Search results for: big data PCA

Authors: Migael van Zyl, Stefanie Visser, Awelani Phaswana

Abstract:

The electricity landscape in South Africa is characterized by frequent occurrences of loadshedding, a measure implemented by Eskom to manage electricity generation shortages by curtailing demand. Loadshedding, classified into stages ranging from 1 to 8 based on severity, involves the systematic rotation of power cuts across municipalities according to predefined schedules. However, this practice introduces distortions in recorded electricity demand, posing challenges to accurate forecasting essential for budgeting, network planning, and generation scheduling. Addressing this challenge requires the development of a methodology to quantify the impact of loadshedding and integrate it back into metered electricity demand data. Fortunately, comprehensive records of loadshedding impacts are maintained in a database, enabling the alignment of Loadshedding effects with hourly demand data. This adjustment ensures that forecasts accurately reflect true demand patterns, independent of loadshedding's influence, thereby enhancing the reliability of electricity supply management in South Africa. This paper presents a methodology for determining the hourly impact of load scheduling and subsequently adjusting historical demand data to account for it. Furthermore, two forecasting models are developed: one utilizing the original dataset and the other using the adjusted data. A comparative analysis is conducted to evaluate forecast accuracy improvements resulting from the adjustment process. By implementing this methodology, stakeholders can make more informed decisions regarding electricity infrastructure investments, resource allocation, and operational planning, contributing to the overall stability and efficiency of South Africa's electricity supply system.

Keywords: electricity demand forecasting, load shedding, demand side management, data science

Procedia PDF Downloads 62

Authors: Raif Parlakkaya, Ahmet Diken, Erkan Kara

Abstract:

This paper examines the relationship between corporate governance rating and stock prices of 26 Turkish firms listed in Turkish stock exchange (Borsa Istanbul) by using panel data analysis over five-year period. The paper also investigates the stock performance of firms with governance rating with regards to the market portfolio (i.e. BIST 100 Index) both prior and after governance scoring began. The empirical results show that there is no relation between corporate governance rating and stock prices when using panel data for annual variation in both rating score and stock prices. Further analysis indicates surprising results that while the selected firms outperform the market significantly prior to rating, the same performance does not continue afterwards.

Keywords: corporate governance, stock price, performance, panel data analysis

Procedia PDF Downloads 394

Authors: Kenneth Kapalu Muzata, Dikeledi Mahlo, Pinkie Mabunda Mabunda

Abstract:

This paper presents results of a study conducted to establish special education teachers’ knowledge and application of curriculum adaptation of the 2013 revised curriculum in Zambia. From a sample of 134 respondents (120 special education teachers, 12 education officers, and 2 curriculum specialists), the study collected both quantitative and qualitative data to establish whether teachers understood and applied the concept of curriculum adaptation in teaching learners with special education needs. To obtain data validity and reliability, the researchers collected data by use of mixed methods. Semi-structured questionnaires and interviews were administered. Lesson Observations and post-lesson discussions were conducted on 12 selected teachers from the 120 sample that answered the questionnaires. Frequencies, percentages, and significant differences were derived through the statistical package for social sciences. Qualitative data were analyzed with the help of NVIVO qualitative software to create themes and obtain coding density to help with conclusions. Both quantitative and qualitative data were concurrently compared and related. The results revealed that special education teachers lacked a thorough understanding of the concept of curriculum adaptation, thus denying learners with special education needs the opportunity to benefit from the revised curriculum. The teachers were not oriented on the revised curriculum and hence facing numerous challenges trying to adapt the curriculum. The study recommended training of special education teachers in curriculum adaptation.

Keywords: curriculum adaptation, special education, learners with special education needs, special education teachers

Procedia PDF Downloads 180

Authors: Marwa A. A. Ragab, Hadir M. Maher, Eman I. El-Kimary

Abstract:

Co-administration of methotrexate (MTX) and aspirin (ASP) can cause a pharmacokinetic interaction and a subsequent increase in blood MTX concentrations which may increase the risk of MTX toxicity. Therefore, it is important to develop a sensitive, selective, accurate and precise method for their simultaneous determination in urine. A new hybrid chemometric method has been applied to the emission response data of the two drugs. Spectrofluorimetric method for determination of MTX through measurement of its acid-degradation product, 4-amino-4-deoxy-10-methylpteroic acid (4-AMP), was developed. Moreover, the acid-catalyzed degradation reaction enables the spectrofluorimetric determination of ASP through the formation of its active metabolite salicylic acid (SA). The proposed chemometric method deals with convolution of emission data using 8-points sin xi polynomials (discrete Fourier functions) after the derivative treatment of these emission data. The first and second derivative curves (D1 & D2) were obtained first then convolution of these curves was done to obtain first and second derivative under Fourier functions curves (D1/FF) and (D2/FF). This new application was used for the resolution of the overlapped emission bands of the degradation products of both drugs to allow their simultaneous indirect determination in human urine. Not only this chemometric approach was applied to the emission data but also the obtained data were subjected to non-parametric linear regression analysis (Theil’s method). The proposed method was fully validated according to the ICH guidelines and it yielded linearity ranges as follows: 0.05-0.75 and 0.5-2.5 µg mL-1 for MTX and ASP respectively. It was found that the non-parametric method was superior over the parametric one in the simultaneous determination of MTX and ASP after the chemometric treatment of the emission spectra of their degradation products. The work combines the advantages of derivative and convolution using discrete Fourier function together with the reliability and efficacy of the non-parametric analysis of data. The achieved sensitivity along with the low values of LOD (0.01 and 0.06 µg mL-1) and LOQ (0.04 and 0.2 µg mL-1) for MTX and ASP respectively, by the second derivative under Fourier functions (D2/FF) were promising and guarantee its application for monitoring the two drugs in patients’ urine samples.

