Search results for: K nearest neighbour

Authors: Victor Bodell, Lukas Ekstrom, Somayeh Aghanavesi

Abstract:

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

Keywords: Artificial neural networks, fuel consumption, machine learning, regression, statistical tests.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 829

Authors: Aya Salama

Abstract:

Digital Twin has emerged as a compelling research area, capturing the attention of scholars over the past decade. It finds applications across diverse fields, including smart manufacturing and healthcare, offering significant time and cost savings. Notably, it often intersects with other cutting-edge technologies such as Data Mining, Artificial Intelligence, and Machine Learning. However, the concept of a Human Digital Twin (HDT) is still in its infancy and requires further demonstration of its practicality. HDT takes the notion of Digital Twin a step further by extending it to living entities, notably humans, who are vastly different from inanimate physical objects. The primary objective of this research was to create an HDT capable of automating real-time human responses by simulating human behavior. To achieve this, the study delved into various areas, including clustering, supervised classification, topic extraction, and sentiment analysis. The paper successfully demonstrated the feasibility of HDT for generating personalized responses in social messaging applications. Notably, the proposed approach achieved an overall accuracy of 63%, a highly promising result that could pave the way for further exploration of the HDT concept. The methodology employed Random Forest for clustering the question database and matching new questions, while K-nearest neighbor was utilized for sentiment analysis.

Keywords: Human Digital twin, sentiment analysis, topic extraction, supervised machine learning, unsupervised machine learning, classification and clustering.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 188

Authors: Kanthida Kusonmano, Michael Netzer, Bernhard Pfeifer, Christian Baumgartner, Klaus R. Liedl, Armin Graber

Abstract:

Availability of high dimensional biological datasets such as from gene expression, proteomic, and metabolic experiments can be leveraged for the diagnosis and prognosis of diseases. Many classification methods in this area have been studied to predict disease states and separate between predefined classes such as patients with a special disease versus healthy controls. However, most of the existing research only focuses on a specific dataset. There is a lack of generic comparison between classifiers, which might provide a guideline for biologists or bioinformaticians to select the proper algorithm for new datasets. In this study, we compare the performance of popular classifiers, which are Support Vector Machine (SVM), Logistic Regression, k-Nearest Neighbor (k-NN), Naive Bayes, Decision Tree, and Random Forest based on mock datasets. We mimic common biological scenarios simulating various proportions of real discriminating biomarkers and different effect sizes thereof. The result shows that SVM performs quite stable and reaches a higher AUC compared to other methods. This may be explained due to the ability of SVM to minimize the probability of error. Moreover, Decision Tree with its good applicability for diagnosis and prognosis shows good performance in our experimental setup. Logistic Regression and Random Forest, however, strongly depend on the ratio of discriminators and perform better when having a higher number of discriminators.

Keywords: Classification, High dimensional data, Machine learning

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2384

Authors: S. M. Seyedhosseini, A. Makui, M. Ghadami

Abstract:

Globalization and therefore increasing tight competition among companies, have resulted to increase the importance of making well-timed decision. Devising and employing effective strategies, that are flexible and adaptive to changing market, stand a greater chance of being effective in the long-term. In other side, a clear focus on managing the entire product lifecycle has emerged as critical areas for investment. Therefore, applying wellorganized tools to employ past experience in new case, helps to make proper and managerial decisions. Case based reasoning (CBR) is based on a means of solving a new problem by using or adapting solutions to old problems. In this paper, an adapted CBR model with k-nearest neighbor (K-NN) is employed to provide suggestions for better decision making which are adopted for a given product in the middle of life phase. The set of solutions are weighted by CBR in the principle of group decision making. Wrapper approach of genetic algorithm is employed to generate optimal feature subsets. The dataset of the department store, including various products which are collected among two years, have been used. K-fold approach is used to evaluate the classification accuracy rate. Empirical results are compared with classical case based reasoning algorithm which has no special process for feature selection, CBR-PCA algorithm based on filter approach feature selection, and Artificial Neural Network. The results indicate that the predictive performance of the model, compare with two CBR algorithms, in specific case is more effective.

