To see the other types of publications on this topic, follow the link: Learner state estimation.
Journal articles on the topic 'Learner state estimation'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Learner state estimation.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Ohmoto, Yoshimasa, Shigen Shimojo, Junya Morita, and Yugo Hayashi. "Estimation of ICAP States Based on Interaction Data During Collaborative Learning." Journal of Educational Data Mining 16, no. 2 (2024): 149–76. https://doi.org/10.5281/zenodo.14283893.
Full textAbstract:
The primary goal of this study is to investigate a method for estimating the state of learners in the near future using nonverbal information used in multimodal interaction as cues to provide adaptive support in collaborative learning. We used interactive-constructive-active-passive (ICAP) theory to classify learners' states in collaborative learning. We attempted to determine whether a learner’s ICAP state was passive based on multimodal data obtained during a collaborative concept-map task. We conducted an experiment on collaborative learning among learners and acquired data on conversational type, the results of learning performance (pre- and post-tests), utterances, facial expressions, gaze, and voice during the experiment. We conducted two analyses. One was sequential pattern mining, to obtain clues for predicting the participants' state after 5 seconds. The other was a support vector machine to try to classify the participants' state based on the obtained clues. We found several candidates that could be used for learner-state estimation in the near future. The learner-state estimation using multimodal information yielded higher than 70% accuracy. In contrast, there were differences in the ease of estimating each pair's learning state. It appears that capturing the characteristics of interactions in collaborative learning for each pair is necessary for a more accurate estimation of the learners' state.
2
Cai, Bingzi, Mutian Li, Huawei Yang, Chunsheng Wang, and Yougen Chen. "State of Charge Estimation of Lithium-Ion Battery Based on Back Propagation Neural Network and AdaBoost Algorithm." Energies 16, no. 23 (2023): 7824. http://dx.doi.org/10.3390/en16237824.
Full textAbstract:
The accurate estimation of the state of charge (SOC) of lithium-ion batteries is critical in battery energy storage systems. This paper introduces a novel approach, the AdaBoost–BPNN model, to overcome the limitations of traditional data-driven estimation methods, such as a low estimation accuracy and poor generalization ability. The proposed model employs a back propagation neural network (BPNN) for the preliminary estimation. Subsequently, an AdaBoost–BPNN model is developed as a strong learner using the AdaBoost integration algorithm. Each BPNN sub-model serves as a weak learner within the AdaBoost framework. The final output of the strong learner is obtained by combining the individual outputs from the weak learners using weighting factors. This adaptive adjustment of weighting factors enhances the accuracy of SOC estimation. The proposed SOC estimation algorithm is evaluated and validated through experimental analysis. Throughout the paper, theoretical analysis is conducted, and the proposed AdaBoost–BPNN model is validated and verified using experimental results. The results demonstrate that the AdaBoost–BPNN model outperforms traditional methods in accurately estimating SOC under various conditions, including constant current-constant voltage (CCCV) charging, dynamical stress testing (DST), US06, a federal urban driving schedule (FUDS), and pulse discharge conditions.
3
Okawa, Kohei, Felix Jimenez, Shuichi Akizuki, and Tomohiro Yoshikawa. "Proposal of Learning Support Model for Teacher-Type Robot Supporting Learning According to Learner’s Perplexed Facial Expressions." Journal of Robotics and Mechatronics 36, no. 1 (2024): 168–80. http://dx.doi.org/10.20965/jrm.2024.p0168.
Full textAbstract:
The introduction of ICT into education in educational settings has become increasingly common. Among these, the research and development of educational support robots have attracted attention. Conventional robots provide academic support through button operation by the learner. However, it has been reported that excessive requests for academic support can be problematic in environments in which learners can freely request academic support. To solve this problem, we developed a perplexion estimation method that estimates the state of perplexion from the learner’s facial expression. When educational support is provided using the proposed method, the robot can autonomously provide academic support. Simulation experiments demonstrated that the perplexion estimation method has the potential to accurately estimate the learner’s state. However, there is still no dedicated model for educational support robots that utilizes the perplexion estimation method. Therefore, this paper proposes an apprenticeship promotion model that integrates a learning support method based on cognitive apprenticeship theory and our perplexion estimation method. We then verified the learning effects of the robot equipped with the proposed model on the learner through participant experiments. The experimental results suggest that the robot equipped with the proposed model not only provides the same learning effect to university students as a conventional robot, but also can autonomously provide academic support at the optimal timing.
4
Li, Ran, Hui Sun, Xue Wei, Weiwen Ta, and Haiying Wang. "Lithium Battery State-of-Charge Estimation Based on AdaBoost.Rt-RNN." Energies 15, no. 16 (2022): 6056. http://dx.doi.org/10.3390/en15166056.
Full textAbstract:
Real-time and accurate state-of-charge estimation performs an important role in the smooth operation of various electric vehicle battery management systems. Neural network theory represents one of the most effective and commonly used methods of SOC prediction. However, traditional neural network methods are disadvantaged by such issues as the limited range of application, limited generalization ability, and low accuracy, which makes it difficult to meet the increasing safety requirements on electric vehicles. In view of these problems, an ensemble learning algorithm based on the AdaBoost.Rt is proposed in this paper. AdaBoost.Rt recurrent neural network model is purposed to ensure the accurate prediction of lithium battery SOC. Relying on a chain-connected recurrent neural network model, this method enables the correlation adaptability of sample data in the spatio-temporal dimension. The ensemble learning method was adopted to devise a method of multi-RNN model integration, with the RNN model as the base learner, thus constructing the AdaBoost.Rt-RNN strong learner model. According to the results of simulation and experimental comparisons, the integrated algorithm proposed in this paper is applicable to improve the accuracy of SOC prediction and the generalization performance of the model.
5
Autenrieth, Maximilian, Richard A. Levine, Juanjuan Fan, and Maureen A. Guarcello. "Stacked Ensemble Learning for Propensity Score Methods in Observational Studies." Journal of Educational Data Mining 13, no. 1 (2021): 24–189. https://doi.org/10.5281/zenodo.5048425.
Full textAbstract:
Propensity score methods account for selection bias in observational studies. However, the consistency of the propensity score estimators strongly depends on a correct specification of the propensity score model. Logistic regression and, with increasing popularity, machine learning tools are used to estimate propensity scores. We introduce a stacked generalization ensemble learning approach to improve propensity score estimation by fitting a meta learner on the predictions of a suitable set of diverse base learners. We perform a comprehensive Monte Carlo simulation study, implementing a broad range of scenarios that mimic characteristics of typical data sets in educational studies. The population average treatment effect is estimated using the propensity score in Inverse Probability of Treatment Weighting. Our proposed stacked ensembles, especially using gradient boosting machines as a meta learner trained on a set of 12 base learner predictions, led to superior reduction of bias compared to the current state-of-the-art in propensity score estimation. Further, our simulations imply that commonly used balance measures (averaged standardized absolute mean differences) might be misleading as propensity score model selection criteria. We apply our proposed model - which we call GBM-Stack - to assess the population average treatment effect of a Supplemental Instruction (SI) program in an introductory psychology (PSY 101) course at San Diego State University. Our analysis provides evidence that moving the whole population to SI attendance would on average lead to 1.69 times higher odds to pass the PSY 101 class compared to not offering SI, with a 95% bootstrap confidence interval of (1.31, 2.20).
6
Feng, Hailin, and Lu Zhang. "A heterogeneous learner fusion method with supplementary feature for lithium-ion batteries state of health estimation." Journal of Energy Storage 92 (July 2024): 111896. http://dx.doi.org/10.1016/j.est.2024.111896.
Full text
7
Li, Ran, Pengdong Liu, Kexin Li, and Xiaoyu Zhang. "AdaBoost.Rt-LSTM Based Joint SOC and SOH Estimation Method for Retired Batteries." Batteries 9, no. 8 (2023): 425. http://dx.doi.org/10.3390/batteries9080425.
Full textAbstract:
Achieving accurate retired battery state of health (SOH) and state of charge (SOC) estimation is a safe prerequisite for securing the battery secondary utilization and thus effectively improving the energy utilization efficiency. The data-driven approach is efficient and accurate, and does not rely on accurate battery models, which is a hot direction in battery state estimation research. However, the huge number of retired batteries and obvious consistency differences bring bottleneck problems such as long learning time and low model updating efficiency to the traditional data-driven algorithm. In view of this, this paper proposes an integrated learning algorithm based on AdaBoost. Rt-LSTM to realize the joint estimation of SOC and SOH of retired lithium batteries, which relies on the LSTM neural network model and completes the correlation adaption in the spatio-temporal dimension of the whole life cycle sample data. The LSTM model is used as the base learner to construct the AdaBoost. Rt-LSTM strong learning model. The LSTM weak predictor is combined with weights to form a strong predictor, which greatly solves the problem of low accuracy of state estimation due to the large number and variability of retired batteries. Simulation and experimental comparison show that the integrated algorithm proposed in this paper is suitable for improving the SOC and SOH prediction accuracy and the generalization performance of the model.
