Journal articles on the topic 'Generalization performance evaluation'
To see the other types of publications on this topic, follow the link: Generalization performance evaluation.
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 'Generalization performance evaluation.'
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
Shi, Wenzhong, and ChuiKwan Cheung. "Performance Evaluation of Line Simplification Algorithms for Vector Generalization." Cartographic Journal 43, no. 1 (March 1, 2006): 27–44. http://dx.doi.org/10.1179/000870406x93490.
Full text
2
Alwakeel, Ahmed, Mohammed Alwakeel, Mohammad Hijji, Tausifa Jan Saleem, and Syed Rameem Zahra. "Performance Evaluation of Different Decision Fusion Approaches for Image Classification." Applied Sciences 13, no. 2 (January 15, 2023): 1168. http://dx.doi.org/10.3390/app13021168.
Full textAbstract:
Image classification is one of the major data mining tasks in smart city applications. However, deploying classification models that have good generalization accuracy is highly crucial for reliable decision-making in such applications. One of the ways to achieve good generalization accuracy is through the use of multiple classifiers and the fusion of their decisions. This approach is known as “decision fusion”. The requirement for achieving good results with decision fusion is that there should be dissimilarity between the outputs of the classifiers. This paper proposes and evaluates two ways of attaining the aforementioned dissimilarity. One is using dissimilar classifiers with different architectures, and the other is using similar classifiers with similar architectures but trained with different batch sizes. The paper also compares a number of decision fusion strategies.
3
Alexander, Melina, Ben Lignugaris/Kraft, and David Forbush. "Online Mathematics Methods Course Evaluation: Student Outcomes, Generalization, and Pupil Performance." Teacher Education and Special Education: The Journal of the Teacher Education Division of the Council for Exceptional Children 30, no. 4 (October 2007): 199–216. http://dx.doi.org/10.1177/088840640703000401.
Full text
4
Emmert-Streib, Frank, and Matthias Dehmer. "Evaluation of Regression Models: Model Assessment, Model Selection and Generalization Error." Machine Learning and Knowledge Extraction 1, no. 1 (March 22, 2019): 521–51. http://dx.doi.org/10.3390/make1010032.
Full textAbstract:
When performing a regression or classification analysis, one needs to specify a statistical model. This model should avoid the overfitting and underfitting of data, and achieve a low generalization error that characterizes its prediction performance. In order to identify such a model, one needs to decide which model to select from candidate model families based on performance evaluations. In this paper, we review the theoretical framework of model selection and model assessment, including error-complexity curves, the bias-variance tradeoff, and learning curves for evaluating statistical models. We discuss criterion-based, step-wise selection procedures and resampling methods for model selection, whereas cross-validation provides the most simple and generic means for computationally estimating all required entities. To make the theoretical concepts transparent, we present worked examples for linear regression models. However, our conceptual presentation is extensible to more general models, as well as classification problems.
5
Gülci, Sercan, Hafiz Hulusi Acar, Abdullah E. Akay, and Neşe Gülci. "Evaluation of Automatic Prediction of Small Horizontal Curve Attributes of Mountain Roads in GIS Environments." ISPRS International Journal of Geo-Information 11, no. 11 (November 9, 2022): 560. http://dx.doi.org/10.3390/ijgi11110560.
Full textAbstract:
Road curve attributes can be determined by using Geographic Information System (GIS) to be used in road vehicle traffic safety and planning studies. This study involves analyzing the GIS-based estimation accuracy in the length, radius and the number of small horizontal road curves on a two-lane rural road and a forest road. The prediction success of horizontal curve attributes was investigated using digitized raw and generalized/simplified road segments. Two different roads were examined, involving 20 test groups and two control groups, using 22 datasets obtained from digitized and surveyed roads based on satellite imagery, GIS estimates, and field measurements. Confusion matrix tables were also used to evaluate the prediction accuracy of horizontal curve geometry. F-score, Mathews Correlation Coefficient, Bookmaker Informedness and Balanced Accuracy were used to investigate the performance of test groups. The Kruskal–Wallis test was used to analyze the statistical relationships between the data. Compared to the Bezier generalization algorithm, the Douglas–Peucker algorithm showed the most accurate horizontal curve predictions at generalization tolerances of 0.8 m and 1 m. The results show that the generalization tolerance level contributes to the prediction accuracy of the number, curve radius, and length of the horizontal curves, which vary with the tolerance value. Thus, this study underlined the importance of calculating generalizations and tolerances following a manual road digitization.
6
Ferreira, Diogo Cunha, and Rui Cunha Marques. "Malmquist and Hicks–Moorsteen Productivity Indexes for Clusters Performance Evaluation." International Journal of Information Technology & Decision Making 15, no. 05 (September 2016): 1015–53. http://dx.doi.org/10.1142/s0219622016500243.
Full textAbstract:
Measuring the performance of clusters characterized by the unbalancedeness and units with no correspondence in other clusters (“uncorrespondencedeness”) has not achieved the desired attention in the literature. Particularly, the operational research has been almost exclusively focused on performance evolution over time, where clusters are generally balanced and the units repeat themselves over these groups. Such analysis has been based on the Malmquist and the Hicks–Moorsteen indexes (MI and HMI), which are solely based on Shephard’s radial distance functions and do not account for all inefficiency sources. Making use of the so-called geometric distance functions (GDFs) and the GDF-based MI, we propose a generalization of the Hicks–Moorsteen index (HMI), based on targets instead of distances to the efficient frontier, allowing the introduction of all inefficiency sources in the productivity model. Moreover, we propose a Monte Carlo-based framework to achieve the pseudo-corresponding units for general cluster performance analysis. This framework is then a generalization of the conventional performance evolution over time. Then, we show that the HMI can be decomposed into economically meaningful indexes and can be rewritten as the geometric mean of the input and the output-oriented MIs. Given these conclusions and our proposed framework, the employment of the HMI to the general clusters analysis is straightforward. Other economically meaningful conclusions are also obtained in this paper.
7
Huang, Ke Wang. "Experimental Study of FPCA on its Generalization Performance in Image Classification." Applied Mechanics and Materials 496-500 (January 2014): 2299–302. http://dx.doi.org/10.4028/www.scientific.net/amm.496-500.2299.
Full textAbstract:
The theoretical study of FPCA shows that FPCA algorithm has better generalization performance than existing PCA and its extended algorithms. But this theoretic conclusion was not confirmed by existing experimental results because of the problems of evaluation criterion. Introducing the idea of clustering performance criterion of LDA, we proposed a general performance metrics for PCA and performed numbers of experimental studies to compare FPCA with existing PCA and its extended algorithms by using our metrics. We found in the feature extraction of image samples that FPCA really has better generalization performance than existing PCA and its extended algorithms under the condition of large sample size. The results confirmed theoretical conclusion of FPCA and improved relevant experimental study.
8
Ahmad, Muhammad, Manuel Mazzara, and Salvatore Distefano. "Regularized CNN Feature Hierarchy for Hyperspectral Image Classification." Remote Sensing 13, no. 12 (June 10, 2021): 2275. http://dx.doi.org/10.3390/rs13122275.
Full textAbstract:
Convolutional Neural Networks (CNN) have been rigorously studied for Hyperspectral Image Classification (HSIC) and are known to be effective in exploiting joint spatial-spectral information with the expense of lower generalization performance and learning speed due to the hard labels and non-uniform distribution over labels. Therefore, this paper proposed an idea to enhance the generalization performance of CNN for HSIC using soft labels that are a weighted average of the hard labels and uniform distribution over ground labels. The proposed method helps to prevent CNN from becoming over-confident. We empirically show that, in improving generalization performance, regularization also improves model calibration, which significantly improves beam-search. Several publicly available Hyperspectral datasets are used to validate the experimental evaluation, which reveals improved performance as compared to the state-of-the-art models with overall 99.29%, 99.97%, and 100.0% accuracy for Indiana Pines, Pavia University, and Salinas dataset, respectively.
