Search results for: data reproducibility

Authors: Nurkhairul Bariyah Baharun, Afzan Adam, Reena Rahayu Md Zin

Abstract:

Tumor microenvironment (TME) in breast cancer is mainly composed of cancer cells, immune cells, and stromal cells. The interaction between cancer cells and their microenvironment plays an important role in tumor development, progression, and treatment response. The TME in breast cancer includes tumor-infiltrating lymphocytes (TILs) that are implicated in killing tumor cells. TILs can be found in tumor stroma (sTILs) and within the tumor (iTILs). TILs in triple negative breast cancer (TNBC) have been demonstrated to have prognostic and potentially predictive value. The international Immune-Oncology Biomarker Working Group (TIL-WG) had developed a guideline focus on the assessment of sTILs using hematoxylin and eosin (H&E)-stained slides. According to the guideline, the pathologists use “eye balling” method on the H&E stained- slide for sTILs assessment. This method has low precision, poor interobserver reproducibility, and is time-consuming for a comprehensive evaluation, besides only counted sTILs in their assessment. The TIL-WG has therefore recommended that any algorithm for computational assessment of TILs utilizing the guidelines provided to overcome the limitations of manual assessment, thus providing highly accurate and reliable TILs detection and classification for reproducible and quantitative measurement. This study is carried out to develop a TNBC digital whole slide image (WSI) dataset from H&E-stained slides and IHC (CD4+ and CD8+) stained slides. TNBC cases were retrieved from the database of the Department of Pathology, Hospital Canselor Tuanku Muhriz (HCTM). TNBC cases diagnosed between the year 2010 and 2021 with no history of other cancer and available block tissue were included in the study (n=58). Tissue blocks were sectioned approximately 4 µm for H&E and IHC stain. The H&E staining was performed according to a well-established protocol. Indirect IHC stain was also performed on the tissue sections using protocol from Diagnostic BioSystems PolyVue™ Plus Kit, USA. The slides were stained with rabbit monoclonal, CD8 antibody (SP16) and Rabbit monoclonal, CD4 antibody (EP204). The selected and quality-checked slides were then scanned using a high-resolution whole slide scanner (Pannoramic DESK II DW- slide scanner) to digitalize the tissue image with a pixel resolution of 20x magnification. A manual TILs (sTILs and iTILs) assessment was then carried out by the appointed pathologist (2 pathologists) for manual TILs scoring from the digital WSIs following the guideline developed by TIL-WG 2014, and the result displayed as the percentage of sTILs and iTILs per mm² stromal and tumour area on the tissue. Following this, we aimed to develop an automated digital image scoring framework that incorporates key elements of manual guidelines (including both sTILs and iTILs) using manually annotated data for robust and objective quantification of TILs in TNBC. From the study, we have developed a digital dataset of TNBC H&E and IHC (CD4+ and CD8+) stained slides. We hope that an automated based scoring method can provide quantitative and interpretable TILs scoring, which correlates with the manual pathologist-derived sTILs and iTILs scoring and thus has potential prognostic implications.

Keywords: automated quantification, digital pathology, triple negative breast cancer, tumour infiltrating lymphocytes

Procedia PDF Downloads 116

Authors: Tak-Chung Fu, Ying-Kit Hung, Fu-Lai Chung

Abstract:

In the field of time series data mining, the concept of the Perceptually Important Point (PIP) identification process is first introduced in 2001. This process originally works for financial time series pattern matching and it is then found suitable for time series dimensionality reduction and representation. Its strength is on preserving the overall shape of the time series by identifying the salient points in it. With the rise of Big Data, time series data contributes a major proportion, especially on the data which generates by sensors in the Internet of Things (IoT) environment. According to the nature of PIP identification and the successful cases, it is worth to further explore the opportunity to apply PIP in time series ‘Big Data’. However, the performance of PIP identification is always considered as the limitation when dealing with ‘Big’ time series data. In this paper, two distributed versions of PIP identification based on the Specialized Binary (SB) Tree are proposed. The proposed approaches solve the bottleneck when running the PIP identification process in a standalone computer. Improvement in term of speed is obtained by the distributed versions.

