Search results for: data reliability

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 97

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 290

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 133

Authors: Pedro Esteban

Abstract:

Today’s electrical networks, including microgrids, are evolving into smart grids. The smart grid concept brings the idea that the power comes from various sources (continuous or intermittent), in various forms (AC or DC, high, medium or low voltage, etc.), and it must be integrated into the electric power system in a smart way to guarantee a continuous and reliable supply that complies with power quality and energy efficiency standards and grid code requirements. This idea brings questions for the different players like how the required power will be generated, what kind of power will be more suitable, how to store exceeding levels for short or long-term usage, and how to combine and distribute all the different generation power sources in an efficient way. To address these issues, there has been lots of development in recent years on the field of on-grid and off-grid hybrid power systems (HPS). These systems usually combine one or more modes of electricity generation together with energy storage to ensure optimal supply reliability and high level of energy security. Hybrid power systems combine power generation and energy storage technologies together with real-time energy management and innovative power quality and energy efficiency improvement functionalities. These systems help customers achieve targets for clean energy generation, they add flexibility to the electrical grid, and they optimize the installation by improving its power quality and energy efficiency.

Keywords: microgrids, hybrid power systems, energy storage, power quality improvement

Procedia PDF Downloads 133

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 340

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 137

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 784

Authors: Esmat Momeni, Shabnam Basari, Mohammad Beheshtinia

Abstract:

The purpose of this study is to provide a symbolic explanation of the four elements in Zoroastrianism and sustainable ecosystems with an ecological approach. The research method is fundamental and deductive content analysis. Data collection has been done through library and documentary methods and through reading books and related articles. The population and sample of the present study are Yazd city and Iran country after discovering symbolic concepts derived from the theoretical foundations of Zoroastrianism in four elements of water, air, soil, fire and conformity with Iranian architecture with the ecological approach in Yazd city, the sustainable ecosystem it is explained by the system of nature. The validity and reliability of the results are based on the trust and confidence of the research literature. Research findings show that Yazd was one of the bases of Zoroastrianism in Iran. Many believe that the first person to discuss the elements of nature and respect Zoroastrians is the Prophet of this religion. Keeping the environment clean and pure by paying attention to and respecting these four elements. The water element is a symbol of existence in Zoroastrianism, so the people of Yazd used the aqueduct and designed a pool in front of the building. The soil element is a symbol of the raw material of human creation in the Zoroastrian religion, the most readily available material in the desert areas of Yazd, used as bricks and adobes, creating one of the most magnificent roof coverings is the dome. The wind element represents the invisible force of the soul in Creation in Zoroastrianism, the most important application of wind in the windy, which is a highly efficient cooling system. The element of fire, which is always a symbol of purity in Zoroastrianism, is located in a special place in Yazd's Ataskadeh (altar/ temple), where the most important religious prayers are held in and against the fire. Consequently, indigenous knowledge and attention to indigenous architecture is a part of the national capital of each nation that encompasses their beliefs, values, methods, and knowledge. According to studies on the four elements of Zoroastrianism, the link between these four elements are that due to the hot and dry fire at the beginning, it is the fire that begins to follow the nature of the movement in the stillness of the earth, and arises from the heat of the fire and because of vigor and its decreases, cold (wind) emerges, and from cold, humidity and wetness. And by examining books and resources on Yazd's architectural design with an ecological approach to the values of the four elements Zoroastrianism has been inspired, it can be concluded that in order to have environmentally friendly architecture, it is essential to use sustainable architectural principles, to link religious and sacrament culture and ecology through architecture.

Keywords: ecology, architecture, quadruple elements of air, soil, water, fire, Zoroastrian religion, sustainable ecosystem, Iran, Yazd city

Procedia PDF Downloads 104

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 194

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 153

Authors: Natcha Laethongkham, Gayan Ramanayake, Philip Charlesworth, Leshan Uggalla

Abstract:

The throttling process in hybrid rocket engines (HREs) poses challenges due to inherent instability, impacting the engine’s reliability and robustness. Identifying and advancing existing technology is crucial to meet the demands of complex mission profiles required for next-generation launch vehicles. This paper reviews the current literature, focusing on oxidiser flow control for throttling purposes in HREs. Covered areas include oxidiser choices, commonly used throttle valves, and literature trends. Common oxidisers for throttling are hydrogen peroxide, nitrous oxide, and liquid oxygen. Two frequently chosen valves for throttling are the ball and variation pintle valves. The review identifies two primary research focuses: flow control valve studies and control system design. The current research stage is highlighted, and suggestions for future directions are proposed to advance thrust control systems in HREs. This includes further studies in existing research focuses and exploring new approaches such as system scheme design, numerical modelling, and applications.