9
Zhang, Dong Sheng. "Generalization Privacy Protection Method for Alarm Data." Applied Mechanics and Materials 543-547 (March 2014): 3646–49. http://dx.doi.org/10.4028/www.scientific.net/amm.543-547.3646.
Full textAbstract:
To resolve conflicts between share and collaborative analysis requirements of security alarm and alert data holders worries about privacy, it firstly probes into the anonymized protection method Incognito. Based on that, it improves the algorithm to solve existing problems by extending common data like privacy protection targets to alert data. The generalized anonymous processing model for alert data is developed and the quantitative evaluation is realized between the level of alert datas secret protection and data quality. With authoritative data set of intrusion detection attack scenario as test data, the experiment validates efficiency and effectiveness of the proposed method on the part of performance and security.
10
Huang, Felix C., James L. Patton, and Ferdinando A. Mussa-Ivaldi. "Manual Skill Generalization Enhanced by Negative Viscosity." Journal of Neurophysiology 104, no. 4 (October 2010): 2008–19. http://dx.doi.org/10.1152/jn.00433.2009.
Full textAbstract:
Recent human-machine interaction studies have suggested that movement augmented with negative viscosity can enhance performance and can even promote better motor learning. To test this, we investigated how negative viscosity influences motor adaptation to an environment where forces acted only in one axis of motion. Using a force-feedback device, subjects performed free exploratory movements with a purely inertia generating forces proportional to hand acceleration, negative viscosity generating destabilizing forces proportional to hand velocity, or a combination of the acceleration and velocity fields. After training, we evaluated each subject's ability to perform circular movements in only the inertial field. Combined training resulted in lowest error and revealed similar responses as inertia training in catch trials. These findings are remarkable because negative viscosity, available only during training, evidently enhanced learning when combined with inertia. This success in generalization is consistent with the ability of the nervous system to decompose the perturbing forces into velocity and acceleration dependent components. Compared with inertia, the combined group exhibited a broader range of speeds along the direction of maximal perturbing force. Broader exploration was also correlated with better performance in subsequent evaluation trials; this suggests that negative viscosity improved performance by enhancing identification of each force field. These findings shed light on a new way to enhance sensorimotor adaptation through robot-applied augmentation of mechanics.
11
Qu, Xudong, Jie Yang, and Meng Chang. "A Deep Learning Model for Concrete Dam Deformation Prediction Based on RS-LSTM." Journal of Sensors 2019 (October 31, 2019): 1–14. http://dx.doi.org/10.1155/2019/4581672.
Full textAbstract:
Deformation is a comprehensive reflection of the structural state of a concrete dam, and research on prediction models for concrete dam deformation provides the basis for safety monitoring and early warning strategies. This paper focuses on practical problems such as multicollinearity among factors; the subjectivity of factor selection; robustness, externality, generalization, and integrity deficiencies; and the unsoundness of evaluation systems for prediction models. Based on rough set (RS) theory and a long short-term memory (LSTM) network, single-point and multipoint concrete dam deformation prediction models for health monitoring based on RS-LSTM are studied. Moreover, a new prediction model evaluation system is proposed, and the model accuracy, robustness, externality, and generalization are defined as quantitative evaluation indexes. An engineering project shows that the concrete dam deformation prediction models based on RS-LSTM can quantitatively obtain the representative factors that affect dam deformation and the importance of each factor relative to the effect. The accuracy evaluation index (AVI), robustness evaluation index (RVI), externality evaluation index (EVI), and generalization evaluation index (GVI) of the model are superior to the evaluation indexes of existing shallow neural network models and statistical models according to the new evaluation system, which can estimate the comprehensive performance of prediction models. The prediction model for concrete dam deformation based on RS-LSTM optimizes the factors that influence the model, quantitatively determines the importance of each factor, and provides high-performance, synchronous, and dynamic predictions for concrete dam behaviours; therefore, the model has strong engineering practicality.
12
Liu, Dali, Xuchen Zhao, Wenjing Cao, Wei Wang, and Yi Lu. "Design and Performance Evaluation of a Deep Neural Network for Spectrum Recognition of Underwater Targets." Computational Intelligence and Neuroscience 2020 (August 1, 2020): 1–11. http://dx.doi.org/10.1155/2020/8848507.
Full textAbstract:
Due to the complexity of the underwater environment, underwater acoustic target recognition (UATR) has always been challenging. Although deep neural networks (DNN) have been used in UATR and some achievements have been made, the performance is not satisfactory when recognizing underwater targets with different Doppler shifts, signal-to-noise ratios (SNR), and interferences. In the paper, a one-dimensional convolutional neural network (1D-CNN) was proposed to recognize the line spectrums of Detection of Envelope Modulation on Noise (DEMON) spectrums of underwater target-radiated noise. Datasets of targets with different Doppler shifts, SNRs, and interferences were designed to evaluate the generalization performance of the proposed CNN. Experimental results show that compared with traditional multilayer perceptron (MLP) networks, the 1D-CNN model better performs in recognition of targets with different Doppler shifts and SNRs. The outstanding generalization ability of the proposed model shows that it is suitable for practical engineering applications.
13
Yang, Yanxia, Pu Wang, and Xuejin Gao. "A Novel Radial Basis Function Neural Network with High Generalization Performance for Nonlinear Process Modelling." Processes 10, no. 1 (January 10, 2022): 140. http://dx.doi.org/10.3390/pr10010140.
Full textAbstract:
A radial basis function neural network (RBFNN), with a strong function approximation ability, was proven to be an effective tool for nonlinear process modeling. However, in many instances, the sample set is limited and the model evaluation error is fixed, which makes it very difficult to construct an optimal network structure to ensure the generalization ability of the established nonlinear process model. To solve this problem, a novel RBFNN with a high generation performance (RBFNN-GP), is proposed in this paper. The proposed RBFNN-GP consists of three contributions. First, a local generalization error bound, introducing the sample mean and variance, is developed to acquire a small error bound to reduce the range of error. Second, the self-organizing structure method, based on a generalization error bound and network sensitivity, is established to obtain a suitable number of neurons to improve the generalization ability. Third, the convergence of this proposed RBFNN-GP is proved theoretically in the case of structure fixation and structure adjustment. Finally, the performance of the proposed RBFNN-GP is compared with some popular algorithms, using two numerical simulations and a practical application. The comparison results verified the effectiveness of RBFNN-GP.
14
Wright, Beverly A., and Yuxuan Zhang. "A review of the generalization of auditory learning." Philosophical Transactions of the Royal Society B: Biological Sciences 364, no. 1515 (October 31, 2008): 301–11. http://dx.doi.org/10.1098/rstb.2008.0262.
Full textAbstract:
The ability to detect and discriminate attributes of sounds improves with practice. Determining how such auditory learning generalizes to stimuli and tasks that are not encountered during training can guide the development of training regimens used to improve hearing abilities in particular populations as well as provide insight into the neural mechanisms mediating auditory performance. Here we review the newly emerging literature on the generalization of auditory learning, focusing on behavioural investigations of generalization on basic auditory tasks in human listeners. The review reveals a variety of generalization patterns across different trained tasks that can not be summarized with a simple rule, and a diversity of views about the definition, evaluation and interpretation of generalization.