Keywords: distributed computing, performance analysis, Perceptually Important Point identification, time series data mining

Procedia PDF Downloads 434

Authors: Philipp Ruf, Massiwa Chabbi, Christoph Reich, Djaffar Ould-Abdeslam

Abstract:

In recent years, convolutional neural networks (CNN) have demonstrated high performance in image analysis, but oftentimes, there is only structured data available regarding a specific problem. By interpreting structured data as images, CNNs can effectively learn and extract valuable insights from tabular data, leading to improved predictive accuracy and uncovering hidden patterns that may not be apparent in traditional structured data analysis. In applying a single neural network for analyzing multimodal data, e.g., both structured and unstructured information, significant advantages in terms of time complexity and energy efficiency can be achieved. Converting structured data into images and merging them with existing visual material offers a promising solution for applying CNN in multimodal datasets, as they often occur in a medical context. By employing suitable preprocessing techniques, structured data is transformed into image representations, where the respective features are expressed as different formations of colors and shapes. In an additional step, these representations are fused with existing images to incorporate both types of information. This final image is finally analyzed using a CNN.

Keywords: CNN, image processing, tabular data, mixed dataset, data transformation, multimodal fusion

Procedia PDF Downloads 123

Authors: Filiz Ersoz, Taner Ersoz, Erkin Guler

Abstract:

This paper addresses the issues and technique for textile industry using data mining techniques. Data mining has been applied to the stitching of garments products that were obtained from a textile company. Data mining techniques were applied to the data obtained from the CHAID algorithm, CART algorithm, Regression Analysis and, Artificial Neural Networks. Classification technique based analyses were used while data mining and decision model about the production per person and variables affecting about production were found by this method. In the study, the results show that as the daily working time increases, the production per person also decreases. In addition, the relationship between total daily working and production per person shows a negative result and the production per person show the highest and negative relationship.

Keywords: data mining, textile production, decision trees, classification

Procedia PDF Downloads 349

Authors: Ashima Anurag Sharma

Abstract:

Optical fiber based networks can deliver performance that can support the increasing demands for high speed connections. One of the new technologies that have emerged in recent years is Passive Optical Networks. This research paper is targeted to show the simultaneous delivery of triple play service (data, voice, and video). The comparison between various data rates is presented. It is demonstrated that as we increase the data rate, number of users to be decreases due to increase in bit error rate.

Keywords: BER, PON, TDMPON, GPON, CWDM, OLT, ONT

Procedia PDF Downloads 527

Authors: Fuad M. Alkoot

Abstract:

Different experimental technologies such as microarray sequencing have been proposed to generate high-resolution genetic data, in order to understand the complex dynamic interactions between complex diseases and the biological system components of genes and gene products. However, the generated samples have a very large dimension reaching thousands. Therefore, hindering all attempts to design a classifier system that can identify diseases based on such data. Additionally, the high overlap in the class distributions makes the task more difficult. The data we experiment with is generated for the identification of autism. It includes 142 samples, which is small compared to the large dimension of the data. The classifier systems trained on this data yield very low classification rates that are almost equivalent to a guess. We aim at reducing the data dimension and improve it for classification. Here, we experiment with applying a multistage PCA on the genetic data to reduce its dimensionality. Results show a significant improvement in the classification rates which increases the possibility of building an automated system for autism detection.

Keywords: PCA, gene expression, dimensionality reduction, classification, autism

Procedia PDF Downloads 560

Authors: Bharti Jain, Rajeev Jain, Abuzar Kabir, Torki Zughaibi, Shweta Sharma

Abstract:

Drug-facilitated crimes (DFCs) entail the use of a single drug or a mixture of drugs to render a victim unable. Traditionally, biological samples have been gathered from victims and conducted analysis to establish evidence of drug administration. Nevertheless, the rapid metabolism of various drugs and delays in analysis can impede the identification of such substances. For this, the present article describes a rapid, sustainable, highly efficient and miniaturized protocol for the identification and quantification of three sedative-hypnotic drugs, namely diazepam, chlordiazepoxide and ketamine in alcoholic beverages and complex food samples (cream of biscuit, flavored milk, juice, cake, tea, sweets and chocolate). The methodology involves utilizing fabric phase sorptive extraction (FPSE) to extract diazepam (DZ), chlordiazepoxide (CDP), and ketamine (KET). Subsequently, the extracted samples are subjected to analysis using gas chromatography-mass spectrometry (GC-MS). Several parameters, including the type of membrane, pH, agitation time and speed, ionic strength, sample volume, elution volume and time, and type of elution solvent, were screened and thoroughly optimized. Sol-gel Carbowax 20M (CW-20M) has demonstrated the most effective extraction efficiency for the target analytes among all evaluated membranes. Under optimal conditions, the method displayed linearity within the range of 0.3–10 µg mL–¹ (or µg g–¹), exhibiting a coefficient of determination (R2) ranging from 0.996–0.999. The limits of detection (LODs) and limits of quantification (LOQs) for liquid samples range between 0.020-0.069 µg mL-¹ and 0.066-0.22 µg mL-¹, respectively. Correspondingly, the LODs for solid samples ranged from 0.056-0.090 µg g-¹, while the LOQs ranged from 0.18-0.29 µg g-¹. Notably, the method showcased better precision, with repeatability and reproducibility both below 5% and 10%, respectively. Furthermore, the FPSE-GC-MS method proved effective in determining diazepam (DZ) in forensic food samples connected to drug-facilitated crimes (DFCs). Additionally, the proposed method underwent evaluation for its whiteness using the RGB12 algorithm.

