Improved Model Configuration Strategies for Kannada Handwritten Numeral Recognition

Handwritten numeral recognition has been an important area in the domain of pattern classification. The task becomes even more daunting when working with non-Roman numerals. While convolutional neural networks are the preferred choice for modeling the image data, the conception of techniques to obtain faster convergence and accurate results still poses an enigma to the researchers. In this paper, we present new methods for the initialization and the optimization of the traditional convolutional neural network architecture to obtain better results for Kannada numeral images. Specifically, we propose two different methods- an encoderdecoder setup for unsupervised training and weight initialization, and a particle swarm optimization strategy for choosing the ideal architecture configuration of the CNN. Unsupervised initial training of the architecture helps for a faster convergence owing to more task-suited weights as compared to random initialization while the optimization strategy is helpful to reduce the time required for the manual iterative approach of architecture selection. The proposed setup is trained on varying handwritten Kannada numerals. The proposed approaches are evaluated on two different datasets: a standard Dig-MNIST dataset and a custom-built dataset. Significant improvements across multiple performance metrics are observed in our proposed system over the traditional CNN training setup. The improvement in results makes a strong case for relying on such methods for faster and more accurate training and inference of digit classification, especially when working in the absence of transfer learning.

Unsupervised feature learning for electrocardiogram data using the convolutional variational autoencoder

Most existing electrocardiogram (ECG) feature extraction methods rely on rule-based approaches. It is difficult to manually define all ECG features. We propose an unsupervised feature learning method using a convolutional variational autoencoder (CVAE) that can extract ECG features with unlabeled data. We used 596,000 ECG samples from 1,278 patients archived in biosignal databases from intensive care units to train the CVAE. Three external datasets were used for feature validation using two approaches. First, we explored the features without an additional training process. Clustering, latent space exploration, and anomaly detection were conducted. We confirmed that CVAE features reflected the various types of ECG rhythms. Second, we applied CVAE features to new tasks as input data and CVAE weights to weight initialization for different models for transfer learning for the classification of 12 types of arrhythmias. The f1-score for arrhythmia classification with extreme gradient boosting was 0.86 using CVAE features only. The f1-score of the model in which weights were initialized with the CVAE encoder was 5% better than that obtained with random initialization. Unsupervised feature learning with CVAE can extract the characteristics of various types of ECGs and can be an alternative to the feature extraction method for ECGs.

Deep/Transfer Learning with Feature Space Ensemble Networks (FeatSpaceEnsNets) and Average Ensemble Networks (AvgEnsNets) for Change Detection Using DInSAR Sentinel-1 and Optical Sentinel-2 Satellite Data Fusion

Differential interferometric synthetic aperture radar (DInSAR), coherence, phase, and displacement are derived from processing SAR images to monitor geological phenomena and urban change. Previously, Sentinel-1 SAR data combined with Sentinel-2 optical imagery has improved classification accuracy in various domains. However, the fusing of Sentinel-1 DInSAR processed imagery with Sentinel-2 optical imagery has not been thoroughly investigated. Thus, we explored this fusion in urban change detection by creating a verified balanced binary classification dataset comprising 1440 blobs. Machine learning models using feature descriptors and non-deep learning classifiers, including a two-layer convolutional neural network (ConvNet2), were used as baselines. Transfer learning by feature extraction (TLFE) using various pre-trained models, deep learning from random initialization, and transfer learning by fine-tuning (TLFT) were all evaluated. We introduce a feature space ensemble family (FeatSpaceEnsNet), an average ensemble family (AvgEnsNet), and a hybrid ensemble family (HybridEnsNet) of TLFE neural networks. The FeatSpaceEnsNets combine TLFE features directly in the feature space using logistic regression. AvgEnsNets combine TLFEs at the decision level by aggregation. HybridEnsNets are a combination of FeatSpaceEnsNets and AvgEnsNets. Several FeatSpaceEnsNets, AvgEnsNets, and HybridEnsNets, comprising a heterogeneous mixture of different depth and architecture models, are defined and evaluated. We show that, in general, TLFE outperforms both TLFT and classic deep learning for the small dataset used and that larger ensembles of TLFE models do not always improve accuracy. The best performing ensemble is an AvgEnsNet (84.862%) comprised of a ResNet50, ResNeXt50, and EfficientNet B4. This was matched by a similarly composed FeatSpaceEnsNet with an F1 score of 0.001 and variance of 0.266 less. The best performing HybridEnsNet had an accuracy of 84.775%. All of the ensembles evaluated outperform the best performing single model, ResNet50 with TLFE (83.751%), except for AvgEnsNet 3, AvgEnsNet 6, and FeatSpaceEnsNet 5. Five of the seven similarly composed FeatSpaceEnsNets outperform the corresponding AvgEnsNet.

