges, such as the analysis of flight data recorded by sensors attached to the drone may take time and require expert help to analyse and understand. This paper presents an autonomous drone control system using a chatbot. The system allows for easy control of drones using conversations with the aid of Natural Language Processing, thus to reduce the workload needed to set up, deploy, control, and monitor drone flight missions. The results obtained at the end of the study revealed that the drone connected to the chatbot was able to initiate flight missions with just text and voice commands, enable conversation and give real-time feedback from data and requests made to the chatbot. The results further revealed that the system was able to process natural language and produced human-like conversational abilities using Artificial Intelligence (Natural Language Understanding). It is recommended that radio signal adapters be used instead of wireless connections thus to increase the range of communication with the aerial vehicle.

Keywords: artificial ntelligence, chatbot, natural language processing, unmanned aerial vehicle

Procedia PDF Downloads 123

Authors: Chandra Prayaga, Lakshmi Prayaga, Aaron Wade, Kyle Rank, Gopi Shankar Mallu, Sri Satya, Harsha Pola

Abstract:

In today's tech-driven world, where connectivity shapes our daily lives, maintaining physical and emotional health is crucial. Athletic trainers play a vital role in optimizing athletes' performance and preventing injuries. However, a shortage of trainers impacts the quality of care. This study introduces a vision-based exercise monitoring system leveraging Google's MediaPipe library for precise tracking of bicep curl exercises and simultaneous posture monitoring. We propose a three-stage methodology: landmark detection, side detection, and angle computation. Our system calculates angles at the elbow, wrist, neck, and torso to assess exercise form. Experimental results demonstrate the system's effectiveness in distinguishing between good and partial repetitions and evaluating body posture during exercises, providing real-time feedback for precise fitness monitoring.

Keywords: physical health, athletic trainers, fitness monitoring, technology driven solutions, Google’s MediaPipe, landmark detection, angle computation, real-time feedback

Procedia PDF Downloads 46

Authors: Omid Amini

Abstract:

Nowadays, technology plays the most important role in the life of human beings because people use technology to share data and to communicate with each other, but the challenge is the security of this data. For instance, as more people turn to technology in the world, more data is generated, and more hackers try to steal or infiltrate data. In addition, the data is under the control of the central authority, which can trigger the challenge of losing information and changing information; this can create widespread anxiety for different people in different communities. In this paper, we sought to investigate Blockchain technology that can guarantee information security and eliminate the challenge of central authority access to information. Now a day, people are suffering from the current voting system. This means that the lack of transparency in the voting system is a big problem for society and the government in most countries, but blockchain technology can be the best alternative to the previous voting system methods because it removes the most important challenge for voting. According to the results, this research can be a good start to getting acquainted with this new technology, especially on the security part and familiarity with how to use a voting system based on blockchain in the world. At the end of this research, it is concluded that the use of blockchain technology can solve the major security problem and lead to a secure and transparent election.

Keywords: blockchain, technology, security, information, voting system, transparency

Procedia PDF Downloads 106

Authors: Nefeli Dimitriadi

Abstract:

This paper aims to present immersive cinema where real actors are filmed and integrated in Virtual Reality environments and 360 cinematic narrative, in comparison to 360 filming of real actors and sets and to fully computer graphics animation movies with 3D avatars. Objectives: This reseach aims to present immersive cinema where real actors are integrated in Virrual Reality environments and 360 cinematic narrative as the future of immersive cinema. Meghdology: A comparative analysis is conducted between real actors filming combined with Virtual Reality sets, to 360 filming of real actors and sets, and to fully computer graphics animation movies with 3D avatars, using as case study Virtual Reality movie Neurosynapses and others. Contribution: This reseach contributes in defining the best practices leading to impactful Immersive cinematic narratives.

Keywords: virtual reality, 360 movies, immersive cinema, directing for virtual reality

Procedia PDF Downloads 98

Authors: Rama Debbarma, Debanjan Das

Abstract:

The performance of multiple tuned mass dampers to mitigate the seismic vibration of structures considering real time history data is investigated in this paper. Three different real earthquake time history data like Kobe, Imperial Valley and Mammoth Lake are taken in the present study. The multiple tuned mass dampers (MTMD) are distributed at each storey. For comparative study, single tuned mass damper (STMD) is installed at top of the similar structure. This study is conducted for a fixed mass ratio (5%) and fixed damping ratio (5%) of structures. Numerical study is performed to evaluate the effectiveness of MTMDs and overall system performance. The displacement, acceleration, base shear and storey drift are obtained for both combined system (structure with MTMD and structure with STMD) for all earthquakes. The same responses are also obtained for structure without damper system. From obtained results, it is investigated that the MTMD configuration is more effective for controlling the seismic response of the primary system with compare to STMD configuration.