15
SONMEZ, Rifat, and Burak SÖZGEN. "A support vector machine method for bid/no bid decision making." JOURNAL OF CIVIL ENGINEERING AND MANAGEMENT 23, no. 5 (May 24, 2017): 641–49. http://dx.doi.org/10.3846/13923730.2017.1281836.
Full textAbstract:
The bid/no bid decision is an important and complex process, and is impacted by numerous variables that are related to the contractor, project, client, competitors, tender and market conditions. Despite the complexity of bid decision making process, in the construction industry the majority of bid/no bid decisions is made informally based on experience, judgment, and perception. In this paper, a procedure based on support vector machines and backward elimination regression is presented for improving the existing bid decision making methods. The method takes advantage of the strong generalization properties of support vector machines and attempts to further enhance generalization performance by eliminating insignificant input variables. The method is implemented for bid/no bid decision making of offshore oil and gas platform fabrication projects to achieve a parsimonious support vector machine classifier. The performance of the support vector machine classifier is compared with the performances of the worth evaluation model, linear regression, and neural network classifiers. The results show that the support vector machine classifier outperforms existing methods significantly, and the proposed procedure provides a powerful tool for bid/no bid decision making. The results also reveal that elimination of the insignificant input variables improves generalization performance of the support vector machines.
16
Venckevičiūtė, Gerda. "The importance of creditworthiness evaluation in the context of Lithuanian SME performance measurement." Ekonomika 94, no. 2 (January 1, 2015): 129–43. http://dx.doi.org/10.15388/ekon.2015.2.8237.
Full textAbstract:
The paper deals with the methodology of Lithuanian small and medium enterprises (here and further – SME) creditworthiness evaluation and part of empirical research which reveals the importance and motives of creditworthiness evaluation in the Lithuanian SME performance measurement process. The aim of this study is to analyse the importance of creditworthiness evaluation in performance measurement and its influence on stable company’s growth. The three main goals of the paper are: 1) to reveal the methodology of Lithuanian SME creditworthiness evaluation, 2) to analyse the periodicity of Lithuanian SME creditworthiness evaluation and the motives of one’s integration into the performance measurement process, and 3) to identify creditworthiness evaluation factors which correlate with stable SME growth results. Analysis of related literature, information comparison and generalization are used for the credit risk and creditworthiness evaluation methodology overview. Empirical research is performed using the survey method, for data evaluation the descriptive statistics method, as well as qualitative (systematization, classification, causal, functional and structural links) and quantitative data analysis (quantitative indicators calculation) were applied. The research results have revealed that the companies evaluating partners’ and their own creditworthiness have by 10% higher three last year revenues and the number of employees growth. The paper concludes that creditworthiness evaluation and stable company’s growth correlate and enable SMEs to pursue stable growth results while increasing competitiveness and considering confidence and trust among business partners.
17
Ji, L., Z. Zhao, W. Huo, J. Zhao, and R. Gao. "EVALUATION OF SEVERAL FULLY CONVOLUTIONAL NETWORKS IN SAR IMAGE CHANGE DETECTION." ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences X-3/W1-2022 (October 27, 2022): 61–68. http://dx.doi.org/10.5194/isprs-annals-x-3-w1-2022-61-2022.
Full textAbstract:
Abstract. In recent years, the world is suffering from frequent natural disasters. Change detection (CD) technology can quickly identify the change information on the ground and has developed into an important means of disaster monitoring and assessment. Synthetic aperture radar (SAR) has the characteristics of periodic observation and wide coverage. Moreover, SAR has the advantages of penetrating, all-day and all-weather observation, which plays an important role in disaster monitoring. Due to the rapid development of satellite sensors, the available CD data has been greatly enriched. This situation provides an opportunity for deep learning change detection (DLCD) techniques. However, SAR data are affected by speckle noise and lack of available labeled samples, it remains challenging to precisely locate the change information with high efficiency. This paper focuses on several commonly used and outstanding networks in the DLCD field to evaluate their performance and develop them to SAR data. In addition, Transfer learning experiments are designed to evaluate the generalization performance of each network for the CD task. The experimental results show that the Siamese CD network encoding multi-temporal data separately has the best ability to detect changes and generalization performance. In addition, adding high quality explicit difference guidance information to the network is more specific for the CD task, which can further improve network performance and refine the boundaries of changed ground objects on change map.
18
Rajaraman, Sivaramakrishnan, Stefan Jaeger, and Sameer K. Antani. "Performance evaluation of deep neural ensembles toward malaria parasite detection in thin-blood smear images." PeerJ 7 (May 28, 2019): e6977. http://dx.doi.org/10.7717/peerj.6977.
Full textAbstract:
Background Malaria is a life-threatening disease caused by Plasmodium parasites that infect the red blood cells (RBCs). Manual identification and counting of parasitized cells in microscopic thick/thin-film blood examination remains the common, but burdensome method for disease diagnosis. Its diagnostic accuracy is adversely impacted by inter/intra-observer variability, particularly in large-scale screening under resource-constrained settings. Introduction State-of-the-art computer-aided diagnostic tools based on data-driven deep learning algorithms like convolutional neural network (CNN) has become the architecture of choice for image recognition tasks. However, CNNs suffer from high variance and may overfit due to their sensitivity to training data fluctuations. Objective The primary aim of this study is to reduce model variance, improve robustness and generalization through constructing model ensembles toward detecting parasitized cells in thin-blood smear images. Methods We evaluate the performance of custom and pretrained CNNs and construct an optimal model ensemble toward the challenge of classifying parasitized and normal cells in thin-blood smear images. Cross-validation studies are performed at the patient level to ensure preventing data leakage into the validation and reduce generalization errors. The models are evaluated in terms of the following performance metrics: (a) Accuracy; (b) Area under the receiver operating characteristic (ROC) curve (AUC); (c) Mean squared error (MSE); (d) Precision; (e) F-score; and (f) Matthews Correlation Coefficient (MCC). Results It is observed that the ensemble model constructed with VGG-19 and SqueezeNet outperformed the state-of-the-art in several performance metrics toward classifying the parasitized and uninfected cells to aid in improved disease screening. Conclusions Ensemble learning reduces the model variance by optimally combining the predictions of multiple models and decreases the sensitivity to the specifics of training data and selection of training algorithms. The performance of the model ensemble simulates real-world conditions with reduced variance, overfitting and leads to improved generalization.
19
Wei, Li Wei, Qiang Xiao, Ying Zhang, and Xiong Fei Ji. "Credit Risk Evaluation Using a New Classification Model: L1-LS-SVM." Applied Mechanics and Materials 321-324 (June 2013): 1917–20. http://dx.doi.org/10.4028/www.scientific.net/amm.321-324.1917.
Full textAbstract:
Least squares support vector machine (LS-SVM) has an outstanding advantage of lower computational complexity than that of standard support vector machines. Its shortcomings are the loss of sparseness and robustness. Thus it usually results in slow testing speed and poor generalization performance. In this paper, a least squares support vector machine with L1 penalty (L1-LS-SVM) is proposed to deal with above shortcomings. A minimum of 1-norm based object function is chosen to get the sparse and robust solution based on the idea of basis pursuit (BP) in the whole feasibility region. Some UCI datasets are used to demonstrate the effectiveness of this model. The experimental results show that L1-LS-SVM can obtain a small number of support vectors and improve the generalization ability of LS-SVM.
