Search results for: data security

Authors: Iftikhar U. Sikder

Abstract:

This paper illustrates an application of granular computing approach, namely rough set theory in data mining. The paper outlines the formalism of granular computing and elucidates the mathematical underpinning of rough set theory, which has been widely used by the data mining and the machine learning community. A real-world application is illustrated, and the classification performance is compared with other contending machine learning algorithms. The predictive performance of the rough set rule induction model shows comparative success with respect to other contending algorithms.

Keywords: concept approximation, granular computing, reducts, rough set theory, rule induction

Procedia PDF Downloads 531

Authors: Subbarao Pichuka, Amar Balakrishna Tej, Vikas Vemula

Abstract:

In recent years, the frequency and intensity of urban floods have increased due to climate change all over the world provoking a significant loss in terms of human lives and property. This study investigates the effect of Land Use and Land Cover (LULC) changes and population growth on the urban environmental conditions in the Indian metropolitan city namely Hyderabad. The centennial built-up area data have been downloaded from the Global Human Settlement Layer (GHSL) web portal for various periods (1975 to 2014). The ArcGIS version 10.8 software is employed to convert the GHSL data into shape files and also to calculate the amount of built-up area in the study locations. The decadal population data are obtained from the Census from 1971 to 2011 and forecasted for the required years (1975 and 2014) utilizing the Geometric Increase Method. Next, the analysis has been carried out with respect to the increase in population and the corresponding rise in the built-up area. Further the effects of extreme rainfall events, which exacerbate urban flooding have also been reviewed. Results demonstrate that the population growth was the primary cause of the increase in impervious surfaces in the urban regions. It in turn leads to the intensification of surface runoff and thereby leads to Urban flooding. The built-up area has been doubled from 1975 to 2014 and the population growth has been observed between 109.24% to 400% for the past four decades (1971 to 2014) in the study area (Hyderabad). Overall, this study provides the hindsight on the current urban flooding scenarios, and the findings of this study can be used in the future planning of cities.

Keywords: urban LULC change, urban flooding, GHSL built-up data, climate change, ArcGIS

Procedia PDF Downloads 81

Authors: Laras Tursilowati, Bambang Siswanto

Abstract:

Urban climate change has short- and long-term implications for decision-makers in urban development. The problem for this important metropolitan regional of population and economic value is that there is very little usable information on climate change. Research about urban climate change has been carried out in Bali Indonesia by using Conformal Cubic Atmospheric Model (CCAM) that runs with Representative Concentration Pathway (RCP)4.5. The history data means average data from 1975 to 2005, climate projections with RCP4.5 scenario means average data from 2006 to 2099, and anomaly (urban climate change) is RCP4.5 minus history. The results are the history of temperature between 22.5-27.5 OC, and RCP4.5 between 25.5-29.5 OC. The temperature anomalies can be seen in most of northern Bali that increased by about 1.6 to 2.9 OC. There is a reduced humidity tendency (drier) in most parts of Bali, especially the northern part of Bali, while a small portion in the south increase moisture (wetter). The comfort index of Bali region in history is still relatively comfortable (20-26 OC), but on the condition RCP4.5 there is no comfortable area with index more than 26 OC (hot and dry). This research is expected to be useful to help the government make good urban planning.

Keywords: CCAM, comfort index, IPCC AR5, temperature, urban climate change

Procedia PDF Downloads 144

Authors: Kyle Phillips, Ndiko Ludidi

Abstract:

Global climate change has resulted in altered rainfall patterns, which has resulted in annual losses in maize crop yields due to drought. Therefore it is important to produce maize cultivars that are more drought-tolerant, which is not an easily accomplished task as plants have a plethora of physical and biochemical adaptation methods. One such mechanism is the drought-induced expression of enzymatic and non-enzymatic proteins which assist plants to resist the effects of drought on their growth and development. One of these proteins is AtRD22 which has been identified in Arabidopsis thaliana. Using an in silico approach, a maize protein with 48% sequence homology to AtRD22 has been identified. This protein appears to be localized in the extracellular matrix, similarly to AtRD22. Promoter analysis of the encoding gene reveals cis-acting elements suggestive of induction of the gene’s expression by abscisic acid (ABA). Semi-quantitative transcriptomic analysis of the putative maize RD22 has revealed an increase in transcript levels after the exposure to drought. Current work elucidates the effect of up-regulation and silencing of the maize RD22 gene on the tolerance of maize to drought. The potential role of the maize RD22 gene in maize drought tolerance can be used as a tool to improve food security.

Keywords: abscisic acid, drought-responsive cis-acting elements, maize drought tolerance, RD22

Procedia PDF Downloads 464

Authors: Usama Massoud, Abeer A. Kenawy, El-Said A. Ragab, Abbas M. Abbas, Heba M. El-Kosery

Abstract:

