There are many interactive design tools: Adobe Photoshop, GIMP, and so on. The interactive design tools often provide their users many visual effects. The users need to look for design parameter values appropriate to ...
详细信息
There are many interactive design tools: Adobe Photoshop, GIMP, and so on. The interactive design tools often provide their users many visual effects. The users need to look for design parameter values appropriate to their desired visual effect. Interactive design can be dealt as a sort of optimal solution search problems. In optimal solution search, initial value setting plays an important role. Onomatopoeia can solve the initial value setting of the interactive design because onomatopoeia can easily describe the visual effect. We proposed a method that allows the users to input their own arbitrary onomatopoeia to design and obtain their desired visual effect. The method hires an onomatopoeia thesaurus map that can convert the arbitrary onomatopoeia to the initial values. We adopted Japanese brush font design system as an experimental example of the interactive design tool in order to evaluate our proposed method. Human subjects used the system and set the initial values of design parameters to design bold and scratched look of target fonts. As a result, the method was able to set more appropriate initial values closer to the optimal values to design the target in comparison with other conventional methods. The proposed method can be useful to solve the initial value setting of the interactive design.
The field of machine learning deals with a huge amount of various algorithms, which are able to transform the observed data into many forms and dimensionality reduction (DR) is one of such transformations. There are m...
详细信息
The field of machine learning deals with a huge amount of various algorithms, which are able to transform the observed data into many forms and dimensionality reduction (DR) is one of such transformations. There are many high quality papers which compares some of the DR's approaches and of course there other experiments which applies them with success. Not everyone is focused on information lost, increase of relevance or decrease of uncertainty during the transformation, which is hard to estimate and only few studies remark it briefly. This study aims to explain these inner features of four different DR's algorithms. These algorithms were not chosen randomly, but in purpose. It is chosen some representative from all of the major DR's groups. The comparison criteria are based on statistical dependencies, such as Correlation Coefficient, Euclidean Distance, Mutual Information and Granger causality. The winning algorithm should reasonably transform the input dataset with keeping the most of the inner dependencies.
The prediction of rutting performance of asphalt materials poses a significant challenge due to the intricate relationships between the rutting performance and its influencing factors. Machine learning models have gai...
详细信息
The prediction of rutting performance of asphalt materials poses a significant challenge due to the intricate relationships between the rutting performance and its influencing factors. Machine learning models have gained popularity to address this challenge by offering sophisticated model structures and algorithms. However, existing models often prioritize model accuracy over stability and rationality. The increasingly complicated model structure may lead to an imbalance between the data and the model, resulting in issues such as overfitting and reduced model applicability and interpretability. In this context, this study proposes a novel modeling framework to predict the rutting performance of asphalt mixture by utilizing autoencoder for feature selection and feedforward neural network for rut depth prediction. Notably, physics information of the selected variables is implemented into the neural network to achieve the appropriate balance of model accuracy, stability, and rationality. The results demonstrate that while maintaining high model accuracy, the implementation of physics information significantly enhances the model's stability and rationality. This framework holds great potential for accurate and reliable predictions of pavement distress by leveraging the complementary strengths of data -driven machine learning and physics -based domain knowledge.
Structural health monitoring (SHM) systems evaluate the state of the infrastructures by analyzing the monitored responses. As measuring all target responses is difficult to accomplish due to technical or economic limi...
详细信息
Structural health monitoring (SHM) systems evaluate the state of the infrastructures by analyzing the monitored responses. As measuring all target responses is difficult to accomplish due to technical or economic limitations, converting other easy-measuring responses to the target one is a popular way. Relative approaches are separated into data-driven and model-driven ones. This paper proposes a deep learning-based framework to reconstruct multitypes of full-field responses. The adopted architecture is a convolutional neural network (CNN) with an autoencoder structure and skip connections. Varied from other data-driven approaches, the training set in this paper is the responses computed by a finite element model (FEM), with which the CNN can learn the full-field mapping relationships among varied response types. Therefore, the proposed framework is data-model-co-driven. In the numerical simulation section, a simply-supported beam and a continuous beam bridge have been adopted to discuss the influence of hyperparameters (training epoch, kernel size, skip connection, and bottleneck size), sensor arrangement, modeling error, and measurement noise, which indicates that the framework applies to the in-field structures. Furtherly, a laboratory experiment has been conducted to validate the framework using a two-span continuous bridge with obvious FEM error. All results have shown that the deep-learning-based response reconstruction algorithms can obtain the training set from not only in-field measurements, but also numerical models to improve the diversity of training data.
With the increasingly serious global energy problem, clean energy sources such as solar energy have become the mainstream focus of development. Among these, solar Photovoltaic thermal (PVT) heat pump systems have prom...
详细信息
With the increasingly serious global energy problem, clean energy sources such as solar energy have become the mainstream focus of development. Among these, solar Photovoltaic thermal (PVT) heat pump systems have promising prospects. However, incorrect data transmitted by sensors can significantly impact the operation and control of the entire heat pump system, leading to reduced efficiency. Given the specific nature of PVT heat pump systems, their internal sensors are prone to errors during operation. To address these challenges, the autoencoder Virtual in-situ calibration (AE-VIC) is applied to PVT heat pump systems. Preliminary studies have shown that this method can effectively reduce systematic and random errors in sensors. However, the current AE-VIC method faces certain issues, including unclear calibration targets and inefficient calibration of multiple sensors simultaneously, making it difficult to implement in practical systems. In order to overcome the limitations, fault detection is integrated with AE-VIC. By combining the feature extraction capability of autoencoder with a Softmax classifier, sensors with faults can be identified before the overall calibration process, making the calibration objective of the AE-VIC more targeted. Following fault detection, inputs of the AE model are optimized using the mRMR algorithm for the identified faulty sensors. This optimization alleviates the difficulty of calibration. Through validation with actual system, the improved method effectively diagnoses and locates faulty sensors, and subsequently calibrates them. After calibration, the sensor system error can be reduced by over 95%. The improved calibration method surpasses the original AEVIC method in terms of both time and accuracy.