Keywords: hybrid rocket engines, oxidiser flow control, thrust control, throttle valve, review

Procedia PDF Downloads 5

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 281

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 301

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 168

Authors: Simrin Kafle, Ulrika Enemark

Abstract:

Catastrophic health expenditure (CHE) is a critical issue in low- and middle-income countries like Nepal, exacerbating financial hardship among vulnerable households. This study assesses the effectiveness of Nepal’s National Health Insurance Program (NHIP), launched in 2015, to reduce out-of-pocket (OOP) healthcare costs and mitigate CHE. Conducted in Pokhara Metropolitan City, the study used an analytical cross-sectional design, sampling 1276 households through a two-stage random sampling method. Data was collected via face-to-face interviews between May and October 2023. The analysis was conducted using SPSS version 29, incorporating propensity score matching to minimize biases and create comparable groups of enrolled and non-enrolled households in the NHIP. PSM helped reduce confounding effects by matching households with similar baseline characteristics. Additionally, a doubly robust methodology was employed, combining propensity score adjustment with regression modeling to enhance the reliability of the results. This comprehensive approach ensured a more accurate estimation of the impact of NHIP enrollment on CHE. Among the 1276 samples, 534 households (41.8%) were enrolled in NHIP. Of them, 84.3% of households renewed their insurance card, though some cited long waiting times, lack of medications, and complex procedures as barriers to renewal. Approximately 57.3% of households reported known diseases before enrollment, with 49.8% attending routine health check-ups in the past year. The primary motivation for enrollment was encouragement from insurance employees (50.2%). The data indicates that 12.5% of enrolled households experienced CHE versus 7.5% among non-enrolled. Enrollment into NHIP does not contribute to lower CHE (AOR: 1.98, 95% CI: 1.21-3.24). Key factors associated with increased CHE risk were presence of non-communicable diseases (NCDs) (AOR: 3.94, 95% CI: 2.10-7.39), acute illnesses/injuries (AOR: 6.70, 95% CI: 3.97-11.30), larger household size (AOR: 3.09, 95% CI: 1.81-5.28), and households below the poverty line (AOR: 5.82, 95% CI: 3.05-11.09). Other factors such as gender, education level, caste/ethnicity, presence of elderly members, and under-five children also showed varying associations with CHE, though not all were statistically significant. The study concludes that enrollment in the NHIP does not significantly reduce the risk of CHE. The reason for this could be inadequate coverage, where high-cost medicines, treatments, and transportation costs are not fully included in the insurance package, leading to significant out-of-pocket expenses. We also considered the long waiting time, lack of medicines, and complex procedures for the utilization of NHIP benefits, which might result in the underuse of covered services. Finally, gaps in enrollment and retention might leave certain households vulnerable to CHE despite the existence of NHIP. Key factors contributing to increased CHE include NCDs, acute illnesses, larger household sizes, and poverty. To improve the program’s effectiveness, it is recommended that NHIP benefits and coverage be expanded to better protect against high healthcare costs. Additionally, simplifying the renewal process, addressing long waiting times, and enhancing the availability of services could improve member satisfaction and retention. Targeted financial protection measures should be implemented for high-risk groups, and efforts should be made to increase awareness and encourage routine health check-ups to prevent severe health issues that contribute to CHE.