Vertical Electrical Sounding (VES) and Transient Electro Magnetic (TEM) survey have been applied for characterizing the groundwater aquifers at El Sadat industrial area. El-Sadat city is one of the most important industrial cities in Egypt. It has been constructed more than three decades ago at about 80 km northwest of Cairo along the Cairo–Alexandria desert road. Groundwater is the main source of water supplies required for domestic, municipal, and industrial activities in this area due to the lack of surface water sources. So, it is important to maintain this vital resource in order to sustain the development plans of this city. In this study, VES and TEM data were identically measured at 24 stations along three profiles trending NE–SW with the elongation of the study area. The measuring points were arranged in a grid like pattern with both inter-station spacing and line–line distance of about 2 km. After performing the necessary processing steps, the VES and TEM data sets were inverted individually to multi-layer models, followed by a joint inversion of both data sets. Joint inversion process has succeeded to overcome the model-equivalence problem encountered in the inversion of individual data set. Then, the joint models were used for the construction of a number of cross sections and contour maps showing the lateral and vertical distribution of the geo-electrical parameters in the subsurface medium. Interpretation of the obtained results and correlation with the available geological and hydrogeological information revealed TWO aquifer systems in the area. The shallow Pleistocene aquifer consists of sand and gravel saturated with fresh water and exhibits large thickness exceeding 200 m. The deep Pliocene aquifer is composed of clay and sand and shows low resistivity values. The water bearing layer of the Pleistocene aquifer and the upper surface of Pliocene aquifer are continuous and no structural features have cut this continuity through the investigated area.

Keywords: El Sadat city, joint inversion, VES, TEM

Procedia PDF Downloads 370

Authors: Merieleen Engtipi

Abstract:

India's total share of global population is nearly 18%; however, its per capita energy consumption is only one-third of global average. The demand and supply of electricity are uneven in the country; around 240 million of the population have no access to electricity. However, with India's trajectory for modernisation and economic growth, the demand for energy is only expected to increase. India is at a crossroad, on the one hand facing the increasing demand for energy and on the other hand meeting the Paris climate policy commitments, and further the struggle to provide efficient energy. This paper analyses the policies to meet India’s need for energy, as the per capita energy consumption is likely to be double in 6-7 years period. Simultaneously, India's Paris commitment requires curbing of carbon emission from fossil fuels. There is an increasing need for renewables to be cheaply and efficiently available in the market and for clean technology to extract fossil fuels to meet climate policy goals. Fossil fuels are the most significant generator of energy in India; with the Paris agreement, the demand for clean energy technology is increasing. Finally, the U.S. decided to withdraw from the Paris Agreement; however, the two countries plan to continue engaging bilaterally on energy issues. The U.S. energy cooperation under Trump administration is significantly vital for greater energy security, transfer of technology and efficiency in energy supply and demand.

Keywords: energy demand, energy cooperation, fossil fuels, technology transfer

Procedia PDF Downloads 252

Authors: Preston Nabors, Nasseh Tabrizi

Abstract:

Portable Document Format (PDF) files have gained significant popularity for sharing and distributing documents due to their universal compatibility. However, the widespread use of PDF files has made them attractive targets for cybercriminals, who exploit vulnerabilities to deliver malware and compromise the security of end-user systems. This paper reviews notable contributions in PDF malware detection, including static, dynamic, signature-based, and hybrid analysis. It presents a comprehensive examination of PDF malware detection techniques, focusing on the emerging threat of adversarial sampling and the need for robust defense mechanisms. The paper highlights the vulnerability of machine learning classifiers to evasion attacks. It explores adversarial sampling techniques in PDF malware detection to produce mimicry and reverse mimicry evasion attacks, which aim to bypass detection systems. Improvements for future research are identified, including accessible methods, applying adversarial sampling techniques to malicious payloads, evaluating other models, evaluating the importance of features to malware, implementing adversarial defense techniques, and conducting comprehensive examination across various scenarios. By addressing these opportunities, researchers can enhance PDF malware detection and develop more resilient defense mechanisms against adversarial attacks.

Keywords: adversarial attacks, adversarial defense, adversarial machine learning, intrusion detection, PDF malware, malware detection, malware detection evasion

Procedia PDF Downloads 39

Authors: Francis Sichimba

Abstract:

Literature has increasingly acknowledged the important role that grandparents play in child care with evidence highlighting differences in grand-parental investment between countries and cultures. However, there are very few systematic cross cultural studies on grandparents’ participation in child care. Thus, we decided to conduct this study in Zambia and the Netherlands because the two countries differ rather drastically socially and culturally. The objective of this study was to investigate grand-parental involvement in child care in Zambia and the Netherlands. In line with the general objective, four hypotheses were formulated using nationality, family size, social economic status (SES), attachment security as independent variables. The study sample consisted of 411 undergraduate students from the University of Zambia and the University of Leiden. A questionnaire was used to measure grand-parental involvement in child care. Results indicated that grandparent involvement in child care was prevalent in both Zambia and Netherlands. However, as predicted it was found that Zambian grandparents (M = 9.69, SD=2.40) provided more care for their grandchildren compared to their Dutch counterparts (M = 7.80, SD=3.31) even after controlling for parents being alive. Using hierarchical logistic regression analysis the study revealed that nationality and attachment-related avoidance were significant predictors of grand-parental involvement in child care. It was concluded that grand-parental care is a great resource in offering complementary care in both countries.

Keywords: attachment, care, grand-parenting involvement, social economic status

Procedia PDF Downloads 721

Authors: Boris M. Fedorov, Liudmila P. Goncharenko, Sergey A. Sybachin, Natalia A. Mamedova, Ekaterina V. Makarenkova, Saule Rakhimova

Abstract:

In modern economic conditions, the question of the possibility of correct recognition of a signature on digital documents in order to verify the expression of will or confirm a certain operation is relevant. The additional complexity of processing lies in the dynamic variability of the signature for each individual, as well as in the way information is processed because the signature refers to biometric data. The article discusses the issues of using artificial intelligence models in order to improve the quality of signature confirmation in document recognition. The analysis of several possible options for using the model is carried out. The results of the study are given, in which it is possible to correctly determine the authenticity of the signature on small samples.