20
Marin, Ivana, Ana Kuzmanic Skelin, and Tamara Grujic. "Empirical Evaluation of the Effect of Optimization and Regularization Techniques on the Generalization Performance of Deep Convolutional Neural Network." Applied Sciences 10, no. 21 (November 4, 2020): 7817. http://dx.doi.org/10.3390/app10217817.
Full textAbstract:
The main goal of any classification or regression task is to obtain a model that will generalize well on new, previously unseen data. Due to the recent rise of deep learning and many state-of-the-art results obtained with deep models, deep learning architectures have become one of the most used model architectures nowadays. To generalize well, a deep model needs to learn the training data well without overfitting. The latter implies a correlation of deep model optimization and regularization with generalization performance. In this work, we explore the effect of the used optimization algorithm and regularization techniques on the final generalization performance of the model with convolutional neural network (CNN) architecture widely used in the field of computer vision. We give a detailed overview of optimization and regularization techniques with a comparative analysis of their performance with three CNNs on the CIFAR-10 and Fashion-MNIST image datasets.
21
Troisi, Orlando, Carlo Torre, and Gennaro Maione. "Performance Evaluation and Measurement in Public Organizations: A Systematic Literature Review." International Journal of Business Administration 8, no. 1 (December 18, 2016): 106. http://dx.doi.org/10.5430/ijba.v8n1p106.
Full textAbstract:
The turbulence of the current competitive environment emphasizes the importance of the role played by performance measurement systems in generating an improvement of business results. Starting from this consideration, the work pursues a twofold goal: firstly, it tries to verify the existence and the degree of a research interest about this topic; secondly, it seeks to identify, in measurement and evaluation systems, which factors are capable of producing an effect on performances of public organizations. In order to well respond to the research purposes, the work begins with a systematic literature review, which highlights a growing attention of scholars on all those variables considered critical in conducting and managing public organizations. The study, highlighting the existence of six variables to be advantageously taken into account in managing public organizations, especially in light of the potential influence that they seem to exert on different types of business performances, could be considered as a useful tool for both practitioners (managers of public organizations) and scholars (professors, researchers, students, etc.) aimed at helping to become aware about the advantages arising from an adequate management of performances measures. The main research limitation is the lack of an empirical analysis of public companies performance plans, which should be thoroughly examined to allow a possible further generalization of the theoretical findings achieved.
22
Ashok, Arjun, Chaitanya Devaguptapu, and Vineeth N. Balasubramanian. "Learning Modular Structures That Generalize Out-of-Distribution (Student Abstract)." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 11 (June 28, 2022): 12905–6. http://dx.doi.org/10.1609/aaai.v36i11.21589.
Full textAbstract:
Out-of-distribution (O.O.D.) generalization remains to be a key challenge for real-world machine learning systems. We describe a method for O.O.D. generalization that, through training, encourages models to only preserve features in the network that are well reused across multiple training domains. Our method combines two complementary neuron-level regularizers with a probabilistic differentiable binary mask over the network, to extract a modular sub-network that achieves better O.O.D. performance than the original network. Preliminary evaluation on two benchmark datasets corroborates the promise of our method.
23
Wang, Juan, Liangzhu Ge, Guorui Liu, and Guoyan Li. "VOVU: A Method for Predicting Generalization in Deep Neural Networks." Mathematical Problems in Engineering 2021 (November 23, 2021): 1–10. http://dx.doi.org/10.1155/2021/6170662.
Full textAbstract:
During the development of deep neural networks (DNNs), it is difficult to trade off the performance of fitting ability and generalization ability in training set and unknown data (such as test set). The current solution is to reduce the complexity of the objective function, using regularization methods. In this paper, we propose a method called VOVU (Variance Of Variance of Units in the last hidden layer) to maximize the optimization of the balance between fitting power and generalization during monitoring the training process. The main idea is to give full play to the predictability of the variance of the hidden layer units in the complexity of the neural network model and use it as a generalization evaluation index. In particular, we take full advantage of the last layer of hidden layers since it has the greatest impact. The algorithm was tested on Fashion-MNIST and CIFAR-10. The experimental results demonstrate that VOVU and test loss are highly positively correlated. This implies that a smaller VOVU indicates that the network has better generalization. VOVU can serve as an alternative method for early stopping and a good predictor of the generalization performance in DNNs. Specially, when the sample size is limited, VOVU will be a better choice because it does not require dividing training data as validation set.
24
Ito, Hiroshi, Kenjiro Yamamoto, Hiroki Mori, and Tetsuya Ogata. "Evaluation of Generalization Performance of Visuo-Motor Learning by Analyzing Internal State Structured from Robot Motion." New Generation Computing 38, no. 1 (January 22, 2020): 7–22. http://dx.doi.org/10.1007/s00354-019-00083-x.
Full text
25
Fiaz, Mustansar, Arif Mahmood, Ki Yeol Baek, Sehar Shahzad Farooq, and Soon Ki Jung. "Improving Object Tracking by Added Noise and Channel Attention." Sensors 20, no. 13 (July 6, 2020): 3780. http://dx.doi.org/10.3390/s20133780.
Full textAbstract:
CNN-based trackers, especially those based on Siamese networks, have recently attracted considerable attention because of their relatively good performance and low computational cost. For many Siamese trackers, learning a generic object model from a large-scale dataset is still a challenging task. In the current study, we introduce input noise as regularization in the training data to improve generalization of the learned model. We propose an Input-Regularized Channel Attentional Siamese (IRCA-Siam) tracker which exhibits improved generalization compared to the current state-of-the-art trackers. In particular, we exploit offline learning by introducing additive noise for input data augmentation to mitigate the overfitting problem. We propose feature fusion from noisy and clean input channels which improves the target localization. Channel attention integrated with our framework helps finding more useful target features resulting in further performance improvement. Our proposed IRCA-Siam enhances the discrimination of the tracker/background and improves fault tolerance and generalization. An extensive experimental evaluation on six benchmark datasets including OTB2013, OTB2015, TC128, UAV123, VOT2016 and VOT2017 demonstrate superior performance of the proposed IRCA-Siam tracker compared to the 30 existing state-of-the-art trackers.
26
Cheng, Yihua, Yiwei Bao, and Feng Lu. "PureGaze: Purifying Gaze Feature for Generalizable Gaze Estimation." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 1 (June 28, 2022): 436–43. http://dx.doi.org/10.1609/aaai.v36i1.19921.
Full textAbstract:
Gaze estimation methods learn eye gaze from facial features. However, among rich information in the facial image, real gaze-relevant features only correspond to subtle changes in eye region, while other gaze-irrelevant features like illumination, personal appearance and even facial expression may affect the learning in an unexpected way. This is a major reason why existing methods show significant performance degradation in cross-domain/dataset evaluation. In this paper, we tackle the cross-domain problem in gaze estimation. Different from common domain adaption methods, we propose a domain generalization method to improve the cross-domain performance without touching target samples. The domain generalization is realized by gaze feature purification. We eliminate gaze-irrelevant factors such as illumination and identity to improve the cross-domain performance. We design a plug-and-play self-adversarial framework for the gaze feature purification. The framework enhances not only our baseline but also existing gaze estimation methods directly and significantly. To the best of our knowledge, we are the first to propose domain generalization methods in gaze estimation. Our method achieves not only state-of-the-art performance among typical gaze estimation methods but also competitive results among domain adaption methods. The code is released in https://github.com/yihuacheng/PureGaze.