8
Victor, Crallet, Salehe Mrutu, and Alloys Mvuma. "A Multitask Learning Framework for Pilot Decontamination in 5G Massive MIMO." Tanzania Journal of Engineering and Technology 42, no. 3 (2023): 78–88. http://dx.doi.org/10.52339/tjet.v42i3.910.
Full textAbstract:
Reference signals enable the acquisition of channel state information (CSI) for purposes such as channel estimation, beam selection, precoding, and symbol detection in 5G massive multiple-input multipleoutput (MAMIMO) systems. Eventually, as more and more users and cells are added, orthogonal reference signals become few which leads to pilot contamination. Pilot contamination limits the performance and occurs when non-orthogonal reference signals occupy time-frequency resources that are alike. Learning-based techniques have been proposed to alleviate it. However, each can only learn to perform a single task namely pilot assignment, power allocation, pilot design, or de-noising for pilot decontamination. In addition, each learner can only be successful if postulated conditions are met. This study proposes a multitask learning framework that can be trained to dynamically select from the multitude of deep learning models which have been suggested for pilot decontamination. Under all signal-to-noise (SNR) ratios, experiments conducted on the deep residual learning aided channel estimator using the multitask learning framework showed minimum channel estimation errors compared to single-task learning.
9
Jamshidpour, Nasehe, Abdolreza Safari, and Saeid Homayouni. "A GA-Based Multi-View, Multi-Learner Active Learning Framework for Hyperspectral Image Classification." Remote Sensing 12, no. 2 (2020): 297. http://dx.doi.org/10.3390/rs12020297.
Full textAbstract:
This paper introduces a novel multi-view multi-learner (MVML) active learning method, in which the different views are generated by a genetic algorithm (GA). The GA-based view generation method attempts to construct diverse, sufficient, and independent views by considering both inter- and intra-view confidences. Hyperspectral data inherently owns high dimensionality, which makes it suitable for multi-view learning algorithms. Furthermore, by employing multiple learners at each view, a more accurate estimation of the underlying data distribution can be obtained. We also implemented a spectral-spatial graph-based semi-supervised learning (SSL) method as the classifier, which improved the performance of the classification task in comparison with supervised learning. The evaluation of the proposed method was based on three different benchmark hyperspectral data sets. The results were also compared with other state-of-the-art AL-SSL methods. The experimental results demonstrated the efficiency and statistically significant superiority of the proposed method. The GA-MVML AL method improved the classification performances by 16.68%, 18.37%, and 15.1% for different data sets after 40 iterations.
10
Wu, Renzhi, Bolin Ding, Xu Chu, et al. "Learning to be a statistician." Proceedings of the VLDB Endowment 15, no. 2 (2021): 272–84. http://dx.doi.org/10.14778/3489496.3489508.
Full textAbstract:
Estimating the number of distinct values (NDV) in a column is useful for many tasks in database systems, such as columnstore compression and data profiling. In this work, we focus on how to derive accurate NDV estimations from random (online/offline) samples. Such efficient estimation is critical for tasks where it is prohibitive to scan the data even once. Existing sample-based estimators typically rely on heuristics or assumptions and do not have robust performance across different datasets as the assumptions on data can easily break. On the other hand, deriving an estimator from a principled formulation such as maximum likelihood estimation is very challenging due to the complex structure of the formulation. We propose to formulate the NDV estimation task in a supervised learning framework, and aim to learn a model as the estimator. To this end, we need to answer several questions: i) how to make the learned model workload agnostic; ii) how to obtain training data; iii) how to perform model training. We derive conditions of the learning framework under which the learned model is workload agnostic , in the sense that the model/estimator can be trained with synthetically generated training data, and then deployed into any data warehouse simply as, e.g. , user-defined functions (UDFs), to offer efficient (within microseconds on CPU) and accurate NDV estimations for unseen tables and workloads. We compare the learned estimator with the state-of-the-art sample-based estimators on nine real-world datasets to demonstrate its superior estimation accuracy. We publish our code for training data generation, model training, and the learned estimator online for reproducibility.
11
Li, Mingxiao, Zehao Wang, Tinne Tuytelaars, and Marie-Francine Moens. "Layout-Aware Dreamer for Embodied Visual Referring Expression Grounding." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 1 (2023): 1386–95. http://dx.doi.org/10.1609/aaai.v37i1.25223.
Full textAbstract:
In this work, we study the problem of Embodied Referring Expression Grounding, where an agent needs to navigate in a previously unseen environment and localize a remote object described by a concise high-level natural language instruction. When facing such a situation, a human tends to imagine what the destination may look like and to explore the environment based on prior knowledge of the environmental layout, such as the fact that a bathroom is more likely to be found near a bedroom than a kitchen. We have designed an autonomous agent called Layout-aware Dreamer (LAD), including two novel modules, that is, the Layout Learner and the Goal Dreamer to mimic this cognitive decision process. The Layout Learner learns to infer the room category distribution of neighboring unexplored areas along the path for coarse layout estimation, which effectively introduces layout common sense of room-to-room transitions to our agent. To learn an effective exploration of the environment, the Goal Dreamer imagines the destination beforehand. Our agent achieves new state-of-the-art performance on the public leaderboard of REVERIE dataset in challenging unseen test environments with improvement on navigation success rate (SR) by 4.02% and remote grounding success (RGS) by 3.43% comparing to previous previous state of the art. The code is released at https://github.com/zehao-wang/LAD.
12
Cheng, Qian, Honggang Xu, Shuaipeng Fei, Zongpeng Li, and Zhen Chen. "Estimation of Maize LAI Using Ensemble Learning and UAV Multispectral Imagery under Different Water and Fertilizer Treatments." Agriculture 12, no. 8 (2022): 1267. http://dx.doi.org/10.3390/agriculture12081267.
Full textAbstract:
The leaf area index (LAI), commonly used as an indicator of crop growth and physiological development, is mainly influenced by the degree of water and fertilizer stress. Accurate assessment of the LAI can help to understand the state of crop water and fertilizer deficit, which is important for crop management and the precision agriculture. The objective of this study is to evaluate the unmanned aerial vehicle (UAV)-based multispectral imaging to estimate the LAI of maize under different water and fertilizer stress conditions. For this, multispectral imagery of the field was conducted at different growth stages (jointing, trumpet, silking and flowering) of maize under three water treatments and five fertilizer treatments. Subsequently, a stacking ensemble learning model was built with Gaussian process regression (GPR), support vector regression (SVR), random forest (RF), least absolute shrinkage and selection operator (Lasso) and cubist regression as primary learners to predict the LAI using UAV-based vegetation indices (VIs) and ground truth data. Results showed that the LAI was influenced significantly by water and fertilizer stress in both years’ experiments. Multispectral VIs were significantly correlated with maize LAI at multiple growth stages. The Pearson correlation coefficients between UAV-based VIs and ground truth LAI ranged from 0.64 to 0.89. Furthermore, the fusion of multiple stage data showed that the correlations were significantly higher between ground truth LAI and UAV-based VIs than that of single growth stage data. The ensemble learning algorithm with MLR as the secondary learner outperformed as a single machine learning algorithm with high prediction accuracy R2 = 0.967 and RMSE = 0.198 in 2020, and R2 = 0.897 and RMSE = 0.220 in 2021. We believe that the ensemble learning algorithm based on stacking is preferable to the single machine learning algorithm to build the LAI prediction model. This study can provide certain theoretical guidance for the rapid and precise management of water and fertilizer for large experimental fields.
13
Wei, Lei, Zhe Cheng, Junsheng Cheng, Niaoqing Hu, and Yi Yang. "A Fault Detection Method Based on an Oil Temperature Forecasting Model Using an Improved Deep Deterministic Policy Gradient Algorithm in the Helicopter Gearbox." Entropy 24, no. 10 (2022): 1394. http://dx.doi.org/10.3390/e24101394.