Keywords: signature recognition, biometric data, artificial intelligence, neural networks

Procedia PDF Downloads 148

Authors: Elif D. Oguz Erkal, David Krackhardt, Erica Cochran-Hameen

Abstract:

Even though social network analysis (SNA) is an abundantly studied concept for many organizations and industries, a clear SNA approach to the project teams has not yet been adopted by the construction industry. The main challenges for performing SNA in construction and the apparent reason for this gap is the unique and complex structure of each construction project, the comparatively high circulation of project team members/contributing parties and the variety of authentic problems for each project. Additionally, there are stakeholders from a variety of professional backgrounds collaborating in a high-stress environment fueled by time and cost constraints. Within this case study on Project RE, a design & build project performed at the Urban Design Build Studio of Carnegie Mellon University, social network analysis of the project design team will be performed with the main goal of applying social network theory to construction project environments. The research objective is to determine a correlation between the network of how individuals relate to each other on one’s perception of their own professional strengths and weaknesses and the communication patterns within the team and the group dynamics. Data is collected through a survey performed over four rounds conducted monthly, detailed follow-up interviews and constant observations to assess the natural alteration in the network with the effect of time. The data collected is processed by the means of network analytics and in the light of the qualitative data collected with observations and individual interviews. This paper presents the full ethnography of this construction design team of fourteen architecture students based on an elaborate social network data analysis over time. This study is expected to be used as an initial step to perform a refined, targeted and large-scale social network data collection in construction projects in order to deduce the impacts of social networks on project performance and suggest better collaboration structures for construction project teams henceforth.

Keywords: construction design teams, construction project management, social network analysis, team collaboration, network analytics

Procedia PDF Downloads 200

Authors: Baha-Aldeen S. Algmati, Ahmed R. Ballil

Abstract:

Multiphase flows occur widely in many engineering and industrial processes as well as in the environment we live in. In particular, bubbly flows are considered to be crucial phenomena in fluid flow applications and can be studied and analyzed experimentally, analytically, and computationally. In the present paper, the dynamic motion of an air bubble rising within a column of liquid is numerically simulated using an open-source CFD modeling tool 'OpenFOAM'. An interface tracking numerical algorithm called MULES algorithm, which is built-in OpenFOAM, is chosen to solve an appropriate mathematical model based on the volume of fluid (VOF) numerical method. The bubbles initially have a spherical shape and starting from rest in the stagnant column of liquid. The algorithm is initially verified against numerical results and is also validated against available experimental data. The comparison revealed that this algorithm provides results that are in a very good agreement with the 2D numerical data of other CFD codes. Also, the results of the bubble shape and terminal velocity obtained from the 3D numerical simulation showed a very good qualitative and quantitative agreement with the experimental data. The simulated rising bubbles yield a very small percentage of error in the bubble terminal velocity compared with the experimental data. The obtained results prove the capability of OpenFOAM as a powerful tool to predict the behavior of rising characteristics of the spherical bubbles in the stagnant column of liquid. This will pave the way for a deeper understanding of the phenomenon of the rise of bubbles in liquids.

Keywords: CFD simulations, multiphase flows, OpenFOAM, rise of bubble, volume of fluid method, VOF

Procedia PDF Downloads 123

Authors: Wondmyibza Tsegaye Bayou, Johannes C. Nonner, Joost Heijkers

Abstract:

This study aimed to identify and estimate dynamic groundwater seepage rates using four comparative methods; the Darcian approach, the water balance approach, the tracer method, and modeling. The theoretical background to these methods is put together in this study. The methodology was applied to a case study area at Zegveld following the advice of the Water Board Stichtse Rijnlanden. Data collection has been from various offices and a field campaign in the winter of 2008/09. In this complex confining layer of the study area, the location of the phreatic groundwater table is at a shallow depth compared to the piezometric water level. Data were available for the model years 1989 to 2000 and winter 2008/09. The higher groundwater table shows predominately-downward seepage in the study area. Results of the study indicated that net recharge to the groundwater table (precipitation excess) and the ditch system are the principal sources for seepage across the complex confining layer. Especially in the summer season, the contribution from the ditches is significant. Water is supplied from River Meije through a pumping system to meet the ditches' water demand. The groundwater seepage rate was distributed unevenly throughout the study area at the nature reserve averaging 0.60 mm/day for the model years 1989 to 2000 and 0.70 mm/day for winter 2008/09. Due to data restrictions, the seepage rates were mainly determined based on the Darcian method. Furthermore, the water balance approach and the tracer methods are applied to compute the flow exchange within the ditch system. The site had various validated groundwater levels and vertical flow resistance data sources. The phreatic groundwater level map compared with TNO-DINO groundwater level data values overestimated the groundwater level depth by 28 cm. The hydraulic resistance values obtained based on the 3D geological map compared with the TNO-DINO data agreed with the model values before calibration. On the other hand, the calibrated model significantly underestimated the downward seepage in the area compared with the field-based computations following the Darcian approach.

