- Supplementary Content
8
- 10.1016/j.matt.2020.09.012
Learning What Makes Catalysts Good
- Oct 01, 2020
- Matter
- Nongnuch Artrith
Learning What Makes Catalysts Good
Recent studies have proposed a model using the supervised neural-network (NN) as the haptic model. However, this model has the problem in expressing human tactile sense. Therefore, we constructed a haptic stage model based on the model of human-tactile sense and cognitive process. Our NN-based model consists of supervised and unsupervised stages. Using surface-scanning results from our trial micro-tactile sensor, we confirmed the material-identification problem with our model. A conventional full conventional NN(CNN) model achieved a 98.0% correct identification rate for 28 materials; our model achieved a rate of 67.2%. Our model employed typically is deepening because we used the convolutional process in all layers, therefore, we consider that our learning result lost local features on each material, and then identification rate was declined as result.
Learning What Makes Catalysts Good
Learning What Makes Catalysts Good
Real-time Haptic Modeling and Simulation for Prosthetic Insertion
In this work a surgical simulator is produced which enables a training otologist to conduct a virtual, real-time prosthetic insertion. The simulator provides the Ear, Nose and Throat surgeon with real-time visual and haptic responses during virtual cochlear implantation into a 3D model of the human Scala Tympani (ST). The parametric model is derived from measured data as published in the literature and accounts for human morphological variance, such as differences in cochlear shape, enabling patient-specific preoperative assessment. Haptic modeling techniques use real physical data and insertion force measurements, to develop a force model which mimics the physical behavior of an implant as it collides with the ST walls during an insertion. Output force profiles are acquired from the insertion studies conducted in the work, to validate the haptic model. The simulator provides the user with real-time, quantitative insertion force information and associated electrode position as user inserts the virtual implant into the ST model. The information provided by this study may also be of use to implant manufacturers for design enhancements as well as for training specialists in optimal force administration, using the simulator. The paper reports on the methods for anatomical modeling and haptic algorithm development, with focus on simulator design, development, optimization and validation. The techniques may be transferrable to other medical applications that involve prosthetic device insertions where user vision is obstructed.
Read moreAn Empirical Study of the Performance of Different Optimizers in the Deep Neural Networks
In recent years, the Stochastic Gradient Descent (SGD) has been commonly used as an optimizer in the Conventional Neural Network (CNN) models. While many researchers have adopted CNN models to classify tasks, to the best of our knowledge, different optimizers developed for CNN have not been thoroughly studied and analyzed in the training CNNs. In this paper, attempts have been made to investigate the effects of the various optimizers on the performance of CNN. Two sets of experiments are conducted. First, for the classification of the records on the CIFAR10, MNIST, and Fashion MNIST datasets, a well-known CNN called VGG11 is trained from scratch by four different kinds of optimizers including SGD, Adam, Adadelta, and AdaGrad. Second, by the same four optimizers, a popular CNN architecture called AlexNet is fine-tuned to classify the Persian handwritten words. In both experiments, the results showed that Adam and AdaGrad have a relatively similar behavior and higher performance in comparison to the other two optimizers in terms of training cost and recognition accuracy. Also, the effect of different values of the initial learning rate on the performance of the Adam optimizer is investigated experimentally. The result revealed that lower values lead to converges more rapidly.
Read moreA Neural Network Approach for Signal Detection in Digital Communications
In this paper, we propose a new approach for signal detection in wireless digital communications based on the neural network with transient chaos and time-varying gain (NNTCTG), and give a concrete model of the signal detector after appropriate transformations and mappings. It is well known that the problem of the maximum likelihood signal detection can be described as a complex optimization problem that has so many local optima that conventional Hopfield-type neural networks fail to solve. By refraining from the serious local optima problem of Hopfield-type neural networks, the NNTCTG makes use of the time-varying parameters of the recurrent neural network to control the evolving behavior of the network so that the network undergoes the transition from chaotic behavior to gradient convergence. It has richer and more flexible dynamics rather than conventional neural networks only with point attractors, so that it can be expected to have much ability to search for globally optimal or near-optimal solutions. After going through a transiently inverse-bifurcation process, the NNTCTG can approach the global optimum or the neighborhood of global optimum of our problem. Simulation experiments have been performed to show the effectiveness and validation of the proposed neural network based method for the signal detection in digital communications.