Keywords: Earthquake, multiple tuned mass dampers, single tuned mass damper, Time history.

Procedia PDF Downloads 254

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 33

Authors: Dalia G. Aseel

Abstract:

The potato (Solanum tubersum, L.) has become one of the major vegetable crops in Egypt and all over the world. Potato leafroll virus(PLRV) was observed on potato plants collected from different governorates in Egypt. Three cultivars, Spunta, Diamont, and Cara, infected with PLRV were collected; RNA was extracted and subjected to Real-Time PCR using the coat protein gene primers. The results showed that the expression of the coat protein was 39.6-fold, 12.45-fold, and 47.43-fold, respectively, for Spunta, Diamont, and Cara cultivars. Differential Display Polymerase Chain Reaction (DD-PCR) using pathogenesis-related protein 1 (PR-1), β-1,3-glucanases (PR-2), chitinase (PR-3), peroxidase (POD), and polyphenol oxidase (PPO) forward primers for pathogenesis-related proteins (PR). The obtained data revealed different banding patterns depending on the viral type and the region of infection. Regarding PLRV, 58 up-regulated and 19 down-regulated genes were detected. Sequence analysis of the up-and down-regulated genes revealed that infected plants were observed in comparison with the healthy control. Sequence analysis of the up-regulated gene was performed, and the encoding sequence analysis showed that the obtained genes include: induced stolen tip protein. On the other hand, two down-regulated genes were identified: disease resistance RPP-like protein and non-specific lipid-transfer protein. In this study, the expressions of PR-1, PR-2, PR-3, POD, and PPO genes in the infected leaves of three potato cultivars were estimated by quantitative real-time PCR. We can conclude that the PLRV-infection of potato plants inhibited the expression of the five PR genes. On the contrary, infected leaves by PLRV elevated the expression of some defense genes. This interaction may also induce and/or suppress the expression of some genes responsible for the plant's defense mechanisms.

Keywords: PLRV, pathogenesis-related proteins (PRs), DD-PCR, sequence, real-time PCR

Procedia PDF Downloads 114

Authors: Raghavi C. Janaswamy

Abstract:

In the healthcare sector, heterogenous data elements such as patients, diagnosis, symptoms, conditions, observation text from physician notes, and prescriptions form the essentials of the Electronic Health Record (EHR). The data in the form of clear text and images are stored or processed in a relational format in most systems. However, the intrinsic structure restrictions and complex joins of relational databases limit the widespread utility. In this regard, the design and development of realistic mapping and deep connections as real-time objects offer unparallel advantages. Herein, a graph neural network-based classification of EHR data has been developed. The patient conditions have been predicted as a node classification task using a graph-based open source EHR data, Synthea Database, stored in Tigergraph. The Synthea DB dataset is leveraged due to its closer representation of the real-time data and being voluminous. The graph model is built from the EHR heterogeneous data using python modules, namely, pyTigerGraph to get nodes and edges from the Tigergraph database, PyTorch to tensorize the nodes and edges, PyTorch-Geometric (PyG) to train the Graph Neural Network (GNN) and adopt the self-supervised learning techniques with the AutoEncoders to generate the node embeddings and eventually perform the node classifications using the node embeddings. The model predicts patient conditions ranging from common to rare situations. The outcome is deemed to open up opportunities for data querying toward better predictions and accuracy.

Keywords: electronic health record, graph neural network, heterogeneous data, prediction

Procedia PDF Downloads 69

Authors: R. Tlili Yaakoubi, H.Nakouri, O. Blanpain, S. Lallahem

Abstract:

The current tools for real time management of sewer systems are based on two software tools: the software of weather forecast and the software of hydraulic simulation. The use of the first ones is an important cause of imprecision and uncertainty, the use of the second requires temporal important steps of decision because of their need in times of calculation. This way of proceeding fact that the obtained results are generally different from those waited. The major idea of this project is to change the basic paradigm by approaching the problem by the "automatic" face rather than by that "hydrology". The objective is to make possible the realization of a large number of simulations at very short times (a few seconds) allowing to take place weather forecasts by using directly the real time meditative pluviometric data. The aim is to reach a system where the decision-making is realized from reliable data and where the correction of the error is permanent. A first model of control laws was realized and tested with different return-period rainfalls. The gains obtained in rejecting volume vary from 19 to 100 %. The development of a new algorithm was then used to optimize calculation time and thus to overcome the subsequent combinatorial problem in our first approach. Finally, this new algorithm was tested with 16- year-rainfall series. The obtained gains are 40 % of total volume rejected to the natural environment and of 65 % in the number of discharges.

