Search results for: classifier algorithms

Authors: Danica Maljkovic, Igor Balen, Bojana Dalbelo Basic

Abstract:

Following the regulation of EU Directive on Energy Efficiency, specifically Article 9, individual metering in district heating systems has to be introduced by the end of 2016. These directions have been implemented in member state’s legal framework, Croatia is one of these states. The directive allows installation of both heat metering devices and heat cost allocators. Mainly due to bad communication and PR, the general public false image was created that the heat cost allocators are devices that save energy. Although this notion is wrong, the aim of this work is to develop a model that would precisely express the influence of installation heat cost allocators on potential energy savings in each unit within multifamily buildings. At the same time, in recent years, a science of machine learning has gain larger application in various fields, as it is proven to give good results in cases where large amounts of data are to be processed with an aim to recognize a pattern and correlation of each of the relevant parameter as well as in the cases where the problem is too complex for a human intelligence to solve. A special method of machine learning, decision tree method, has proven an accuracy of over 92% in prediction general building consumption. In this paper, a machine learning algorithms will be used to isolate the sole impact of installation of heat cost allocators on a single building in multifamily houses connected to district heating systems. Special emphasises will be given regression analysis, logistic regression, support vector machines, decision trees and random forest method.

Keywords: district heating, heat cost allocator, energy efficiency, machine learning, decision tree model, regression analysis, logistic regression, support vector machines, decision trees and random forest method

Procedia PDF Downloads 249

Authors: Kyle Yatich Terik, Collins Oduor

Abstract:

The current healthcare system has made healthcare more accessible and efficient by the use of information technology through the implementation of computer algorithms that generate menus based on the diagnosis. While many systems just like these have been created over the years, their main objective is to help healthy individuals calculate their calorie intake and assist them by providing food selections based on a pre-specified calorie. That application has been proven to be useful in some ways, and they are not suitable for monitoring, planning, and managing hospital patients, especially that critical condition their dietary needs. The system also addresses a number of objectives, such as; the main objective is to be able to design, develop and implement an efficient, user-friendly as well as and interactive dietary management system. The specific design development objectives include developing a system that will facilitate a monitoring feature for users using graphs, developing a system that will provide system-generated reports to the users, dietitians, and system admins, design a system that allows users to measure their BMI (Body Mass Index), the system will also provide food template feature that will guide the user on a balanced diet plan. In order to develop the system, further research was carried out in Kenya, Nairobi County, using online questionnaires being the preferred research design approach. From the 44 respondents, one could create discussions such as the major challenges encountered from the manual dietary system, which include no easily accessible information of the calorie intake for food products, expensive to physically visit a dietitian to create a tailored diet plan. Conclusively, the system has the potential of improving the quality of life of people as a whole by providing a standard for healthy living and allowing individuals to have readily available knowledge through food templates that will guide people and allow users to create their own diet plans that consist of a balanced diet.

Keywords: DMS, dietitian, patient, administrator

Procedia PDF Downloads 161

Authors: Fuyuan Ma, Yuhan Wang, Junhe Zhang, Ying Wang

Abstract:

Identifying the sources of information dissemination is a pivotal task in the study of collective behaviors in networks, enabling us to discern and intercept the critical pathways through which information propagates from its origins. This allows for the control of the information’s dissemination impact in its early stages. Numerous methods for source detection rely on pre-existing, underlying propagation models as prior knowledge. Current models that eschew prior knowledge attempt to harness label propagation algorithms to model the statistical characteristics of propagation states or employ Graph Neural Networks (GNNs) for deep reverse modeling of the diffusion process. These approaches are either deficient in modeling the propagation patterns of information or are constrained by the over-smoothing problem inherent in GNNs, which limits the stacking of sufficient model depth to excavate global propagation patterns. Consequently, we introduce the ODESI model. Initially, the model employs a label propagation algorithm to delineate the distribution density of infected states within a graph structure and extends the representation of infected states from integers to state vectors, which serve as the initial states of nodes. Subsequently, the model constructs a deep architecture based on GNNs-coupled Ordinary Differential Equations (ODEs) to model the global propagation patterns of continuous propagation processes. Addressing the challenges associated with solving ODEs on graphs, we approximate the analytical solutions to reduce computational costs. Finally, we conduct simulation experiments on two real-world social network datasets, and the results affirm the efficacy of our proposed ODESI model in source identification tasks.

Keywords: source identification, ordinary differential equations, label propagation, complex networks

Procedia PDF Downloads 20

Authors: Joseph Lillington, Tom Gout, Mike Harrison, Ian Farnan

Abstract:

The vitrification of high-level nuclear waste within borosilicate glass and its incorporation within a multi-barrier repository deep underground is widely accepted as the preferred disposal method. However, for this to happen, any safety case will require validation that the initially localized radionuclides will not be considerably released into the near/far-field. Therefore, accurate mechanistic models are necessary to predict glass dissolution, and these should be robust to a variety of incorporated waste species and leaching test conditions, particularly given substantial variations across international waste-streams. Here, machine learning is used to predict glass material properties (viscosity, density) and glass leaching model parameters from large-scale industrial data. A variety of different machine learning algorithms have been compared to assess performance. Density was predicted solely from composition, whereas viscosity additionally considered temperature. To predict suitable glass leaching model parameters, a large simulated dataset was created by coupling MATLAB and the chemical reactive-transport code HYTEC, considering the state-of-the-art GRAAL model (glass reactivity in allowance of the alteration layer). The trained models were then subsequently applied to the large-scale industrial, experimental data to identify potentially appropriate model parameters. Results indicate that ensemble methods can accurately predict viscosity as a function of temperature and composition across all three industrial datasets. Glass density prediction shows reliable learning performance with predictions primarily being within the experimental uncertainty of the test data. Furthermore, machine learning can predict glass dissolution model parameters behavior, demonstrating potential value in GRAAL model development and in assessing suitable model parameters for large-scale industrial glass dissolution data.