27
Wua, Shuai, Peiyu Li, Xi Chen, and Hui Wang. "Analysis and Research on Provincial Postgraduate Cultivation Performance Based on BP Neural Network." BCP Education & Psychology 4 (May 31, 2022): 15–23. http://dx.doi.org/10.54691/bcpep.v4i.765.
Full textAbstract:
According to relevant data, the comprehensive competitiveness and quality of graduate education in Henan Province are in the middle of the 31 provinces in China, and its graduate education has a great room for improvement. Through the research on the current situation of educational performance evaluation at home and abroad, and the analysis of the limitations in the evaluation process of postgraduate training in Henan province, we proposed a performance evaluation method based on BP neural network. This method uses the theory and technology of information theory, analytic hierarchy process, and BP neural network to establish an educational performance evaluation model. Through this model, the shortcomings of the existing performance evaluation methods of graduate student training are overcome, and performance evaluation methods that are closer to the actual situation are excavated, which provides a scientific decision-making reference for the performance evaluation of graduate education in Henan Province. This experiment uses the university education data of Henan Province as the experimental data test set. The experimental results show that this model has good generalization ability and can provide reference for the reform and construction of postgraduate education in Henan province.
28
Anyika, Emma. "Financial Sector Performance Enhancers." International Journal of Social Sciences and Humanities Invention 7, no. 06 (June 29, 2020): 5995–6000. http://dx.doi.org/10.18535/ijsshi/v7i06.02.
Full textAbstract:
In any state or country there are certain sectors that are relied upon to drive its economy. For many of these countries the financial sector is seen as the driving force of the economy. This is witnessed in many world economic crises which commence with the large organizations in the financial sector. The results of this study should aid entrepreneurs to be aware of the areas of emphasis and factors for consideration for positive growth of their organizations. Existing organizations will also benefit by improving the said areas and adopting the factors for continued growth and sustainability. Both non-parametric and parametric methods were used to relate performance to its enhancers. Tests of hypothesis were then made to allow for the generalization of the findings to the whole population. Both the non-parametric and parametric results of the study indicate that adoption of improved practices, marketing policy, performance evaluation, and location of an organization affect the actual financial performance of the organization to a significant extent.
29
BOUAMAR, M., and M. LADJAL. "PERFORMANCE EVALUATION OF THREE PATTERN CLASSIFICATION TECHNIQUES USED FOR WATER QUALITY MONITORING." International Journal of Computational Intelligence and Applications 11, no. 02 (June 2012): 1250013. http://dx.doi.org/10.1142/s1469026812500137.
Full textAbstract:
Water quality is one of the major concerns of countries around the world. Monitoring of water quality is becoming more and more interesting because of its effects on human life. The control of risks in the factories that produce and distribute water ensures the quality of this vital resource. Many techniques were developed in order to improve this process attending to rigorous follow-ups of the water quality. In this paper, we present a comparative study of the performance of three techniques resulting from the field of the artificial intelligence namely: Artificial Neural Networks (ANN), RBF Neural Networks (RBF-NN), and Support Vector Machines (SVM). Developed from the statistical learning theory, these methods display optimal training performances and generalization in many fields of application, among others the field of pattern recognition. In order to evaluate their performances regarding the recognition rate, training time, and robustness, a simulation using generated and real data is carried out. To validate their functionalities, an application performed on real data is presented. Applied as a classification tool, the technique selected should ensure, within a multisensor monitoring system, a direct and quasi permanent control of water quality.
30
Pan, Junlin, Guanliang Li, and Haiyan Luo. "Reverse Logistics Enterprise Performance Research Based on Super-Efficiency DEA and LMBP Neural Network." Journal of Physics: Conference Series 2025, no. 1 (September 1, 2021): 012087. http://dx.doi.org/10.1088/1742-6596/2025/1/012087.
Full textAbstract:
Abstract On the basis of considering the characteristics of reverse logistics enterprises, this paper uses stakeholder theory to establish an evaluation system containing 36 indicators in five dimensions, based on the balanced scorecard, and adopts PCA optimization index. In view of the performance evaluation problem, first, the performance data is obtained by using the super-efficiency DEA, then the enterprise performance of A company is fitted by LMBP neural network to obtain the quantitative model of performance evaluation, and finally, according to the resulting weight reference performance benchmark, the direction of reverse logistics enterprise performance improvement is given. The simulation results show that the index system can react to the reverse logistics characteristics very well, and the BP neural network based on LM algorithm can accurately and efficiently evaluate the performance of reverse logistics enterprises which has better generalization, and can find out the key performance indicators and give reasonable optimization direction for enterprises by reverse tracking the weights of the neural network.
31
Bočková, Nina. "Visegrad Four countries: evaluation in R&D sectors of performance." Acta Universitatis Agriculturae et Silviculturae Mendelianae Brunensis 61, no. 4 (2013): 873–80. http://dx.doi.org/10.11118/actaun201361040873.
Full textAbstract:
Competitiveness is currently being studied by many economic analyses. Generalization of the countries’ competitiveness definition as a measure of understanding of the performance evaluation economies is important. Visegrad Four countries: Hungary, the Czech Republic, Slovakia and Poland were admitted to the European Union in May 2004. EU Member States must respect the common EU objectives. The European Union, as expressed in the strategy Europe 2020, is obliged to increase competitiveness, innovation, by introduction of modern technology and especially the growth R&D investment. Limited data to evaluate R&D expenditure: inconsistencies in the R&D support, the absence of data concerning the other means of financing in the sector BERD, limitations of statistical data on the number of innovations only to firms with R&D activities. The aim of this paper is to evaluate the development of R&D expenditures by sector of funding in the Visegrad Four countries in comparison with the values of the EU-27 and countries of Visegrad Four together.
32
Lee, Seung-Yeon, Hyeon Kang, Jong-Hun Jeong, and Do-young Kang. "Performance evaluation in [18F]Florbetaben brain PET images classification using 3D Convolutional Neural Network." PLOS ONE 16, no. 10 (October 20, 2021): e0258214. http://dx.doi.org/10.1371/journal.pone.0258214.
Full textAbstract:
High accuracy has been reported in deep learning classification for amyloid brain scans, an important factor in Alzheimer’s disease diagnosis. However, the possibility of overfitting should be considered, as this model is fitted with sample data. Therefore, we created and evaluated an [18F]Florbetaben amyloid brain positron emission tomography (PET) scan classification model with a Dong-A University Hospital (DAUH) dataset based on a convolutional neural network (CNN), and performed external validation with the Alzheimer’s Disease Neuroimaging Initiative dataset. Spatial normalization, count normalization, and skull stripping preprocessing were performed on the DAUH and external datasets. However, smoothing was only performed on the external dataset. Three types of models were used, depending on their structure: Inception3D, ResNet3D, and VGG3D. After training with 80% of the DAUH dataset, an appropriate model was selected, and the rest of the DAUH dataset was used for model evaluation. The generalization potential of the selected model was then validated using the external dataset. The accuracy of the model evaluation for Inception3D, ResNet3D, and VGG3D was 95.4%, 92.0%, and 97.7%, and the accuracy of the external validation was 76.7%, 67.1%, and 85.3%, respectively. Inception3D and ResNet3D were retrained with the external dataset; then, the area under the curve was compared to determine the binary classification performance with a significance level of less than 0.05. When external validation was performed again after fine tuning, the performance improved to 15.3%p for Inception3D and 16.9%p for ResNet3D. In [18F]Florbetaben amyloid brain PET scan classification using CNN, the generalization potential can be seen through external validation. When there is a significant difference between the model classification performance and the external validation, changing the model structure or fine tuning the model can help improve the classification performance, and the optimal model can also be found by collaborating through a web-based open platform.