Keywords: groundwater seepage, phreatic water table, piezometric water level, nature reserve, Zegveld, The Netherlands

Procedia PDF Downloads 85

Authors: Eric Bang

Abstract:

Interactions between receptors and ligands are crucial for many essential biological processes, including neurotransmission and metabolism. Ligand-receptor analyses that examine cell behavior and interactions often utilize cell type-specific RNA expressions from single-cell RNA sequencing (scRNA-seq) data. Using CellPhoneDB, a public repository consisting of ligands, receptors, and ligand-receptor interactions, the cell-cell interactions were explored in a specific scRNA-seq dataset from kidney tissue and portrayed the results with dot plots and heat maps. Depending on the type of cell, each ligand-receptor pair was aligned with the interacting cell type and calculated the positori probabilities of these associations, with corresponding P values reflecting average expression values between the triads and their significance. Using single-cell data (sample kidney cell references), genes in the dataset were cross-referenced with ones in the existing CellPhoneDB dataset. For example, a gene such as Pleiotrophin (PTN) present in the single-cell data also needed to be present in the CellPhoneDB dataset. Using the single-cell transcriptomics data via slide-seq and reference data, the CellPhoneDB program defines cell types and plots them in different formats, with the two main ones being dot plots and heat map plots. The dot plot displays derived measures of the cell to cell interaction scores and p values. For the dot plot, each row shows a ligand-receptor pair, and each column shows the two interacting cell types. CellPhoneDB defines interactions and interaction levels from the gene expression level, so since the p-value is on a -log10 scale, the larger dots represent more significant interactions. By performing an interaction analysis, a significant interaction was discovered for myeloid and T-cell ligand-receptor pairs, including those between Secreted Phosphoprotein 1 (SPP1) and Fibronectin 1 (FN1), which is consistent with previous findings. It was proposed that an effective protocol would involve a filtration step where cell types would be filtered out, depending on which ligand-receptor pair is activated in that part of the tissue, as well as the incorporation of the CellPhoneDB data in a streamlined workflow pipeline. The filtration step would be in the form of a Python script that expedites the manual process necessary for dataset filtration. Being in Python allows it to be integrated with the CellPhoneDB dataset for future workflow analysis. The manual process involves filtering cell types based on what ligand/receptor pair is activated in kidney cells. One limitation of this would be the fact that some pairings are activated in multiple cells at a time, so the manual manipulation of the data is reflected prior to analysis. Using the filtration script, accurate sorting is incorporated into the CellPhoneDB database rather than waiting until the output is produced and then subsequently applying spatial data. It was envisioned that this would reveal wherein the cell various ligands and receptors are interacting with different cell types, allowing for easier identification of which cells are being impacted and why, for the purpose of disease treatment. The hope is this new computational method utilizing spatially explicit ligand-receptor association data can be used to uncover previously unknown specific interactions within kidney tissue.

Keywords: bioinformatics, Ligands, kidney tissue, receptors, spatial transcriptome

Procedia PDF Downloads 139

Authors: Néstor Iván Rojas, Wilson Medina Sierra

Abstract:

Managing spatial information is described through a Geographic Information System (GIS), for some neighborhoods in the city of Tunja, in relation to the structural typology of the buildings. The use of GIS provides tools that facilitate the capture, processing, analysis and dissemination of cartographic information, product quality evaluation of the classification of buildings. Allows the development of a method that unifies and standardizes processes information. The project aims to generate a geographic database that is useful to the entities responsible for planning and disaster prevention and care for vulnerable populations, also seeks to be a basis for seismic vulnerability studies that can contribute in a study of urban seismic microzonation. The methodology consists in capturing the plat including road naming, neighborhoods, blocks and buildings, to which were added as attributes, the product of the evaluation of each of the housing data such as the number of inhabitants and classification, year of construction, the predominant structural systems, the type of mezzanine board and state of favorability, the presence of geo-technical problems, the type of cover, the use of each building, damage to structural and non-structural elements . The above data are tabulated in a spreadsheet that includes cadastral number, through which are systematically included in the respective building that also has that attribute. Geo-referenced data base is obtained, from which graphical outputs are generated, producing thematic maps for each evaluated data, which clearly show the spatial distribution of the information obtained. Using GIS offers important advantages for spatial information management and facilitates consultation and update. Usefulness of the project is recognized as a basis for studies on issues of planning and prevention.

Keywords: microzonation, buildings, geo-processing, cadastral number

Procedia PDF Downloads 334

Authors: Annika Stechemesser, Rachel Pounds, Emma Lucas, Chris Dawson, Julia Lipecki, Pavle Vrljicak, Jan Brosens, Sean Kehoe, Jason Yap, Lawrence Young, Sascha Ott

Abstract:

Advances in technology make it now possible to retrieve the genetic information of thousands of single cancerous cells. One of the key challenges in single cell analysis of cancerous tissue is to determine the number of different cell types and their characteristic genes within the sample to better understand the tumors and their reaction to different treatments. For this analysis to be possible, it is crucial to filter out background noise as it can severely blur the downstream analysis and give misleading results. In-depth analysis of the state-of-the-art filtering methods for single cell data showed that they do, in some cases, not separate noisy and normal cells sufficiently. We introduced an algorithm that filters and clusters single cell data simultaneously without relying on certain genes or thresholds chosen by eye. It detects communities in a Shared Nearest Neighbor similarity network, which captures the similarities and dissimilarities of the cells by optimizing the modularity and then identifies and removes vertices with a weak clustering belonging. This strategy is based on the fact that noisy data instances are very likely to be similar to true cell types but do not match any of these wells. Once the clustering is complete, we apply a set of evaluation metrics on the cluster level and accept or reject clusters based on the outcome. The performance of our algorithm was tested on three datasets and led to convincing results. We were able to replicate the results on a Peripheral Blood Mononuclear Cells dataset. Furthermore, we applied the algorithm to two samples of ovarian cancer from the same patient before and after chemotherapy. Comparing the standard approach to our algorithm, we found a hidden cell type in the ovarian postchemotherapy data with interesting marker genes that are potentially relevant for medical research.