Keywords: drug facilitated crime, fabric phase sorptive extraction, food forensics, white analytical chemistry

Procedia PDF Downloads 70

Authors: Fei Gao, Rodolfo C. Raga Jr.

Abstract:

This research proposal will ascertain the major risk factors for diabetes and to design a predictive model for risk assessment. The project aims to improve diabetes early detection and management by utilizing data science techniques, which may improve patient outcomes and healthcare efficiency. The phase relation values of each attribute were used to analyze and choose the attributes that might influence the examiner's survival probability using Diabetes Health Indicators Dataset from Kaggle’s data as the research data. We compare and evaluate eight machine learning algorithms. Our investigation begins with comprehensive data preprocessing, including feature engineering and dimensionality reduction, aimed at enhancing data quality. The dataset, comprising health indicators and medical data, serves as a foundation for training and testing these algorithms. A rigorous cross-validation process is applied, and we assess their performance using five key metrics like accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC-ROC). After analyzing the data characteristics, investigate their impact on the likelihood of diabetes and develop corresponding risk indicators.

Keywords: diabetes, risk factors, predictive model, risk assessment, data science techniques, early detection, data analysis, Kaggle

Procedia PDF Downloads 75

Authors: Chang Qin, Daham Mustafa, Abderrahmane Khiat, Pierre Bienert, Paulo Zanini

Abstract:

Nowadays, companies are facing lots of challenges in the process of digital transformation, which can be a complex and costly undertaking. Digital transformation involves the collection and analysis of large amounts of data, which can create challenges around data management and governance. Furthermore, it is also challenged to integrate data from multiple systems and technologies. Although with these pains, companies are still pursuing digitalization because by embracing advanced technologies, companies can improve efficiency, quality, decision-making, and customer experience while also creating different business models and revenue streams. In this paper, the issue that data is stored in data silos with different schema and structures is focused. The conventional approaches to addressing this issue involve utilizing data warehousing, data integration tools, data standardization, and business intelligence tools. However, these approaches primarily focus on the grammar and structure of the data and neglect the importance of semantic modeling and semantic standardization, which are essential for achieving data interoperability. In this session, the challenge of data silos in Industry 4.0 is addressed by developing a semantic modeling approach compliant with Asset Administration Shell (AAS) models as an efficient standard for communication in Industry 4.0. The paper highlights how our approach can facilitate the data mapping process and semantic lifting according to existing industry standards such as ECLASS and other industrial dictionaries. It also incorporates the Asset Administration Shell technology to model and map the company’s data and utilize a knowledge graph for data storage and exploration.

Keywords: data interoperability in industry 4.0, digital integration, industrial dictionary, semantic modeling

Procedia PDF Downloads 94

Authors: Waziri Victor Onomza, John K. Alhassan, Idris Ismaila, Noel Dogonyaro Moses

Abstract:

This paper describes the problem of building secure computational services for encrypted information in the Cloud Computing without decrypting the encrypted data; therefore, it meets the yearning of computational encryption algorithmic aspiration model that could enhance the security of big data for privacy, confidentiality, availability of the users. The cryptographic model applied for the computational process of the encrypted data is the Fully Homomorphic Encryption Scheme. We contribute theoretical presentations in high-level computational processes that are based on number theory and algebra that can easily be integrated and leveraged in the Cloud computing with detail theoretic mathematical concepts to the fully homomorphic encryption models. This contribution enhances the full implementation of big data analytics based cryptographic security algorithm.

Keywords: big data analytics, security, privacy, bootstrapping, homomorphic, homomorphic encryption scheme

Procedia PDF Downloads 379

Authors: Bilquis Ferdousi

Abstract:

With the exponential growth of the online business, the threat to consumers’ privacy and data security has become a serious challenge. This literature review-based study focuses on a better understanding of those threats and what legislative measures have been taken to address those challenges. Research shows that people are increasingly involved in online business using different digital devices and platforms, although this practice varies based on age groups. The threat to consumers’ privacy and data security is a serious hindrance in developing trust among consumers in online businesses. There are some legislative measures taken at the federal and state level to protect consumers’ privacy and data security. The study was based on an extensive review of current literature on protecting consumers’ privacy and data security and legislative measures that have been taken.

