Extreme learning machines for weather-based modelling of silk cocoon production

In spite of the immense popularity and sheer power of the neural network models, their application in sericulture is still very much limited. With this backdrop, this study evaluates the suitability of neural network models in comparison with the linear regression models in predicting silk cocoon production of the selected six districts (Kolar, Chikballapur, Ramanagara, Chamarajanagar, Mandya and Mysuru) of Karnataka by utilising weather variables for ten consecutive years (2009-2018). As the weather variables are found to be correlated, principal components are obtained and fed into the linear (principal component regression) and non-linear models (back propagation-artificial neural network and extreme learning machine) as inputs. Outcomes emanated from this experiment have revealed the clear advantages of employing extreme learning machines (ELMs) for weather-based modelling of silk cocoon production. Application of ELM would be particularly useful, when the relation between production and its attributing characters is complex and non-linear.

Prediction of survival of Pinus radiata seedlings subjected to physical-water restriction extreme using learning neural networks

Drought is one of the main environmental factors that limit plant growth. For this reason, it is necessary to apply nursery cultural practices to produce quality seedlings for successful reforestation in drought- prone sites. In this study, the extreme learning machines and multilayer are applied to predict survival in 5-month-old Pinus radiataseedlings belonging to 98 families of a genetic improvement program and subjected to a period of water restriction in the nursery. After applying the water restriction, survival was registered in each seedling as a categorical variable (1 = alive seedling, 0 = dead seedling). Additionally, the following morphological attributes of each seedling were also measured: total height, root collar diameter, slenderness index, dry weight of needles, stems and roots, total dry weight, and the root to shoot ratio. The extreme learning machines predicted with a better rate the survival of the “alive” class compared to the “dead” class. On the other hand, the multilayer-extreme learning machines improved the precision of survival concerning the class of “dead” seedlings. According to the results of the model, an overall precision of 74% was obtained. This may be due to the great genetic variability presented by each of the Pinus radiatafamily used in the database. However, this technique allowed predicting the survival of a group of seedlings grown in the nursery, which can be a tool to support the selection process of high quality planting stock.

Parallel Extreme Learning Machines Based on Frequency Multiplexing

In a recent work, we reported on an Extreme Learning Machine (ELM) implemented in a photonic system based on frequency multiplexing, where each wavelength of the light encodes a different neuron state. In the present work, we experimentally demonstrate the parallelization potentialities of this approach. We show that multiple frequency combs centered on different frequencies can copropagate in the same system, resulting in either multiple independent ELMs executed in parallel on the same substrate or a single ELM with an increased number of neurons. We experimentally tested the performances of both these operation modes on several classification tasks, employing up to three different light sources, each of which generates an independent frequency comb. We also numerically evaluated the performances of the system in configurations containing up to 15 different light sources.

Energy Consumption Forecasting for Smart Meters Using Extreme Learning Machine Ensemble

The employment of smart meters for energy consumption monitoring is essential for planning and management of power generation systems. In this context, forecasting energy consumption is a valuable asset for decision making, since it can improve the predictability of forthcoming demand to energy providers. In this work, we propose a data-driven ensemble that combines five single well-known models in the forecasting literature: a statistical linear autoregressive model and four artificial neural networks: (radial basis function, multilayer perceptron, extreme learning machines, and echo state networks). The proposed ensemble employs extreme learning machines as the combination model due to its simplicity, learning speed, and greater ability of generalization in comparison to other artificial neural networks. The experiments were conducted on real consumption data collected from a smart meter in a one-step-ahead forecasting scenario. The results using five different performance metrics demonstrate that our solution outperforms other statistical, machine learning, and ensembles models proposed in the literature.

Online Learning of Oil Leak Anomalies in Wind Turbines with Block-Based Binary Reservoir

The focus of this work is to design a deeply quantized anomaly detector of oil leaks that may happen at the junction between the wind turbine high-speed shaft and the external bracket of the power generator. We propose a block-based binary shallow echo state network (BBS-ESN) architecture belonging to the reservoir computing (RC) category and, as we believe, it also extends the extreme learning machines (ELM) domain. Furthermore, BBS-ESN performs binary block-based online training using fixed and minimal computational complexity to achieve low power consumption and deployability on an off-the-shelf micro-controller (MCU). This has been achieved through binarization of the images and 1-bit quantization of the network weights and activations. 3D rendering has been used to generate a novel publicly available dataset of photo-realistic images similar to those potentially acquired by image sensors on the field while monitoring the junction, without and with oil leaks. Extensive experimentation has been conducted using a STM32H743ZI2 MCU running at 480 MHz and the results achieved show an accurate identification of anomalies, with a reduced computational cost per image and memory occupancy. Based on the obtained results, we conclude that BBS-ESN is feasible on off-the-shelf 32 bit MCUs. Moreover, the solution is also scalable in the number of image cameras to be deployed and to achieve accurate and fast oil leak detections from different viewpoints.