Keywords: chemometrics, emission curves, derivative, convolution, Fourier transform, human urine, non-parametric regression, Theil’s method

Procedia PDF Downloads 430

Authors: Clare Cunningham

Abstract:

Whilst there is a strong global research base on the benefits of structured writing retreats and similar provisions, such as Shut Up and Write events, for academic staff and postgraduate researchers, very little has been published about the worth of such events for undergraduate students. This is despite the fact that, internationally, undergraduate student researchers experience similar pressures, distractions and feelings towards writing as those who are at more senior levels within the academy. This paper reports on a mixed-methods study with cohorts of third-year undergraduate students over the course of four academic years. This involved a range of research instruments adopted over the four years of the study. They include the administration of four questionnaires across three academic years, a collection of ethnographic recordings in the second year, and the collation of reflective journal entries and evaluations from all four years. The final two years of data collection took place during the period of Covid-19 restrictions when writing retreats moved to the virtual space which adds an additional dimension of interest to the analysis. The analysis involved the collation of quantitative questionnaire data to observe patterns in expressions of attitudes towards writing. Qualitative data were analysed thematically and used to corroborate and support the quantitative data when appropriate. The resulting data confirmed that one of the biggest challenges for undergraduate students mirrors those reported in the findings of studies focused on more experienced researchers. This is not surprising, especially given the number of undergraduate students who now work alongside their studies, as well as the increasing number who have caring responsibilities, but it has, as yet, been under-reported. The data showed that the groups of writing retreat participants all had very positive experiences, with accountability, a sense of community and procrastination avoidance some of the key aspects. The analysis revealed the sometimes transformative power of these events for a number of these students in terms of changing the way they viewed writing and themselves as writers. The data presented in this talk will support the proposal that retreats should much more widely be offered to undergraduate students across the world.

Keywords: academic writing, students, undergraduates, writing retreat

Procedia PDF Downloads 200

Authors: Mohd Asrul Affedi, Nyi Nyi Naing

Abstract:

Overdispersion is present in count data, and basically when a phenomenon happened, a Negative Binomial (NB) is commonly used to replace a standard Poisson model. Analysis of count data event, such as mortality cases basically Poisson regression model is appropriate. Hence, the model is not appropriate when existing a zero values. The zero-inflated negative binomial model is appropriate. In this article, we modelled the mortality cases as a dependent variable by age categorical. The objective of this study to determine existing overdispersion in mortality data of AIDS co-infection patients in Kelantan.

Keywords: negative binomial death rate, overdispersion, zero-inflation negative binomial death rate, AIDS

Procedia PDF Downloads 464

Authors: Mace Bentley, Zhuojun Duan, Tobias Gerken, Dudley Bonsal, Henry Way, Endre Szakal, Mia Pham, Hunter Donaldson, Chelsea Lang, Hayden Abbott, Leah Wilcynzski

Abstract:

Air pollution has the potential to modify the lifespan and intensity of thunderstorms and the properties of lightning. Using data mining and geovisualization, we investigate how background climate and weather conditions shape variability in urban air pollution and how this, in turn, shapes thunderstorms as measured by the intensity, distribution, and frequency of cloud-to-ground lightning. A spatiotemporal analysis was conducted in order to identify thunderstorms using high-resolution lightning detection network data. Over seven million lightning flashes were used to identify more than 196,000 thunderstorms that occurred between 2006 - 2020 in the Washington, DC Metropolitan Region. Each lightning flash in the dataset was grouped into thunderstorm events by means of a temporal and spatial clustering algorithm. Once the thunderstorm event database was constructed, hourly wind direction, wind speed, and atmospheric thermodynamic data were added to the initiation and dissipation times and locations for the 196,000 identified thunderstorms. Hourly aerosol and air quality data for the thunderstorm initiation times and locations were also incorporated into the dataset. Developing thunderstorm climatologies using a lightning tracking algorithm and lightning detection network data was found to be useful for visualizing the spatial and temporal distribution of urban augmented thunderstorms in the region.