Keywords: machine learning, predictive modelling, pattern recognition, radioactive waste glass

Procedia PDF Downloads 116

Authors: Mohammad Hossain Mohammadi, Saif Al Ameri, Sana Ziaei, Jinane Mounsef

Abstract:

Automated enumeration of the number of hand fingers is widely used in several motion gaming and distance control applications, and is discussed in several published papers as a starting block for hand recognition systems. The automated finger enumeration technique should not only be accurate, but also must have a fast response for a moving-picture input. The high performance of video in motion games or distance control will inhibit the program’s overall speed, for image processing software such as Matlab need to produce results at high computation speeds. Since an automated finger enumeration with minimum error and processing time is desired, a comparative study between two finger enumeration techniques is presented and analyzed in this paper. In the pre-processing stage, various image processing functions were applied on a real-time video input to obtain the final cleaned auto-cropped image of the hand to be used for the two techniques. The first technique uses the known morphological tool of skeletonization to count the number of skeleton’s endpoints for fingers. The second technique uses a radial distance method to enumerate the number of fingers in order to obtain a one dimensional hand representation. For both discussed methods, the different steps of the algorithms are explained. Then, a comparative study analyzes the accuracy and speed of both techniques. Through experimental testing in different background conditions, it was observed that the radial distance method was more accurate and responsive to a real-time video input compared to the skeletonization method. All test results were generated in Matlab and were based on displaying a human hand for three different orientations on top of a plain color background. Finally, the limitations surrounding the enumeration techniques are presented.

Keywords: comparative study, hand recognition, fingertip detection, skeletonization, radial distance, Matlab

Procedia PDF Downloads 382

Authors: El Harraj Abdeslam, Raissouni Naoufal

Abstract:

The detection of moving objects from a video image sequences is very important for object tracking, activity recognition, and behavior understanding in video surveillance. The most used approach for moving objects detection / tracking is background subtraction algorithms. Many approaches have been suggested for background subtraction. But, these are illumination change sensitive and the solutions proposed to bypass this problem are time consuming. In this paper, we propose a robust yet computationally efficient background subtraction approach and, mainly, focus on the ability to detect moving objects on dynamic scenes, for possible applications in complex and restricted access areas monitoring, where moving and motionless persons must be reliably detected. It consists of three main phases, establishing illumination changes in variance, background/foreground modeling and morphological analysis for noise removing. We handle illumination changes using Contrast Limited Histogram Equalization (CLAHE), which limits the intensity of each pixel to user determined maximum. Thus, it mitigates the degradation due to scene illumination changes and improves the visibility of the video signal. Initially, the background and foreground images are extracted from the video sequence. Then, the background and foreground images are separately enhanced by applying CLAHE. In order to form multi-modal backgrounds we model each channel of a pixel as a mixture of K Gaussians (K=5) using Gaussian Mixture Model (GMM). Finally, we post process the resulting binary foreground mask using morphological erosion and dilation transformations to remove possible noise. For experimental test, we used a standard dataset to challenge the efficiency and accuracy of the proposed method on a diverse set of dynamic scenes.

Keywords: video surveillance, background subtraction, contrast limited histogram equalization, illumination invariance, object tracking, object detection, behavior understanding, dynamic scenes

Procedia PDF Downloads 256

Authors: Mahmoud Huleihel, George Abu-Aqil, Manal Suleiman, Klaris Riesenberg, Itshak Lapidot, Ahmad Salman

Abstract:

Urinary tract infections (UTIs) are considered to be the most common bacterial infections worldwide, which are caused mainly by Escherichia (E.) coli (about 80%). Klebsiella pneumoniae (about 10%) and Pseudomonas aeruginosa (about 6%). Although antibiotics are considered as the most effective treatment for bacterial infectious diseases, unfortunately, most of the bacteria already have developed resistance to the majority of the commonly available antibiotics. Therefore, it is crucial to identify the infecting bacteria and to determine its susceptibility to antibiotics for prescribing effective treatment. Classical methods are time consuming, require ~48 hours for determining bacterial susceptibility. Thus, it is highly urgent to develop a new method that can significantly reduce the time required for determining both infecting bacterium at the species level and diagnose its susceptibility to antibiotics. Fourier-Transform Infrared (FTIR) spectroscopy is well known as a sensitive and rapid method, which can detect minor molecular changes in bacterial genome associated with the development of resistance to antibiotics. The main goal of this study is to examine the potential of FTIR spectroscopy, in tandem with machine learning algorithms, to identify the infected bacteria at the species level and to determine E. coli susceptibility to different antibiotics directly from patients' urine in about 30minutes. For this goal, 1600 different E. coli isolates were isolated for different patients' urine sample, measured by FTIR, and analyzed using different machine learning algorithm like Random Forest, XGBoost, and CNN. We achieved 98% success in isolate level identification and 89% accuracy in susceptibility determination.

Keywords: urinary tract infections (UTIs), E. coli, Klebsiella pneumonia, Pseudomonas aeruginosa, bacterial, susceptibility to antibiotics, infrared microscopy, machine learning

Procedia PDF Downloads 170

Authors: Fathi Kallel, Abdulelah Alabd Uljabbar, Abdulrahman Aldukhail, Abdulaziz Alomran

Abstract:

The brain is an important organ in our body since it is responsible about the majority actions such as vision, memory, etc. However, different diseases such as Alzheimer and tumors could affect the brain and conduct to a partial or full disorder. Regular diagnosis are necessary as a preventive measure and could help doctors to early detect a possible trouble and therefore taking the appropriate treatment, especially in the case of brain tumors. Different imaging modalities are proposed for diagnosis of brain tumor. The powerful and most used modality is the Magnetic Resonance Imaging (MRI). MRI images are analyzed by doctor in order to locate eventual tumor in the brain and describe the appropriate and needed treatment. Diverse image processing methods are also proposed for helping doctors in identifying and analyzing the tumor. In fact, a large Computer Aided Diagnostic (CAD) tools including developed image processing algorithms are proposed and exploited by doctors as a second opinion to analyze and identify the brain tumors. In this paper, we proposed a new advanced CAD for brain tumor identification, classification and feature extraction. Our proposed CAD includes three main parts. Firstly, we load the brain MRI. Secondly, a robust technique for brain tumor extraction is proposed. This technique is based on both Discrete Wavelet Transform (DWT) and Principal Component Analysis (PCA). DWT is characterized by its multiresolution analytic property, that’s why it was applied on MRI images with different decomposition levels for feature extraction. Nevertheless, this technique suffers from a main drawback since it necessitates a huge storage and is computationally expensive. To decrease the dimensions of the feature vector and the computing time, PCA technique is considered. In the last stage, according to different extracted features, the brain tumor is classified into either benign or malignant tumor using Support Vector Machine (SVM) algorithm. A CAD tool for brain tumor detection and classification, including all above-mentioned stages, is designed and developed using MATLAB guide user interface.