Keywords: privacy, data security, legislation, online business

Procedia PDF Downloads 106

Authors: Orhun Vural, Oguz Bayat, Rustu Akay, Osman N. Ucan

Abstract:

This study presents a new parallel approach clustering of GPS data. Evaluation has been made by comparing execution time of various clustering algorithms on GPS data. This paper aims to propose a parallel based on neighborhood K-means algorithm to make it faster. The proposed parallelization approach assumes that each GPS data represents a vehicle and to communicate between vehicles close to each other after vehicles are clustered. This parallelization approach has been examined on different sized continuously changing GPS data and compared with serial K-means algorithm and other serial clustering algorithms. The results demonstrated that proposed parallel K-means algorithm has been shown to work much faster than other clustering algorithms.

Keywords: parallel k-means algorithm, parallel clustering, clustering algorithms, clustering on flowing data

Procedia PDF Downloads 222

Authors: Dhananjay Singh, M. Abdullah-Al-Wadud

Abstract:

The Internet of Things is a concept of a large scale ecosystem of wireless actuators. The actuators are defined as things in the IoT, those which contribute or produces some data to the ecosystem. However, ubiquitous data collection, data security, privacy preserving, large volume data processing, and intelligent analytics are some of the key challenges into the IoT technologies. In order to solve the security requirements, challenges and threats in the IoT, we have discussed a message authentication mechanism for IoT applications. Finally, we have discussed data encryption mechanism for messages authentication before propagating into IoT networks.

Keywords: Internet of Things (IoT), message authentication, privacy, security

Procedia PDF Downloads 382

Authors: N. D. Iswarya, M. A. Maluk Mohamed, N. Vijaya

Abstract:

Grid is infrastructure that allows the deployment of distributed data in large size from multiple locations to reach a common goal. Scheduling data intensive applications becomes challenging as the size of data sets are very huge in size. Only two solutions exist in order to tackle this challenging issue. First, computation which requires huge data sets to be processed can be transferred to the data site. Second, the required data sets can be transferred to the computation site. In the former scenario, the computation cannot be transferred since the servers are storage/data servers with little or no computational capability. Hence, the second scenario can be considered for further exploration. During scheduling, transferring huge data sets from one site to another site requires more network bandwidth. In order to mitigate this issue, this work focuses on incorporating cognitive science in scheduling. Cognitive Science is the study of human brain and its related activities. Current researches are mainly focused on to incorporate cognitive science in various computational modeling techniques. In this work, the problem solving approach of human brain is studied and incorporated during the data intensive scheduling in grid environments. Here, a cognitive engine is designed and deployed in various grid sites. The intelligent agents present in CE will help in analyzing the request and creating the knowledge base. Depending upon the link capacity, decision will be taken whether to transfer data sets or to partition the data sets. Prediction of next request is made by the agents to serve the requesting site with data sets in advance. This will reduce the data availability time and data transfer time. Replica catalog and Meta data catalog created by the agents assist in decision making process.

Keywords: data grid, grid workflow scheduling, cognitive artificial intelligence

Procedia PDF Downloads 394

Authors: Xinge Liao, Francesc Xavier Roige Ventura, Dolores Sanchez Aguilera

Abstract:

With the development of the Internet, the study of tourism behavior has rapidly expanded from the traditional physical market to the online market. Data on the Internet is characterized by dynamic changes, and new data appear all the time. In recent years the generation of a large volume of data was characterized, such as forums, blogs, and other sources, which have expanded over time and space, together they constitute large-scale Internet data, known as Big Data. This data of technological origin that derives from the use of devices and the activity of multiple users is becoming a source of great importance for the study of geography and the behavior of tourists. The study will focus on cultural heritage tourist practices in the context of Big Data. The research will focus on exploring the characteristics and behavior of Chinese tourists in relation to the cultural heritage of Catalonia. Geographical information, target image, perceptions in user-generated content will be studied through data analysis from Weibo -the largest social networks of blogs in China. Through the analysis of the behavior of heritage tourists in the Big Data environment, this study will understand the practices (activities, motivations, perceptions) of cultural tourists and then understand the needs and preferences of tourists in order to better guide the sustainable development of tourism in heritage sites.