Keywords: lightning, urbanization, thunderstorms, climatology

Procedia PDF Downloads 76

Authors: Zahra Ramezanpanah, Joachim Carvallo, Aurelien Rodriguez

Abstract:

This paper aims to detect anomalies in streaming data using machine learning algorithms. In this regard, we designed two separate pipelines and evaluated the effectiveness of each separately. The first pipeline, based on supervised machine learning methods, consists of two phases. In the first phase, we trained several supervised models using the UNSW-NB15 data-set. We measured the efficiency of each using different performance metrics and selected the best model for the second phase. At the beginning of the second phase, we first, using Argus Server, sniffed a local area network. Several types of attacks were simulated and then sent the sniffed data to a running algorithm at short intervals. This algorithm can display the results of each packet of received data in real-time using the trained model. The second pipeline presented in this paper is based on unsupervised algorithms, in which a Temporal Graph Network (TGN) is used to monitor a local network. The TGN is trained to predict the probability of future states of the network based on its past behavior. Our contribution in this section is introducing an indicator to identify anomalies from these predicted probabilities.

Keywords: temporal graph network, anomaly detection, cyber security, IDS

Procedia PDF Downloads 103

Authors: Usiobaifo Agharese Rosemary, Osaseri Roseline Oghogho

Abstract:

Diabetes is a complex group of disease with a variety of causes; it is a disorder of the body metabolism in the digestion of carbohydrates food. The application of machine learning in the field of medical diagnosis has been the focus of many researchers and the use of recognition and classification model as a decision support tools has help the medical expert in diagnosis of diseases. Considering the large volume of medical data which require special techniques, experience, and high diagnostic skill in the diagnosis of diseases, the application of an artificial intelligent system to assist medical personnel in order to enhance their efficiency and accuracy in diagnosis will be an invaluable tool. In this study will propose a diabetes diagnosis model using rough set and K-nearest Neighbor classifier algorithm. The system consists of two modules: the feature extraction module and predictor module, rough data set is used to preprocess the attributes while K-nearest neighbor classifier is used to classify the given data. The dataset used for this model was taken for University of Benin Teaching Hospital (UBTH) database. Half of the data was used in the training while the other half was used in testing the system. The proposed model was able to achieve over 80% accuracy.

Keywords: classifier algorithm, diabetes, diagnostic model, machine learning

Procedia PDF Downloads 336

Authors: Budhvin T. Withana, Sulochana Rupasinghe

Abstract:

The problem of Dyslexia and Dysgraphia, two learning disabilities that affect reading and writing abilities, respectively, is a major concern for the educational system. Due to the complexity and uniqueness of the Sinhala language, these conditions are especially difficult for children who speak it. The traditional risk detection methods for Dyslexia and Dysgraphia frequently rely on subjective assessments, making it difficult to cover a wide range of risk detection and time-consuming. As a result, diagnoses may be delayed and opportunities for early intervention may be lost. The project was approached by developing a hybrid model that utilized various deep learning techniques for detecting risk of Dyslexia and Dysgraphia. Specifically, Resnet50, VGG16 and YOLOv8 were integrated to detect the handwriting issues, and their outputs were fed into an MLP model along with several other input data. The hyperparameters of the MLP model were fine-tuned using Grid Search CV, which allowed for the optimal values to be identified for the model. This approach proved to be effective in accurately predicting the risk of Dyslexia and Dysgraphia, providing a valuable tool for early detection and intervention of these conditions. The Resnet50 model achieved an accuracy of 0.9804 on the training data and 0.9653 on the validation data. The VGG16 model achieved an accuracy of 0.9991 on the training data and 0.9891 on the validation data. The MLP model achieved an impressive training accuracy of 0.99918 and a testing accuracy of 0.99223, with a loss of 0.01371. These results demonstrate that the proposed hybrid model achieved a high level of accuracy in predicting the risk of Dyslexia and Dysgraphia.

Keywords: neural networks, risk detection system, Dyslexia, Dysgraphia, deep learning, learning disabilities, data science

Procedia PDF Downloads 118

Authors: Thanduxolo Nomngcoyiya, Simon M. Kang’ethe

Abstract:

The paper aimed to critically analyse gaps pertaining to the cultural policy environments governing traditional male circumcision in the Eastern Cape as exemplified by an empirical case study. The original study which this paper is derived from utilized qualitative paradigm; and encompassed 28 participants. It used in-depth one-on-one interviews complemented by focus group discussions and key informants as a method of data collection. It also adopted interview guide as a data collection instrument. The original study was cross-sectional in nature, and the data was audio recorded and transcribed later during the data analysis and coding process. The study data analysis was content thematic analysis and identified the following key major findings on the culture of male circumcision policy: Lack of clarity on culture of male circumcision policy operations; Myths surrounding procedures on culture of male circumcision; Divergent views on cultural policies between government and male circumcision custodians; Unclear cultural policies on selection criteria of practitioners; and Lack of policy enforcement and implementation on transgressors of culture of male circumcision. It recommended: a stringent selection criteria of practitioners; a need to carry out death-free male circumcision; a need for male circumcision stakeholders to work with other culture and tradition-friendly stakeholders.