Robot path planning based on genetic algorithm with hybrid initialization method

The research of path planning method based on genetic algorithm (GA) for the mobile robot has received much attention in recent years. GA, as one evolutionary computation model, mimics the process of natural evolution and genetics. The quality of the initial population plays an essential role in improving the performance of GA. However, when GA based on a random initialization method is applied to path planning problems, it will lead to the emergence of infeasible solutions and reduce the performance of the algorithm. A novel GA with a hybrid initialization method, termed NGA, is proposed to solve this problem in this paper. In the initial population, NGA first randomly selects three free grids as intermediate nodes. Then, a part of the population uses a random initialization method to obtain the complete path. The other part of the population obtains the complete path using a greedy-related method. Finally, according to the actual situation, the redundant nodes or duplicate paths in the path are deleted to avoid the redundant paths. In addition, the deletion operation and the reverse operation are also introduced to the NGA iteration process to prevent the algorithm from falling into the local optimum. Simulation experiments are carried out with other algorithms to verify the effectiveness of the NGA. Simulation results show that NGA is superior to other algorithms in convergence accuracy, optimization ability, and success rate. Besides, NGA can generate the optimal feasible paths in complex environments.

ANALYSIS OF THE APPLICABILITY CRITERION FOR K MEANS CLUSTERING ALGORITHM RUN TEN NUMBER OF TIMES ON THE FIRST 25 NUMBERS OF THE FIBONACCI SERIES

In this research investigation Analysis Of The Applicability Criterion For K Means Clustering Algorithm Run Ten Number Of Times On The First 25 Numbers Of The Fibonacci Series is performed. For this analysis RCB Model Of Applicability Criterion For K Means Clustering Algorithm is used. K-means is one of the simplest unsupervised learning algorithms that solve the well-known clustering problem. K- Means clustering algorithm is a scheme for clustering continuous and numeric data. As K-Means algorithm consists of scheme of random initialization of centroids, every time it is run, it gives different or slightly different results because it may reach some local optima. Quantification of such aforementioned variation is of some importance as this sheds light on the nature of the Discrete K-Means Objective function with regards its maxima and minima. The K-Means Clustering algorithm aims at minimizing the aforementioned Objective function. The RCB Model Of Applicability Criterion for K-Means Clustering aims at telling us if we can use the K-Means Clustering Algorithm on a given set of data within acceptable variation limits of the results of the K-Means Clustering Algorithm when it is run several times. KEY WORDS: K-means clustering algorithm, RCB model and Cluster evaluation.

Implementation of Pruned Backpropagation Neural Network Based on Photonic Integrated Circuits

We demonstrate a pruned high-speed and energy-efficient optical backpropagation (BP) neural network. The micro-ring resonator (MRR) banks, as the core of the weight matrix operation, are used for large-scale weighted summation. We find that tuning a pruned MRR weight banks model gives an equivalent performance in training with the model of random initialization. Results show that the overall accuracy of the optical neural network on the MNIST dataset is 93.49% after pruning six-layer MRR weight banks on the condition of low insertion loss. This work is scalable to much more complex networks, such as convolutional neural networks and recurrent neural networks, and provides a potential guide for truly large-scale optical neural networks.

Neural Network Based Transfer Learning for Robot Path Generation

In this paper, an artificial neural network (ANN) based transfer learning approach of inverse displacement analysis of robot manipulators is studied. ANNs with different structures are applied utilizing data from different end effector paths of a manipulator for training purposes. Four transfer learning methods are proposed by applying pretrained initial parameters. Final training results of ANN with transfer learning are compared with those of ANN with random initialization. To investigate the rate of convergence of data fitting comprehensively, different values of performance targets are defined. The computing epochs and performance measures are compared. It is presented that, depending on the structure of ANN, the proposed transfer learning methods can accelerate the training process and achieve higher accuracy. Depending on the method, the transfer learning improves the performance differently.