Keywords: Barcelona, Big Data, Catalonia, cultural heritage, Chinese tourism market, tourists’ behavior

Procedia PDF Downloads 138

Authors: Darusalam, Jorish Hulstijn, Marijn Janssen

Abstract:

Media has revealed a variety of corruption cases in the regional and local governments all over the world. Many governments pursued many anti-corruption reforms and have created a system of checks and balances. Three types of corruption are faced by citizens; administrative corruption, collusion and extortion. Accountability is one of the benchmarks for building transparent government. The public sector is required to report the results of the programs that have been implemented so that the citizen can judge whether the institution has been working such as economical, efficient and effective. Open Data is offering solutions for the implementation of good governance in organizations who want to be more transparent. In addition, Open Data can create transparency and accountability to the community. The objective of this paper is to build a framework of open data for accountability to combating corruption. This paper will investigate the relationship between open data, and accountability as part of anti-corruption initiatives. This research will investigate the impact of open data implementation on public organization.

Keywords: open data, accountability, anti-corruption, framework

Procedia PDF Downloads 336

Authors: David Ming Liu, Benjamin Hirsch, Bashir Aden

Abstract:

Syndromic surveillance is to detect or predict disease outbreaks through the analysis of medical sources of data. Using social media data like tweets to do syndromic surveillance becomes more and more popular with the aid of open platform to collect data and the advantage of microblogging text and mobile geographic location features. In this paper, a Syndromic Surveillance Framework is presented with machine learning kernel using tweets data analytics. Influenza and the three cities Abu Dhabi, Al Ain and Dubai of United Arabic Emirates are used as the test disease and trial areas. Hospital cases data provided by the Health Authority of Abu Dhabi (HAAD) are used for the correlation purpose. In our model, Latent Dirichlet allocation (LDA) engine is adapted to do supervised learning classification and N-Fold cross validation confusion matrix are given as the simulation results with overall system recall 85.595% performance achieved.

Keywords: Syndromic surveillance, Tweets, Machine Learning, data mining, Latent Dirichlet allocation (LDA), Influenza

Procedia PDF Downloads 116

Authors: Yuyun Wabula, B. J. Dewancker

Abstract:

In the past decade, the social networking app has been growing very rapidly. Geolocation data is one of the important features of social media that can attach the user's location coordinate in the real world. This paper proposes the use of geolocation data from the Twitter social media application to gain knowledge about urban dynamics, especially on human mobility behavior. This paper aims to explore the relation between geolocation Twitter with the existence of people in the urban area. Firstly, the study will analyze the spread of people in the particular area, within the city using Twitter social media data. Secondly, we then match and categorize the existing place based on the same individuals visiting. Then, we combine the Twitter data from the tracking result and the questionnaire data to catch the Twitter user profile. To do that, we used the distribution frequency analysis to learn the visitors’ percentage. To validate the hypothesis, we compare it with the local population statistic data and land use mapping released by the city planning department of Makassar local government. The results show that there is the correlation between Twitter geolocation and questionnaire data. Thus, integration the Twitter data and survey data can reveal the profile of the social media users.

Keywords: geolocation, Twitter, distribution analysis, human mobility

Procedia PDF Downloads 314

Authors: Zeineb Baatout, Safa Teka, Nejmeddine Jaballah, Nawfel Sakly, Xiaonan Sun, Mustapha Majdoub

Abstract:

Currently, the economic interests linked to the development of bio-based materials make biomass one of the most interesting areas for science development. We are interested in the β-cyclodextrin (β-CD), one of the popular bio-sourced macromolecule, produced from the starch via enzymatic conversion. It is a cyclic oligosaccharide formed by the association of seven glucose units. It presents a rigid conical and amphiphilic structure with hydrophilic exterior, allowing it to be water-soluble. It has also a hydrophobic interior enabling the formation of inclusion complexes, which support its application for the elaboration of electrochemical and optical sensors. Nevertheless, the solubility of β-CD in water makes its use as sensitive layer limit and difficult due to their instability in aqueous media. To overcome this limitation, we chose to precede by modification of the hydroxyl groups to obtain hydrophobic derivatives which lead to water-stable sensing layers. Hence, a series of benzylated β-CDs were synthesized in basic aqueous media in one pot. This work reports the synthesis of a new family of substituted amphiphilic β-CDs using a green methodology. The obtained β-CDs showed different degree of substitution (DS) between 0.85 and 2.03. These organic macromolecular materials were soluble in common organic volatile solvents, and their structures were investigated by NMR, FT-IR and MALDI-TOF spectroscopies. Thermal analysis showed a correlation between the thermal properties of these derivatives and the benzylation degree. The surface properties of the thin films based on the benzylated β-CDs were characterized by contact angle measurements and atomic force microscopy (AFM). These organic materials were investigated as sensitive layers, deposited on quartz crystal microbalance (QCM) gravimetric transducer, for humidity sensor at room temperature. The results showed that the performances of the prepared sensors are greatly influenced by the benzylation degree of β-CD. The partially modified β-CD (DS=1) shows linear response with best sensitivity, good reproducibility, low hysteresis, fast response time (15s) and recovery time (17s) at higher relative humidity levels (RH) between 11% and 98% in room temperature.