Keywords: cancer research, graph theory, machine learning, single cell analysis

Procedia PDF Downloads 113

Authors: Chaudhary Muhammad Aqdus Ilyas, Matthias Rehm, Kamal Nasrollahi, Thomas B. Moeslund

Abstract:

This paper presents the investigation of data collection procedures, associated with robots when placed with traumatic brain injured (TBI) patients for rehabilitation purposes through facial expression and mood analysis. Rehabilitation after TBI is very crucial due to nature of injury and variation in recovery time. It is advantageous to analyze these emotional signals in a contactless manner, due to the non-supportive behavior of patients, limited muscle movements and increase in negative emotional expressions. This work aims at the development of framework where robots can recognize TBI emotions through facial expressions to perform rehabilitation tasks by physical, cognitive or interactive activities. The result of these studies shows that with customized data collection strategies, proposed framework identify facial and emotional expressions more accurately that can be utilized in enhancing recovery treatment and social interaction in robotic context.

Keywords: computer vision, convolution neural network- long short term memory network (CNN-LSTM), facial expression and mood recognition, multimodal (RGB-thermal) analysis, rehabilitation, robots, traumatic brain injured patients

Procedia PDF Downloads 155

Authors: M. T. Alodat

Abstract:

In this paper, we propose a generalization to the Gaussian process regression(GPR) model called the extended skew Gaussian process for regression(ESGPr) model. The ESGPR model works better than the GPR model when the errors are skewed. We derive the predictive distribution for the ESGPR model at a new input. Also we apply the ESGPR model to FOREX data and we find that it fits the Forex data better than the GPR model.

Keywords: extended skew normal distribution, Gaussian process for regression, predictive distribution, ESGPr model

Procedia PDF Downloads 554

Authors: Yao-Hong Tsai

Abstract:

Due to the sensor technology, video surveillance has become the main way for security control in every big city in the world. Surveillance is usually used by governments for intelligence gathering, the prevention of crime, the protection of a process, person, group or object, or the investigation of crime. Many surveillance systems based on computer vision technology have been developed in recent years. Moving target tracking is the most common task for Unmanned Aerial Vehicle (UAV) to find and track objects of interest in mobile aerial surveillance for civilian applications. The paper is focused on vision-based collision avoidance for UAVs by recurrent neural networks. First, images from cameras on UAV were fused based on deep convolutional neural network. Then, a recurrent neural network was constructed to obtain high-level image features for object tracking and extracting low-level image features for noise reducing. The system distributed the calculation of the whole system to local and cloud platform to efficiently perform object detection, tracking and collision avoidance based on multiple UAVs. The experiments on several challenging datasets showed that the proposed algorithm outperforms the state-of-the-art methods.

Keywords: unmanned aerial vehicle, object tracking, deep learning, collision avoidance

Procedia PDF Downloads 160

Authors: Aliya Grig, Konstantin Sokolov, Igor Shatalin

Abstract:

The report describes the methodology for collecting data and building an ML model for determining the personality psychotype using profiling and personality traits methods based on several short messages of a user communicating on an arbitrary topic with a chitchat bot. In the course of the experiments, the minimum amount of text was revealed to confidently determine aspects of personality. Model accuracy - 85%. Users' language of communication is English. AI for a personalized communication with a user based on his mood, personality, and current emotional state. Features investigated during the research: personalized communication; providing empathy; adaptation to a user; predictive analytics. In the report, we describe the processes that captures both structured and unstructured data pertaining to a user in large quantities and diverse forms. This data is then effectively processed through ML tools to construct a knowledge graph and draw inferences regarding users of text messages in a comprehensive manner. Specifically, the system analyzes users' behavioral patterns and predicts future scenarios based on this analysis. As a result of the experiments, we provide for further research on training AI models to be empathetic, creating personalized communication for a user

Keywords: AI, empathetic, chatbot, AI models

Procedia PDF Downloads 93

Authors: Majeda Hammoud

Abstract:

Background: Anemia during pregnancy increases the risk of delivery by cesarean section, low birth weight, preterm birth, perinatal mortality, stillbirth, and maternal mortality. In this study, we aimed to assess the prevalence of anemia in pregnant women and its associated factors in the Kuwait birth cohort study. Methods: The Kuwait birth cohort (N=1108) was a prospective cohort study in which pregnant women were recruited in the third trimester. Data were collected through personal interviews with mothers who attend antenatal care visits, including data on socio-economic status and lifestyle factors. Blood samples were taken after the recruitment to measure multiple laboratory indicators. Clinical data were extracted from the medical records by a clinician including data on comorbidities. Anemia was defined as having Hemoglobin (Hb) <110 g/L with further classification as mild (100-109 g/L), moderate (70-99 g/L), or severe (<70 g/L). Predictors of anemia were classified as underlying or direct factors, and logistic regression was used to investigate their association with anemia. Results: The mean Hb level in the study group was 115.21 g/L (95%CI: 114.56- 115.87 g/L), with significant differences between age groups (p=0.034). The prevalence of anemia was 28.16% (95%CI: 25.53-30.91%), with no significant difference by age group (p=0.164). Of all 1108 pregnant women, 8.75% had moderate anemia, and 19.40% had mild anemia, but no pregnant women had severe anemia. In multivariable analysis, getting pregnant while using contraception, adjusted odds ratio (AOR) 1.73(95%CI:1.01-2.96); p=0.046 and current use of supplements, AOR 0.50 (95%CI: 0.26-0.95); p=0.035 were significantly associated with anemia (underlying factors). From the direct factors group, only iron and ferritin levels were significantly associated with anemia (P<0.001). Conclusion: Although the severe form of anemia is low among pregnant women in Kuwait, mild and moderate anemia remains a significant health problem despite free access to antenatal care.