Keywords: automation, optimization, paradigm, RTC

Procedia PDF Downloads 282

Authors: Alicia Regodon Puyalto, Alfonso Garcia-Santos

Abstract:

This article presents a method to analyze the use of indoor spaces based on data analytics obtained from inbuilt digital devices. The study uses the data generated by the in-place devices, such as smart locks, Wi-Fi routers, and electrical sensors, to gain additional insights on space occupancy, user behaviour, and comfort. Those devices, originally installed to facilitate remote operations, report data through the internet that the research uses to analyze information on human real-time use of spaces. Using an in-place Internet of Things (IoT) network enables a faster, more affordable, seamless, and scalable solution to analyze building interior spaces without incorporating external data collection systems such as sensors. The methodology is applied to a real case study of coliving, a residential building of 3000m², 7 floors, and 80 users in the centre of Madrid. The case study applies the method to classify IoT devices, assess, clean, and analyze collected data based on the analysis framework. The information is collected remotely, through the different platforms devices' platforms; the first step is to curate the data, understand what insights can be provided from each device according to the objectives of the study, this generates an analysis framework to be escalated for future building assessment even beyond the residential sector. The method will adjust the parameters to be analyzed tailored to the dataset available in the IoT of each building. The research demonstrates how human-centered data analytics can improve the future spatial design of indoor spaces.

Keywords: in-place devices, IoT, human-centred data-analytics, spatial design

Procedia PDF Downloads 176

Authors: Wei-Na Li, Mei-Lan Piao, Nam Kim

Abstract:

We proposed a novel computer-generated hologram (CGH) achieved scheme, wherein the CGH is generated from a point cloud which is transformed by a mapping relationship of a series of elemental images captured from a real three-dimensional (3D) object by using a lens array. This scheme is composed of three procedures: mapping from elemental images to point cloud, hologram generation, and hologram display. A mapping method is figured out to achieve a virtual volume date (point cloud) from a series of elemental images. This mapping method consists of two steps. Firstly, the coordinate (x, y) pairs and its appearing number are calculated from the series of sub-images, which are generated from the elemental images. Secondly, a series of corresponding coordinates (x, y, z) are calculated from the elemental images. Then a hologram is generated from the volume data that is calculated by the previous two steps. Eventually, a spatial light modulator (SLM) and a green laser beam are utilized to display this hologram and reconstruct the original 3D object. In this paper, in order to show a more auto stereoscopic display of a real 3D object, we successfully obtained the actual depth data of every discrete point of the real 3D object, and overcame the inherent drawbacks of the depth camera by obtaining point cloud from the elemental images.

Keywords: elemental image, point cloud, computer-generated hologram (CGH), autostereoscopic display

Procedia PDF Downloads 561

Authors: Abdul Ghani Rajput

Abstract:

Although monitoring and evaluation concept adopted by Technical Vocational Education and Training (TVET) organization to track the progress over the continuous interval of time based on planned interventions and subsequently, evaluating it for the impact, quality assurance and sustainability. In digital world, TVET providers are giving preference to have real time information to do monitoring of training activities. Identifying the benefits and challenges of digitized monitoring & evaluation real time information system has not been sufficiently tackled in this date. This research paper looks at the impact of digitized M&E in TVET sector by analyzing two case studies and describe the benefits and challenges of using digitized M&E system. Finally, digitized M&E have been identified as carriers for high potential of TVET sector.

Keywords: digitized M&E, innovation, quality assurance, TVET

Procedia PDF Downloads 198

Authors: Lipeng Zhang, Limei Li, Yanming Pearl Zhang

Abstract:

This paper takes a philosophical view as axiom, and reveals the relationship between information theory and Natural Intelligence and Artificial Intelligence under real world conditions. This paper also derives the relationship between natural intelligence and nature. According to communication principle of information theory, Natural Intelligence can be divided into real part and virtual part. Based on information theory principle that Information does not increase, the restriction mechanism of Natural Intelligence creativity is conducted. The restriction mechanism of creativity reveals the limit of natural intelligence and artificial intelligence. The paper provides a new angle to observe natural intelligence and artificial intelligence.