Keywords: MRI, brain tumor, CAD, feature extraction, DWT, PCA, classification, SVM

Procedia PDF Downloads 250

Authors: Rohini Hariharan, Yazhini R, Bhamidipati Naga Shrikarti

Abstract:

In the realm of cricket, particularly within the context of the Indian Premier League (IPL), the ability to predict team scores accurately holds significant importance for both cricket enthusiasts and stakeholders alike. This paper presents a comprehensive study on IPL score prediction utilizing various machine learning algorithms, including Support Vector Machines (SVM), XGBoost, Multiple Regression, Linear Regression, K-nearest neighbors (KNN), and Random Forest. Through meticulous data preprocessing, feature engineering, and model selection, we aimed to develop a robust predictive framework capable of forecasting team scores with high precision. Our experimentation involved the analysis of historical IPL match data encompassing diverse match and player statistics. Leveraging this data, we employed state-of-the-art machine learning techniques to train and evaluate the performance of each model. Notably, Multiple Regression emerged as the top-performing algorithm, achieving an impressive accuracy of 77.19% and a precision of 54.05% (within a threshold of +/- 10 runs). This research contributes to the advancement of sports analytics by demonstrating the efficacy of machine learning in predicting IPL team scores. The findings underscore the potential of advanced predictive modeling techniques to provide valuable insights for cricket enthusiasts, team management, and betting agencies. Additionally, this study serves as a benchmark for future research endeavors aimed at enhancing the accuracy and interpretability of IPL score prediction models.

Keywords: indian premier league (IPL), cricket, score prediction, machine learning, support vector machines (SVM), xgboost, multiple regression, linear regression, k-nearest neighbors (KNN), random forest, sports analytics

Procedia PDF Downloads 53

Authors: Altilio Rosa, Chirico Francesco, Foglia Goffredo

Abstract:

In recent years, the number of Unmanned Aerial Vehicles (UAVs) has significantly increased. The rapid development of commercial and recreational drones makes them an important part of our society. Despite the growing list of their applications, these vehicles pose a huge threat to civil and military installations: detection, classification and neutralization of such flying objects become an urgent need. Radar is an effective remote sensing tool for detecting and tracking flying objects, but scenarios characterized by the presence of a high number of tracks related to flying birds make especially challenging the drone detection task: operator PPI is cluttered with a huge number of potential threats and his reaction time can be severely affected. Flying birds compared to UAVs show similar velocity, RADAR cross-section and, in general, similar characteristics. Building from the absence of a single feature that is able to distinguish UAVs and birds, this paper uses a multiple features approach where an original feature selection technique is developed to feed binary classifiers trained to distinguish birds and UAVs. RADAR tracks acquired on the field and related to different UAVs and birds performing various trajectories were used to extract specifically designed target movement-related features based on velocity, trajectory and signal strength. An optimization strategy based on a genetic algorithm is also introduced to select the optimal subset of features and to estimate the performance of several classification algorithms (Neural network, SVM, Logistic regression…) both in terms of the number of selected features and misclassification error. Results show that the proposed methods are able to reduce the dimension of the data space and to remove almost all non-drone false targets with a suitable classification accuracy (higher than 95%).

Keywords: birds, classification, machine learning, UAVs

Procedia PDF Downloads 222

Authors: Yindi Zhao, Yun Zhang, Silu Xia, Lixin Wu

Abstract:

The contours and areas of water surfaces, especially lakes, often change due to natural disasters and construction activities. It is an effective way to extract and update water contours from satellite images using image processing algorithms. However, to produce optimal water surface contours that are close to true boundaries is still a challenging task. This paper compares the performances of three different level set models, including the Chan-Vese (CV) model, the signed pressure force (SPF) model, and the region-scalable fitting (RSF) energy model for extracting lake contours. After experiment testing, it is indicated that the RSF model, in which a region-scalable fitting (RSF) energy functional is defined and incorporated into a variational level set formulation, is superior to CV and SPF, and it can get desirable contour lines when there are “holes” in the regions of waters, such as the islands in the lake. Therefore, the RSF model is applied to extracting lake contours from Landsat satellite images. Four temporal Landsat satellite images of the years of 2000, 2005, 2010, and 2014 are used in our study. All of them were acquired in May, with the same path/row (121/036) covering Xuzhou City, Jiangsu Province, China. Firstly, the near infrared (NIR) band is selected for water extraction. Image registration is conducted on NIR bands of different temporal images for information update, and linear stretching is also done in order to distinguish water from other land cover types. Then for the first temporal image acquired in 2000, lake contours are extracted via the RSF model with initialization of user-defined rectangles. Afterwards, using the lake contours extracted the previous temporal image as the initialized values, lake contours are updated for the current temporal image by means of the RSF model. Meanwhile, the changed and unchanged lakes are also detected. The results show that great changes have taken place in two lakes, i.e. Dalong Lake and Panan Lake, and RSF can actually extract and effectively update lake contours using multi-temporal satellite image.

Keywords: level set model, multi-temporal image, lake contour extraction, contour update

Procedia PDF Downloads 366

Authors: O’Day Luke

Abstract:

Purpose: To validate virtual non-contrast reconstructions generated from dual-layer spectral computed tomography (DL-CT) data as an alternative for the acquisition of a dedicated true non-contrast dataset during multiphase contrast studies. Material and methods: Thirty-three patients underwent a routine multiphase clinical CT examination, using Dual-Layer Spectral CT, from March to August 2021. True non-contrast (TNC) and virtual non-contrast (VNC) datasets, generated from both portal venous and arterial phase imaging were evaluated. For every patient in both true and virtual non-contrast datasets, a region-of-interest (ROI) was defined in aorta, liver, fluid (i.e. gallbladder, urinary bladder), kidney, muscle, fat and spongious bone, resulting in 693 ROIs. Differences in attenuation for VNC and TNV images were compared, both separately and combined. Consistency between VNC reconstructions obtained from the arterial and portal venous phase was evaluated. Results: Comparison of CT density (HU) on the VNC and TNC images showed a high correlation. The mean difference between TNC and VNC images (excluding bone results) was 5.5 ± 9.1 HU and > 90% of all comparisons showed a difference of less than 15 HU. For all tissues but spongious bone, the mean absolute difference between TNC and VNC images was below 10 HU. VNC images derived from the arterial and the portal venous phase showed a good correlation in most tissue types. The aortic attenuation was somewhat dependent however on which dataset was used for reconstruction. Bone evaluation with VNC datasets continues to be a problem, as spectral CT algorithms are currently poor in differentiating bone and iodine. Conclusion: Given the increasing availability of DL-CT and proven accuracy of virtual non-contrast processing, VNC is a promising tool for generating additional data during routine contrast-enhanced studies. This study shows the utility of virtual non-contrast scans as an alternative for true non-contrast studies during multiphase CT, with potential for dose reduction, without loss of diagnostic information.