Keywords: anemia, pregnancy, hemoglobin, ferritin

Procedia PDF Downloads 50

Authors: Xiangtuo Chen, Paul-Henry Cournéde

Abstract:

Crop yield prediction is a paramount issue in agriculture. The main idea of this paper is to find out efficient way to predict the yield of corn based meteorological records. The prediction models used in this paper can be classified into model-driven approaches and data-driven approaches, according to the different modeling methodologies. The model-driven approaches are based on crop mechanistic modeling. They describe crop growth in interaction with their environment as dynamical systems. But the calibration process of the dynamic system comes up with much difficulty, because it turns out to be a multidimensional non-convex optimization problem. An original contribution of this paper is to propose a statistical methodology, Multi-Scenarios Parameters Estimation (MSPE), for the parametrization of potentially complex mechanistic models from a new type of datasets (climatic data, final yield in many situations). It is tested with CORNFLO, a crop model for maize growth. On the other hand, the data-driven approach for yield prediction is free of the complex biophysical process. But it has some strict requirements about the dataset. A second contribution of the paper is the comparison of these model-driven methods with classical data-driven methods. For this purpose, we consider two classes of regression methods, methods derived from linear regression (Ridge and Lasso Regression, Principal Components Regression or Partial Least Squares Regression) and machine learning methods (Random Forest, k-Nearest Neighbor, Artificial Neural Network and SVM regression). The dataset consists of 720 records of corn yield at county scale provided by the United States Department of Agriculture (USDA) and the associated climatic data. A 5-folds cross-validation process and two accuracy metrics: root mean square error of prediction(RMSEP), mean absolute error of prediction(MAEP) were used to evaluate the crop prediction capacity. The results show that among the data-driven approaches, Random Forest is the most robust and generally achieves the best prediction error (MAEP 4.27%). It also outperforms our model-driven approach (MAEP 6.11%). However, the method to calibrate the mechanistic model from dataset easy to access offers several side-perspectives. The mechanistic model can potentially help to underline the stresses suffered by the crop or to identify the biological parameters of interest for breeding purposes. For this reason, an interesting perspective is to combine these two types of approaches.

Keywords: crop yield prediction, crop model, sensitivity analysis, paramater estimation, particle swarm optimization, random forest

Procedia PDF Downloads 231

Authors: Asikhia Olubusayo Aduke

Abstract:

Students’ inability to set data-based (specific, measurable, attainable, reliable, and time-bound) personal improvement goals threatens their academic success. Hence, the study aimed to investigate year-one students’ academic goal-setting practices at Lagos State University of Education, Nigeria. Descriptive survey research was used in carrying out this study. The study population consisted of 3,101 year-one students of the University. A sample size of five hundred (501) participants was selected through a proportional and simple random sampling technique. The Formative Goal Setting Questionnaire (FGSQ) developed by Research Collaboration (2015) was adapted and used as an instrument for the study. Two main research questions were answered, while two null hypotheses were formulated and tested for the study. The study revealed higher data-based goals for all students than personal improvement goals. Nevertheless, data-based and personal improvement goal-setting for female students was higher than for male students. One sample test statistic and Anova used to analyse data for the two hypotheses also revealed that the mean difference between male and female year one students’ data-based and personal improvement goal-setting formation was statistically significant (p < 0.05). This means year one students’ data-based and personal improvement goals showed significant gender differences. Based on the findings of this study, it was recommended, among others, that therapeutic techniques that can help to change students’ faulty thinking and challenge their lack of desire for personal improvement should be sought to treat students who have problems with setting high personal improvement goals. Counsellors also need to advocate continued research into how to increase the goal-setting ability of male students and should focus more on counselling male students’ goal-setting ability. The main contributions of the study are higher institutions must prioritize early intervention in first-year students' academic goal setting. Researching gender differences in this practice reveals a crucial insight: male students often lag behind in setting meaningful goals, impacting their motivation and performance. Focusing on this demographic with data-driven personal improvement goals can be transformative. By promoting goal setting that is specific, measurable, and focused on self-growth (rather than competition), male students can unlock their full potential. Researchers and counselors play a vital role in detecting and supporting students with lower goal-setting tendencies. By prioritizing this intervention, we can empower all students to set ambitious, personalized goals that ignite their passion for learning and pave the way for academic success.