Keywords: Case based reasoning, Genetic algorithm, Groupdecision making, Product management.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2174

Authors: Muhammad Sajjad, Naveed Khattak, Noman Jafri

Abstract:

World has entered in 21st century. The technology of computer graphics and digital cameras is prevalent. High resolution display and printer are available. Therefore high resolution images are needed in order to produce high quality display images and high quality prints. However, since high resolution images are not usually provided, there is a need to magnify the original images. One common difficulty in the previous magnification techniques is that of preserving details, i.e. edges and at the same time smoothing the data for not introducing the spurious artefacts. A definitive solution to this is still an open issue. In this paper an image magnification using adaptive interpolation by pixel level data-dependent geometrical shapes is proposed that tries to take into account information about the edges (sharp luminance variations) and smoothness of the image. It calculate threshold, classify interpolation region in the form of geometrical shapes and then assign suitable values inside interpolation region to the undefined pixels while preserving the sharp luminance variations and smoothness at the same time. The results of proposed technique has been compared qualitatively and quantitatively with five other techniques. In which the qualitative results show that the proposed method beats completely the Nearest Neighbouring (NN), bilinear(BL) and bicubic(BC) interpolation. The quantitative results are competitive and consistent with NN, BL, BC and others.

Keywords: Adaptive, digital image processing, imagemagnification, interpolation, geometrical shapes, qualitative &quantitative analysis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1800

Authors: Rajvir Kaur, Jeewani Anupama Ginige

Abstract:

With recent trends in Big Data and advancements in Information and Communication Technologies, the healthcare industry is at the stage of its transition from clinician oriented to technology oriented. Many people around the world die of cancer because the diagnosis of disease was not done at an early stage. Nowadays, the computational methods in the form of Machine Learning (ML) are used to develop automated decision support systems that can diagnose cancer with high confidence in a timely manner. This paper aims to carry out the comparative evaluation of a selected set of ML classifiers on two existing datasets: breast cancer and cervical cancer. The ML classifiers compared in this study are Decision Tree (DT), Support Vector Machine (SVM), k-Nearest Neighbor (k-NN), Logistic Regression, Ensemble (Bagged Tree) and Artificial Neural Networks (ANN). The evaluation is carried out based on standard evaluation metrics Precision (P), Recall (R), F1-score and Accuracy. The experimental results based on the evaluation metrics show that ANN showed the highest-level accuracy (99.4%) when tested with breast cancer dataset. On the other hand, when these ML classifiers are tested with the cervical cancer dataset, Ensemble (Bagged Tree) technique gave better accuracy (93.1%) in comparison to other classifiers.

Keywords: Artificial neural networks, breast cancer, cancer dataset, classifiers, cervical cancer, F-score, logistic regression, machine learning, precision, recall, support vector machine.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1553

Authors: Seyhan Karaçavuş, Bülent Yılmaz, Ömer Kayaaltı, Semra İçer, Arzu Taşdemir, Oğuzhan Ayyıldız, Kübra Eset, Eser Kaya

Abstract:

In this study, our goal was to perform tumor staging and subtype determination automatically using different texture analysis approaches for a very common cancer type, i.e., non-small cell lung carcinoma (NSCLC). Especially, we introduced a texture analysis approach, called Law’s texture filter, to be used in this context for the first time. The 18F-FDG PET images of 42 patients with NSCLC were evaluated. The number of patients for each tumor stage, i.e., I-II, III or IV, was 14. The patients had ~45% adenocarcinoma (ADC) and ~55% squamous cell carcinoma (SqCCs). MATLAB technical computing language was employed in the extraction of 51 features by using first order statistics (FOS), gray-level co-occurrence matrix (GLCM), gray-level run-length matrix (GLRLM), and Laws’ texture filters. The feature selection method employed was the sequential forward selection (SFS). Selected textural features were used in the automatic classification by k-nearest neighbors (k-NN) and support vector machines (SVM). In the automatic classification of tumor stage, the accuracy was approximately 59.5% with k-NN classifier (k=3) and 69% with SVM (with one versus one paradigm), using 5 features. In the automatic classification of tumor subtype, the accuracy was around 92.7% with SVM one vs. one. Texture analysis of FDG-PET images might be used, in addition to metabolic parameters as an objective tool to assess tumor histopathological characteristics and in automatic classification of tumor stage and subtype.