Keywords: dual-layer spectral computed tomography, virtual non-contrast, true non-contrast, clinical comparison

Procedia PDF Downloads 141

Authors: Sokkhey Phauk, Takeo Okazaki

Abstract:

The challenging task in educational institutions is to maximize the high performance of students and minimize the failure rate of poor-performing students. An effective method to leverage this task is to know student learning patterns with highly influencing factors and get an early prediction of student learning outcomes at the timely stage for setting up policies for improvement. Educational data mining (EDM) is an emerging disciplinary field of data mining, statistics, and machine learning concerned with extracting useful knowledge and information for the sake of improvement and development in the education environment. The study is of this work is to propose techniques in EDM and integrate it into a web-based system for predicting poor-performing students. A comparative study of prediction models is conducted. Subsequently, high performing models are developed to get higher performance. The hybrid random forest (Hybrid RF) produces the most successful classification. For the context of intervention and improving the learning outcomes, a feature selection method MICHI, which is the combination of mutual information (MI) and chi-square (CHI) algorithms based on the ranked feature scores, is introduced to select a dominant feature set that improves the performance of prediction and uses the obtained dominant set as information for intervention. By using the proposed techniques of EDM, an academic performance prediction system (APPS) is subsequently developed for educational stockholders to get an early prediction of student learning outcomes for timely intervention. Experimental outcomes and evaluation surveys report the effectiveness and usefulness of the developed system. The system is used to help educational stakeholders and related individuals for intervening and improving student performance.

Keywords: academic performance prediction system, educational data mining, dominant factors, feature selection method, prediction model, student performance

Procedia PDF Downloads 106

Authors: Gianpaolo Ghiani, Emanuela Guerriero, Emanuele Manni, Alessandro Romano

Abstract:

In this article, we deal with a variant of the classical course timetabling problem that has a practical application in many areas of education. In particular, in this paper we are interested in high schools remedial courses. The purpose of such courses is to provide under-prepared students with the skills necessary to succeed in their studies. In particular, a student might be under prepared in an entire course, or only in a part of it. The limited availability of funds, as well as the limited amount of time and teachers at disposal, often requires schools to choose which courses and/or which teaching units to activate. Thus, schools need to model the training offer and the related timetabling, with the goal of ensuring the highest possible teaching quality, by meeting the above-mentioned financial, time and resources constraints. Moreover, there are some prerequisites between the teaching units that must be satisfied. We first present a Mixed-Integer Programming (MIP) model to solve this problem to optimality. However, the presence of many peculiar constraints contributes inevitably in increasing the complexity of the mathematical model. Thus, solving it through a general purpose solver may be performed for small instances only, while solving real-life-sized instances of such model requires specific techniques or heuristic approaches. For this purpose, we also propose a heuristic approach, in which we make use of a fast constructive procedure to obtain a feasible solution. To assess our exact and heuristic approaches we perform extensive computational results on both real-life instances (obtained from a high school in Lecce, Italy) and randomly generated instances. Our tests show that the MIP model is never solved to optimality, with an average optimality gap of 57%. On the other hand, the heuristic algorithm is much faster (in about the 50% of the considered instances it converges in approximately half of the time limit) and in many cases allows achieving an improvement on the objective function value obtained by the MIP model. Such an improvement ranges between 18% and 66%.

Keywords: heuristic, MIP model, remedial course, school, timetabling

Procedia PDF Downloads 605

Authors: Andrew R. Willis, Kevin Brink, Kathleen Dipple

Abstract:

This article describes a software package called ROS-georegistration intended for use with the robot operating system (ROS) and the Gazebo 3D simulation environment. ROSgeoregistration provides tools for the simulation, test, and deployment of aerial georegistration algorithms and is available at github.com/uncc-visionlab/rosgeoregistration. A model creation package is provided which downloads multi-spectral images from the Google Earth Engine database and, if necessary, incorporates these images into a single, possibly very large, reference image. Additionally a Gazebo plugin which uses the real-time sensor pose and image formation model to generate simulated imagery using the specified reference image is provided along with related plugins for UAV relevant data. The novelty of this work is threefold: (1) this is the first system to link the massive multi-spectral imaging database of Google’s Earth Engine to the Gazebo simulator, (2) this is the first example of a system that can simulate geospatially and radiometrically accurate imagery from multiple sensor views of the same terrain region, and (3) integration with other UAS tools creates a new holistic UAS simulation environment to support UAS system and subsystem development where real-world testing would generally be prohibitive. Sensed imagery and ground truth registration information is published to client applications which can receive imagery synchronously with telemetry from other payload sensors, e.g., IMU, GPS/GNSS, barometer, and windspeed sensor data. To highlight functionality, we demonstrate ROSgeoregistration for simulating Electro-Optical (EO) and Synthetic Aperture Radar (SAR) image sensors and an example use case for developing and evaluating image-based UAS position feedback, i.e., pose for image-based Guidance Navigation and Control (GNC) applications.