33
Wang, Yu. "Multimedia Vocal Performance Automation Evaluation Model Based on RBF Network." Mathematical Problems in Engineering 2022 (January 28, 2022): 1–12. http://dx.doi.org/10.1155/2022/3868389.
Full textAbstract:
Aiming at the problems of the radial basis network model, this paper proposes a multimedia vocal singing automation evaluation network model, combined with the characteristics of multimedia modeling innovation design, and proposes a two-level comprehensive model. First of all, the theory and algorithm of analytic hierarchy process and radial basis function network are researched and analyzed, and the RBF is predicted for the mature area of multimedia development based on the three indicators of the total amount of classified vocals. The prediction scheme evaluation system is then used to fit the prediction data and influencing factors using the RBF network, and then the classified vocals are adjusted and synthesized hierarchically, and a multimedia vocal classification prediction model is established. Finally, this paper uses an example to verify the feasibility performance and prediction accuracy. Based on the above theory, the experiment uses VC++ 6.0 and Matlab 6.5 combined with database technology to initially realize the evaluation system and achieves a good evaluation effect. The simulation results show that three different algorithms are used to establish RBFO content prediction models. The correlation coefficient limit, root mean square error prediction, and relative analysis error (RED) reached 0.9937, 15.5095, and 8.216, respectively. At the same time, the evaluation results have high accuracy and credibility, which not only provide designers with ideas and improvement basis for innovative designs but also ensure design quality, improve design efficiency, and show that RBF networks have good generalization capabilities.
34
Yan, Jianhong, and Suqing Han. "Classifying Imbalanced Data Sets by a Novel RE-Sample and Cost-Sensitive Stacked Generalization Method." Mathematical Problems in Engineering 2018 (2018): 1–13. http://dx.doi.org/10.1155/2018/5036710.
Full textAbstract:
Learning with imbalanced data sets is considered as one of the key topics in machine learning community. Stacking ensemble is an efficient algorithm for normal balance data sets. However, stacking ensemble was seldom applied in imbalance data. In this paper, we proposed a novel RE-sample and Cost-Sensitive Stacked Generalization (RECSG) method based on 2-layer learning models. The first step is Level 0 model generalization including data preprocessing and base model training. The second step is Level 1 model generalization involving cost-sensitive classifier and logistic regression algorithm. In the learning phase, preprocessing techniques can be embedded in imbalance data learning methods. In the cost-sensitive algorithm, cost matrix is combined with both data characters and algorithms. In the RECSG method, ensemble algorithm is combined with imbalance data techniques. According to the experiment results obtained with 17 public imbalanced data sets, as indicated by various evaluation metrics (AUC, GeoMean, and AGeoMean), the proposed method showed the better classification performances than other ensemble and single algorithms. The proposed method is especially more efficient when the performance of base classifier is low. All these demonstrated that the proposed method could be applied in the class imbalance problem.
35
Gao, Feng, Fei Song, Guo Qing Huang, and Mao Yang. "Study on the Effectiveness Evaluation of the Weapon Equipment Based on Artificial Neural Network." Advanced Materials Research 926-930 (May 2014): 3262–65. http://dx.doi.org/10.4028/www.scientific.net/amr.926-930.3262.
Full textAbstract:
A new approach to weapons and equipment effectiveness evaluation based on artificial neural network (ANN) performs better than traditional method, which is in view of the complex relationship between the effectiveness and many factors that influence the evaluation. The structure and learning algorithm of BP neural network is evaluated the fighters’ air-to-air combat capability. The evaluation is accomplished by a two-layer BP neural network and MATLAB toolbox. The simulation results show that the artificial neural network have better generalization ability and approximation performance for continuous function, which is valuable in weapons and equipment effectiveness evaluation application.
36
Liu, Zuo Jun, and Li Hong Li. "An Evaluation Method of Water Quality Based on Improved PSO-BP Network." Advanced Materials Research 846-847 (November 2013): 1243–46. http://dx.doi.org/10.4028/www.scientific.net/amr.846-847.1243.
Full textAbstract:
Because of the existing problems of BP network: easily falling into local minimum point, slowly converging and generalization ability can not be guaranteed, the evaluation method of water quality based on BP network is not satisfactory. Therefore, an algorithm of improved particle swarm optimizing is used to optimize the BP network. On the basis of this, an evaluation method of water quality based on improved PSO-BP network is designed. Proved by experiments, the BP network optimized by improved PSO is stable. So, the performance and efficiency of the water quality evaluation based on improved PSO-BP is pretty good.
37
Abbasi, Wajid Arshad, and Fayyaz Ul Amir Afsar Minhas. "Issues in performance evaluation for host–pathogen protein interaction prediction." Journal of Bioinformatics and Computational Biology 14, no. 03 (June 2016): 1650011. http://dx.doi.org/10.1142/s0219720016500116.
Full textAbstract:
The study of interactions between host and pathogen proteins is important for understanding the underlying mechanisms of infectious diseases and for developing novel therapeutic solutions. Wet-lab techniques for detecting protein–protein interactions (PPIs) can benefit from computational predictions. Machine learning is one of the computational approaches that can assist biologists by predicting promising PPIs. A number of machine learning based methods for predicting host–pathogen interactions (HPI) have been proposed in the literature. The techniques used for assessing the accuracy of such predictors are of critical importance in this domain. In this paper, we question the effectiveness of K-fold cross-validation for estimating the generalization ability of HPI prediction for proteins with no known interactions. K-fold cross-validation does not model this scenario, and we demonstrate a sizable difference between its performance and the performance of an alternative evaluation scheme called leave one pathogen protein out (LOPO) cross-validation. LOPO is more effective in modeling the real world use of HPI predictors, specifically for cases in which no information about the interacting partners of a pathogen protein is available during training. We also point out that currently used metrics such as areas under the precision-recall or receiver operating characteristic curves are not intuitive to biologists and propose simpler and more directly interpretable metrics for this purpose.
38
Sun, Qixuan, Nianhua Fang, Zhuo Liu, Liang Zhao, Youpeng Wen, and Hongxiang Lin. "HybridCTrm: Bridging CNN and Transformer for Multimodal Brain Image Segmentation." Journal of Healthcare Engineering 2021 (October 1, 2021): 1–10. http://dx.doi.org/10.1155/2021/7467261.
Full textAbstract:
Multimodal medical image segmentation is always a critical problem in medical image segmentation. Traditional deep learning methods utilize fully CNNs for encoding given images, thus leading to deficiency of long-range dependencies and bad generalization performance. Recently, a sequence of Transformer-based methodologies emerges in the field of image processing, which brings great generalization and performance in various tasks. On the other hand, traditional CNNs have their own advantages, such as rapid convergence and local representations. Therefore, we analyze a hybrid multimodal segmentation method based on Transformers and CNNs and propose a novel architecture, HybridCTrm network. We conduct experiments using HybridCTrm on two benchmark datasets and compare with HyperDenseNet, a network based on fully CNNs. Results show that our HybridCTrm outperforms HyperDenseNet on most of the evaluation metrics. Furthermore, we analyze the influence of the depth of Transformer on the performance. Besides, we visualize the results and carefully explore how our hybrid methods improve on segmentations.
39
Palkyna, Elena. "BUILDING PERSONNEL MOTIVATION SYSTEM AIMED AT IMPLEMENTATION OF TRANSPORT ORGANIZATION GROWTH STRATEGY." Bulletin of scientific research results, no. 4 (December 17, 2017): 52–62. http://dx.doi.org/10.20295/2223-9987-2017-4-52-62.