Keywords: academic goal setting, counselling, practice, university, year one students

Procedia PDF Downloads 62

Authors: Chieh-Chun Chang, Cheng-Ting Shih, Yan-Lin Liu, Shu-Jun Chang, Jay Wu

Abstract:

With the widespread use of digital mammography (DM), radiation dose evaluation of breasts has become important. X-ray spectra are one of the key factors that influence the absorbed dose of glandular tissue. In this study, we estimated the X-ray spectrum of DM using the expectation maximization (EM) algorithm with the transmission measurement data. The interpolating polynomial model proposed by Boone was applied to generate the initial guess of the DM spectrum with the target/filter combination of Mo/Mo and the tube voltage of 26 kVp. The Monte Carlo N-particle code (MCNP5) was used to tally the transmission data through aluminum sheets of 0.2 to 3 mm. The X-ray spectrum was reconstructed by using the EM algorithm iteratively. The influence of the initial guess for EM reconstruction was evaluated. The percentage error of the average energy between the reference spectrum inputted for Monte Carlo simulation and the spectrum estimated by the EM algorithm was -0.14%. The normalized root mean square error (NRMSE) and the normalized root max square error (NRMaSE) between both spectra were 0.6% and 2.3%, respectively. We conclude that the EM algorithm with transmission measurement data is a convenient and useful tool for estimating x-ray spectra for DM in clinical practice.

Keywords: digital mammography, expectation maximization algorithm, X-Ray spectrum, X-Ray

Procedia PDF Downloads 730

Authors: Sarah Beaver, Renee Bryce

Abstract:

Audiograms detect hearing impairment, but missing values pose problems. This work explores imputations in an attempt to improve accuracy. This work implements Linear Regression, Lasso, Linear Support Vector Regression, Bayesian Ridge, K Nearest Neighbors (KNN), and Random Forest machine learning techniques to impute audiogram frequencies ranging from 125Hz to 8000Hz. The data contains patients who had or were candidates for cochlear implants. Accuracy is compared across two different Nested Cross-Validation k values. Over 4000 audiograms were used from 800 unique patients. Additionally, training on data combines and compares left and right ear audiograms versus single ear side audiograms. The accuracy achieved using Root Mean Square Error (RMSE) values for the best models for Random Forest ranges from 4.74 to 6.37. The R\textsuperscript{2} values for the best models for Random Forest ranges from .91 to .96. The accuracy achieved using RMSE values for the best models for KNN ranges from 5.00 to 7.72. The R\textsuperscript{2} values for the best models for KNN ranges from .89 to .95. The best imputation models received R\textsuperscript{2} between .89 to .96 and RMSE values less than 8dB. We also show that the accuracy of classification predictive models performed better with our best imputation models versus constant imputations by a two percent increase.

Keywords: machine learning, audiograms, data imputations, single imputations

Procedia PDF Downloads 82

Authors: Kohkan Shamsi

Abstract:

Background: MRI and PET are now extensively utilized in Alzheimer's disease (AD) trials for patient eligibility, efficacy assessment, and safety evaluations but including imaging in AD trials impacts site selection process, patient recruitment, and patient retention. Methods: PET/MRI are performed at baseline and at multiple follow-up timepoints. This requires prospective site imaging qualification, evaluation of phantom data, training and continuous monitoring of machines for acquisition of standardized and consistent data. This also requires prospective patient/caregiver training as patients must go to multiple facilities for imaging examinations. We will share our experience form one of the largest AD programs. Lesson learned: Many neurological diseases have a similar presentation as AD or could confound the assessment of drug therapy. The inclusion of wrong patients has ethical and legal issues, and data could be excluded from the analysis. Centralized eligibility evaluation read process will be discussed. Amyloid related imaging abnormalities (ARIA) were observed in amyloid-β trials. FDA recommended regular monitoring of ARIA. Our experience in ARIA evaluations in large phase III study at > 350 sites will be presented. Efficacy evaluation: MRI is utilized to evaluate various volumes of the brain. FDG PET or amyloid PET agents has been used in AD trials. We will share our experience about site and central independent reads. Imaging logistic issues that need to be handled in the planning phase will also be discussed as it can impact patient compliance thereby increasing missing data and affecting study results. Conclusion: imaging must be prospectively planned to include standardizing imaging methodologies, site selection process and selecting assessment criteria. Training should be transparently conducted and documented. Prospective patient/caregiver awareness of imaging requirement is essential for patient compliance and reduction in missing imaging data.

Keywords: Alzheimer's disease, ARIA, MRI, PET, patient recruitment, retention

Procedia PDF Downloads 115

Authors: Ayse Ozturk Samur, Gozde Inal Kiziltepe

Abstract:

No matter what level of education it is, starting a school is an exciting process as it includes new experiences. In this process, child steps into a different environment and institution except from the family institution which he was born into and feels secure. That new environment is different from home; it is a social environment which has its own rules, and involves duties and responsibilities that should be fulfilled and new vital experiences. The children who have a positive attitude towards school and like school are more enthusiastic and eager to participate in classroom activities. Moreover, a close relationship with the teacher enables the child to have positive emotions and ideas about the teacher and school and helps children adapt to school easily. In this study, it is aimed to identify children’s perceptions of academic competence, attitudes towards school and ideas about their teachers. In accordance with the aim a mixed method that includes both qualitative and quantitative data collection methods are used. The study is supported with qualitative data after collecting quantitative data. The study group of the research consists of randomly chosen 250 children who are 60-72 month old and attending a preschool institution in a city center located West Anatolian region of Turkey. Quantitative data was collected using Feelings about School scale. The scale consists of 12 items and 4 dimensions; school, teacher, mathematic, and literacy. Reliability and validity study for the scale used in the study was conducted by the researchers with 318 children who were 60-72 months old. For content validity experts’ ideas were asked, for construct validity confirmatory factor analysis was utilized. Reliability of the scale was examined by calculating internal consistency coefficient (Cronbach alpha). At the end of the analyses it was found that FAS is a valid and reliable instrument to identify 60-72 month old children’ perception of their academic competency, attitude toward school and ideas about their teachers. For the qualitative dimension of the study, semi-structured interviews were done with 30 children aged 60-72 month. At the end of the study, it was identified that children’s’ perceptions of their academic competencies and attitudes towards school was medium-level and their ideas about their teachers were high. Based on the semi structured interviews done with children, it is identified that they have a positive perception of school and teacher. That means quantitatively gathered data is supported by qualitatively collected data.