Full textAbstract:
The main gearbox is very important for the operation safety of helicopters, and the oil temperature reflects the health degree of the gearbox; therefore establishing an accurate oil temperature forecasting model is an important step for reliable fault detection. Firstly, in order to achieve accurate gearbox oil temperature forecasting, an improved deep deterministic policy gradient algorithm with a CNN–LSTM basic learner is proposed, which can excavate the complex relationship between oil temperature and working condition. Secondly, a reward incentive function is designed to accelerate the training time costs and to stabilize the model. Further, a variable variance exploration strategy is proposed to enable the agents of the model to fully explore the state space in the early training stage and to gradually converge in the training later stage. Thirdly, a multi-critics network structure is adopted to solve the problem of inaccurate Q-value estimation, which is the key to improving the prediction accuracy of the model. Finally, KDE is introduced to determine the fault threshold to judge whether the residual error is abnormal after EWMA processing. The experimental results show that the proposed model achieves higher prediction accuracy and shorter fault detection time costs.
14
Khattak, Afaq, Hamad Almujibah, Ahmed Elamary, and Caroline Mongina Matara. "Interpretable Dynamic Ensemble Selection Approach for the Prediction of Road Traffic Injury Severity: A Case Study of Pakistan’s National Highway N-5." Sustainability 14, no. 19 (2022): 12340. http://dx.doi.org/10.3390/su141912340.
Full textAbstract:
Road traffic accidents are among the top ten major causes of fatalities in the world, taking millions of lives annually. Machine-learning ensemble classifiers have been frequently used for the prediction of traffic injury severity. However, their inability to comprehend complex models due to their “black box” nature may lead to unrealistic traffic safety judgments. First, in this research, we propose three state-of-the-art Dynamic Ensemble Learning (DES) algorithms including Meta-Learning for Dynamic Ensemble Selection (META-DES), K-Nearest Oracle Elimination (KNORAE), and Dynamic Ensemble Selection Performance (DES-P), with Random Forest (RF), Adaptive Boosting (AdaBoost), Classification and Regression Tree (CART), and Binary Logistic Regression (BLR) as the base learners. The DES algorithm automatically chooses the subset of classifiers most likely to perform well for each new test instance to be classified when generating a prediction, making it more efficient and flexible. The META-DES model using RF as the base learner outperforms other models with accuracy (75%), recall (69%), precision (71%), and F1-score (72%). Afterwards, the risk factors are analyzed with SHapley Additive exPlanations (SHAP). The driver’s age, month of the year, day of the week, and vehicle type influence SHAP estimation the most. Young drivers are at a heightened risk of fatal accidents. Weekends and summer months see the most fatal injuries. The proposed novel META-DES-RF algorithm with SHAP for predicting injury severity may be of interest to traffic safety researchers.
15
Liu, Jie, Wenqian Dong, Qingqing Zhou, and Dong Li. "Fauce." Proceedings of the VLDB Endowment 14, no. 11 (2021): 1950–63. http://dx.doi.org/10.14778/3476249.3476254.
Full textAbstract:
Cardinality estimation is a fundamental and critical problem in databases. Recently, many estimators based on deep learning have been proposed to solve this problem and they have achieved promising results. However, these estimators struggle to provide accurate results for complex queries, due to not capturing real inter-column and inter-table correlations. Furthermore, none of these estimators contain the uncertainty information about their estimations. In this paper, we present a join cardinality estimator called Fauce. Fauce learns the correlations across all columns and all tables in the database. It also contains the uncertainty information of each estimation. Among all studied learned estimators, our results are promising: (1) Fauce is a light-weight estimator, it has 10× faster inference speed than the state of the art estimator; (2) Fauce is robust to the complex queries, it provides 1.3×--6.7× smaller estimation errors for complex queries compared with the state of the art estimator; (3) To the best of our knowledge, Fauce is the first estimator that incorporates uncertainty information for cardinality estimation into a deep learning model.
16
Ramasamy, Saravanakumar, Koperundevi Ganesan, and Venkadesan Arunachalam. "Power Flow Parameter Estimation in Power System Using Machine Learning Techniques Under Varying Load Conditions." International Journal of Electrical and Electronics Research 10, no. 4 (2022): 1299–305. http://dx.doi.org/10.37391/ijeer.100484.
Full textAbstract:
In power transmission network state estimation is more complex and the measurements are critical in nature. Estimation of power flow parameters such as voltage magnitude and phasor angle in a power system is challenging when the loads are varying. The objective of the work is to estimate the voltage magnitude and phase angle using machine learning techniques. Some of the Machine learning techniques are decision trees (DT), support vector machines (SVM), ensemble boost (E-Boost), ensemble bags (E-bag), and artificial neural networks (ANN) are proposed in this work. Among these methods, the best machine learning techniques are selected for this study based on performance metrics. Performance metrics are Mean Square Error (MSE), Mean Absolute Error (MAE), and Root Mean Square Error (RMSE). Neural network produces minimum error when compared to other ML Techniques. Among three Performance Metrics MSE provides minimum error and is used to predict the exact model in this work. Therefore, it is concluded that the neural network can predict voltage and angle accurately under various load conditions in the power system effectively. Neural Network (NN) is applied to different load condition, and performance metrics are computed. To validate the proposed work, IEEE 14 and IEEE 30 bus systems are considered. The predicted value is compared to the actual value for all the load variation and residues are measured. The regression learner software in MATLAB is used to implement ML approaches in this work. The Outcome of this proposed work is used in phasor measurement units. The predicted value of voltage and angle using a neural network can be used to minimize the voltage magnitude and phase angle error in phasor Measurement Units (PMU).
17
Liu, Zehao, Yishan Ji, Xiuxiu Ya, et al. "Ensemble Learning for Pea Yield Estimation Using Unmanned Aerial Vehicles, Red Green Blue, and Multispectral Imagery." Drones 8, no. 6 (2024): 227. http://dx.doi.org/10.3390/drones8060227.
Full textAbstract:
Peas are one of the most important cultivated legumes worldwide, for which early yield estimations are helpful for agricultural planning. The unmanned aerial vehicles (UAVs) have become widely used for crop yield estimations, owing to their operational convenience. In this study, three types of sensor data (red green blue [RGB], multispectral [MS], and a fusion of RGB and MS) across five growth stages were applied to estimate pea yield using ensemble learning (EL) and four base learners (Cubist, elastic net [EN], K nearest neighbor [KNN], and random forest [RF]). The results showed the following: (1) the use of fusion data effectively improved the estimation accuracy in all five growth stages compared to the estimations obtained using a single sensor; (2) the mid filling growth stage provided the highest estimation accuracy, with coefficients of determination (R2) reaching up to 0.81, 0.8, 0.58, and 0.77 for the Cubist, EN, KNN, and RF algorithms, respectively; (3) the EL algorithm achieved the best performance in estimating pea yield than base learners; and (4) the different models were satisfactory and applicable for both investigated pea types. These results indicated that the combination of dual-sensor data (RGB + MS) from UAVs and appropriate algorithms can be used to obtain sufficiently accurate pea yield estimations, which could provide valuable insights for agricultural remote sensing research.
18
Xiao, Qinfeng, and Jing Wang. "DRL-SRS: A Deep Reinforcement Learning Approach for Optimizing Spaced Repetition Scheduling." Applied Sciences 14, no. 13 (2024): 5591. http://dx.doi.org/10.3390/app14135591.
Full textAbstract:
Optimizing spaced repetition schedules is of great importance for enhancing long-term memory retention in both real-world applications, e.g., online learning platforms, and academic applications, e.g., cognitive science. Traditional methods tackle this problem by employing handcrafted rules while modern methods try to optimize scheduling using deep reinforcement learning (DRL). Existing DRL-based approaches model the problem by selecting the optimal next item to appear, which implies the learner can only learn one item in a day. However, the most essential point to enhancing long-term memory is to select the optimal interval to review. To this end, we present a novel approach to DRL to optimize spaced repetition scheduling. The contribution of our framework is three-fold. We first introduce a Transformer-based model to estimate the recall probability of a learning item accurately, which encodes the temporal dynamics of a learner’s learning trajectories. Second, we build a simulation environment based on our recall probability estimation model. Third, we utilize the Deep Q-Network (DQN) as the agent to learn the optimal review intervals for learning items and train the policy in a recurrent manner. Experimental results demonstrate that our framework achieves state-of-the-art performance against competing methods. Our method achieves an MAE (mean average error) score of 0.0274 on a memory prediction task, which is 11% lower than the second-best method. For spaced repetition scheduling, our method achieves mean recall probabilities of 0.92, 0.942, and 0.372 in three different environments, the best performance in all scenarios.