Keywords: human rights, policy enforcement, traditional male circumcision, traditional surgeons and nurses

Procedia PDF Downloads 297

Authors: Christopher B. Obida, George A. Blackburn, James D. Whyatt, Kirk T. Semple

Abstract:

In many regions of the world, especially in developing countries, river network data are outdated or completely absent, yet such information is critical for supporting important functions such as flood mitigation efforts, land use and transportation planning, and the management of water resources. In this study, a method was developed for delineating river networks using Sentinel 1 imagery. Unsupervised classification was applied to multi-temporal Sentinel 1 data to discriminate water bodies from other land covers then the outputs were combined to generate a single persistent water bodies product. A thinning algorithm was then used to delineate river centre lines, which were converted into vector features and built into a topologically structured geometric network. The complex river system of the Niger Delta was used to compare the performance of the Sentinel-based method against alternative freely available water body products from United States Geological Survey, European Space Agency and OpenStreetMap and a river network derived from a Shuttle Rader Topography Mission Digital Elevation Model. From both raster-based and vector-based accuracy assessments, it was found that the Sentinel-based river network products were superior to the comparator data sets by a substantial margin. The geometric river network that was constructed permitted a flow routing analysis which is important for a variety of environmental management and planning applications. The extracted network will potentially be applied for modelling dispersion of hydrocarbon pollutants in Ogoniland, a part of the Niger Delta. The approach developed in this study holds considerable potential for generating up to date, detailed river network data for the many countries where such data are deficient.

Keywords: Sentinel 1, image processing, river delineation, large scale mapping, data comparison, geometric network

Procedia PDF Downloads 140

Authors: Khan R. Rahaman, Quazi K. Hassan

Abstract:

Global changes in climate, environment, economies, populations, governments, institutions, and cultures converge in localities. Changes at a local scale, in turn, contribute to global changes as well as being affected by them. Our hypothesis is built on a consideration that temperature does vary at local level (i.e., termed as local warming) in comparison to the predicted models at the regional and/or global scale. To date, the bulk of the research relating local places to global climate change has been top-down, from the global toward the local, concentrating on methods of impact analysis that use as a starting point climate change scenarios derived from global models, even though these have little regional or local specificity. Thus, our focus is to understand such trends over the southern Alberta, which will enable decision makers, scientists, researcher community, and local people to adapt their policies based on local level temperature variations and to act accordingly. Specific objectives in this study are: (i) to understand the local warming (temperature in particular) trend in context of temperature normal during the period 1961-2010 at point locations using meteorological data; (ii) to validate the data by using specific yearly data, and (iii) to delineate the spatial extent of the local warming trends and understanding influential factors to adopt situation by local governments. Existing data has brought the evidence of such changes and future research emphasis will be given to validate this hypothesis based on remotely sensed data (i.e. MODIS product by NASA).

Keywords: local warming, climate change, urban area, Alberta, Canada

Procedia PDF Downloads 348

Authors: Katsuyuki Umezawa, Makoto Nakazawa, Manabu Kobayashi, Yutaka Ishii, Michiko Nakano, Shigeichi Hirasawa

Abstract:

This research aims to develop a self-study system equipped with an artificial teacher who gives advice to students by detecting the learners and to evaluate language learning in a unified framework. 'Detecting the learners' means that the system understands the learners' learning conditions, such as each learner’s degree of understanding, the difference in each learner’s thinking process, the degree of concentration or boredom in learning, and problem solving for each learner, which can be interpreted from learning behavior. In this paper, we propose a system to efficiently collect brain waves from learners by focusing on only the brain waves among the biological information for 'detecting the learners'. The conventional Electroencephalograph (EEG) measurement method during learning using a simple EEG has the following disadvantages. (1) The start and end of EEG measurement must be done manually by the experiment participant or staff. (2) Even when the EEG signal is weak, it may not be noticed, and the data may not be obtained. (3) Since the acquired EEG data is stored in each PC, there is a possibility that the time of data acquisition will be different in each PC. This time, we developed a system to collect brain wave data on the server side. This system overcame the above disadvantages.

Keywords: artificial teacher, e-learning, self-study system, simple EEG

Procedia PDF Downloads 146

Authors: Valentina Alessandra Carvalho do Vale, Elmo Thiago Lins Cöuras Ford

Abstract:

Increasingly telecommunications sectors are adopting optical technologies, due to its ability to transmit large amounts of data over long distances. However, as in all systems of data transmission, optical communication channels suffer from undesirable and non-deterministic effects, being essential to know the same. Thus, this research allows the assessment of these effects, as well as their characterization and beneficial uses of these effects.