Read moreRetrieving ground-level PM 2.5 concentrations in China (2013–2021) with a numerical-model-informed testbed to mitigate sample-imbalance-induced biases
Abstract. Ground-level PM2.5 data derived from satellites with machine learning are crucial for health and climate assessments. However, uncertainties persist due to the absence of spatially covered observations. To address this, we propose a novel testbed using nontraditional numerical simulations to evaluate PM2.5 estimation across the entire spatial domain. The testbed emulates the general machine-learning approach by training the model with grids corresponding to ground monitoring sites and subsequently testing its predictive accuracy for other locations. Our approach enables comprehensive evaluation of various machine-learning methods' performance in estimating PM2.5 across the spatial domain for the first time. Unexpected results are shown in the application in China, with larger absolute PM2.5 biases found in densely populated regions with abundant ground observations across all benchmark models due to the higher baseline concentration, though the relative error (approximately 20 %) is smaller compared to that in rural areas (over 50 %). The imbalance in training samples, mostly from urban areas with high emissions, is the main reason, leading to significant overestimation due to the lack of monitors in downwind areas where PM2.5 is transported from urban areas with varying vertical profiles. Our proposed testbed also provides an efficient strategy for optimizing model structure or training samples to enhance satellite-retrieval model performance. Integration of spatiotemporal features, especially with conventional neural network (CNN)-based deep-learning approaches like the residual neural network (ResNet) model, has successfully mitigated PM2.5 overestimation (by 5–30 µg m−3) and the corresponding exposure (by 3 million people ⋅ µg m−3) in the downwind area over 9 years (2013–2021) compared to the traditional approach. Furthermore, the incorporation of 600 strategically positioned ground monitoring sites identified through the testbed is essential for achieving a more balanced distribution of training samples, thereby ensuring precise PM2.5 estimation and facilitating the assessment of the associated impacts in China. In addition to presenting the retrieved surface PM2.5 concentrations in China from 2013 to 2021, this study provides a testbed dataset derived from physical modeling simulations which can serve to evaluate the performance of data-driven methodologies, such as machine learning, in estimating spatial PM2.5 concentrations for the community (Li et al., 2024a; https://doi.org/10.5281/zenodo.11122294).
Read morePerformance comparison of artificial neural network and multiple regression models for wire electrical discharge machining of haste alloy
Performance comparison of artificial neural network and multiple regression models for wire electrical discharge machining of haste alloy
Read moreFour Models of Hopfield-Type Octonion Neural Networks and Their Existing Conditions of Energy Functions
Recently, models of neural networks in the real domain have been extended into the high dimensional domain such as the complex number and quaternion domain, and several high-dimensional models have been proposed. These extensions are generalized by introducing Clifford algebra (geometric algebra). In this paper we extend conventional real-valued Hopfield-type neural networks into the octonion domain and discuss their dynamics. The octonions represent a particular extension of the quaternions which also represent a particular extension of the complex numbers and have 7 imaginary parts. They are non-commutative and non-associative on multiplication and do not belong to Clifford algebra due to the latter fact. With this in mind we propose four models of octonion Hopfield-type neural networks. We derive existence conditions of an energy function and construct energy function for each model.
Read moreIntroduction to JSTQE Issue on Photonics for Deep Learning and Neural Computing
The papers in this special section examine neuromorphic photonics which combines optical physics and unconventional computing, resulting in a new class of ultrafast information processors for neuromorphic information and signal processing, machine learning, and high-performance computing. These processors can enable applications where low latency, high bandwidth, and low switching energies are paramount. Fundamentally, such computing concepts heavily depend on interconnects, a functionality where photonic processors can significantly outperform electronic systems. By combining the high bandwidth and efficiency of photonic devices with the adaptive, parallelism and complexity similar to the brain, photonic neural networks have the potential to be faster than conventional neural networks, while consuming less energy.