Keywords: feelings, preschool education, school, teacher, thoughts

Procedia PDF Downloads 225

Authors: Veena Chaudhary, Rakesh P. Gakkhar

Abstract:

In this study, energy and exergy analysis are applied to the experimental data of an internal combustion engine operating on conventional diesel cycle. The experimental data are collected using an engine unit which enables accurate measurements of fuel flow rate, combustion air flow rate, engine load, engine speed and all relevant temperatures. First and second law efficiencies are calculated for different engine speed and compared. Results indicate that the first law (energy) efficiency is maximum at 1700 rpm whereas exergy efficiency is maximum and exergy destruction is minimum at 1900 rpm.

Keywords: diesel engine, exergy destruction, exergy efficiency, second law of thermodynamics

Procedia PDF Downloads 330

Authors: Asmamaw Yehun, Tsegaye Kassa, Addisu Hunegnaw, Martin Vermeer

Abstract:

There are various models to estimate the neutral atmospheric parameter values, such as in-suite and reanalysis datasets from numerical models. Accurate estimated values of the atmospheric parameters are useful for weather forecasting and, climate modeling and monitoring of climate change. Recently, Global Navigation Satellite System (GNSS) measurements have been applied for atmospheric sounding due to its robust data quality and wide horizontal and vertical coverage. The Global Positioning System (GPS) solutions that includes tropospheric parameters constitute a reliable set of data to be assimilated into climate models. The objective of this paper is, to estimate the neutral atmospheric parameters such as Wet Zenith Delay (WZD), Precipitable Water Vapour (PWV) and Total Zenith Delay (TZD) using six selected GPS stations in the equatorial regions, more precisely, the Ethiopian GPS stations from 2012 to 2015 observational data. Based on historic estimated GPS-derived values of PWV, we forecasted the PWV from 2015 to 2030. During data processing and analysis, we applied GAMIT-GLOBK software packages to estimate the atmospheric parameters. In the result, we found that the annual averaged minimum values of PWV are 9.72 mm for IISC and maximum 50.37 mm for BJCO stations. The annual averaged minimum values of WZD are 6 cm for IISC and maximum 31 cm for BDMT stations. In the long series of observations (from 2012 to 2015), we also found that there is a trend and cyclic patterns of WZD, PWV and TZD for all stations.

Keywords: atmosphere, GNSS, neutral atmosphere, precipitable water vapour

Procedia PDF Downloads 61

Authors: Larry Lai, Evans Leung

Abstract:

Falun gong is a self-proclaimed religious group that has been under crackdown by Beijing for more than two decades. Diaosi, on the other hand, is an emerging community with members loosely connected on the internet through different online social platforms, centering around the sharing of different hobbies and interests. Diaosi community has been transformed from a potential threat to the Chinese authority for different causes to a pro-government force. This paper seeks to explain the different strategies adopted by the People's Republic of China (PRC) regime in handling these two potential threatening communities. Both communities share some obvious similarities: (1) both have massive nation-wide participation; (2) both have attempted to challenge the PRC's authority through contentious means; (3) both have high level of mobility, online or offline; and (4) both have at first been unnoticed until the threat against the PRC have taken form. But the strategies the PRC endorsed against the communities were, in many ways, different. The question is: if the strategy against Falun Gong has been an effective one, why used other strategies against Diaosi? The authors argue that the main reason for using different strategies lies in the differences between the two communities in terms of (i) the nature of the groups, and (ii) the group dynamics. Lastly, based on this analysis, the authors attempt to explore the possible strategies that the PRC would adopt against the Hong Kong cyber-world political community in light of the latest national security law in Hong Kong.

Keywords: contentious politics, Diaosi, Falun Gong, Hong Kong, People's Republic of China

Procedia PDF Downloads 145

Authors: Budoor Al Abid

Abstract:

Educational systems are increasingly provided as open online services, providing guidance and support for individual learners. To adapt the learning systems, a proper evaluation must be made. This paper builds the evaluation model Fuzzy C Means Adaptive System (FCMAS) based on data mining techniques to assess the difficulty of the questions. The following steps are implemented; first using a dataset from an online international learning system called (slepemapy.cz) the dataset contains over 1300000 records with 9 features for students, questions and answers information with feedback evaluation. Next, a normalization process as preprocessing step was applied. Then FCM clustering algorithms are used to adaptive the difficulty of the questions. The result is three cluster labeled data depending on the higher Wight (easy, Intermediate, difficult). The FCM algorithm gives a label to all the questions one by one. Then Random Forest (RF) Classifier model is constructed on the clustered dataset uses 70% of the dataset for training and 30% for testing; the result of the model is a 99.9% accuracy rate. This approach improves the Adaptive E-learning system because it depends on the student behavior and gives accurate results in the evaluation process more than the evaluation system that depends on feedback only.

Keywords: machine learning, adaptive, fuzzy logic, data mining

Procedia PDF Downloads 196