Keywords: optical communication, optical fiber, non-deterministic effects, telecommunication

Procedia PDF Downloads 788

Authors: Arturo Daag

Abstract:

The Philippine Institute of Volcanology and Seismology (PHIVOLCS) is enhancing its liquefaction hazard map towards a detailed probabilistic approach using SDS and geophysical data. Target sites for liquefaction assessment are public schools in Metro Manila. Since target sites are in highly urbanized-setting, the objective of the project is to conduct both non-destructive geotechnical studies using Screw Driving Testing (SDFS) combined with geophysical data such as refraction microtremor array (ReMi), 3 component microtremor Horizontal to Vertical Spectral Ratio (HVSR), and ground penetrating RADAR (GPR). Initial test data was conducted in liquefaction impacted areas from the Mw 6.1 earthquake in Central Luzon last April 22, 2019 Province of Pampanga. Numerous accounts of liquefaction events were documented areas underlain by quaternary alluvium and mostly covered by recent lahar deposits. SDS estimated values showed a good correlation to actual SPT values obtained from available borehole data. Thus, confirming that SDS can be an alternative tool for liquefaction assessment and more efficient in terms of cost and time compared to SPT and CPT. Conducting borehole may limit its access in highly urbanized areas. In order to extend or extrapolate the SPT borehole data, non-destructive geophysical equipment was used. A 3-component microtremor obtains a subsurface velocity model in 1-D seismic shear wave velocity of the upper 30 meters of the profile (Vs30). For the ReMi, 12 geophone array with 6 to 8-meter spacing surveys were conducted. Microtremor data were computed through the Factor of Safety, which is the quotient of Cyclic Resistance Ratio (CRR) and Cyclic Stress Ratio (CSR). Complementary GPR was used to study the subsurface structure and used to inferred subsurface structures and groundwater conditions.

Keywords: screw drive testing, microtremor, ground penetrating RADAR, liquefaction

Procedia PDF Downloads 203

Authors: Abir Derouiche, Abdesslem Layeb

Abstract:

Association Rule Mining (ARM) is one of the most popular data mining tasks and it is widely used in various areas. The search for association rules is an NP-complete problem that is why metaheuristics have been widely used to solve it. The present paper presents the ARM as an optimization problem and surveys the proposed approaches in the literature based on metaheuristics.

Keywords: Optimization, Metaheuristics, Data Mining, Association rules Mining

Procedia PDF Downloads 161

Authors: Yi-Ping Lo, Shi-Yao Wei, Chih-Chun Ma

Abstract:

Since Google launched Google Glass in 2012, numbers of commercial wearable devices were released, such as smart belt, smart band, smart shoes, smart clothes ... etc. However, most of these devices perform as sensors to show the readings of measurements and few of them provide the interactive feedback to the user. Furthermore, these devices are single task devices which are not able to communicate with each other. In this paper a new health promotion system, Ubiquitous Life People Informatics Engine (U-Life PIE), will be presented. This engine consists of People Informatics Engine (PIE) and the interactive user interface. PIE collects all the data from the compatible devices, analyzes this data comprehensively and communicates between devices via various application programming interfaces. All the data and informations are stored on the PIE unit, therefore, the user is able to view the instant and historical data on their mobile devices any time. It also provides the real-time hands-free feedback and instructions through the user interface visually, acoustically and tactilely. These feedback and instructions suggest the user to adjust their posture or habits in order to avoid the physical injuries and prevent illness.

Keywords: machine learning, wearable devices, user interface, user experience, internet of things

Procedia PDF Downloads 294

Authors: Julia Desiree Velastegui Caceres, Luis Alejandro Velastegui Caceres, Oswaldo Padilla, Eduardo Kirby, Francisco Guerrero, Theofilos Toulkeridis

Abstract:

It is fundamental to conserve sites of natural and cultural heritage with any available technique or existing methodology of preservation in order to sustain them for the following generations. We propose a further skill to protect the actual view of such sites, in which with high technology instrumentation we are able to digitally preserve natural and cultural heritages applied in Ecuador. In this project the use of laser technology is presented for three-dimensional models, with high accuracy in a relatively short period of time. In Ecuador so far, there are not any records on the use and processing of data obtained by this new technological trend. The importance of the project is the description of the methodology of the laser scanner system using the Faro Laser Scanner Focus 3D 120, the method for 3D modeling of geospatial data and the development of virtual environments in the areas of Cultural and Natural Heritage. In order to inform users this trend in technology in which three-dimensional models are generated, the use of such tools has been developed to be able to be displayed in all kinds of digitally formats. The results of the obtained 3D models allows to demonstrate that this technology is extremely useful in these areas, but also indicating that each data campaign needs an individual slightly different proceeding starting with the data capture and processing to obtain finally the chosen virtual environments.