19
Tian, Shengjing, Xiuping Liu, Meng Liu, Yuhao Bian, Junbin Gao, and Baocai Yin. "Learning the Incremental Warp for 3D Vehicle Tracking in LiDAR Point Clouds." Remote Sensing 13, no. 14 (2021): 2770. http://dx.doi.org/10.3390/rs13142770.
Full textAbstract:
Object tracking from LiDAR point clouds, which are always incomplete, sparse, and unstructured, plays a crucial role in urban navigation. Some existing methods utilize a learned similarity network for locating the target, immensely limiting the advancements in tracking accuracy. In this study, we leveraged a powerful target discriminator and an accurate state estimator to robustly track target objects in challenging point cloud scenarios. Considering the complex nature of estimating the state, we extended the traditional Lucas and Kanade (LK) algorithm to 3D point cloud tracking. Specifically, we propose a state estimation subnetwork that aims to learn the incremental warp for updating the coarse target state. Moreover, to obtain a coarse state, we present a simple yet efficient discrimination subnetwork. It can project 3D shapes into a more discriminatory latent space by integrating the global feature into each point-wise feature. Experiments on KITTI and PandaSet datasets showed that compared with the most advanced of other methods, our proposed method can achieve significant improvements—in particular, up to 13.68% on KITTI.
20
Li, Yingze, Hongzhi Wang, and Xianglong Liu. "One Seed, Two Birds: A Unified Learned Structure for Exact and Approximate Counting." Proceedings of the ACM on Management of Data 2, no. 1 (2024): 1–26. http://dx.doi.org/10.1145/3639270.
Full textAbstract:
The modern database has many precise and approximate counting requirements. Nevertheless, a solitary multidimensional index or cardinality estimator is insufficient to cater to the escalating demands across all counting scenarios. Such approaches are constrained either by query selectivity or by the compromise between query accuracy and efficiency. We propose CardIndex, a unified learned structure to solve the above problems. CardIndex serves as a versatile solution that not only functions as a multidimensional learned index for accurate counting but also doubles as an adaptive cardinality estimator, catering to varying counting scenarios with diverse requirements for precision and efficiency. Rigorous experimentation has showcased its superiority. Compared to the state-of-the-art (SOTA) autoregressive data-driven cardinality estimation baselines, our structure achieves training and updating times that are two orders of magnitude faster. Additionally, our CPU-based query estimation latency surpasses GPU-based baselines by two to three times. Notably, the estimation accuracy of low-selectivity queries is up to 314 times better than the current SOTA estimator. In terms of indexing tasks, the construction speed of our structure is two orders of magnitude faster than RSMI and 1.9 times faster than R-tree. Furthermore, it exhibits a point query processing speed that is 3%-17% times faster than RSMI and 1.07 to 2.75 times faster than R-tree and KDB-tree. Range queries under specific loads are 20% times faster than the SOTA indexes.
21
Ramalakshmanna, Y., Dr P. Shanmugaraja, Dr P. V. Rama Raju, and Dr T. V. Hymalakshmi. "Adaptive Infinite Impulse Response System Identification Using Elitist Teaching-Learning- Based Optimization Algorithm." International Journal of Circuits, Systems and Signal Processing 17 (March 3, 2023): 1–17. http://dx.doi.org/10.46300/9106.2023.17.1.
Full textAbstract:
Infinite Impulse Response (IIR) systems identification is complicated by traditional learning approaches. When reduced-order adaptive models are utilised for such identification, the performance suffers dramatically. The IIR system is identified as an optimization issue in this study. For system identification challenges, a novel population-based technique known as Elitist teacher learner-based optimization (ETLBO) is used to calculate the best coefficients of unknown infinite impulse response (IIR) systems. The MSE function is minimised and the optimal coefficients of an unknown IIR system are found in the system identification problem. The MSE is the difference between an adaptive IIR system's outputs and an unknown IIR system's outputs. For the unknown system coefficients of the same order and decreased order cases, exhaustive simulations have been performed. In terms of mean square error, convergence speed, and coefficient estimation, the results of actual and reduced-order identification for the standard system using the novel method outperform state-of-the-art techniques. For approximating the same-order and reduced-order IIR systems, four benchmark functions are examined utilizing GA, PSO, CSO, and BA. To demonstrate the improvements, the approach is evaluated on three conventional IIR systems of 2nd, 3rd, and 4th order models. On the basis of computing the mean square error (MSE) and fitness function, the suggested ETLBO approach for system identification is proven to be the best among others. Furthermore, it is confirmed that the suggested ETLBO method outperforms some of the other known system identification strategies. Finally, the efficiency of the dynamic nature of the control parameters of DE, TLBO, and BA in finding near parameter values of unknown systems is demonstrated through comparison data. The simulation results show that the suggested system identification approach outperforms the current methods for system identification.
22
Yamamoto, Sho, Yuto Tobe, Yoshimasa Tawatsuji, and Tsukasa Hirashima. "In-process feedback by detecting deadlock based on EEG data in exercise of learning by problem- posing and its evaluation." Research and Practice in Technology Enhanced Learning 18 (December 28, 2022): 028. http://dx.doi.org/10.58459/rptel.2023.18028.
Full textAbstract:
Feedback on learning activities is one of the most important issues in achieving adaptive learning. In this study, we propose a mechanism for solving this problem by detecting the deadlock state of a learner during a learning activity and providing feedback to eliminate such a state. Feedback on the products of learning activities (we call it “after-process feedback”) has been implemented in numerous interactive and adaptive learning environments. However, feedback during an activity (we call it “in-process feedback”) has rarely been implemented. In-process feedback is considered to be much better than after-process feedback when learners have difficulty or become frustrated with the learning material during the learning process. The difficulty in implementing in-process feedback lies in the timing and content of the feedback. It has been pointed out that the detection of a deadlock must be achieved as early as possible; otherwise, it reduces the learning motivation of the learner. Therefore, we focused on electroencephalograph (EEG) data, which are difficult to cheat and can clearly detect the state of the learner. By combining EEG data with machine learning, we developed a model for detecting when a learner is stuck, allowing us to detect the timing. After that, we generate the proper feedback by estimating the knowledge state of the learner based on the knowledge structure and task response status. We implemented and evaluated the in-process feedback approach in a learning environment posing arithmetic word problems.
23
Suresh, Adithya. "Advanced Ensemble Framework for Diabetes Outcome Forecasting." International Journal for Research in Applied Science and Engineering Technology 12, no. 5 (2024): 3156–63. http://dx.doi.org/10.22214/ijraset.2024.62259.
Full textAbstract:
Abstract: Diabetes is one of the chronic diseases, which is increasing from year to year. Developing an automated system that can detect diabetes patients plays an important role in medical science. A stack classifier model is designed for the detection of diabetes by combining three base estimators such as Random Forest Classifier, LightGBM Classifier, and K-Nearest Neighbors Classifier, and Logistic Regression as meta-classifiers. The data preprocessing includes transforming categorical variables into numerical format. Each base learner is trained on the preprocessed data and predictions are made. In the meta learner stage, Logistic Regression is trained to make predictions based on the predictions of the base learners. The goal of the meta learner is to learn how to combine the predictions of the base learners to make a more accurate final prediction on whether the patient is diabetic or not. The use of a stacking classifier improves prediction accuracy compared to using a single classifier. The developed model gives an accuracy of 98%. The 5-fold cross validation is used to get a more robust estimation of generalization error. Thus, the developed model offers a means to enhance early detection and elevate the quality of care for diabetic patients.
24
Weber, Ben, Michael Mateas, and Arnav Jhala. "A Particle Model for State Estimation in Real-Time Strategy Games." Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment 7, no. 1 (2011): 103–8. http://dx.doi.org/10.1609/aiide.v7i1.12424.
Full textAbstract:
A big challenge for creating human-level game AI is building agents capable of operating in imperfect information environments. In real-time strategy games the technological progress of an opponent and locations of enemy units are partially observable. To overcome this limitation, we explore a particle-based approach for estimating the location of enemy units that have been encountered. We represent state estimation as an optimization problem, and automatically learn parameters for the particle model by mining a corpus of expert StarCraft replays. The particle model tracks opponent units and provides conditions for activating tactical behaviors in our StarCraft bot. Our results show that incorporating a learned particle model improves the performance of EISBot by 10% over baseline approaches.
25
Zeeshan A Rahman and Syed Imran Mehmood. "Learner Competence Across Cognitive Levels In Undergraduate Medical Education: An Item Response Approach." JMMC 14, no. 2 (2024): 76–81. http://dx.doi.org/10.62118/jmmc.v14i2.322.