Keywords: catastrophic health expenditure, effectiveness, national health insurance program, Nepal

Procedia PDF Downloads 13

Authors: Balazs Somodi, Balazs Kovesdi

Abstract:

In the research praxis of civil engineering the statistical evaluation of experimental and numerical investigations is an essential task in order to compare the experimental and numerical resistances of a specific structural problem with the proposed resistances of the standards. However, in the standards and in the international literature there are several different safety factor evaluation methods that can be used to check the necessary safety level (e.g.: 5% quantile level, 2.3% quantile level, 1‰ quantile level, γM partial safety factor, γM* partial safety factor, β reliability index). Moreover, in the international literature different calculation methods could be found even for the same safety factor as well. In the present study the flexural buckling resistance of high strength steel (HSS) welded closed sections are analyzed. The authors investigated the flexural buckling resistances of the analyzed columns by laboratory experiments. In the present study the safety levels of the obtained experimental resistances are calculated based on several safety approaches and compared with the EN 1990. The results of the different safety approaches are compared and evaluated. Based on the evaluation tendencies are identified and the differences between the statistical evaluation methods are explained.

Keywords: flexural buckling, high strength steel, partial safety factor, statistical evaluation

Procedia PDF Downloads 158

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 143

Authors: Shalini Tripathi, Pardeep Kumar

Abstract:

The method of translating observed symptoms into disease names is known as disease diagnosis. The ability to solve clinical problems in a complex manner is critical to a doctor's effectiveness in providing health care. The accuracy of his or her expertise is crucial to the survival and well-being of his or her patients. Artificial Intelligence (AI) has a huge economic influence depending on how well it is applied. In the medical sector, human brain-simulated intellect can help not only with classification accuracy, but also with reducing diagnostic time, cost and pain associated with pathologies tests. In light of AI's present and prospective applications in the biomedical, we will identify them in the paper based on potential benefits and risks, social and ethical consequences and issues that might be contentious but have not been thoroughly discussed in publications and literature. Current apps, personal tracking tools, genetic tests and editing programmes, customizable models, web environments, virtual reality (VR) technologies and surgical robotics will all be investigated in this study. While AI holds a lot of potential in medical diagnostics, it is still a very new method, and many clinicians are uncertain about its reliability, specificity and how it can be integrated into clinical practice without jeopardising clinical expertise. To validate their effectiveness, more systemic refinement of these implementations, as well as training of physicians and healthcare facilities on how to effectively incorporate these strategies into clinical practice, will be needed.

Keywords: Artificial Intelligence, medical diagnosis, virtual reality, healthcare ethical implications 

Procedia PDF Downloads 127

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 118

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 187

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 290

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 434

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 126

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 650

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 126

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 349

Authors: Victor Bodell, Lukas Ekstrom, Somayeh Aghanavesi

Abstract:

Fuel consumption (FC) is one of the key factors in determining expenses of operating a heavy-duty vehicle. A customer may therefore request an estimate of the FC of a desired vehicle. The modular design of heavy-duty vehicles allows their construction by specifying the building blocks, such as gear box, engine and chassis type. If the combination of building blocks is unprecedented, it is unfeasible to measure the FC, since this would first r equire the construction of the vehicle. This paper proposes a machine learning approach to predict FC. This study uses around 40,000 vehicles specific and o perational e nvironmental c onditions i nformation, such as road slopes and driver profiles. A ll v ehicles h ave d iesel engines and a mileage of more than 20,000 km. The data is used to investigate the accuracy of machine learning algorithms Linear regression (LR), K-nearest neighbor (KNN) and Artificial n eural n etworks (ANN) in predicting fuel consumption for heavy-duty vehicles. Performance of the algorithms is evaluated by reporting the prediction error on both simulated data and operational measurements. The performance of the algorithms is compared using nested cross-validation and statistical hypothesis testing. The statistical evaluation procedure finds that ANNs have the lowest prediction error compared to LR and KNN in estimating fuel consumption on both simulated and operational data. The models have a mean relative prediction error of 0.3% on simulated data, and 4.2% on operational data.

Keywords: artificial neural networks, fuel consumption, friedman test, machine learning, statistical hypothesis testing

Procedia PDF Downloads 174

Authors: Sinan Alsaadi, Mustafa Merdan

Abstract:

Communication and access systems can be made with many methods in today’s world. These systems are such standards as Wifi, Wimax, Bluetooth, GPS and GPRS. Devices which use these standards also use system resources excessively in direct proportion to their transmission speed. However, large-scale data communication is not always needed. In such cases, a technology which will use system resources as little as possible and support smart network topologies has been needed in order to enable the transmissions of such small packet data and provide the control for this kind of devices. IEEE issued 802.15.4 standard upon this necessity and enabled the production of Zigbee protocol which takes these standards as its basis and devices which support this protocol. In our project, this communication protocol was preferred. The aim of this study is to provide the immediate data transmission of our robot from the field within the scope of the project. In addition, making the communication with the robot through Zigbee Protocol has also been aimed. While sitting on the computer, obtaining the desired data from the region where the robot is located has been taken as the basis. Arduino Uno R3 microcontroller which provides the control mechanism, 1298 shield as the motor driver.

