Artificial Neural Networks and Machine Learning – ICANN 2017

Abstract

Abstract. Images are an important data source for diagnosis and treatment of oral diseases. The manual classification of images may lead to misdiagnosis or mistreatment due to subjective errors. In this paper an image classification model based on Convolutional Neural Network is applied to Quantitative Light-induced Fluorescence images. The deep neural network outperforms other state of the art shallow classification models in predicting labels derived from three different dental plaque assessment scores. The model directly benefits from multi-channel representation of the images resulting in improved performance when, besides the Red colour channel, additional Green and Blue colour channels are used.

A novel intelligent approach for man‐in‐the‐middle attacks detection over internet of things environments based on message queuing telemetry transport

“…Artificial neural networks (ANN) is a method that corresponds to a mathematical model inspired by the human brain and its neural networks. Thus, ANNs use artificial neurons, which are interconnected, forming a network or matrix Da Silva et al (2017).…”

From observing to predicting single-cell structure and function with high-throughput/high-content microscopy

“…We anticipate that in the future GANs and related methods will provide an invaluable tool to allow the enrichment of available datasets with computationally generated but biologically meaningful additions (including e.g. by data augmentation [109,110]) and will enable previously inaccessible studies. Importantly, going forward and as with Deep Learning in general, thorough, unbiased and study-specific evaluation and controls will be crucial to ensure trust and reproducibility.…”

Generative Adversarial Networks Time Series Models to Forecast Medicine Daily Sales in Hospital

“…Time series forecasting is widely presented in the literature with applications in various fields such as care, health, inventory, climate modeling, financial trading and monitoring tools such as water, electricity and other quality [16], time series forecasting models not only focus on the results of predictive accuracy but must also measure and adjust to uncertainty over time. In depth learning (DN)models have demonstrated capabilities in the field of forecasting, such as financial forecasting in [17] using a combination of convolutional neural networks models with WaveNet architecture models to optimize access to historical data and optimize data processing and correlation structures between time, depth of air quality [36] proposing a hybrid model approach in one framework, and [37] proposing the RNN model for predicting proenvironment consumption status, predictive results evaluated by comparing the Artificial Neural Network model.…”

“…Research [38] proposes a deep neural network (DNN) method for estimating the consistent sales of pharmaceutical products in the next one week. Forecasting the scenario of a power plant process is presented by [35] which produces a series of scenarios that represent realistic possibilities for future behavior. Zhu, L., & Laptev, N [39] reviewed models prediction number of trips during special events, driver incentive allocation and anomaly detection of requests.…”

“…Recently deep learning for the task of classify time series is many proposed [17] with approaches to various models, such as Recurrent Neural Networks (RNN) [18], [19], Product-based Neural Networks (PNN) [20], Deep Neural Networks (DNN) [21], Deep Recurrent Neural Networks (DRNN) [22], Multivariate LSTM-FCNs [23], to improve forecasting performance. The RNN model can be used in various forecasting tasks because it has flexibility in the network, but has weaknesses in long-term forecasting [24], simple PNN in implementation, but needs to improve performance in testing so that it is more appropriate to apply in datasets that do not require training.…”