Keywords: Cancer stage, cancer cell type, non-small cell lung carcinoma, PET, texture analysis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 977

Authors: Nachawit Tikul

Abstract:

This study aimed to determine low-income housing adaptations for flooding, which causes living problems and housing damage, and the results from improvement. Three low-income settlements in Chiang Mai which experienced different flood types, i.e. flash floods in Samukeepattana, drainage floods in Bansanku, and river floods in Kampangam, were chosen for the study. Almost all of the residents improved their houses to protect the property from flood damage by changing building materials to flood damage resistant materials for walls, floors, and other parts of the structure that were below the base of annual flood elevation. They could only build some parts of their own homes, so hiring skilled workers or contractors was still important. Building materials which have no need for any special tools and are easy to access and use for construction, as well as low cost, are selected for construction. The residents in the three slums faced living problems for only a short time and were able to cope with them. This may be due to the location of the three slums near the city where assistance is readily available. But the housing and the existence in the slums can endure only the regular floods and residence still have problems in unusual floods, which have been experienced 1-2 times during the past 10 years. The residents accept the need for evacuations and prepare for them. When faced with extreme floods, residence have evacuated to the nearest safe place such as schools and public building, and come back to repair the houses after the flood. These are the distinguishing characteristics of low-income living which can withstand serious situations due to the simple lifestyle. Therefore, preparation of living areas for use during severe floods and encouraging production of affordable flood resistant materials should be areas of concern when formulating disaster assistance policies for low income people.

Keywords: Flooding, low-income settlement, housing, adaptation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1114

Authors: I. Kurashvili, G. Darsavelidze, T. Kimeridze, G. Chubinidze, I. Tabatadze

Abstract:

At present, a number of modern semiconductor devices based on SiGe alloys have been created in which the latest achievements of high technologies are used. These devices might cause significant changes to networking, computing, and space technology. In the nearest future new materials based on SiGe will be able to restrict the A³B⁵ and Si technologies and firmly establish themselves in medium frequency electronics. Effective realization of these prospects requires the solution of prediction and controlling of structural state and dynamical physical –mechanical properties of new SiGe materials. Based on these circumstances, a complex investigation of structural defects and structural-sensitive dynamic mechanical characteristics of SiGe alloys under different external impacts (deformation, radiation, thermal cycling) acquires great importance. Internal friction (IF) and shear modulus temperature and amplitude dependences of the monocrystalline boron-doped Si_1-xGe_x(x≤0.05) alloys grown by Czochralski technique is studied in initial and ⁶⁰Co gamma-irradiated states. In the initial samples, a set of dislocation origin relaxation processes and accompanying modulus defects are revealed in a temperature interval of 400-800 ⁰C. It is shown that after gamma-irradiation intensity of relaxation internal friction in the vicinity of 280 ⁰C increases and simultaneously activation parameters of high temperature relaxation processes reveal clear rising. It is proposed that these changes of dynamical mechanical characteristics might be caused by a decrease of the dislocation mobility in the Cottrell atmosphere enriched by the radiation defects.