Full textAbstract:
Objective: The current study endeavors to evaluate competence of learners using item response theory approach in undergraduate medical education. Methodology: The responses of the examinees from first professional year (MBBS) were evaluated for Anatomy discipline to gauge learner competence through knowledge, understanding and application in the subject using item response theory approach (IRT) which is an effective tool to measure the validity (discrimination and difficulty index) of assessment, while KR-20 is used to gauge reliability of the items with statistical software STATA 17. The quality of question and level of examinee responses provide skill level and competence of learners. Results: The current study found that the C1 and C3 level items from the Anatomy discipline are mostly acceptable and effectively gauge learner competence while flawed C2 level items need complete restructuring. The study also identified weak areas of average learner for items in each cognitive level. Conclusion: The study found significant role of IRT in effectively estimating competence of the examinees across cognitive levels for each discipline and in building of an effective test pool through assessment of learner ability and construction of quality SBAs to achieve valid and reliable assessment tool. Keywords: Difficulty index; Discrimination index; Single best answer questions; Cognitive levels; Item characteristic curve.
26
Mi, Jian, and Yasutake Takahashi. "Whole-Body Joint Angle Estimation for Real-Time Humanoid Robot Imitation Based on Gaussian Process Dynamical Model and Particle Filter." Applied Sciences 10, no. 1 (2019): 5. http://dx.doi.org/10.3390/app10010005.
Full textAbstract:
Real-time imitation enables a humanoid robot to mirror the behavior of humans, being important for applications of human–robot interaction. For imitation, the corresponding joint angles of the humanoid robot should be estimated. Generally, a humanoid robot comprises dozens of joints that construct a high-dimensional exploration space for estimating the joint angles. Although a particle filter can estimate the robot state and provides a solution for estimating joint angles, the computational cost becomes prohibitive given the high dimension of the exploration space. Furthermore, a particle filter can only estimate the joint angles accurately using a motion model. To realize accurate joint angle estimation at low computational cost, Gaussian process dynamical models (GPDMs) can be adopted. Specifically, a compact state space can be constructed through the GPDM learning of high-dimensional time-series motion data to obtain a suitable motion model. We propose a GPDM-based particle filter using a compact state space from the learned motion models to realize efficient estimation of joint angles for robot imitation. Simulations and real experiments demonstrate that the proposed method efficiently estimates humanoid robot joint angles at low computational cost, enabling real-time imitation.
27
Li, Bing, Cheng Zheng, Silvio Giancola, and Bernard Ghanem. "SCTN: Sparse Convolution-Transformer Network for Scene Flow Estimation." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 2 (2022): 1254–62. http://dx.doi.org/10.1609/aaai.v36i2.20012.
Full textAbstract:
We propose a novel scene flow estimation approach to capture and infer 3D motions from point clouds. Estimating 3D motions for point clouds is challenging, since a point cloud is unordered and its density is significantly non-uniform. Such unstructured data poses difficulties in matching corresponding points between point clouds, leading to inaccurate flow estimation. We propose a novel architecture named Sparse Convolution-Transformer Network (SCTN) that equips the sparse convolution with the transformer. Specifically, by leveraging the sparse convolution, SCTN transfers irregular point cloud into locally consistent flow features for estimating spatially consistent motions within an object/local object part. We further propose to explicitly learn point relations using a point transformer module, different from exiting methods. We show that the learned relation-based contextual information is rich and helpful for matching corresponding points, benefiting scene flow estimation. In addition, a novel loss function is proposed to adaptively encourage flow consistency according to feature similarity. Extensive experiments demonstrate that our proposed approach achieves a new state of the art in scene flow estimation. Our approach achieves an error of 0.038 and 0.037 (EPE3D) on FlyingThings3D and KITTI Scene Flow respectively, which significantly outperforms previous methods by large margins.
28
Park, Uyeol, Yunho Kang, Haneul Lee, and Seokheon Yun. "A Stacking Heterogeneous Ensemble Learning Method for the Prediction of Building Construction Project Costs." Applied Sciences 12, no. 19 (2022): 9729. http://dx.doi.org/10.3390/app12199729.
Full textAbstract:
The accurate cost estimation of a construction project in the early stage plays a very important role in successfully completing the project. In the initial stage of construction, when the information necessary to predict construction cost is insufficient, a machine learning model using past data can be an alternative. We suggest a two-level stacking heterogeneous ensemble algorithm combining RF, SVM and CatBoosting. In the step of training the base learner, the optimal hyperparameter values of the base learners were determined using Bayesian optimization with cross-validation. Cost information data disclosed by the Public Procurement Service in South Korea are used to evaluate ML algorithms and the proposed stacking-based ensemble model. According to the analysis results, the two-level stacking ensemble model showed better performance than the individual ensemble models.
29
Salman, Sartaj Ahmed, Ali Zakir, and Hiroki Takahashi. "SDFPoseGraphNet: Spatial Deep Feature Pose Graph Network for 2D Hand Pose Estimation." Sensors 23, no. 22 (2023): 9088. http://dx.doi.org/10.3390/s23229088.
Full textAbstract:
In the field of computer vision, hand pose estimation (HPE) has attracted significant attention from researchers, especially in the fields of human–computer interaction (HCI) and virtual reality (VR). Despite advancements in 2D HPE, challenges persist due to hand dynamics and occlusions. Accurate extraction of hand features, such as edges, textures, and unique patterns, is crucial for enhancing HPE. To address these challenges, we propose SDFPoseGraphNet, a novel framework that combines the strengths of the VGG-19 architecture with spatial attention (SA), enabling a more refined extraction of deep feature maps from hand images. By incorporating the Pose Graph Model (PGM), the network adaptively processes these feature maps to provide tailored pose estimations. First Inference Module (FIM) potentials, alongside adaptively learned parameters, contribute to the PGM’s final pose estimation. The SDFPoseGraphNet, with its end-to-end trainable design, optimizes across all components, ensuring enhanced precision in hand pose estimation. Our proposed model outperforms existing state-of-the-art methods, achieving an average precision of 7.49% against the Convolution Pose Machine (CPM) and 3.84% in comparison to the Adaptive Graphical Model Network (AGMN).
30
Coenen, M., F. Rottensteiner, and C. Heipke. "DETECTION AND 3D MODELLING OF VEHICLES FROM TERRESTRIAL STEREO IMAGE PAIRS." ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLII-1/W1 (May 31, 2017): 505–12. http://dx.doi.org/10.5194/isprs-archives-xlii-1-w1-505-2017.
Full textAbstract:
The detection and pose estimation of vehicles plays an important role for automated and autonomous moving objects e.g. in autonomous driving environments. We tackle that problem on the basis of street level stereo images, obtained from a moving vehicle. Processing every stereo pair individually, our approach is divided into two subsequent steps: the vehicle detection and the modelling step. For the detection, we make use of the 3D stereo information and incorporate geometric assumptions on vehicle inherent properties in a firstly applied generic 3D object detection. By combining our generic detection approach with a state of the art vehicle detector, we are able to achieve satisfying detection results with values for completeness and correctness up to more than 86%. By fitting an object specific vehicle model into the vehicle detections, we are able to reconstruct the vehicles in 3D and to derive pose estimations as well as shape parameters for each vehicle. To deal with the intra-class variability of vehicles, we make use of a deformable 3D active shape model learned from 3D CAD vehicle data in our model fitting approach. While we achieve encouraging values up to 67.2% for correct position estimations, we are facing larger problems concerning the orientation estimation. The evaluation is done by using the object detection and orientation estimation benchmark of the KITTI dataset (Geiger et al., 2012).
31
Singh, Priya, and Pradipta Bandyopadhyay. "Accurate Calculation of the Density of States near the Ground-State Energy of the Peptides Met-Enkephalin and (Alanine)5 with the Wang-Landau Method: Lessons Learned." Journal of Atomic, Molecular, and Optical Physics 2012 (June 3, 2012): 1–6. http://dx.doi.org/10.1155/2012/782806.
Full textAbstract:
The Wang-Landau method estimates the relative density of states (DOS) by performing random walk in energy space. However, estimation of the DOS near the ground state minimum is highly challenging because of the dearth of states in the low-energy region compared to that at the high-energy region. Ideally the derivative of the logarithm of the DOS with respect to energy, which is proportional to the inverse of temperature, should become steeper with decrease in energy. However, in actual estimation of the DOS for molecular systems, it is nontrivial to achieve this. In the current work, the accuracy of the Wang-Landau method in estimating the DOS near the ground state minimum is investigated for two peptides, Met-enkephalin and (Alanine)5. It has been found that the steepness of the DOS can be achieved if the correct ground state energy is found, the bin used to discretize the energy space is extremely small (0.1 kcal/mol was used in the current case) and the energy range used to estimate the DOS is small. The findings of this work can help in devising new protocols for calculating the DOS with high accuracy near the ground state minimum for molecular systems.