Keywords: β-cyclodextrin, green synthesis, humidity sensor, quartz crystal microbalance

Procedia PDF Downloads 271

Authors: Rezaei Hachesu Peyman, Oliyaee Azadeh, Salahzadeh Zahra, Alizadeh Somayyeh, Safaei Naser

Abstract:

Coronary Artery Disease (CAD) is one major cause of disability in adults and one main cause of death in developed. In this study, data mining techniques including Decision Trees, Artificial neural networks (ANNs), and Support Vector Machine (SVM) analyze CAD data. Data of 4948 patients who had suffered from heart diseases were included in the analysis. CAD is the target variable, and 24 inputs or predictor variables are used for the classification. The performance of these techniques is compared in terms of sensitivity, specificity, and accuracy. The most significant factor influencing CAD is chest pain. Elderly males (age > 53) have a high probability to be diagnosed with CAD. SVM algorithm is the most useful way for evaluation and prediction of CAD patients as compared to non-CAD ones. Application of data mining techniques in analyzing coronary artery diseases is a good method for investigating the existing relationships between variables.

Keywords: classification, coronary artery disease, data-mining, knowledge discovery, extract

Procedia PDF Downloads 657

Authors: Sudipto Shanker Dasgupta

Abstract:

One of the largest mining companies wanted to look at health analytics for their driverless trucks. These trucks were the key to their supply chain logistics. The automated trucks had multi-level sub-assemblies which would send out sensor information. The use case that was worked on was to capture the sensor signal from the truck subcomponents and analyze the health of the trucks from repair and replacement purview. Open source software was used to stream the data into a clustered Hadoop setup in Amazon Web Services cloud and Apache Spark SQL was used to analyze the data. All of this was achieved through a 10 node amazon 32 core, 64 GB RAM setup real-time analytics was achieved on ‘300 million records’. To check the scalability of the system, the cluster was increased to 100 node setup. This talk will highlight how Open Source software was used to achieve the above use case and the insights on the high data throughput on a cloud set up.

Keywords: streaming analytics, data science, big data, Hadoop, high throughput, sensor data

Procedia PDF Downloads 404

Authors: Sheldon Liu, Gordon Wang, Lei Liu, Xuefeng Liu

Abstract:

Anomaly detection, also referred to as one-class classification, plays a crucial role in identifying product images that deviate from the expected distribution. This study introduces Data-centric Anomaly Detection with Diffusion Models (DCADDM), presenting a systematic strategy for data collection and further diversifying the data with image generation via diffusion models. The algorithm addresses data collection challenges in real-world scenarios and points toward data augmentation with the integration of generative AI capabilities. The paper explores the generation of normal images using diffusion models. The experiments demonstrate that with 30% of the original normal image size, modeling in an unsupervised setting with state-of-the-art approaches can achieve equivalent performances. With the addition of generated images via diffusion models (10% equivalence of the original dataset size), the proposed algorithm achieves better or equivalent anomaly localization performance.

Keywords: diffusion models, anomaly detection, data-centric, generative AI

Procedia PDF Downloads 82

Authors: Elizabeta Krstić Vukelja

Abstract:

Digitization of personal data is a consequence of the development of information and communication technologies that create a new work environment with many advantages and challenges, but also potential threats to privacy and personal data protection. Regulation (EU) 2016/679 of the European Parliament and of the Council is becoming a law and obligation that should address the issues of personal data protection and information security. The existence of the Regulation leads to the conclusion that national legislation in the field of virtual environment, protection of the rights of EU citizens and processing of their personal data is insufficiently effective. In the health system, special emphasis is placed on the processing of special categories of personal data, such as health data. The healthcare industry is recognized as a particularly sensitive area in which a large amount of medical data is processed, the digitization of which enables quick access and quick identification of the health insured. The protection of the individual requires quality IT solutions that guarantee the technical protection of personal categories. However, the real problems are the technical and human nature and the spatial limitations of the application of the Regulation. Some conclusions will be drawn by analyzing the implementation of the basic principles of the Regulation on the example of the Croatian health care system and comparing it with similar activities in other EU member states.