Keywords: natural intelligence, artificial intelligence, creativity, information theory, restriction of creativity

Procedia PDF Downloads 352

Authors: Oualid Walid Ben Ali

Abstract:

Big Data has become one of the buzzwords today. The recent explosion of digital data has led the organization, either private or public, to a new era towards a more efficient decision making. At some point, business decided to use that concept in order to learn what make their clients tick with phrases like ‘sales funnel’ analysis, ‘actionable insights’, and ‘positive business impact’. So, it stands to reason that Big Data was viewed through green (read: money) colored lenses. Somewhere along the line, however someone realized that collecting and processing data doesn’t have to be for business purpose only, but also could be used for other purposes to assist law enforcement or to improve policing or in road safety. This paper presents briefly, how Big Data have been used in the fields of policing order to improve the decision making process in the daily operation of the police. As example, we present a big-data driven system which is sued to accurately dispatch the patrol cars in a geographic environment. The system is also used to allocate, in real-time, the nearest patrol car to the location of an incident. This system has been implemented and applied in the Emirate of Abu Dhabi in the UAE.

Keywords: big data, big data analytics, patrol car allocation, dispatching, GIS, intelligent, Abu Dhabi, police, UAE

Procedia PDF Downloads 466

Authors: Migena Mana, Ahmed Khalid Syed, Abdul Malik, Nikhil Cherian

Abstract:

In recent years, advancements in deep learning enabled researchers to tackle the problem of self-driving cars. Car companies use huge datasets to train their deep learning models to make autonomous cars a reality. However, this approach has certain drawbacks in that the state space of possible actions for a car is so huge that there cannot be a dataset for every possible road scenario. To overcome this problem, the concept of reinforcement learning (RL) is being investigated in this research. Since the problem of autonomous driving can be modeled in a simulation, it lends itself naturally to the domain of reinforcement learning. The advantage of this approach is that we can model different and complex road scenarios in a simulation without having to deploy in the real world. The autonomous agent can learn to drive by finding the optimal policy. This learned model can then be easily deployed in a real-world setting. In this project, we focus on three RL algorithms: Q-learning, Deep Deterministic Policy Gradient (DDPG), and Proximal Policy Optimization (PPO). To model the environment, we have used TORCS (The Open Racing Car Simulator), which provides us with a strong foundation to test our model. The inputs to the algorithms are the sensor data provided by the simulator such as velocity, distance from side pavement, etc. The outcome of this research project is a comparative analysis of these algorithms. Based on the comparison, the PPO algorithm gives the best results. When using PPO algorithm, the reward is greater, and the acceleration, steering angle and braking are more stable compared to the other algorithms, which means that the agent learns to drive in a better and more efficient way in this case. Additionally, we have come up with a dataset taken from the training of the agent with DDPG and PPO algorithms. It contains all the steps of the agent during one full training in the form: (all input values, acceleration, steering angle, break, loss, reward). This study can serve as a base for further complex road scenarios. Furthermore, it can be enlarged in the field of computer vision, using the images to find the best policy.

Keywords: autonomous driving, DDPG (deep deterministic policy gradient), PPO (proximal policy optimization), reinforcement learning

Procedia PDF Downloads 122

Authors: Sunghoon Park, Hank Kim, Jinwon An, Sungzoon Cho

Abstract:

Internet of Things allows one to collect data from facilities which are then used to monitor them and even predict malfunctions in advance. Conventional quality control methods focus on setting a normal range on a sensor value defined between a lower control limit and an upper control limit, and declaring as an anomaly anything falling outside it. However, interactions among sensor values are ignored, thus leading to suboptimal performance. We propose a multivariate approach which takes into account many sensor values at the same time. In particular Gaussian Mixture Model is used which is trained to maximize likelihood value using Expectation-Maximization algorithm. The number of Gaussian component distributions is determined by Bayesian Information Criterion. The negative Log likelihood value is used as an anomaly score. The actual usage scenario goes like a following. For each instance of sensor values from a facility, an anomaly score is computed. If it is larger than a threshold, an alarm will go off and a human expert intervenes and checks the system. A real world data from Building energy system was used to test the model.

Keywords: facility anomaly detection, gaussian mixture model, anomaly score, expectation maximization algorithm

Procedia PDF Downloads 252