32
Choi, Youn-Ho, and Seok-Cheol Kee. "Monocular Depth Estimation Using a Laplacian Image Pyramid with Local Planar Guidance Layers." Sensors 23, no. 2 (2023): 845. http://dx.doi.org/10.3390/s23020845.
Full textAbstract:
It is important to estimate the exact depth from 2D images, and many studies have been conducted for a long period of time to solve depth estimation problems. Recently, as research on estimating depth from monocular camera images based on deep learning is progressing, research for estimating accurate depths using various techniques is being conducted. However, depth estimation from 2D images has been a problem in predicting the boundary between objects. In this paper, we aim to predict sophisticated depths by emphasizing the precise boundaries between objects. We propose a depth estimation network with encoder–decoder structures using the Laplacian pyramid and local planar guidance method. In the process of upsampling the learned features using the encoder, the purpose of this step is to obtain a clearer depth map by guiding a more sophisticated boundary of an object using the Laplacian pyramid and local planar guidance techniques. We train and test our models with KITTI and NYU Depth V2 datasets. The proposed network constructs a DNN using only convolution and uses the ConvNext networks as a backbone. A trained model shows the performance of the absolute relative error (Abs_rel) 0.054 and root mean square error (RMSE) 2.252 based on the KITTI dataset and absolute relative error (Abs_rel) 0.102 and root mean square error 0.355 based on the NYU Depth V2 dataset. On the state-of-the-art monocular depth estimation, our network performance shows the fifth-best performance based on the KITTI Eigen split and the eighth-best performance based on the NYU Depth V2.
33
Liao, Hengrui, and Yue Li. "LC-TMNet: learned lossless medical image compression with tunable multi-scale network." PeerJ Computer Science 10 (December 20, 2024): e2511. https://doi.org/10.7717/peerj-cs.2511.
Full textAbstract:
In medicine, high-quality images are crucial for accurate clinical diagnosis, making lossless compression essential to preserve image integrity. Neural networks, with their powerful probabilistic estimation capabilities, seamlessly integrate with entropy encoders to achieve lossless compression. Recent studies have demonstrated that this approach outperforms traditional compression algorithms. However, existing methods have yet to adequately address the issue of inaccurate probabilistic estimation by neural networks when processing edge or complex textured regions. This limitation leaves significant room for improvement in compression performance. To address these challenges, this study proposes a novel lossless image compression method that employs a flexible tree-structured image segmentation mechanism. Due to the close relationships between subimages, this mechanism allows neural networks to fully exploit the prior knowledge of encoded subimages, thereby improving the accuracy of probabilistic estimation in complex textured regions of unencoded subimages. In terms of network architecture, we have introduced an attention mechanism into the UNet network to enhance the accuracy of probabilistic estimation across the entire subimage regions. Additionally, the flexible tree-structured image segmentation mechanism enabled us to implement variable-speed compression. We provide benchmarks for both fast and slow compression modes. Experimental results indicate that the proposed method achieves state-of-the-art compression speed in the fast mode. In the slow mode, it attains state-of-the-art performance.
34
Ahrens, Achim, Christian B. Hansen, Mark E. Schaffer, and Thomas Wiemann. "ddml: Double/debiased machine learning in Stata." Stata Journal: Promoting communications on statistics and Stata 24, no. 1 (2024): 3–45. http://dx.doi.org/10.1177/1536867x241233641.
Full textAbstract:
In this article, we introduce a package, ddml, for double/debiased machine learning in Stata. Estimators of causal parameters for five different econometric models are supported, allowing for flexible estimation of causal effects of endogenous variables in settings with unknown functional forms or many exogenous variables. ddml is compatible with many existing supervised machine learning programs in Stata. We recommend using double/debiased machine learning in combination with stacking estimation, which combines multiple machine learners into a final predictor. We provide Monte Carlo evidence to support our recommendation.
35
Erickson, Graham, and Michael Buro. "Global State Evaluation in StarCraft." Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment 10, no. 1 (2021): 112–18. http://dx.doi.org/10.1609/aiide.v10i1.12725.
Full textAbstract:
State evaluation and opponent modelling are important areasto consider when designing game-playing Artificial Intelligence.This paper presents a model for predicting whichplayer will win in the real-time strategy game StarCraft.Model weights are learned from replays using logistic regression.We also present some metrics for estimating player skillwhich can be used a features in the predictive model, includingusing a battle simulation as a baseline to compare playerperformance against.
36
Qin, Zengyi, Jinglu Wang, and Yan Lu. "MonoGRNet: A Geometric Reasoning Network for Monocular 3D Object Localization." Proceedings of the AAAI Conference on Artificial Intelligence 33 (July 17, 2019): 8851–58. http://dx.doi.org/10.1609/aaai.v33i01.33018851.
Full textAbstract:
Localizing objects in the real 3D space, which plays a crucial role in scene understanding, is particularly challenging given only a single RGB image due to the geometric information loss during imagery projection. We propose MonoGRNet for the amodal 3D object localization from a monocular RGB image via geometric reasoning in both the observed 2D projection and the unobserved depth dimension. MonoGRNet is a single, unified network composed of four task-specific subnetworks, responsible for 2D object detection, instance depth estimation (IDE), 3D localization and local corner regression. Unlike the pixel-level depth estimation that needs per-pixel annotations, we propose a novel IDE method that directly predicts the depth of the targeting 3D bounding box’s center using sparse supervision. The 3D localization is further achieved by estimating the position in the horizontal and vertical dimensions. Finally, MonoGRNet is jointly learned by optimizing the locations and poses of the 3D bounding boxes in the global context. We demonstrate that MonoGRNet achieves state-of-the-art performance on challenging datasets.
37
Li, Yaoyi, and Hongtao Lu. "Natural Image Matting via Guided Contextual Attention." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 07 (2020): 11450–57. http://dx.doi.org/10.1609/aaai.v34i07.6809.
Full textAbstract:
Over the last few years, deep learning based approaches have achieved outstanding improvements in natural image matting. Many of these methods can generate visually plausible alpha estimations, but typically yield blurry structures or textures in the semitransparent area. This is due to the local ambiguity of transparent objects. One possible solution is to leverage the far-surrounding information to estimate the local opacity. Traditional affinity-based methods often suffer from the high computational complexity, which are not suitable for high resolution alpha estimation. Inspired by affinity-based method and the successes of contextual attention in inpainting, we develop a novel end-to-end approach for natural image matting with a guided contextual attention module, which is specifically designed for image matting. Guided contextual attention module directly propagates high-level opacity information globally based on the learned low-level affinity. The proposed method can mimic information flow of affinity-based methods and utilize rich features learned by deep neural networks simultaneously. Experiment results on Composition-1k testing set and alphamatting.com benchmark dataset demonstrate that our method outperforms state-of-the-art approaches in natural image matting. Code and models are available at https://github.com/Yaoyi-Li/GCA-Matting.
38
Hashimoto, Seiji, Hiroki Watanabe, and Kenji Nakajima. "Estimation of Physical Parameters Using Learning Algorithm in Precision Positioning Control." Advanced Materials Research 211-212 (February 2011): 469–73. http://dx.doi.org/10.4028/www.scientific.net/amr.211-212.469.
Full textAbstract:
In this paper, a high precision control and a state estimation methods based on the learning algorithm are proposed. By means of the feedback error-learning method, at first, the variation of physical parameter is identified. Then, online estimation can be performed comparing the learned weighting coefficients in the neural network. The proposed method is applied to a precision control system, and is verified through the experiments.
39
Dyartanti, Endah Retno, Anif Jamaluddin, Muhammad Farrel Akshya, et al. "The State of Charge Estimation of LiFePO4 Batteries Performance Using Feed Forward Neural Network Model." Applied Mechanics and Materials 918 (January 9, 2024): 85–94. http://dx.doi.org/10.4028/p-iidzs6.