Read morePerformance of Qubit Neural Network in Chaotic Time Series Forecasting
In recent years, quantum inspired neural networks have been applied to various practical problems since their proposal. Here we investigate whether our qubit neural network(QNN) leads to an advantage over the conventional (real-valued) neural network(NN) in the forecasting of chaotic time series. QNN is constructed from a set of qubit neuron, of which internal state is a coherent superposition of qubit states. In this paper, we evaluate the performance of QNN through a prediction of well-known Lorentz attractor, which produces chaotic time series by three dynamical systems. The experimental results show that QNN can forecast time series more precisely, compared with the conventional NN. In addition, we found that QNN outperforms the conventional NN by reconstructing the trajectories of Lorentz attractor.
Read moreMultivariate optimization of the electrochemical degradation for COD and TN removal from wastewater: An inverse computation machine learning approach
Multivariate optimization of the electrochemical degradation for COD and TN removal from wastewater: An inverse computation machine learning approach
Read moreDesign of a Novel Neural Networks Based On Rough Sets
This paper proposed a novel neural network based on rough sets theory. Firstly a rules extracted method is discussed, and a set of rough rules are found from the given training data based on rough sets theory. Secondly, the structure and model of the neural network are designed according to these rules, and the training algorithm with high-precision of learning is formulated based on neural networks techniques. Compared with the conventional neural network, the proposed neural network have the following advantage: good understandability, simple computation and high-precision.. Finally, a lot of numerical simulations have been conducted, and simulation results have shown that the novel neural network is feasible and efficient in function approximation. The novel neural network has great potential in the application areas of signal processing, pattern recognition, process modeling and implementation of high-precision real-time intelligent controller.
Read morePlant Species Classification Based on Hyperspectral Imaging via a Lightweight Convolutional Neural Network Model.
In recent years, many image-based approaches have been proposed to classify plant species. Most methods utilized red green blue (RGB) imaging materials and designed custom features to classify the plant images using machine learning algorithms. Those works primarily focused on analyzing single-leaf images instead of live-crown images. Without considering the additional features of the leaves’ color and spatial pattern, they failed to handle cases that contained leaves similar in appearance due to the limited spectral information of RGB imaging. To tackle this dilemma, this study proposes a novel framework that combines hyperspectral imaging (HSI) and deep learning techniques for plant image classification. We built a plant image dataset containing 1,500 images of 30 different plant species taken by a 470–900 nm hyperspectral camera and designed a lightweight conventional neural network (CNN) model (LtCNN) to perform image classification. Several state-of-art CNN classifiers are chosen for comparison. The impact of using different band combinations as the network input is also investigated. Results show that using simulated RGB images achieves a kappa coefficient of nearly 0.90 while using the combination of 3-band RGB and 3-band near-infrared images can improve to 0.95. It is also found that the proposed LtCNN can obtain a satisfactory performance of plant classification (kappa = 0.95) using critical spectral features of the green edge (591 nm), red-edge (682 nm), and near-infrared (762 nm) bands. This study also demonstrates the excellent adaptability of the LtCNN model in recognizing leaf features of plant live-crown images while using a relatively smaller number of training samples than complex CNN models such as AlexNet, GoogLeNet, and VGGNet.
Read moreThe Sixth International Symposium on Neural Networks (ISNN 2009)
The Sixth International Symposium on Neural Networks (ISNN 2009)
Are Neural Networks Better than Machine Learning? A Comparative Study for Travel Mode Predictions
Predicting how people choose their travel modes accurately is important in the transportation field. Machine learning (ML) and neural networks (NNs) have gradually become popular in recent years. However, which is better is seldom discussed in previous studies. Therefore, we collect several real-world travel datasets from different countries, and pick five typical ML models, six classic NN models, and ten new NN models for comparison. Some methods for improvement are also considered, including SMOTE, Near-Miss, and using focal loss. The results show that, when looking at the F1-score, the NN models do not perform as well as ML models. While the performances of different classic NN models are similar, making the neural network more complex does not improve the prediction results. Some new NN models can reach the level of ML models on small datasets, but they still perform poorly on large datasets. Due to such a result, we further discuss two important topics: why NN models are not as good as compared to the ones in some other fields, and why this phenomenon is not revealed in many previous papers. In summary, we think this study gives a good reference for future research on predicting travel modes and choosing the right models.
Read moreA tutorial on deep learning-based data analytics in manufacturing through a welding case study
A tutorial on deep learning-based data analytics in manufacturing through a welding case study