This paper mainly is to compare vowel recognition of mandarin isolated words using different neural network architectures including MLP, RBFN, and DNN. MFCC features extracted and preprocessed from voice signal are se...
详细信息
This paper mainly is to compare vowel recognition of mandarin isolated words using different neural network architectures including MLP, RBFN, and DNN. MFCC features extracted and preprocessed from voice signal are served as the input data. We find MLP and the pretrained version of it, DNN, are both comparable as well as superior to RBFN in terms of recognition rate. The properties of each kind of neural network are also graphed and explored. Both MLP and RBFN decrease word error rates rapidly in the early stage of learning. DNN gets a very good start after pretraining. Many tentative methods revising the standard algorithms are further conducted, trying to improve the recognition. With proper design, the speaker-dependent speech recognition rate can achieve 95.4%. Our constructive scheme of neural network also substantially shortens the training time which is an issue for deeper or wider neural networks.
Detecting abnormal conditions in manufacturing processes is a crucial task to avoid unplanned downtimes and prevent quality issues. The increasing amount of available high-frequency process data combined with advances...
详细信息
Detecting abnormal conditions in manufacturing processes is a crucial task to avoid unplanned downtimes and prevent quality issues. The increasing amount of available high-frequency process data combined with advances in the field of deep autoencoder-based monitoring offers huge potential in enhancing the performance of existing Multivariate Statistical Process Control approaches. We investigate the application of deep auto encoder-based monitoring approaches and experiment with the reconstruction error and the latent representation of the input data to compute Hotelling’s T 2 and Squared Prediction Error monitoring statistics. The investigated approaches are validated using a real-world sheet metal forming process and show promising results.
The advances in deep neural networks (DNN) have significantly enhanced real-time detection of anomalous data in IoT applications. However, the complexity-accuracy-delay dilemma persists: Complex DNN models offer highe...
详细信息
The advances in deep neural networks (DNN) have significantly enhanced real-time detection of anomalous data in IoT applications. However, the complexity-accuracy-delay dilemma persists: Complex DNN models offer higher accuracy, but typical IoT devices can barely afford the computation load, and the remedy of offloading the load to the cloud incurs long delay. In this article, we address this challenge by proposing an adaptive anomaly detection scheme with hierarchical edge computing (HEC). Specifically, we first construct multiple anomaly detection DNN models with increasing complexity and associate each of them to a corresponding HEC layer. Then, we design an adaptive model selection scheme that is formulated as a contextual-bandit problem and solved by using a reinforcement learning policy network. We also incorporate a parallelism policy training method to accelerate the training process by taking advantage of distributed models. We build an HEC testbed using real IoT devices and implement and evaluate our contextual-bandit approach with both univariate and multivariate IoT datasets. In comparison with both baseline and state-of-the-art schemes, our adaptive approach strikes the best accuracy-delay tradeoff on the univariate dataset and achieves the best accuracy and F1-score on the multivariate dataset with only negligibly longer delay than the best (but inflexible) scheme.
A smile is a specific movement of face muscles to relay an optimistic feeling. A smile represents satisfaction and happiness. Many application created using smile detection technology, for example product rating, pati...
详细信息
A smile is a specific movement of face muscles to relay an optimistic feeling. A smile represents satisfaction and happiness. Many application created using smile detection technology, for example product rating, patient monitoring, image capturing, video conferencing and interactive systems. There are many smile detections techniques have been proposed for smile detection in the unconstrained scenarios. However, the dimensions of most notable feature descriptors are humongous, which is challenging in real-time applications. Besides, feature should be more powerful to identify between smiling and non-smiling face. The proposed method has two consecutive actions: 1) amalgamation of geometric feature extraction (GFE) and regional local binary pattern (LBP) features extraction using autoencoders; 2) Kohonen selforganizing map (KSOM) is adopted to classify smile based on these features. The proposed method is mathematics more dynamic and performance wise more precise. The performance of the propounded approach is proved on GENKI-4K database.
River, which supply 90% of the readily accessible water, are key elements of universal water source system. Terengganu River situated in Terengganu, Malaysia is a modern busy city known for tourism, fishing, and indus...
详细信息
River, which supply 90% of the readily accessible water, are key elements of universal water source system. Terengganu River situated in Terengganu, Malaysia is a modern busy city known for tourism, fishing, and industry. Due to that, it has increased risk of water pollution exposure. Therefore, this paper proposes unsupervised ML include autoencoder and Self-Organizing Map (SOM) for clustering water pollution area along the Terengganu River. Then, uses Silhouette analysis to assess the total of optimum clusters in a dataset. Next, applies Adjusted Rank Index (ARI) to discover the finest comparing within original data with autoencoder and SOM. Lastly, applies Elbow method to double verify the most excellent clusters for each clustering algorithm. Lastly, lists of polluted area in each cluster are retrieved from 14 main sampling stations with 24 water quality parameters, including 405 water samples. Result shows different cluster with different water samples. Thus, offer different strategies to manage polluted area for Terengganu River.
暂无评论