Quantum annealing initialization of the quantum approximate optimization algorithm

The quantum approximate optimization algorithm (QAOA) is a prospective near-term quantum algorithm due to its modest circuit depth and promising benchmarks. However, an external parameter optimization required in QAOA could become a performance bottleneck. This motivates studies of the optimization landscape and search for heuristic ways of parameter initialization. In this work we visualize the optimization landscape of the QAOA applied to the MaxCut problem on random graphs, demonstrating that random initialization of the QAOA is prone to converging to local minima with sub-optimal performance. We introduce the initialization of QAOA parameters based on the Trotterized quantum annealing (TQA) protocol, parameterized by the Trotter time step. We find that the TQA initialization allows to circumvent the issue of false minima for a broad range of time steps, yielding the same performance as the best result out of an exponentially scaling number of random initializations. Moreover, we demonstrate that the optimal value of the time step coincides with the point of proliferation of Trotter errors in quantum annealing. Our results suggest practical ways of initializing QAOA protocols on near-term quantum devices and reveals new connections between QAOA and quantum annealing.

Uncertainty Estimation in Hydrogeological Forecasting with Neural Networks: Impact of Spatial Distribution of Rainfalls and Random Initialization of the Model

Neural networks are used to forecast hydrogeological risks, such as droughts and floods. However, uncertainties generated by these models are difficult to assess, possibly leading to a low use of these solutions by water managers. These uncertainties are the result of three sources: input data, model architecture and parameters and their initialization. The aim of the study is, first, to calibrate a model to predict Champagne chalk groundwater level at Vailly (Grand-Est, France), and, second, to estimate related uncertainties, linked both to the spatial distribution of rainfalls and to the parameter initialization. The parameter uncertainties are assessed following a previous methodology, using nine mixed probability density functions (pdf), thus creating models of correctness. Spatial distribution of rainfall uncertainty is generated by swapping three rainfall inputs and then observing dispersion of 27 model outputs. This uncertainty is incorporated into models of correctness. We show that, in this case study, an ensemble model of 40 different initializations is sufficient to estimate parameter uncertainty while preserving quality. Logistic, Gumbel and Raised Cosine laws fit the distribution of increasing and decreasing groundwater levels well, which then allows the establishment of models of correctness. These models of correctness provide a confidence interval associated with the forecasts, with an arbitrary degree of confidence chosen by the user. These methodologies have proved to have significant advantages: the rigorous design of the neural network model has allowed the realisation of models able to generalize outside of the range of the data used for training. Furthermore, it is possible to flexibly choose the confidence index according to the hydrological configuration (e.g., recession or rising water table).

A Spatial temporal classification analysis and visualization of tropical cyclone tracks in Bay of Bengal using GIS

Tropical cyclones (TC) are among the most devastating forms of natural hazards and the east coast of India is more prone to TC landfall causing significant socio-economic impacts. The Bay of Bengal (BoB) which forms the eastern sub basin of North Indian Ocean experiences the seasonally reversing monsoon, depression and TCs. In this study TC best track dataset of NIO basin over the period 1960–2016 from the IBTrACKs archive maintained by NOAA are used. In this work Firefly optimization is coupled with FCM for TC tracks classification. The classical FCM uses random initialization of cluster centroid often gets trapped in local optimal problem. The firefly algorithm is applied on the FCM for the cluster centroid computation, in this way improving the efficiency of FCM algorithm. The obtained classes are then projected in the visualization space. Visualizations are generated using the GIS environment to gain insight into the spatial distribution of TC tracks over decades. This study aims to develop a comprehensive assessment of variability in tropical cyclones with respect to ENSO modulated events, inter decadal variability and track sinuosity. In this paper we attempt to convey the cognitive results of comparative visualizations of TC tracks over Arabian Sea and Bay of Bengal sub basin during the strong, very strong El Niño and La Niña events. Finally we use Parallel Coordinate Plot (PCP) a visualization technique to demonstrate the correlation patterns of the TC parameters.