Keywords: EO-to-EO, EO-to-SAR, flight simulation, georegistration, image generation, robot operating system, vision-based navigation

Procedia PDF Downloads 104

Authors: Hung-Sheng Lin, Cheng-Hsuan Li

Abstract:

Over the past few years, kernel-based algorithms have been widely used to extend some linear feature extraction methods such as principal component analysis (PCA), linear discriminate analysis (LDA), and nonparametric weighted feature extraction (NWFE) to their nonlinear versions, kernel principal component analysis (KPCA), generalized discriminate analysis (GDA), and kernel nonparametric weighted feature extraction (KNWFE), respectively. These nonlinear feature extraction methods can detect nonlinear directions with the largest nonlinear variance or the largest class separability based on the given kernel function. Moreover, they have been applied to improve the target detection or the image classification of hyperspectral images. The double nearest proportion feature extraction (DNP) can effectively reduce the overlap effect and have good performance in hyperspectral image classification. The DNP structure is an extension of the k-nearest neighbor technique. For each sample, there are two corresponding nearest proportions of samples, the self-class nearest proportion and the other-class nearest proportion. The term “nearest proportion” used here consider both the local information and other more global information. With these settings, the effect of the overlap between the sample distributions can be reduced. Usually, the maximum likelihood estimator and the related unbiased estimator are not ideal estimators in high dimensional inference problems, particularly in small data-size situation. Hence, an improved estimator by shrinkage estimation (regularization) is proposed. Based on the DNP structure, LDA is included as a special case. In this paper, the kernel method is applied to extend DNP to kernel-based DNP (KDNP). In addition to the advantages of DNP, KDNP surpasses DNP in the experimental results. According to the experiments on the real hyperspectral image data sets, the classification performance of KDNP is better than that of PCA, LDA, NWFE, and their kernel versions, KPCA, GDA, and KNWFE.

Keywords: feature extraction, kernel method, double nearest proportion feature extraction, kernel double nearest feature extraction

Procedia PDF Downloads 344

Authors: Anderson S. Fonseca, Italo F. S. Da Silva, Robert D. A. Santos, Mayara G. Da Silva, Pedro H. C. Vieira, Antonio M. S. Sobrinho, Victor H. B. Lemos, Petterson S. Diniz, Anselmo C. Paiva, Eliana M. G. Monteiro

Abstract:

In Brazil, the National Electric Energy Agency (ANEEL) establishes that electrical energy companies are responsible for measuring and billing their customers. Among these regulations, it’s defined that a company must bill your customers within 27-33 days. If a relocation or a change of period is required, the consumer must be notified in writing, in advance of a billing period. To make it easier to organize a workday’s measurements, these companies create a reading plan. These plans consist of grouping customers into reading groups, which are visited by an employee responsible for measuring consumption and billing. The creation process of a plan efficiently and optimally is a capacitated clustering problem with constraints related to homogeneity and compactness, that is, the employee’s working load and the geographical position of the consuming unit. This process is a work done manually by several experts who have experience in the geographic formation of the region, which takes a large number of days to complete the final planning, and because it’s human activity, there is no guarantee of finding the best optimization for planning. In this paper, the GBKMeans method presents a technique based on K-Means and genetic algorithms for creating a capacitated cluster that respects the constraints established in an efficient and balanced manner, that minimizes the cost of relocating consumer units and the time required for final planning creation. The results obtained by the presented method are compared with the current planning of a real city, showing an improvement of 54.71% in the standard deviation of working load and 11.97% in the compactness of the groups.

Keywords: capacitated clustering, k-means, genetic algorithm, districting problems

Procedia PDF Downloads 198

Authors: Eric Lee G. Escobedo-Wu, Nidhi Rohatgi, Fouzel Dhebar

Abstract:

It is challenging for patients to navigate through healthcare systems after-hours. This leads to delays in care, patient/provider dissatisfaction, inappropriate resource utilization, readmissions, and higher costs. It is important to provide patients and providers with effective clinical decision-making tools to allow seamless connectivity and coordinated care. In August 2015, patient-centric Stanford Health Care established Clinical Advice Services (CAS) to provide clinical decision support after-hours. CAS is founded on key Lean principles: Value stream mapping, empathy mapping, waste walk, takt time calculations, standard work, plan-do-check-act cycles, and active daily management. At CAS, Clinical Assistants take the initial call and manage all non-clinical calls (e.g., appointments, directions, general information). If the patient has a clinical symptom, the CAS nurses take the call and utilize standardized clinical algorithms to triage the patient to home, clinic, urgent care, emergency department, or 911. Nurses may also contact the on-call physician based on the clinical algorithm for further direction and consultation. Since August 2015, CAS has managed 228,990 calls from 26 clinical specialties. Reporting is built into the electronic health record for analysis and data collection. 65.3% of the after-hours calls are clinically related. Average clinical algorithm adherence rate has been 92%. An average of 9% of calls was escalated by CAS nurses to the physician on call. An average of 5% of patients was triaged to the Emergency Department by CAS. Key learnings indicate that a seamless connectivity vision, cascading, multidisciplinary ownership of the problem, and synergistic enterprise improvements have contributed to this success while striving for continuous improvement.

Keywords: after hours phone calls, clinical advice services, nurse triage, Stanford Health Care

Procedia PDF Downloads 174

Authors: Shih-Wen Hsiao, Yi-Cheng Tsao

Abstract:

In the field of reverse engineering and creative industries, applying 3D scanning process to obtain geometric forms of the objects is a mature and common technique. For instance, organic objects such as faces and nonorganic objects such as products could be scanned to acquire the geometric information for further application. However, although the data resolution of 3D scanning device is increasing and there are more and more abundant complementary applications, the penetration rate of 3D scanning for the public is still limited by the relative high price of the devices. On the other hand, Kinect, released by Microsoft, is known for its powerful functions, considerably low price, and complete technology and database support. Therefore, related studies can be done with the applying of Kinect under acceptable cost and data precision. Due to the fact that Kinect utilizes optical mechanism to extracting depth information, limitations are found due to the reason of the straight path of the light. Thus, various angles are required sequentially to obtain the complete 3D information of the object when applying a single Kinect for 3D scanning. The integration process which combines the 3D data from different angles by certain algorithms is also required. This sequential scanning process costs much time and the complex integration process often encounter some technical problems. Therefore, this paper aimed to apply multiple Kinects simultaneously on the field of developing a rapid 3D mannequin scan platform and proposed suggestions on the number and angles of Kinects. In the content, a method of establishing the coordination based on the relation between mannequin and the specifications of Kinect is proposed, and a suggestion of angles and number of Kinects is also described. An experiment of applying multiple Kinect on the scanning of 3D mannequin is constructed by Microsoft API, and the results show that the time required for scanning and technical threshold can be reduced in the industries of fashion and garment design.