Keywords: laser scanner system, 3D model, cultural heritage, natural heritage

Procedia PDF Downloads 308

Authors: Mohadeseh Shojaei Shahrokhabadi, Ding-Geng (Din) Chen

Abstract:

Positive continuous outcomes with a substantial number of zero values and incomplete longitudinal follow-up are quite common in medical cost data. To jointly model semi-continuous longitudinal cost data and survival data and to provide marginalized covariate effect estimates, a marginalized two-part joint model (MTJM) has been developed for outcome variables with lognormal distributions. In this paper, we propose MTJM models for outcome variables from a generalized gamma (GG) family of distributions. The GG distribution constitutes a general family that includes approximately all of the most frequently used distributions like the Gamma, Exponential, Weibull, and Log Normal. In the proposed MTJM-GG model, the conditional mean from a conventional two-part model with a three-parameter GG distribution is parameterized to provide the marginal interpretation for regression coefficients. In addition, MTJM-gamma and MTJM-Weibull are developed as special cases of MTJM-GG. To illustrate the applicability of the MTJM-GG, we applied the model to a set of real electronic health record data recently collected in Iran, and we provided SAS code for application. The simulation results showed that when the outcome distribution is unknown or misspecified, which is usually the case in real data sets, the MTJM-GG consistently outperforms other models. The GG family of distribution facilitates estimating a model with improved fit over the MTJM-gamma, standard Weibull, or Log-Normal distributions.

Keywords: marginalized two-part model, zero-inflated, right-skewed, semi-continuous, generalized gamma

Procedia PDF Downloads 176

Authors: Nishank Raisinghani

Abstract:

Efficiently predicting drug response remains a challenge in the realm of drug discovery. To address this issue, we propose four model architectures that combine graphical representation with varying positions of multiheaded self-attention mechanisms. By leveraging two types of multi-omics data, transcriptomics and genomics, we create a comprehensive representation of target cells and enable drug response prediction in precision medicine. A majority of our architectures utilize multiple transformer models, one with a graph attention mechanism and the other with a multiheaded self-attention mechanism, to generate latent representations of both drug and omics data, respectively. Our model architectures apply an attention mechanism to both drug and multiomics data, with the goal of procuring more comprehensive latent representations. The latent representations are then concatenated and input into a fully connected network to predict the IC-50 score, a measure of cell drug response. We experiment with all four of these architectures and extract results from all of them. Our study greatly contributes to the future of drug discovery and precision medicine by looking to optimize the time and accuracy of drug response prediction.

Keywords: drug discovery, transformers, graph neural networks, multiomics

Procedia PDF Downloads 156

Authors: Ling Qi, Matloob Khushi, Josiah Poon

Abstract:

This paper introduces a pre-trained Masked Candlestick Model (MCM) for trading time-series data. The pre-trained model is based on three core designs. First, we convert trading price data at each data point as a set of normalized elements and produce embeddings of each element. Second, we generate a masked sequence of such embedded elements as inputs for self-supervised learning. Third, we use the encoder mechanism from the transformer to train the inputs. The masked model learns the contextual relations among the sequence of embedded elements, which can aid downstream classification tasks. To evaluate the performance of the pre-trained model, we fine-tune MCM for three different downstream classification tasks to predict future price trends. The fine-tuned models achieved better accuracy rates for all three tasks than the baseline models. To better analyze the effectiveness of MCM, we test the same architecture for three currency pairs, namely EUR/GBP, AUD/USD, and EUR/JPY. The experimentation results demonstrate MCM’s effectiveness on all three currency pairs and indicate the MCM’s capability for signal extraction from trading data.

Keywords: masked language model, transformer, time series prediction, trading prediction, embedding, transfer learning, self-supervised learning

Procedia PDF Downloads 129

Authors: Muhammad Nouman, Fahad Tiwana, Muhammad Irfan, Mohsin Tiwana

Abstract:

Traffic congestion has been increasing significantly in major metropolitan areas as a result of increased motorization, urbanization, population growth and changes in the urban density. Traffic congestion compromises efficiency of transport infrastructure and causes multiple traffic concerns; including but not limited to increase of travel time, safety hazards, air pollution, and fuel consumption. Traffic management has become a serious challenge for federal and provincial governments, as well as exasperated commuters. Effective, flexible, efficient and user-friendly traffic information/database management systems characterize traffic conditions by making use of traffic counts for storage, processing, and visualization. While, the emerging data collection technologies continue to proliferate, its accuracy can be guaranteed through the comparison of observed data with the manual handheld counters. This paper presents the design of tablet based manual traffic counting application and framework for development of traffic database management system for Pakistan. The database management system comprises of three components including traffic counting android application; establishing online database and its visualization using Google maps. Oracle relational database was chosen to develop the data structure whereas structured query language (SQL) was adopted to program the system architecture. The GIS application links the data from the database and projects it onto a dynamic map for traffic conditions visualization. The traffic counting device and example of a database application in the real-world problem provided a creative outlet to visualize the uses and advantages of a database management system in real time. Also, traffic data counts by means of handheld tablet/ mobile application can be used for transportation planning and forecasting.