Keywords: ZigBee, wireless network, remote monitoring, smart home, agricultural industry

Procedia PDF Downloads 272

Authors: Sirus Mohammadi, Rohala Moghimi

Abstract:

The main advantages of microgrids are high energy efficiency through the application of Combined Heat and Power (CHP), high quality and reliability of the delivered electric energy and environmental and economic advantages. This study presents an energy management system (EMS) to optimize the operation of the microgrid (MG). In this paper an Adaptive Modified Firefly Algorithm (AMFA) is presented for optimal operation of a typical MG with renewable energy sources (RESs) accompanied by a back-up Micro-Turbine/Fuel Cell/Battery hybrid power source to level the power mismatch or to store the energy surplus when it’s needed. The problem is formulated as a nonlinear constraint problem to minimize the total operating cost. The management of Energy storage system (ESS), economic load dispatch and operation optimization of distributed generation (DG) are simplified into a single-object optimization problem in the EMS. The proposed algorithm is tested on a typical grid-connected MG including WT/PV/Micro Turbine/Fuel Cell and Energy Storage Devices (ESDs) then its superior performance is compared with those from other evolutionary algorithms such as Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Fuzzy Self Adaptive PSO (FSAPSO), Chaotic Particle PSO (CPSO), Adaptive Modified PSO (AMPSO), and Firefly Algorithm (FA).

Keywords: microgrid, operation management, optimization, firefly algorithm (AMFA)

Procedia PDF Downloads 335

Authors: Massimiliano Condotta, Paolo Ruggeri, Chiara Scanagatta, Giovanni Borga

Abstract:

Architects and urban planners, when designing and renewing cities, have to face a complex set of problems, including the issues of noise and air pollution which are considered as hot topics (i.e., the Clean Air Act of London and the Soundscape definition). It is usually taken for granted that these problems go by together because the noise pollution present in cities is often linked to traffic and industries, and these produce air pollutants as well. Traffic congestion can create both noise pollution and air pollution, because NO₂ is mostly created from the oxidation of NO, and these two are notoriously produced by processes of combustion at high temperatures (i.e., car engines or thermal power stations). We can see the same process for industrial plants as well. What have to be investigated – and is the topic of this paper – is whether or not there really is a correlation between noise pollution and air pollution (taking into account NO₂) in urban areas. To evaluate if there is a correlation, some low-cost methodologies will be used. For noise measurements, the OpeNoise App will be installed on an Android phone. The smartphone will be positioned inside a waterproof box, to stay outdoor, with an external battery to allow it to collect data continuously. The box will have a small hole to install an external microphone, connected to the smartphone, which will be calibrated to collect the most accurate data. For air, pollution measurements will be used the AirMonitor device, an Arduino board to which the sensors, and all the other components, are plugged. After assembling the sensors, they will be coupled (one noise and one air sensor) and placed in different critical locations in the area of Mestre (Venice) to map the existing situation. The sensors will collect data for a fixed period of time to have an input for both week and weekend days, in this way it will be possible to see the changes of the situation during the week. The novelty is that data will be compared to check if there is a correlation between the two pollutants using graphs that should show the percentage of pollution instead of the values obtained with the sensors. To do so, the data will be converted to fit on a scale that goes up to 100% and will be shown thru a mapping of the measurement using GIS methods. Another relevant aspect is that this comparison can help to choose which are the right mitigation solutions to be applied in the area of the analysis because it will make it possible to solve both the noise and the air pollution problem making only one intervention. The mitigation solutions must consider not only the health aspect but also how to create a more livable space for citizens. The paper will describe in detail the methodology and the technical solution adopted for the realization of the sensors, the data collection, noise and pollution mapping and analysis.

Keywords: air quality, data analysis, data collection, NO₂, noise mapping, noise pollution, particulate matter

Procedia PDF Downloads 207