Keywords: 3D scan, depth sensor, fashion and garment design, mannequin, multiple Kinect sensor

Procedia PDF Downloads 366

Authors: Nelson Kimeli Kemboi Yego, Juma Kasozi, Joseph Nkruzinza, Francis Kipkogei

Abstract:

The study investigated the low uptake of health insurance in Kenya despite efforts to achieve universal health coverage through various health insurance schemes. Unsupervised machine learning techniques were employed to identify patterns in health insurance uptake based on sociodemographic factors among Kenyan households. The aim was to identify key demographic groups that are underinsured and to provide insights for the development of effective policies and outreach programs. Using the 2021 FinAccess Survey, the study clustered Kenyan households based on their health insurance uptake and sociodemographic features to reveal patterns in health insurance uptake across the country. The effectiveness of k-prototypes clustering, hierarchical clustering, and agglomerative hierarchical clustering in clustering based on sociodemographic factors was compared. The k-prototypes approach was found to be the most effective at uncovering distinct and well-separated clusters in the Kenyan sociodemographic data related to health insurance uptake based on silhouette, Calinski-Harabasz, Davies-Bouldin, and Rand indices. Hence, it was utilized in uncovering the patterns in uptake. The results of the analysis indicate that inclusivity in health insurance is greatly related to affordability. The findings suggest that targeted policy interventions and outreach programs are necessary to increase health insurance uptake in Kenya, with the ultimate goal of achieving universal health coverage. The study provides important insights for policymakers and stakeholders in the health insurance sector to address the low uptake of health insurance and to ensure that healthcare services are accessible and affordable to all Kenyans, regardless of their socio-demographic status. The study highlights the potential of unsupervised machine learning techniques to provide insights into complex health policy issues and improve decision-making in the health sector.

Keywords: health insurance, unsupervised learning, clustering algorithms, machine learning

Procedia PDF Downloads 138

Authors: Misganaw Chere Siferih

Abstract:

This study assessed the impact of crossbreed dairy cows on household income and food security. The study area is found in Dejen Woreda, East Gojam Zone, and Amhara region of Ethiopia. Random sampling technique was used to obtain a sample of 80 crossbreed dairy cow owners and 176 indigenous dairy cow owners. The study employed food consumption score analytical framework to measure food security status of the household. No Statistical significant mean difference is found between crossbreed owners and indigenous owners. Logistic regression was employed to investigate crossbreed dairy cow adoption determinants , the result indicates that gender, education, labor number, land size cultivated, dairy cooperatives membership, net income and food security status of the household are statistically significant independent variables, which explained the binary dependent variable, crossbreed dairy cow adoption. Propensity score matching (PSM) was employed to analyze the impact of crossbreed dairy cow owners on farmers’ income and food security. The average net income of crossbreed dairy cow owners was found to be significantly higher than indigenous dairy cow owners. Estimates of average treatment effect of the treated (ATT) indicated that crossbreed dairy cow is able to impact households’ net income by 42%, 38.5%, 30.8% and 44.5% higher in kernel, radius, nearest neighborhood and stratification matching algorithms respectively as compared to indigenous dairy cow owners. However, estimates of average treatment of the treated (ATT) suggest that being an owner of crossbreed dairy cow is not able to affect food security significantly. Thus, crossbreed dairy cow enables farmers to increase income but not their food security in the study area. Finally, the study recommended establishing dairy cooperatives and advice farmers to become a member of them, attention to promoting the impact of crossbreed dairy cows and promotion of nutrition focus projects.

Keywords: crossbreed dairy cow, net income, food security, propensity score matching

Procedia PDF Downloads 65

Authors: Cristy Stagnar, Nina Hubig, Diana Ivankovic

Abstract:

The epigenome is a compelling candidate for mediating long-term responses to environmental effects modifying disease risk. The main goal of this research is to develop a machine learning-based DNA methylation score, which will be valuable in delineating the unique contribution of paternal epigenetic modifications to the germline impacting childhood health outcomes. It will also be a useful tool in validating self-reports of nonsmoking and in adjusting epigenome-wide DNA methylation association studies for this early-life exposure. Using secondary data from two population-based methylation profiling studies, our DNA methylation score is based on CpG DNA methylation measurements from cord blood gathered from children whose fathers smoked pre- and peri-conceptually. Each child’s mother and father fell into one of three class labels in the accompanying questionnaires -never smoker, former smoker, or current smoker. By applying different machine learning algorithms to the accessible resource for integrated epigenomic studies (ARIES) sub-study of the Avon longitudinal study of parents and children (ALSPAC) data set, which we used for training and testing of our model, the best-performing algorithm for classifying the father smoker and mother never smoker was selected based on Cohen’s κ. Error in the model was identified and optimized. The final DNA methylation score was further tested and validated in an independent data set. This resulted in a linear combination of methylation values of selected probes via a logistic link function that accurately classified each group and contributed the most towards classification. The result is a unique, robust DNA methylation score which combines information on DNA methylation and early life exposure of offspring to paternal smoking during pregnancy and which may be used to examine the paternal contribution to offspring health outcomes.

Keywords: epigenome, health outcomes, paternal preconception environmental exposures, supervised machine learning

Procedia PDF Downloads 185

Authors: M. Varin, A. M. Dubois, R. Gadbois-Langevin, B. Chalghaf

Abstract:

Good knowledge of the physical environment is essential for an integrated forest planning. This information enables better forecasting of operating costs, determination of cutting volumes, and preservation of ecologically sensitive areas. The use of satellite images in stereoscopic pairs gives the capacity to generate high precision 3D models, which are scale-adapted for harvesting operations. These models could represent an alternative to 3D LiDAR data, thanks to their advantageous cost of acquisition. The objective of the study was to assess the quality of stereo-derived canopy height models (CHM) in comparison to a traditional LiDAR CHM and ground tree-height samples. Two study sites harboring two different forest stand types (broadleaf and conifer) were analyzed using stereo pairs and tri-stereo images from the WorldView-3 satellite to calculate CHM. Acquisition of multispectral images from an Unmanned Aerial Vehicle (UAV) was also realized on a smaller part of the broadleaf study site. Different algorithms using two softwares (PCI Geomatica and Correlator3D) with various spatial resolutions and band selections were tested to select the 3D modeling technique, which offered the best performance when compared with LiDAR. In the conifer study site, the CHM produced with Corelator3D using only the 50-cm resolution panchromatic band was the one with the smallest Root-mean-square deviation (RMSE: 1.31 m). In the broadleaf study site, the tri-stereo model provided slightly better performance, with an RMSE of 1.2 m. The tri-stereo model was also compared to the UAV, which resulted in an RMSE of 1.3 m. At individual tree level, when ground samples were compared to satellite, lidar, and UAV CHM, RMSE were 2.8, 2.0, and 2.0 m, respectively. Advanced analysis was done for all of these cases, and it has been noted that RMSE is reduced when the canopy cover is higher when shadow and slopes are lower and when clouds are distant from the analyzed site.