Keywords: manual count, emerging data sources, traffic information quality, traffic surveillance, traffic counting device, android; data visualization, traffic management

Procedia PDF Downloads 196

Authors: A. Al-Rashidi, A. El-Hamalawi

Abstract:

In this paper, a performance study was conducted to investigate single and dual-axis PV systems to generate electricity in five different sites in Kuwait. Relevant data were obtained by using two sources for validation purposes. A commercial software, PVsyst, was used to analyse the data, such as metrological data and other input parameters, and compute the performance parameters such as capacity factor (CF) and final yield (YF). The results indicated that single and dual-axis PV systems would be very beneficial to electricity generation in Kuwait as an alternative source to conventional power plants, especially with the increased demand over time. The ranges were also found to be competitive in comparison to leading countries using similar systems. A significant increase in CF and YF values around 24% and 28.8% was achieved related to the use of single and dual systems, respectively.

Keywords: single-axis and dual-axis photovoltaic systems, capacity factor, final yield, Kuwait

Procedia PDF Downloads 296

Authors: Jing Jiang, Wenhuan XU, Lei Zhang, Shiyi Zhang, Tongli Wang

Abstract:

Climate data quality significantly affects the reliability of ecological modeling. In the Asia Pacific (AP) region, low-quality climate data hinders ecological modeling. ClimateAP, a software developed in 2017, generates high-quality climate data for the AP region, benefiting researchers in forestry and agriculture. However, its adoption remains limited. This study aims to confirm the validity of biologically relevant variable data generated by ClimateAP during the normal climate period through comparison with the currently available gridded data. Climate data from 2,366 weather stations were used to evaluate the prediction accuracy of ClimateAP in comparison with the commonly used gridded data from WorldClim1.4. Univariate regressions were applied to 48 monthly biologically relevant variables, and the relationship between the observational data and the predictions made by ClimateAP and WorldClim was evaluated using Adjusted R-Squared and Root Mean Squared Error (RMSE). Locations were categorized into mountainous and flat landforms, considering elevation, slope, ruggedness, and Topographic Position Index. Univariate regressions were then applied to all biologically relevant variables for each landform category. Random Forest (RF) models were implemented for the climatic niche modeling of Cunninghamia lanceolata. A comparative analysis of the prediction accuracies of RF models constructed with distinct climate data sources was conducted to evaluate their relative effectiveness. Biologically relevant variables were obtained from three unpublished Chinese meteorological datasets. ClimateAPv3.0 and WorldClim predictions were obtained from weather station coordinates and WorldClim1.4 rasters, respectively, for the normal climate period of 1961-1990. Occurrence data for Cunninghamia lanceolata came from integrated biodiversity databases with 3,745 unique points. ClimateAP explains a minimum of 94.74%, 97.77%, 96.89%, and 94.40% of monthly maximum, minimum, average temperature, and precipitation variances, respectively. It outperforms WorldClim in 37 biologically relevant variables with lower RMSE values. ClimateAP achieves higher R-squared values for the 12 monthly minimum temperature variables and consistently higher Adjusted R-squared values across all landforms for precipitation. ClimateAP's temperature data yields lower Adjusted R-squared values than gridded data in high-elevation, rugged, and mountainous areas but achieves higher values in mid-slope drainages, plains, open slopes, and upper slopes. Using ClimateAP improves the prediction accuracy of tree occurrence from 77.90% to 82.77%. The biologically relevant climate data produced by ClimateAP is validated based on evaluations using observations from weather stations. The use of ClimateAP leads to an improvement in data quality, especially in non-mountainous regions. The results also suggest that using biologically relevant variables generated by ClimateAP can slightly enhance climatic niche modeling for tree species, offering a better understanding of tree species adaptation and resilience compared to using gridded data.

Keywords: climate data validation, data quality, Asia pacific climate, climatic niche modeling, random forest models, tree species

Procedia PDF Downloads 68

Authors: S. Nandagopalan, N. Pradeep

Abstract:

The aim of this paper is to propose a general framework for storing, analyzing, and extracting knowledge from two-dimensional echocardiographic images, color Doppler images, non-medical images, and general data sets. A number of high performance data mining algorithms have been used to carry out this task. Our framework encompasses four layers namely physical storage, object identification, knowledge discovery, user level. Techniques such as active contour model to identify the cardiac chambers, pixel classification to segment the color Doppler echo image, universal model for image retrieval, Bayesian method for classification, parallel algorithms for image segmentation, etc., were employed. Using the feature vector database that have been efficiently constructed, one can perform various data mining tasks like clustering, classification, etc. with efficient algorithms along with image mining given a query image. All these facilities are included in the framework that is supported by state-of-the-art user interface (UI). The algorithms were tested with actual patient data and Coral image database and the results show that their performance is better than the results reported already.