Full textAbstract:
Lithium-ion batteries like LiFePO4 become a new choice for electrical energy sources in the world and can be used on electric vehicles. Battery packs monitoring by Battery Management System in electric vehicles require accurate monitoring. The inaccuracy of monitoring such property can lead to low safety, low efficiency and battery’s life reduction. Estimating state of charge (SoC) to prevent battery damage from overcharging and over discharging. Some of the methods used to estimate SoC such as Coulomb Counting have errors during the charge and discharge process. This research proposes a counting method for measuring SoC with the artificial neural networks (ANN) to provide more precise estimation. Feed Forward Neural Network (FFNN) is an ANN model that can give an accurate estimation of SoC by learning data of the charge-discharge process performed on sample batteries. The sample batteries are tested with a battery analyzer to get its charging-discharging data consisting of variables such as voltage, current, capacity, and time with C-Rate variations. These variables data are then learned by the modeled FFNN to predict SoC value. The FFNN model consisted of 16 neurons in the first layer, 8 neurons in the second layer, and 4 neurons in the third layer. The predicted SoC value from FFNN has a similar value with its real SoC value. The relationship between SoC and battery voltage is plotted in a curve and shows an identical characteristic with how the SoC-Voltage curve of a battery should be and have a low mae value. This FFNN model can be applied further such as in electric vehicles to maintain its safety and for longer use.
40
Hilprecht, Benjamin, and Carsten Binnig. "Zero-shot cost models for out-of-the-box learned cost prediction." Proceedings of the VLDB Endowment 15, no. 11 (2022): 2361–74. http://dx.doi.org/10.14778/3551793.3551799.
Full textAbstract:
In this paper, we introduce zero-shot cost models, which enable learned cost estimation that generalizes to unseen databases. In contrast to state-of-the-art workload-driven approaches, which require to execute a large set of training queries on every new database, zero-shot cost models thus allow to instantiate a learned cost model out-of-the-box without expensive training data collection. To enable such zero-shot cost models, we suggest a new learning paradigm based on pre-trained cost models. As core contributions to support the transfer of such a pre-trained cost model to unseen databases, we introduce a new model architecture and representation technique for encoding query workloads as input to those models. As we will show in our evaluation, zero-shot cost estimation can provide more accurate cost estimates than state-of-the-art models for a wide range of (real-world) databases without requiring any query executions on unseen databases. Furthermore, we show that zero-shot cost models can be used in a few-shot mode that further improves their quality by retraining them just with a small number of additional training queries on the unseen database.
41
Lee, Hyun-Chul, Eul-Bum Lee, and Douglas Alleman. "Schedule Modeling to Estimate Typical Construction Durations and Areas of Risk for 1000 MW Ultra-Critical Coal-Fired Power Plants." Energies 11, no. 10 (2018): 2850. http://dx.doi.org/10.3390/en11102850.
Full textAbstract:
To date, Korea has built four 1000 MW gross-power ultra-critical coal-fired power plants. With the introduction of this new power plant type, there is a need for the development of best practices and lessons learned associated with its construction. One such need identified as a gap in literature is the early project planning estimation of project duration. To fill this research gap, this study utilized the Program Evaluation and Review Technique/Critical Path Method (PERT/CPM) and Monte Carlo simulations for estimating the appropriate construction duration at the planning stage of a new 1000 MW class coal-fired power plant project. Through the case study of the four Korean ultra-critical coal-fired power plants in operation, there was found an 85% likelihood of construction duration to be between 64 and 68 months. From interviews with subject matter experts, the most significant risk factors were found to be labor strikes and construction safety incidents. The findings within aid early planning decision makers by providing a replicable and accurate schedule estimation process. While the findings are based on Korean power plants, the results of this research can be used as a tool for coal-fired power plant construction schedule estimation worldwide.
42
Li, Hongjun, Miguel Barão, Luís Rato, and Shengjun Wen. "HMM-Based Dynamic Mapping with Gaussian Random Fields." Electronics 11, no. 5 (2022): 722. http://dx.doi.org/10.3390/electronics11050722.
Full textAbstract:
This paper focuses on the mapping problem for mobile robots in dynamic environments where the state of every point in space may change, over time, between free or occupied. The dynamical behaviour of a single point is modelled by a Markov chain, which has to be learned from the data collected by the robot. Spatial correlation is based on Gaussian random fields (GRFs), which correlate the Markov chain parameters according to their physical distance. Using this strategy, one point can be learned from its surroundings, and unobserved space can also be learned from nearby observed space. The map is a field of Markov matrices that describe not only the occupancy probabilities (the stationary distribution) as well as the dynamics in every point. The estimation of transition probabilities of the whole space is factorised into two steps: The parameter estimation for training points and the parameter prediction for test points. The parameter estimation in the first step is solved by the expectation maximisation (EM) algorithm. Based on the estimated parameters of training points, the parameters of test points are obtained by the predictive equation in Gaussian processes with noise-free observations. Finally, this method is validated in experimental environments.
43
Semenova, Vira, Matt Goldman, Victor Chernozhukov, and Matt Taddy. "Inference on heterogeneous treatment effects in high‐dimensional dynamic panels under weak dependence." Quantitative Economics 14, no. 2 (2023): 471–510. http://dx.doi.org/10.3982/qe1670.
Full textAbstract:
This paper provides estimation and inference methods for conditional average treatment effects (CATE) characterized by a high‐dimensional parameter in both homogeneous cross‐sectional and unit‐heterogeneous dynamic panel data settings. In our leading example, we model CATE by interacting the base treatment variable with explanatory variables. The first step of our procedure is orthogonalization, where we partial out the controls and unit effects from the outcome and the base treatment and take the cross‐fitted residuals. This step uses a novel generic cross‐fitting method that we design for weakly dependent time series and panel data. This method “leaves out the neighbors” when fitting nuisance components, and we theoretically power it by using Strassen's coupling. As a result, we can rely on any modern machine learning method in the first step, provided it learns the residuals well enough. Second, we construct an orthogonal (or residual) learner of CATE—the lasso CATE—that regresses the outcome residual on the vector of interactions of the residualized treatment with explanatory variables. If the complexity of CATE function is simpler than that of the first‐stage regression, the orthogonal learner converges faster than the single‐stage regression‐based learner. Third, we perform simultaneous inference on parameters of the CATE function using debiasing. We also can use ordinary least squares in the last two steps when CATE is low‐dimensional. In heterogeneous panel data settings, we model the unobserved unit heterogeneity as a weakly sparse deviation from Mundlak's (1978) model of correlated unit effects as a linear function of time‐invariant covariates and make use of L1‐penalization to estimate these models. We demonstrate our methods by estimating price elasticities of groceries based on scanner data. We note that our results are new even for the cross‐sectional (i.i.d.) case.
44
Li, Lianfa. "Geographically Weighted Machine Learning and Downscaling for High-Resolution Spatiotemporal Estimations of Wind Speed." Remote Sensing 11, no. 11 (2019): 1378. http://dx.doi.org/10.3390/rs11111378.
Full textAbstract:
High-resolution spatiotemporal wind speed mapping is useful for atmospheric environmental monitoring, air quality evaluation and wind power siting. Although modern reanalysis techniques can obtain reliable interpolated surfaces of meteorology at a high temporal resolution, their spatial resolutions are coarse. Local variability of wind speed is difficult to capture due to its volatility. Here, a two-stage approach was developed for robust spatiotemporal estimations of wind speed at a high resolution. The proposed approach consists of geographically weighted ensemble machine learning (Stage 1) and downscaling based on meteorological reanalysis data (Stage 2). The geographically weighted machine learning method is based on three base learners, which are an autoencoder-based deep residual network, XGBoost and random forest, and it incorporates spatial autocorrelation and heterogeneity to boost the ensemble predictions. With reanalysis data, downscaling was introduced in Stage 2 to reduce bias and spatial abrupt (non-natural) variation in the predictions inferred from Stage 1. The autoencoder-based residual network was used in Stage 2 to adjust the difference between the averages of the fine-resolution predicted values and the coarse-resolution reanalysis data to ensure consistency. Using mainland China as a case study, the geographically weighted regression (GWR) ensemble predictions were shown to perform better than individual learners’ predictions (with an approximately 12–16% improvement in R2 and a decrease of 0.14–0.19 m/s in root mean square error). Downscaling further improved the predictions by reducing inconsistency and obtaining better spatial variation (smoothing). The proposed approach can also be applied for the high-resolution spatiotemporal estimation of other meteorological parameters or surface variables involving remote sensing images (i.e. reliable coarsely resolved data), ground monitoring data and other relevant factors.
45
Esmeir, S., and S. Markovitch. "Anytime Induction of Low-cost, Low-error Classifiers: a Sampling-based Approach." Journal of Artificial Intelligence Research 33 (September 17, 2008): 1–31. http://dx.doi.org/10.1613/jair.2602.