Keywords: very high spatial resolution, satellite imagery, WorlView-3, canopy height models, CHM, LiDAR, unmanned aerial vehicle, UAV

Procedia PDF Downloads 127

Authors: Gayathri Nagarajan, L. D. Dhinesh Babu

Abstract:

Health care is one of the prominent industries that generate voluminous data thereby finding the need of machine learning techniques with big data solutions for efficient processing and prediction. Missing data, incomplete data, real time streaming data, sensitive data, privacy, heterogeneity are few of the common challenges to be addressed for efficient processing and mining of health care data. In comparison with other applications, accuracy and fast processing are of higher importance for health care applications as they are related to the human life directly. Though there are many machine learning techniques and big data solutions used for efficient processing and prediction in health care data, different techniques and different frameworks are proved to be effective for different applications largely depending on the characteristics of the datasets. In this paper, we present a framework that uses ensemble machine learning technique gradient boosted trees for data classification in health care big data. The framework is built on Spark platform which is fast in comparison with other traditional frameworks. Unlike other works that focus on a single technique, our work presents a comparison of six different machine learning techniques along with gradient boosted trees on datasets of different characteristics. Five benchmark health care datasets are considered for experimentation, and the results of different machine learning techniques are discussed in comparison with gradient boosted trees. The metric chosen for comparison is misclassification error rate and the run time of the algorithms. The goal of this paper is to i) Compare the performance of gradient boosted trees with other machine learning techniques in Spark platform specifically for health care big data and ii) Discuss the results from the experiments conducted on datasets of different characteristics thereby drawing inference and conclusion. The experimental results show that the accuracy is largely dependent on the characteristics of the datasets for other machine learning techniques whereas gradient boosting trees yields reasonably stable results in terms of accuracy without largely depending on the dataset characteristics.

Keywords: big data analytics, ensemble machine learning, gradient boosted trees, Spark platform

Procedia PDF Downloads 241

Authors: Anand Malik

Abstract:

The Himalayas with high tectonic activities poses a great threat to human life and property. Climate change is another reason which triggering extreme events multiple fold effect on high mountain glacial environment, rock falls, landslides, debris flows, flash flood and snow avalanches. One such extreme event of cloud burst along with breach of moraine dammed Chorabri Lake occurred from June 14 to June 17, 2013, triggered flooding of Saraswati and Mandakini rivers in the Kedarnath Valley of Rudraprayag district of Uttrakhand state of India. As a result, huge volume of water with its high velocity created a catastrophe of the century, which resulted into loss of large number of human/animals, pilgrimage, tourism, agriculture and property. Thus a comprehensive assessment of debris flow hazards requires GIS-based modeling using numerical methods. The aim of present study is to focus on analysis and mapping of debris flow movements using geospatial data with flow-r (developed by team at IGAR, University of Lausanne). The model is based on combined probabilistic and energetic algorithms for the assessment of spreading of flow with maximum run out distances. Aster Digital Elevation Model (DEM) with 30m x 30m cell size (resolution) is used as main geospatial data for preparing the run out assessment, while Landsat data is used to analyze land use land cover change in the study area. The results of the study area show that model can be applied with great accuracy as the model is very useful in determining debris flow areas. The results are compared with existing available landslides/debris flow maps. ArcGIS software is used in preparing run out susceptibility maps which can be used in debris flow mitigation and future land use planning.

Keywords: debris flow, geospatial data, GIS based modeling, flow-R

Procedia PDF Downloads 273

Authors: Thomas Weber, Nina Strobel, Thomas Kohne, Eberhard Abele

Abstract:

In context of the energy transition in Germany, the importance of so-called virtual power plants in the energy supply continues to increase. The progressive dismantling of the large power plants and the ongoing construction of many new decentralized plants result in great potential for optimization through synergies between the individual plants. These potentials can be exploited by mathematical optimization algorithms to calculate the optimal application planning of decentralized power and heat generators and storage systems. This also includes linear or linear mixed integer optimization. In this paper, procedures for reducing the number of decision variables to be calculated are explained and validated. On the one hand, this includes combining n similar installation types into one aggregated unit. This aggregated unit is described by the same constraints and target function terms as a single plant. This reduces the number of decision variables per time step and the complexity of the problem to be solved by a factor of n. The exact operating mode of the individual plants can then be calculated in a second optimization in such a way that the output of the individual plants corresponds to the calculated output of the aggregated unit. Another way to reduce the number of decision variables in an optimization problem is to reduce the number of time steps to be calculated. This is useful if a high temporal resolution is not necessary for all time steps. For example, the volatility or the forecast quality of environmental parameters may justify a high or low temporal resolution of the optimization. Both approaches are examined for the resulting calculation time as well as for optimality. Several optimization models for virtual power plants (combined heat and power plants, heat storage, power storage, gas turbine) with different numbers of plants are used as a reference for the investigation of both processes with regard to calculation duration and optimality.