Keywords: active contour, Bayesian, echocardiographic image, feature vector

Procedia PDF Downloads 445

Authors: Janet Holland

Abstract:

Eye tracking is a great way to triangulate multiple data sources for deeper, more complete knowledge of how instructional materials are really being used and emotional connections made. Using sensor based biometrics provides a detailed local analysis in real time expanding our ability to collect science based data for a more comprehensive level of understanding, not previously possible, for teaching and learning. The knowledge gained will be used to make future improvements to instructional materials, tools, and interactions. The literature has been examined and a preliminary pilot test was implemented to develop a methodology for research in Instructional Design and Technology. Eye tracking now offers the addition of objective metrics obtained from eye tracking and other biometric data collection with analysis for a fresh perspective.

Keywords: area of interest, eye tracking, biometrics, fixation, fixation count, fixation sequence, fixation time, gaze points, heat map, saccades, time to first fixation

Procedia PDF Downloads 132

Authors: M. T. Alodat

Abstract:

In this paper, we propose a mechanism for skewing any symmetric distribution. The new distribution is called the deflation-inflation distribution (DID). We discuss some statistical properties of the DID such moments, stochastic representation, log-concavity. Also we fit the distribution to real data and we compare it to normal distribution and Azzlaini's skew normal distribution. Numerical results show that the DID fits the the tree ring data better than the other two distributions.

Keywords: normal distribution, moments, Fisher information, symmetric distributions

Procedia PDF Downloads 659

Authors: Najoua El Hajjaji El Idrissi, Necip Gokhan Kasapoglu

Abstract:

Polarimetric Synthetic Aperture Radar-based imaging is a powerful technique used for earth observation and classification of surfaces. Forest evolution has been one of the vital areas of attention for the remote sensing experts. The information about forest areas can be achieved by remote sensing, whether by using active radars or optical instruments. However, due to several weather constraints, such as cloud cover, limited information can be recovered using optical data and for that reason, Polarimetric Synthetic Aperture Radar (PolSAR) is used as a powerful tool for forestry inventory. In this [14paper, we applied support vector machine (SVM) and Mahalanobis distance to the fully polarimetric AIRSAR P, L, C-bands data from the Nezer forest areas, the classification is based in the separation of different tree ages. The classification results were evaluated and the results show that the SVM performs better than the Mahalanobis distance and SVM achieves approximately 75% accuracy. This result proves that SVM classification can be used as a useful method to evaluate fully polarimetric SAR data with sufficient value of accuracy.

Keywords: classification, synthetic aperture radar, SAR polarimetry, support vector machine, mahalanobis distance

Procedia PDF Downloads 133

Authors: Shalaka Kadam, Dinesh Apte, Sagar Mainkar

Abstract:

The life cycle of products is becoming shorter and shorter due to increased competition in market, shorter product development time and increased product diversity. Short life cycles are normal in retail industry, style business, entertainment media, and telecom and semiconductor industry. The subject of accurate forecasting for demand of short lifecycle products is of special enthusiasm for many researchers and organizations. Due to short life cycle of products the amount of historical data that is available for forecasting is very minimal or even absent when new or modified products are launched in market. The companies dealing with such products want to increase the accuracy in demand forecasting so that they can utilize the full potential of the market at the same time do not oversupply. This provides the challenge to develop a forecasting model that can forecast accurately while handling large variations in data and consider the complex relationships between various parameters of data. Many statistical models have been proposed in literature for forecasting time series data. Traditional time series forecasting models do not work well for short life cycles due to lack of historical data. Also artificial neural networks (ANN) models are very time consuming to perform forecasting. We have studied the existing models that are used for forecasting and their limitations. This work proposes an effective and powerful forecasting approach for short life cycle time series forecasting. We have proposed an approach which takes into consideration different scenarios related to data availability for short lifecycle products. We then suggest a methodology which combines statistical analysis with structured judgement. Also the defined approach can be applied across domains. We then describe the method of creating a profile from analogous products. This profile can then be used for forecasting products with historical data of analogous products. We have designed an application which combines data, analytics and domain knowledge using point-and-click technology. The forecasting results generated are compared using MAPE, MSE and RMSE error scores. Conclusion: Based on the results it is observed that no one approach is sufficient for short life-cycle forecasting and we need to combine two or more approaches for achieving the desired accuracy.

Keywords: forecast, short life cycle product, structured judgement, time series

Procedia PDF Downloads 360