Keywords: regulation, healthcare system, personal dana protection, quality data assurance

Procedia PDF Downloads 38

Authors: Ariadne C. Catto, Luis F. da Silva, Khalifa Aguir, Valmor Roberto Mastelaro

Abstract:

Zinc oxide (ZnO) pure or doped are one of the most promising metal oxide semiconductors for gas sensing applications due to the well-known high surface-to-volume area and surface conductivity. It was shown that ZnO is an excellent gas-sensing material for different gases such as CO, O2, NO2 and ethanol. In this context, pure and doped ZnO exhibiting different morphologies and a high surface/volume ratio can be a good option regarding the limitations of the current commercial sensors. Different studies showed that the sensitivity of metal-doped ZnO (e.g. Co, Fe, Mn,) enhanced its gas sensing properties. Motivated by these considerations, the aim of this study consisted on the investigation of the role of Co ions on structural, morphological and the gas sensing properties of nanostructured ZnO samples. ZnO and Zn1-xCoxO (0 < x < 5 wt%) thin films were obtained via the polymeric precursor method. The sensitivity, selectivity, response time and long-term stability gas sensing properties were investigated when the sample was exposed to a different concentration range of ozone (O3) at different working temperatures. The gas sensing property was probed by electrical resistance measurements. The long and short-range order structure around Zn and Co atoms were investigated by X-ray diffraction and X-ray absorption spectroscopy. X-ray photoelectron spectroscopy measurement was performed in order to identify the elements present on the film surface as well as to determine the sample composition. Microstructural characteristics of the films were analyzed by a field-emission scanning electron microscope (FE-SEM). Zn1-xCoxO XRD patterns were indexed to the wurtzite ZnO structure and any second phase was observed even at a higher cobalt content. Co-K edge XANES spectra revealed the predominance of Co2+ ions. XPS characterization revealed that Co-doped ZnO samples possessed a higher percentage of oxygen vacancies than the ZnO samples, which also contributed to their excellent gas sensing performance. Gas sensor measurements pointed out that ZnO and Co-doped ZnO samples exhibit a good gas sensing performance concerning the reproducibility and a fast response time (around 10 s). Furthermore, the Co addition contributed to reduce the working temperature for ozone detection and improve the selective sensing properties.

Keywords: cobalt-doped ZnO, nanostructured, ozone gas sensor, polymeric precursor method

Procedia PDF Downloads 247

Authors: Nagi Mekhiel

Abstract:

Many applications use vector operations by applying single instruction to multiple data that map to different locations in conventional memory. Transferring data from memory is limited by access latency and bandwidth affecting the performance gain of vector processing. We present a memory system that makes all of its content available to processors in time so that processors need not to access the memory, we force each location to be available to all processors at a specific time. The data move in different orbits to become available to other processors in higher orbits at different time. We use this memory to apply parallel vector operations to data streams at first orbit level. Data processed in the first level move to upper orbit one data element at a time, allowing a processor in that orbit to apply another vector operation to deal with serial code limitations inherited in all parallel applications and interleaved it with lower level vector operations.

Keywords: Memory Organization, Parallel Processors, Serial Code, Vector Processing

Procedia PDF Downloads 270

Authors: David Percy

Abstract:

Landslides are a geologic phenomenon that affects a large number of inhabited places and are constantly being monitored and studied for the prediction of future occurrences. Reconstructability analysis (RA) is a methodology for extracting informative models from large volumes of data that work exclusively with discrete data. While RA has been used in medical applications and social science extensively, we are introducing it to the spatial sciences through applications like landslide prediction. Since RA works exclusively with discrete data, such as soil classification or bedrock type, working with continuous data, such as porosity, requires that these data are binned for inclusion in the model. RA constructs models of the data which pick out the most informative elements, independent variables (IVs), from each layer that predict the dependent variable (DV), landslide occurrence. Each layer included in the model retains its classification data as a primary encoding of the data. Unlike other machine learning algorithms that force the data into one-hot encoding type of schemes, RA works directly with the data as it is encoded, with the exception of continuous data, which must be binned. The usual physical and derived layers are included in the model, and testing our results against other published methodologies, such as neural networks, yields accuracy that is similar but with the advantage of a completely transparent model. The results of an RA session with a data set are a report on every combination of variables and their probability of landslide events occurring. In this way, every combination of informative state combinations can be examined.