Keywords: CHP, Energy 4.0, energy storage, MILP, optimization, virtual power plant

Procedia PDF Downloads 178

Authors: Mst Shapna Akter, Hossain Shahriar

Abstract:

One of the most important challenges in the field of software code audit is the presence of vulnerabilities in software source code. Every year, more and more software flaws are found, either internally in proprietary code or revealed publicly. These flaws are highly likely exploited and lead to system compromise, data leakage, or denial of service. C and C++ open-source code are now available in order to create a largescale, machine-learning system for function-level vulnerability identification. We assembled a sizable dataset of millions of opensource functions that point to potential exploits. We developed an efficient and scalable vulnerability detection method based on deep neural network models that learn features extracted from the source codes. The source code is first converted into a minimal intermediate representation to remove the pointless components and shorten the dependency. Moreover, we keep the semantic and syntactic information using state-of-the-art word embedding algorithms such as glove and fastText. The embedded vectors are subsequently fed into deep learning networks such as LSTM, BilSTM, LSTM-Autoencoder, word2vec, BERT, and GPT-2 to classify the possible vulnerabilities. Furthermore, we proposed a neural network model which can overcome issues associated with traditional neural networks. Evaluation metrics such as f1 score, precision, recall, accuracy, and total execution time have been used to measure the performance. We made a comparative analysis between results derived from features containing a minimal text representation and semantic and syntactic information. We found that all of the deep learning models provide comparatively higher accuracy when we use semantic and syntactic information as the features but require higher execution time as the word embedding the algorithm puts on a bit of complexity to the overall system.

Keywords: cyber security, vulnerability detection, neural networks, feature extraction

Procedia PDF Downloads 89

Authors: Nwachukwu Ifeanyi

Abstract:

Wind energy is a vital component of the global renewable energy portfolio, with wind turbines serving as the primary means of harnessing this abundant resource. However, the efficiency and stability of wind turbines remain critical challenges in maximizing energy output and ensuring long-term operational viability. This study proposes a comprehensive approach utilizing computational aerodynamics and aeromechanics to optimize wind turbine performance across multiple objectives. The proposed research aims to integrate advanced computational fluid dynamics (CFD) simulations with structural analysis techniques to enhance the aerodynamic efficiency and mechanical stability of wind turbine blades. By leveraging multi-objective optimization algorithms, the study seeks to simultaneously optimize aerodynamic performance metrics such as lift-to-drag ratio and power coefficient while ensuring structural integrity and minimizing fatigue loads on the turbine components. Furthermore, the investigation will explore the influence of various design parameters, including blade geometry, airfoil profiles, and turbine operating conditions, on the overall performance and stability of wind turbines. Through detailed parametric studies and sensitivity analyses, valuable insights into the complex interplay between aerodynamics and structural dynamics will be gained, facilitating the development of next-generation wind turbine designs. Ultimately, this research endeavours to contribute to the advancement of sustainable energy technologies by providing innovative solutions to enhance the efficiency, reliability, and economic viability of wind power generation systems. The findings have the potential to inform the design and optimization of wind turbines, leading to increased energy output, reduced maintenance costs, and greater environmental benefits in the transition towards a cleaner and more sustainable energy future.

Keywords: computation, robotics, mathematics, simulation

Procedia PDF Downloads 59

Authors: M. Uysal, M. Yilmaz, I. Tiryakioğlu

Abstract:

Digital Terrain Model (DTM) is a digital numerical representation of the Earth's surface. DTMs have been applied to a diverse field of tasks, such as urban planning, military, glacier mapping, disaster management. In the expression of the Earth' surface as a mathematical model, an infinite number of point measurements are needed. Because of the impossibility of this case, the points at regular intervals are measured to characterize the Earth's surface and DTM of the Earth is generated. Hitherto, the classical measurement techniques and photogrammetry method have widespread use in the construction of DTM. At present, RADAR, LiDAR, and stereo satellite images are also used for the construction of DTM. In recent years, especially because of its superiorities, Airborne Light Detection and Ranging (LiDAR) has an increased use in DTM applications. A 3D point cloud is created with LiDAR technology by obtaining numerous point data. However recently, by the development in image mapping methods, the use of unmanned aerial vehicles (UAV) for photogrammetric data acquisition has increased DTM generation from image-based point cloud. The accuracy of the DTM depends on various factors such as data collection method, the distribution of elevation points, the point density, properties of the surface and interpolation methods. In this study, the random data reduction method is compared for DTMs generated from image based point cloud data. The original image based point cloud data set (100%) is reduced to a series of subsets by using random algorithm, representing the 75, 50, 25 and 5% of the original image based point cloud data set. Over the ANS campus of Afyon Kocatepe University as the test area, DTM constructed from the original image based point cloud data set is compared with DTMs interpolated from reduced data sets by Kriging interpolation method. The results show that the random data reduction method can be used to reduce the image based point cloud datasets to 50% density level while still maintaining the quality of DTM.

Keywords: DTM, Unmanned Aerial Vehicle (UAV), uniform, random, kriging

Procedia PDF Downloads 155

Authors: Zahid Ullah, Atlas Khan

Abstract:

The rapid advancements in data collection, storage, and processing capabilities have led to an explosion of data in various domains. In this era of big data, mathematical sciences play a crucial role in uncovering valuable insights and driving informed decision-making through data analytics. The purpose of this abstract is to present the latest advances in mathematical sciences and their application in harnessing the power of data analytics. This abstract highlights the interdisciplinary nature of data analytics, showcasing how mathematics intersects with statistics, computer science, and other related fields to develop cutting-edge methodologies. It explores key mathematical techniques such as optimization, mathematical modeling, network analysis, and computational algorithms that underpin effective data analysis and interpretation. The abstract emphasizes the role of mathematical sciences in addressing real-world challenges across different sectors, including finance, healthcare, engineering, social sciences, and beyond. It showcases how mathematical models and statistical methods extract meaningful insights from complex datasets, facilitating evidence-based decision-making and driving innovation. Furthermore, the abstract emphasizes the importance of collaboration and knowledge exchange among researchers, practitioners, and industry professionals. It recognizes the value of interdisciplinary collaborations and the need to bridge the gap between academia and industry to ensure the practical application of mathematical advancements in data analytics. The abstract highlights the significance of ongoing research in mathematical sciences and its impact on data analytics. It emphasizes the need for continued exploration and innovation in mathematical methodologies to tackle emerging challenges in the era of big data and digital transformation. In summary, this abstract sheds light on the advances in mathematical sciences and their pivotal role in unveiling the power of data analytics. It calls for interdisciplinary collaboration, knowledge exchange, and ongoing research to further unlock the potential of mathematical methodologies in addressing complex problems and driving data-driven decision-making in various domains.

Keywords: mathematical sciences, data analytics, advances, unveiling

Procedia PDF Downloads 93