Full textAbstract:
Objective: To determine the strategy and tools for building personnel motivation system, aimed at implementation of the transport company’s growth strategy. Methods: The methods of generalization, grouping, analysis, synthesis, systemic approach, abstraction, modeling, formalization, problem setting, the search of literature, documents and performance results, observation, instrumentation, expert evaluation, monitoring, practice research and generalization. Results: The topicality of system integrated approach to personnel motivation was justified. The foundations of personnel motivation were introduced for growth strategy implementation. The conclusion was made on the expedience of building an personnel motivation system on the basis of a balanced system of key performance indicators. The specificity of the developed proposals implementation was demonstrated by the example of a railroad transport operator. Practical importance: The implementation of the introduced principles of building personnel motivation system, based on conceptual regulations of system integrated approach, will make it possible to improve the performance and efficiency of transport organization growth strategy implementation.
40
Berniker, Max, David W. Franklin, J. Randall Flanagan, Daniel M. Wolpert, and Konrad Kording. "Motor learning of novel dynamics is not represented in a single global coordinate system: evaluation of mixed coordinate representations and local learning." Journal of Neurophysiology 111, no. 6 (March 15, 2014): 1165–82. http://dx.doi.org/10.1152/jn.00493.2013.
Full textAbstract:
Successful motor performance requires the ability to adapt motor commands to task dynamics. A central question in movement neuroscience is how these dynamics are represented. Although it is widely assumed that dynamics (e.g., force fields) are represented in intrinsic, joint-based coordinates (Shadmehr R, Mussa-Ivaldi FA. J Neurosci 14: 3208–3224, 1994), recent evidence has questioned this proposal. Here we reexamine the representation of dynamics in two experiments. By testing generalization following changes in shoulder, elbow, or wrist configurations, the first experiment tested for extrinsic, intrinsic, or object-centered representations. No single coordinate frame accounted for the pattern of generalization. Rather, generalization patterns were better accounted for by a mixture of representations or by models that assumed local learning and graded, decaying generalization. A second experiment, in which we replicated the design of an influential study that had suggested encoding in intrinsic coordinates (Shadmehr and Mussa-Ivaldi 1994), yielded similar results. That is, we could not find evidence that dynamics are represented in a single coordinate system. Taken together, our experiments suggest that internal models do not employ a single coordinate system when generalizing and may well be represented as a mixture of coordinate systems, as a single system with local learning, or both.
41
Feng, Li, Nowshad Amin, Jingwei Zhang, Kun Ding, and Frank U. Hamelmann. "Module-Level Performance Evaluation for a Smart PV System Based on Field Conditions." Applied Sciences 13, no. 3 (January 22, 2023): 1448. http://dx.doi.org/10.3390/app13031448.
Full textAbstract:
This study presents an approach with a simple structure, low complexity and low costs to evaluate the real-time status and localize the faults of a smart PV system at module level based on field conditions. The performance evaluation approach of a PV system is developed through the defined performance indicators, a complex data matrix to track module locations and a thermal model to determine the module temperature. The generalization potential of the proposed approach has been demonstrated through the successful experiment validation. The results show that the performance indicators are greatly corrected by the estimated module temperature with great linear agreement in R2 of 0.922 compared to actual measured temperature under same conditions. Due to the effective performance indicators capturing more performance differences caused by faults of cracks in 0.22 of PV_ΔV, partial shading in 0.47 of PV_ΔV, broken sensors in 0.17 of PI_ΔI and 1 of PV_ΔV separately, the proposed approach is very effective in evaluating the performance of PV modules at = module level. Meanwhile, the faulty modules are diagnosed and located through these findings and the data matrix in the smart PV system. Additionally, the sensitivity of the proposed approach to fault in cracks is much higher than that of monitoring only the power.
42
Parakh, Anushri, Hyunkwang Lee, Jeong Hyun Lee, Brian H. Eisner, Dushyant V. Sahani, and Synho Do. "Urinary Stone Detection on CT Images Using Deep Convolutional Neural Networks: Evaluation of Model Performance and Generalization." Radiology: Artificial Intelligence 1, no. 4 (July 2019): e180066. http://dx.doi.org/10.1148/ryai.2019180066.
Full text
43
Wilson, Christy, T. F. McLaughlin, and Andrea Bennett. "Using DI Flashcards with a Count-By Series Procedure with a Fourth Grade Student with ADHD and Learning Issues in a Resource Room Setting Math Facts with an Evaluation of Generalization to New Math Facts." Asian Education Studies 1, no. 1 (February 26, 2016): 23. http://dx.doi.org/10.20849/aes.v1i1.6.
Full textAbstract:
<p>DI flashcards have been proven be improve student performance in a wide range of subject matter-areas. Students with memory issues may well benefit from being taught with DI flashcards. Employing a count-by series has been employed by classroom teachers to teach multiplication. Count-bys can provide students an easy transition from addition to multiplication. This project implemented DI flashcards with a count by series to improve the performance of a single elementary school student having difficulty in math. These two procedures were evaluated in an ABABCB single case design. The results indicated that our participant’s performance increased when these two procedures were combined. Finally generalization was carried out with new math facts. When DI flashcards and the count by series charts were again employed with his new math facts, his performance quickly increased. Suggestions for future research employing DI flashcards and generalization of treatment outcomes were also provided.</p>
44
Zhang, Lei, and Qiankun Song. "Credit Evaluation of SMEs Based on GBDT-CNN-LR Hybrid Integrated Model." Wireless Communications and Mobile Computing 2022 (February 11, 2022): 1–8. http://dx.doi.org/10.1155/2022/5251228.
Full textAbstract:
Under the background of the increasing demand for credit evaluation and risk prediction, the establishment of an effective credit evaluation model for small- and medium-sized enterprises has become a research hotspot. Based on previous studies, this paper proposes a two-layer feature extraction method based on Gradient Boosting Decision Tree (GBDT) and Convolutional Neural Network (CNN). First, based on the original features, GBDT is used to combine and automatically screen them, the missing values in the feature are processed, and the transformed high-dimensional sparse features are obtained. Then, CNN is used to extract features further, and finally, the logistic regression (LR) model is used to predict. In the simulation experiment, this paper takes a dataset of 14,366 small- and medium-sized enterprise credit evaluations as the analysis samples to verify the results. The results show that the GBDT-CNN-LR model has the best performance. The model also shows good generalization ability and stability in the reliability test.
45
Xue, Cheng, Vimukthini Pinto, Chathura Gamage, Ekaterina Nikonova, Peng Zhang, and Jochen Renz. "Phy-Q as a measure for physical reasoning intelligence." Nature Machine Intelligence 5, no. 1 (January 25, 2023): 83–93. http://dx.doi.org/10.1038/s42256-022-00583-4.
Full textAbstract:
AbstractHumans are well versed in reasoning about the behaviours of physical objects and choosing actions accordingly to accomplish tasks, while this remains a major challenge for artificial intelligence. To facilitate research addressing this problem, we propose a new testbed that requires an agent to reason about physical scenarios and take an action appropriately. Inspired by the physical knowledge acquired in infancy and the capabilities required for robots to operate in real-world environments, we identify 15 essential physical scenarios. We create a wide variety of distinct task templates, and we ensure that all the task templates within the same scenario can be solved by using one specific strategic physical rule. By having such a design, we evaluate two distinct levels of generalization, namely local generalization and broad generalization. We conduct an extensive evaluation with human players, learning agents with various input types and architectures, and heuristic agents with different strategies. Inspired by how the human intelligence quotient is calculated, we define the physical reasoning quotient (Phy-Q score) that reflects the physical reasoning intelligence of an agent using the physical scenarios we considered. Our evaluation shows that (1) all the agents are far below human performance, and (2) learning agents, even with good local generalization ability, struggle to learn the underlying physical reasoning rules and fail to generalize broadly. We encourage the development of intelligent agents that can reach the human-level Phy-Q score.