Keywords: reconstructability analysis, machine learning, landslides, raster analysis

Procedia PDF Downloads 66

Authors: Tammy Wee, Detlev Remy, Arif Perdana

Abstract:

In the recent years, data analytics has become the buzzword in the hospitality industry. The hospitality industry is another example of a data-rich industry that has yet fully benefited from the insights of data analytics. Effective use of data analytics can change how hotels operate, market and position themselves competitively in the hospitality industry. However, at the moment, the data obtained by individual hotels remain under-utilized. This research is a preliminary research on data analytics in the hospitality industry, using an in-depth face-to-face interview on one hotel as a start to a multi-level research. The main case study of this research, hotel A, is a chain brand of international hotel that has been systematically gathering and collecting data on its own customer for the past five years. The data collection points begin from the moment a guest book a room until the guest leave the hotel premises, which includes room reservation, spa booking, and catering. Although hotel A has been gathering data intelligence on its customer for some time, they have yet utilized the data to its fullest potential, and they are aware of their limitation as well as the potential of data analytics. Currently, the utilization of data analytics in hotel A is limited in the area of customer service improvement, namely to enhance the personalization of service for each individual customer. Hotel A is able to utilize the data to improve and enhance their service which in turn, encourage repeated customers. According to hotel A, 50% of their guests returned to their hotel, and 70% extended nights because of the personalized service. Apart from using the data analytics for enhancing customer service, hotel A also uses the data in marketing. Hotel A uses the data analytics to predict or forecast the change in consumer behavior and demand, by tracking their guest’s booking preference, payment preference and demand shift between properties. However, hotel A admitted that the data they have been collecting was not fully utilized due to two challenges. The first challenge of using data analytics in hotel A is the data is not clean. At the moment, the data collection of one guest profile is meaningful only for one department in the hotel but meaningless for another department. Cleaning up the data and getting standards correctly for usage by different departments are some of the main concerns of hotel A. The second challenge of using data analytics in hotel A is the non-integral internal system. At the moment, the internal system used by hotel A do not integrate with each other well, limiting the ability to collect data systematically. Hotel A is considering another system to replace the current one for more comprehensive data collection. Hotel proprietors recognized the potential of data analytics as reported in this research, however, the current challenges of implementing a system to collect data come with a cost. This research has identified the current utilization of data analytics and the challenges faced when it comes to implementing data analytics.

Keywords: data analytics, hospitality industry, customer relationship management, hotel marketing

Procedia PDF Downloads 179

Authors: Djelloul Benatiallah, Ali Benatiallah, Abdelkader Harouz

Abstract:

Geographic Information Systems (GIS) include various methods and computer techniques to model, capture digitally, store, manage, view and analyze. Geographic information systems have the characteristic to appeal to many scientific and technical field, and many methods. In this article we will present a complete and operational geographic information system, following the theoretical principles of data management and adapting to spatial data, especially data concerning the monitoring of drinking water supply wells (DWS) Adrar region. The expected results of this system are firstly an offer consulting standard features, updating and editing beneficiaries and geographical data, on the other hand, provides specific functionality contractors entered data, calculations parameterized and statistics.

Keywords: GIS, DWS, drilling, Adrar

Procedia PDF Downloads 309

Authors: S. Habte, K. Ouazzane, P. Patel, S. Patel

Abstract:

The dynamic and highly competitive nature of the consumer electronics retail industry means that businesses in this industry are experiencing different decision making challenges in relation to pricing, inventory control, consumer satisfaction and product offerings. To overcome the challenges facing retailers and create opportunities, we propose a generic data warehousing solution which can be applied to a wide range of consumer electronics retailers with a minimum configuration. The solution includes a dimensional data model, a template SQL script, a high level architectural descriptions, ETL tool developed using C#, a set of APIs, and data access tools. It has been successfully applied by ASK Outlets Ltd UK resulting in improved productivity and enhanced sales growth.

Keywords: consumer electronics, data warehousing, dimensional data model, generic, retail industry

Procedia PDF Downloads 411

Authors: Lei Ren, Michael Hartnett, Stephen Nash

Abstract:

The abundant measured surface current from HF radar system in coastal area is assimilated into model to improve the modeling forecasting ability. A simple sequential data assimilation scheme, Direct Insertion (DI), is applied to update model forecast states. The influence of Direct Insertion data assimilation over time is analyzed at one reference point. Vector maps of surface current from models are compared with HF radar measurements. Root-Mean-Squared-Error (RMSE) between modeling results and HF radar measurements is calculated during the last four days with no data assimilation.

Keywords: data assimilation, CODAR, HF radar, surface current, direct insertion

Procedia PDF Downloads 574