Keywords: Gamma-irradiation, internal friction, shear modulus, SiGe alloys.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 624

Authors: Reeta Devi, Hitender Kumar Tyagi, Dinesh Kumar

Abstract:

In present scenario, cardiovascular problems are growing challenge for researchers and physiologists. As heart disease have no geographic, gender or socioeconomic specific reasons; detecting cardiac irregularities at early stage followed by quick and correct treatment is very important. Electrocardiogram is the finest tool for continuous monitoring of heart activity. Heart rate variability (HRV) is used to measure naturally occurring oscillations between consecutive cardiac cycles. Analysis of this variability is carried out using time domain, frequency domain and non-linear parameters. This paper presents HRV analysis of the online dataset for normal sinus rhythm (taken as healthy subject) and sudden cardiac death (SCD subject) using all three methods computing values for parameters like standard deviation of node to node intervals (SDNN), square root of mean of the sequences of difference between adjacent RR intervals (RMSSD), mean of R to R intervals (mean RR) in time domain, very low-frequency (VLF), low-frequency (LF), high frequency (HF) and ratio of low to high frequency (LF/HF ratio) in frequency domain and Poincare plot for non linear analysis. To differentiate HRV of healthy subject from subject died with SCD, k –nearest neighbor (k-NN) classifier has been used because of its high accuracy. Results show highly reduced values for all stated parameters for SCD subjects as compared to healthy ones. As the dataset used for SCD patients is recording of their ECG signal one hour prior to their death, it is therefore, verified with an accuracy of 95% that proposed algorithm can identify mortality risk of a patient one hour before its death. The identification of a patient’s mortality risk at such an early stage may prevent him/her meeting sudden death if in-time and right treatment is given by the doctor.

Keywords: Early stage prediction, heart rate variability, linear and non linear analysis, sudden cardiac death.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1805

Authors: Addin Osman, Anwar Ali Yahya, Mohammed Basit Kamal

Abstract:

Datasets or collections are becoming important assets by themselves and now they can be accepted as a primary intellectual output of a research. The quality and usage of the datasets depend mainly on the context under which they have been collected, processed, analyzed, validated, and interpreted. This paper aims to present a collection of program educational objectives mapped to student’s outcomes collected from self-study reports prepared by 32 engineering programs accredited by ABET. The manual mapping (classification) of this data is a notoriously tedious, time consuming process. In addition, it requires experts in the area, which are mostly not available. It has been shown the operational settings under which the collection has been produced. The collection has been cleansed, preprocessed, some features have been selected and preliminary exploratory data analysis has been performed so as to illustrate the properties and usefulness of the collection. At the end, the collection has been benchmarked using nine of the most widely used supervised multiclass classification techniques (Binary Relevance, Label Powerset, Classifier Chains, Pruned Sets, Random k-label sets, Ensemble of Classifier Chains, Ensemble of Pruned Sets, Multi-Label k-Nearest Neighbors and Back-Propagation Multi-Label Learning). The techniques have been compared to each other using five well-known measurements (Accuracy, Hamming Loss, Micro-F, Macro-F, and Macro-F). The Ensemble of Classifier Chains and Ensemble of Pruned Sets have achieved encouraging performance compared to other experimented multi-label classification methods. The Classifier Chains method has shown the worst performance. To recap, the benchmark has achieved promising results by utilizing preliminary exploratory data analysis performed on the collection, proposing new trends for research and providing a baseline for future studies.

Keywords: Benchmark collection, program educational objectives, student outcomes, ABET, Accreditation, machine learning, supervised multiclass classification, text mining.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 837

Authors: Murray L. Ireland, Kevin J. Worrall, Rebecca Mackenzie, Thaleia Flessa, Euan McGookin, Douglas Thomson

Abstract:

Robotic rovers which are designed to work in extra-terrestrial environments present a unique challenge in terms of the reliability and availability of systems throughout the mission. Should some fault occur, with the nearest human potentially millions of kilometres away, detection and identification of the fault must be performed solely by the robot and its subsystems. Faults in the system sensors are relatively straightforward to detect, through the residuals produced by comparison of the system output with that of a simple model. However, faults in the input, that is, the actuators of the system, are harder to detect. A step change in the input signal, caused potentially by the loss of an actuator, can propagate through the system, resulting in complex residuals in multiple outputs. These residuals can be difficult to isolate or distinguish from residuals caused by environmental disturbances. While a more complex fault detection method or additional sensors could be used to solve these issues, an alternative is presented here. Using inverse simulation (InvSim), the inputs and outputs of the mathematical model of the rover system are reversed. Thus, for a desired trajectory, the corresponding actuator inputs are obtained. A step fault near the input then manifests itself as a step change in the residual between the system inputs and the input trajectory obtained through inverse simulation. This approach avoids the need for additional hardware on a mass- and power-critical system such as the rover. The InvSim fault detection method is applied to a simple four-wheeled rover in simulation. Additive system faults and an external disturbance force and are applied to the vehicle in turn, such that the dynamic response and sensor output of the rover are impacted. Basic model-based fault detection is then employed to provide output residuals which may be analysed to provide information on the fault/disturbance. InvSim-based fault detection is then employed, similarly providing input residuals which provide further information on the fault/disturbance. The input residuals are shown to provide clearer information on the location and magnitude of an input fault than the output residuals. Additionally, they can allow faults to be more clearly discriminated from environmental disturbances.

Keywords: Fault detection, inverse simulation, rover, ground robot.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 946

Authors: G. Henini, Y. Laidani, F. Souahi, A. Labbaci, S. Hanini

Abstract:

Environmental contamination is a major problem being faced by the society today. Industrial, agricultural, and domestic wastes, due to the rapid development in the technology, are discharged in the several receivers. Generally, this discharge is directed to the nearest water sources such as rivers, lakes, and seas. While the rates of development and waste production are not likely to diminish, efforts to control and dispose of wastes are appropriately rising. Wastewaters from textile industries represent a serious problem all over the world. They contain different types of synthetic dyes which are known to be a major source of environmental pollution in terms of both the volume of dye discharged and the effluent composition. From an environmental point of view, the removal of synthetic dyes is of great concern. Among several chemical and physical methods, adsorption is a promising technique due to the ease of use and low cost compared to other applications in the process of discoloration, especially if the adsorbent is inexpensive and readily available. The focus of the present study was to assess the potentiality of Brahea edulis (BE) for the removal of synthetic dye Yellow bemacid (YB) from aqueous solutions. The results obtained here may transfer to other dyes with a similar chemical structure. Biosorption studies were carried out under various parameters such as mass adsorbent particle, pH, contact time, initial dye concentration, and temperature. The biosorption kinetic data of the material (BE) was tested by the pseudo first-order and the pseudo-second-order kinetic models. Thermodynamic parameters including the Gibbs free energy ΔG, enthalpy ΔH, and entropy ΔS have revealed that the adsorption of YB on the BE is feasible, spontaneous, and endothermic. The equilibrium data were analyzed by using Langmuir, Freundlich, Elovich, and Temkin isotherm models. The experimental results show that the percentage of biosorption increases with an increase in the biosorbent mass (0.25 g: 12 mg/g; 1.5 g: 47.44 mg/g). The maximum biosorption occurred at around pH value of 2 for the YB. The equilibrium uptake was increased with an increase in the initial dye concentration in solution (C_o = 120 mg/l; q = 35.97 mg/g). Biosorption kinetic data were properly fitted with the pseudo-second-order kinetic model. The best fit was obtained by the Langmuir model with high correlation coefficient (R² > 0.998) and a maximum monolayer adsorption capacity of 35.97 mg/g for YB.