46
Wanyama, Mildred Bakhoya, and Frederick Aila. "Strategic Management Practices and Performance of Parastatals in Kenya." European Journal of Management Issues 30, no. 2 (June 25, 2022): 116–22. http://dx.doi.org/10.15421/192211.
Full textAbstract:
Purpose: The purpose of the study is to help firms use strategy as an important tool helping both management and employees in control and evaluation of whether or not the institution’s objectives are met.
Design / Method / Approach: The researcher used an exploratory study design, and the data was collected through organised interviews via telephone to gather everything that is relevant for the study. Qualitative data collected was thereafter analysed by finding out similarities and differences among the responses collected from different institutions and conclusions made.
Findings: The findings indicate that strategic management practices are useful predictor variables of performance. The composite R2 value of .714 which indicates that 71.4% variation of performance in parastatals in Kenya is as a result of strategic management practices. Of these practices, strategy implementation had the highest impact on performance. The least was strategy evaluation.
Theoretical Implications: Strategic fit theory was used to analyse the performance of each parastatal. The researcher then presented the data using a descriptive approach by the use of illustrative quotes.
Practical Implications: The performance of parastatals is good with both employees and consumers reporting high levels of satisfaction.
Originality/Value: To achieve any organizational goals, a parastatal needs to plan, formulate and implement. The document is to encourage top management in parastatals to practice strategic management as it will have a positive impact on performance in parastatals in Kenya.
Research Limitations / Future Research: Like many research studies, a small group of 14 parastatals was examined, and conclusions were made basing on the findings from this sample. This brought about a generalization that was applied to all other subjects in the field. This generalization appeared somewhat unfair judgement about other parastatals from where participants were not selected because different institutions may have different cultures and levels of professionalism, practice and performance when it comes to matters of strategic management.
Paper type: Empirical
47
Noh, Kyoung Ju, Chi Yoon Jeong, Jiyoun Lim, Seungeun Chung, Gague Kim, Jeong Mook Lim, and Hyuntae Jeong. "Multi-Path and Group-Loss-Based Network for Speech Emotion Recognition in Multi-Domain Datasets." Sensors 21, no. 5 (February 24, 2021): 1579. http://dx.doi.org/10.3390/s21051579.
Full textAbstract:
Speech emotion recognition (SER) is a natural method of recognizing individual emotions in everyday life. To distribute SER models to real-world applications, some key challenges must be overcome, such as the lack of datasets tagged with emotion labels and the weak generalization of the SER model for an unseen target domain. This study proposes a multi-path and group-loss-based network (MPGLN) for SER to support multi-domain adaptation. The proposed model includes a bidirectional long short-term memory-based temporal feature generator and a transferred feature extractor from the pre-trained VGG-like audio classification model (VGGish), and it learns simultaneously based on multiple losses according to the association of emotion labels in the discrete and dimensional models. For the evaluation of the MPGLN SER as applied to multi-cultural domain datasets, the Korean Emotional Speech Database (KESD), including KESDy18 and KESDy19, is constructed, and the English-speaking Interactive Emotional Dyadic Motion Capture database (IEMOCAP) is used. The evaluation of multi-domain adaptation and domain generalization showed 3.7% and 3.5% improvements, respectively, of the F1 score when comparing the performance of MPGLN SER with a baseline SER model that uses a temporal feature generator. We show that the MPGLN SER efficiently supports multi-domain adaptation and reinforces model generalization.
48
Arkhipova, I. V. "ASSESSMENT OF THE RELIABILITY OF VACUUM PRECISION PIEZOELECTRIC RESONATORS ACCORDING TO THE RESULTS OF THE ACCUMULATION AND COMPILATION OF THEIR LIFE CYCLE." Issues of radio electronics, no. 7 (July 20, 2018): 65–71. http://dx.doi.org/10.21778/2218-5453-2018-7-65-71.
Full textAbstract:
Within the framework of this article the question of reliability evaluation of resonators with strict performance requirements for resistance to external factors is considered. Due to the increase in requirements for these products in terms of gamma-percentile time to failure and gamma-percentile storageability time, there is a need to develop new ideas and methods of reliability theory. As a methodical basis for generalization of data of their life cycle the approach on the basis of Bayesian theorem is offered. Based on the results of generalization of the statistics of resonator tests for various types of climatic influences and reliability tests, as well as the results of their use in the electronic equipment have been identified their main reliability indicators.
49
Huang, Cheng, Fang Li, Lei Wei, Xudong Hu, and Yingdong Yang. "Landslide Susceptibility Modeling Using a Deep Random Neural Network." Applied Sciences 12, no. 24 (December 15, 2022): 12887. http://dx.doi.org/10.3390/app122412887.
Full textAbstract:
Developing landslide susceptibility modeling is essential for detecting landslide-prone areas. Recently, deep learning theories and methods have been investigated in landslide modeling. However, their generalization is hindered because of the limited size of landslide data. In the present study, a novel deep learning-based landslide susceptibility assessment method named deep random neural network (DRNN) is proposed. In DRNN, a random mechanism is constructed to drop network layers and nodes randomly during landslide modeling. We take the Lushui area (Southwest China) as the case and select 12 landslide conditioning factors to perform landslide modeling. The performance evaluation results show that our method achieves desirable generalization performance (Kappa = 0.829) and outperforms other network models such as the convolution neural network (Kappa = 0.767), deep feedforward neural network (Kappa = 0.731), and Adaboost-based artificial neural network (Kappa = 0.732). Moreover, the robustness test shows the advantage of our DRNN, which is insensitive to variations in training data size. Our method yields an accuracy higher than 85% when the training data size stands at only 10%. The results demonstrate the effectiveness of the proposed landslide modeling method in enhancing generalization. The proposed DRNN produces accurate results in terms of delineating landslide-prone areas and shows promising applications.
50
Mehdipour Pirbazari, Aida, Mina Farmanbar, Antorweep Chakravorty, and Chunming Rong. "Short-Term Load Forecasting Using Smart Meter Data: A Generalization Analysis." Processes 8, no. 4 (April 21, 2020): 484. http://dx.doi.org/10.3390/pr8040484.
Full textAbstract:
Short-term load forecasting ensures the efficient operation of power systems besides affording continuous power supply for energy consumers. Smart meters that are capable of providing detailed information on buildings energy consumption, open several doors of opportunity to short-term load forecasting at the individual building level. In the current paper, four machine learning methods have been employed to forecast the daily peak and hourly energy consumption of domestic buildings. The utilized models depend merely on buildings historical energy consumption and are evaluated on the profiles that were not previously trained on. It is evident that developing data-driven models lacking external information such as weather and building data are of great importance under the situations that the access to such information is limited or the computational procedures are costly. Moreover, the performance evaluation of the models on separated house profiles determines their generalization ability for unseen consumption profiles. The conducted experiments on the smart meter data of several UK houses demonstrated that if the models are fed with sufficient historical data, they can be generalized to a satisfactory level and produce quite accurate results even if they only use past consumption values as the predictor variables. Furthermore, among the four applied models, the ones based on deep learning and ensemble techniques, display better performance in predicting daily peak load consumption than those of others.