Full textAbstract:
Machine learning techniques are gaining prevalence in the production of a wide range of classifiers for complex real-world applications with nonuniform testing and misclassification costs. The increasing complexity of these applications poses a real challenge to resource management during learning and classification. In this work we introduce ACT (anytime cost-sensitive tree learner), a novel framework for operating in such complex environments. ACT is an anytime algorithm that allows learning time to be increased in return for lower classification costs. It builds a tree top-down and exploits additional time resources to obtain better estimations for the utility of the different candidate splits. Using sampling techniques, ACT approximates the cost of the subtree under each candidate split and favors the one with a minimal cost. As a stochastic algorithm, ACT is expected to be able to escape local minima, into which greedy methods may be trapped. Experiments with a variety of datasets were conducted to compare ACT to the state-of-the-art cost-sensitive tree learners. The results show that for the majority of domains ACT produces significantly less costly trees. ACT also exhibits good anytime behavior with diminishing returns.
46
Shin, Joongchol, and Joonki Paik. "Photo-Realistic Image Dehazing and Verifying Networks via Complementary Adversarial Learning." Sensors 21, no. 18 (2021): 6182. http://dx.doi.org/10.3390/s21186182.
Full textAbstract:
Physical model-based dehazing methods cannot, in general, avoid environmental variables and undesired artifacts such as non-collected illuminance, halo and saturation since it is difficult to accurately estimate the amount of the illuminance, light transmission and airlight. Furthermore, the haze model estimation process requires very high computational complexity. To solve this problem by directly estimating the radiance of the haze images, we present a novel dehazing and verifying network (DVNet). In the dehazing procedure, we enhanced the clean images by using a correction network (CNet), which uses the ground truth to learn the haze network. Haze images are then restored through a haze network (HNet). Furthermore, a verifying method verifies the error of both CNet and HNet using a self-supervised learning method. Finally, the proposed complementary adversarial learning method can produce results more naturally. Note that the proposed discriminator and generators (HNet & CNet) can be learned via an unpaired dataset. Overall, the proposed DVNet can generate a better dehazed result than state-of-the-art approaches under various hazy conditions. Experimental results show that the DVNet outperforms state-of-the-art dehazing methods in most cases.
47
Liu, Haozhe, Bing Li, Haoqian Wu, et al. "Combating Mode Collapse via Offline Manifold Entropy Estimation." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 7 (2023): 8834–42. http://dx.doi.org/10.1609/aaai.v37i7.26062.
Full textAbstract:
Generative Adversarial Networks (GANs) have shown compelling results in various tasks and applications in recent years. However, mode collapse remains a critical problem in GANs. In this paper, we propose a novel training pipeline to address the mode collapse issue of GANs. Different from existing methods, we propose to generalize the discriminator as feature embedding and maximize the entropy of distributions in the embedding space learned by the discriminator. Specifically, two regularization terms, i.e., Deep Local Linear Embedding (DLLE) and Deep Isometric feature Mapping (DIsoMap), are introduced to encourage the discriminator to learn the structural information embedded in the data, such that the embedding space learned by the discriminator can be well-formed. Based on the well-learned embedding space supported by the discriminator, a non-parametric entropy estimator is designed to efficiently maximize the entropy of embedding vectors, playing as an approximation of maximizing the entropy of the generated distribution. By improving the discriminator and maximizing the distance of the most similar samples in the embedding space, our pipeline effectively reduces the mode collapse without sacrificing the quality of generated samples. Extensive experimental results show the effectiveness of our method which outperforms the GAN baseline, MaF-GAN on CelebA (9.13 vs. 12.43 in FID) and surpasses the recent state-of-the-art energy-based model on the ANIMEFACE dataset (2.80 vs. 2.26 in Inception score).
48
Xu, Ningshan, Dongao Ma, Guoqiang Ren, and Yongmei Huang. "BM-IQE: An Image Quality Evaluator with Block-Matching for Both Real-Life Scenes and Remote Sensing Scenes." Sensors 20, no. 12 (2020): 3472. http://dx.doi.org/10.3390/s20123472.
Full textAbstract:
Like natural images, remote sensing scene images; of which the quality represents the imaging performance of the remote sensor, also suffer from the degradation caused by imaging system. However, current methods measuring the imaging performance in engineering applications require for particular image patterns and lack generality. Therefore, a more universal approach is demanded to assess the imaging performance of remote sensor without constraints of land cover. Due to the fact that existing general-purpose blind image quality assessment (BIQA) methods cannot obtain satisfying results on remote sensing scene images; in this work, we propose a BIQA model of improved performance for natural images as well as remote sensing scene images namely BM-IQE. We employ a novel block-matching strategy called Structural Similarity Block-Matching (SSIM-BM) to match and group similar image patches. In this way, the potential local information among different patches can get expressed; thus, the validity of natural scene statistics (NSS) feature modeling is enhanced. At the same time, we introduce several features to better characterize and express remote sensing images. The NSS features are extracted from each group and the feature vectors are then fitted to a multivariate Gaussian (MVG) model. This MVG model is therefore used against a reference MVG model learned from a corpus of high-quality natural images to produce a basic quality estimation of each patch (centroid of each group). The further quality estimation of each patch is obtained by weighting averaging of its similar patches’ basic quality estimations. The overall quality score of the test image is then computed through average pooling of the patch estimations. Extensive experiments demonstrate that the proposed BM-IQE method can not only outperforms other BIQA methods on remote sensing scene image datasets but also achieve competitive performance on general-purpose natural image datasets as compared to existing state-of-the-art FR/NR-IQA methods.
49
Li, Chaoran, Fei Xiao, and Yaxiang Fan. "An Approach to State of Charge Estimation of Lithium-Ion Batteries Based on Recurrent Neural Networks with Gated Recurrent Unit." Energies 12, no. 9 (2019): 1592. http://dx.doi.org/10.3390/en12091592.
Full textAbstract:
State of charge (SOC) represents the amount of electricity stored and is calculated and used by battery management systems (BMSs). However, SOC cannot be observed directly, and SOC estimation is a challenging task due to the battery’s nonlinear characteristics when operating in complex conditions. In this paper, based on the new advanced deep learning techniques, a SOC estimation approach for Lithium-ion batteries using a recurrent neural network with gated recurrent unit (GRU-RNN) is introduced where observable variables such as voltage, current, and temperature are directly mapped to SOC estimation. The proposed technique requires no model or knowledge of the battery’s internal parameters and is able to estimate SOC at various temperatures by using a single set of self-learned network parameters. The proposed method is evaluated on two public datasets of vehicle drive cycles and another high rate pulse discharge condition dataset with mean absolute errors (MAEs) of 0.86%, 1.75%, and 1.05%. Experiment results show that the proposed method is accurate and robust.
50
Traynor, Anne, and Allison E. A. Chapman. "Impeded Attainment? The Role of State Exit Examination-Alternative Route Policy Combinations." Teachers College Record: The Voice of Scholarship in Education 117, no. 9 (2015): 1–34. http://dx.doi.org/10.1177/016146811511700904.
Full textAbstract:
Background To allay public concerns that state graduation examination mandates might unfairly hinder some students’ educational attainment prospects, most states with exit exam requirements offer alternative routes to earning a regular high school diploma. In spite of poor public documentation of alternative route usage rates, some exit exam states’ alternative credentialing policies have been linked to their relatively high reported graduation rates. However, there is little empirical evidence that these alternative route policies blunt the reported negative effects of exit exam requirements on diploma attainment in the general student population. Purpose We investigate the consequences of several distinct state exit exam-alternative route graduation policy combinations on the subsequent educational attainment of tenth graders in the graduating class of 2004. Research Design Data for our study are drawn from the cohort of U.S. tenth graders (N = 13,636) sampled by the Education Longitudinal Study of 2002–2006. We use logistic regression models to estimate the relationships between state exam difficulty-alternative route policy combinations and two educational attainment outcomes: high school diploma acquisition and postsecondary school enrollment. Conclusions While we find no relationship between exit exam policies and students’ subsequent postsecondary school enrollment, we conclude that students subject to relatively difficult state exit exams are less likely to earn a regular high school diploma than those not subject to an exam requirement. Estimating our models in the subsample of English language learner students as a model plausibility check, we observe marginally significant, but sizable, negative effects of both minimum-competency and more-difficult exit exams on diploma attainment. Our results suggest that alternative route options neither eliminate, nor appreciably attenuate, more-difficult exit exams’ negative impact on diploma attainment in the general student population or among English language learners.