Keywords: Adsorption, Brahea edulis, isotherm, yellow bemacid.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1275

Authors: E. Dabbour, S. M. Easa

Abstract:

Most of the collision warning systems currently available in the automotive market are mainly designed to warn against imminent rear-end and lane-changing collisions. No collision warning system is commercially available to warn against imminent turning collisions at intersections, especially for left-turn collisions when a driver attempts to make a left-turn at either a signalized or non-signalized intersection, conflicting with the path of other approaching vehicles traveling on the opposite-direction traffic stream. One of the major factors that lead to left-turn collisions is the human error and misjudgment of the driver of the turning vehicle when perceiving the speed and acceleration of other vehicles traveling on the opposite-direction traffic stream; therefore, using a properly-designed collision warning system will likely reduce, or even eliminate, this type of collisions by reducing human error. This paper introduces perceptual framework for a proposed collision warning system that can detect imminent left-turn collisions at intersections. The system utilizes a commercially-available detection sensor (either a radar sensor or a laser detector) to detect approaching vehicles traveling on the opposite-direction traffic stream and calculate their speeds and acceleration rates to estimate the time-tocollision and compare that time to the time required for the turning vehicle to clear the intersection. When calculating the time required for the turning vehicle to clear the intersection, consideration is given to the perception-reaction time of the driver of the turning vehicle, which is the time required by the driver to perceive the message given by the warning system and react to it by engaging the throttle. A regression model was developed to estimate perception-reaction time based on age and gender of the driver of the host vehicle. Desired acceleration rate selected by the driver of the turning vehicle, when making the left-turn movement, is another human factor that is considered by the system. Another regression model was developed to estimate the acceleration rate selected by the driver of the turning vehicle based on driver-s age and gender as well as on the location and speed of the nearest approaching vehicle along with the maximum acceleration rate provided by the mechanical characteristics of the turning vehicle. By comparing time-to-collision with the time required for the turning vehicle to clear the intersection, the system displays a message to the driver of the turning vehicle when departure is safe. An application example is provided to illustrate the logic algorithm of the proposed system.

Keywords: Collision warning systems, intelligent transportationsystems, vehicle safety.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2055

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 APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1174

Authors: Mohammad H. Taheri, David J. Brown, Nasser Sherkat

Abstract:

Engagement is one of the most important factors in determining successful outcomes and deep learning in students. Existing approaches to detect student engagement involve periodic human observations that are subject to inter-rater reliability. Our solution uses real-time multimodal multisensor data labeled by objective performance outcomes to infer the engagement of students. The study involves four students with a combined diagnosis of cerebral palsy and a learning disability who took part in a 3-month trial over 59 sessions. Multimodal multisensor data were collected while they participated in a continuous performance test. Eye gaze, electroencephalogram, body pose, and interaction data were used to create a model of student engagement through objective labeling from the continuous performance test outcomes. In order to achieve this, a type of continuous performance test is introduced, the Seek-X type. Nine features were extracted including high-level handpicked compound features. Using leave-one-out cross-validation, a series of different machine learning approaches were evaluated. Overall, the random forest classification approach achieved the best classification results. Using random forest, 93.3% classification for engagement and 42.9% accuracy for disengagement were achieved. We compared these results to outcomes from different models: AdaBoost, decision tree, k-Nearest Neighbor, naïve Bayes, neural network, and support vector machine. We showed that using a multisensor approach achieved higher accuracy than using features from any reduced set of sensors. We found that using high-level handpicked features can improve the classification accuracy in every sensor mode. Our approach is robust to both sensor fallout and occlusions. The single most important sensor feature to the classification of engagement and distraction was shown to be eye gaze. It has been shown that we can accurately predict the level of engagement of students with learning disabilities in a real-time approach that is not subject to inter-rater reliability, human observation or reliant on a single mode of sensor input. This will help teachers design interventions for a heterogeneous group of students, where teachers cannot possibly attend to each of their individual needs. Our approach can be used to identify those with the greatest learning challenges so that all students are supported to reach their full potential.

Keywords: Affective computing in education, affect detection, continuous performance test, engagement, flow, HCI, interaction, learning disabilities, machine learning, multimodal, multisensor, physiological sensors, Signal Detection Theory, student engagement.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1262