Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

This paper presents different deep neural network architectures designed to forecast the distribution of returns on a portfolio of U.S. Treasury securities. A long short-term memory model and a convolutional neural network are tested as the main building blocks of each architecture. The models are then augmented by cross-sectional data and the portfolio's empirical distribution. The paper also presents the fit and generalization potential of each approach.

Convolution --- Long Short-Term Memory --- LSTM --- Machine Learning --- Macroeconomics and Economic Growth --- Market Risk --- Neural Networks --- Taxation and Subsidies

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

In Belgium, the global warming offers new opportunities for the wine culture. In the past fifteen years, the area dedicated for vineyards became eight times bigger, rising from 72 hectares in 2006 to 587 hectares in 2020.
Nevertheless, the Belgian climate is not always indulgent with vineyards throughout the year. In the spring particularly, when the bud has already grew and became more sensitive to frost, a few cold nights may arise and lead to the destruction of the grapes.

Hopefully, few methods exist to fight bud freezing. From one vineyard to another, different techniques will be used depending on, amongst other, the size of the plantation, the intensity of the frost or the financial means. 
In 2017, half of the plantations have a size below one hectare. For this kind of small area, the construction of expensive infrastructures is not viable and more adapted methods must be chosen. The most suitable solution, and often the only one conceivable in small vineyards, consists in lightning large candles all over the place to increase the temperature around the grapes.
Although this solution has the advantages to be simple and relatively cheap, it also has two drawbacks. The first one, common to other more expensive methods, is the temperature monitoring, which consist in determining when to take action. The second one, inherent to this particular method, is the need of a workforce available in a hurry to light all the candles in the middle of the night.

In our work, we propose to assist Belgian wine makers by means of acrfull{ml} techniques in the two aspects aforementioned. We achieved to accurately forecast the temperatures around the grapes up to 36 hours ahead with an error below 1 degree Celsius. Additionally, we also provide a live supervising model capable of detecting negative temperatures with an error below 0.5 degree. In doing so, we avoid the wine growers to unnecessarily wake up during night to monitor the temperatures and we also allow them to organize a workforce sufficiently early enough.

data science --- random forest regressor --- machine learning --- normalizing flows --- neural network --- weather forecasting --- probabilistic model --- vine culture --- air temperature prediction --- bud freezing --- Regional Atmospheric Model --- Long Short-Term Memory --- temperature supervising --- Ingénierie, informatique & technologie > Sciences informatiques

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

The introduction of new topologies and training procedures to deep neural networks has solicited a renewed interest in the field of neural computation. The use of deep structures has significantly improved state-of-the-art applications in many fields, such as computer vision, speech and text processing, medical applications, and IoT (Internet of Things). The probability of a successful outcome from a neural network is linked to selection of an appropriate network architecture and training algorithm. Accordingly, much of the recent research on neural networks has been devoted to the study and proposal of novel architectures, including solutions tailored to specific problems. This book gives significant contributions to the above-mentioned fields by merging theoretical aspects and relevant applications.

Information technology industries --- facial image analysis --- facial nerve paralysis --- deep convolutional neural networks --- image classification --- Chinese text classification --- long short-term memory --- convolutional neural network --- Arabic named entity recognition --- bidirectional recurrent neural network --- GRU --- LSTM --- natural language processing --- word embedding --- CNN --- object detection network --- attention mechanism --- feature fusion --- LSTM-CRF model --- elements recognition --- linguistic features --- POS syntactic rules --- action recognition --- fused features --- 3D convolution neural network --- motion map --- long short-term-memory --- tooth-marked tongue --- gradient-weighted class activation maps --- ship identification --- fully convolutional network --- embedded deep learning --- scalability --- gesture recognition --- human computer interaction --- alternative fusion neural network --- deep learning --- sentiment attention mechanism --- bidirectional gated recurrent unit --- Internet of Things --- convolutional neural networks --- graph partitioning --- distributed systems --- resource-efficient inference --- pedestrian attribute recognition --- graph convolutional network --- multi-label learning --- autoencoders --- long-short-term memory networks --- convolution neural Networks --- object recognition --- sentiment analysis --- text recognition --- IoT (Internet of Thing) systems --- medical applications

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

The world today is threatened by a dramatic biodiversity crisis. It is therefore becoming essential to monitor the animal and plant populations that inhabit the earth's ecosystems. In this sense, camera traps are cameras that capture images or videos when they detect movement. These cameras are increasingly used in the scientific world and could become an essential tool in wildlife monitoring systems. They have the advantage of being very low-intrusive and of being able to be installed in remote and difficult-to-access places. The main weakness of this technology is that it generates a huge amount of data. The analysis of this data by humans is therefore very time-consuming and tedious. A solution to this problem could be found in the use of deep learning. This allows deep neural networks to be trained to automate a task usually performed by humans. Some deep learning approaches have achieved better results in solving complex problems. The main objective of this work is therefore to use deep learning to automate the recognition of animal species in videos of camera traps installed in the tropical rainforests of Central Africa. To this end, three datasets were created and 22 classes were defined. Different model architectures were then tested. These are composed of convolutional neural networks (two-dimensional and three-dimensional ResNet) and recurrent neural networks (convolutional long short-term memory (ConvLSTM) and long short-term memory (LSTM)). This work also discusses the comparison of different tools that have been developed to automatically classify camera traps data. The best trained models achieved, on a test dataset, an overall accuracy of 67,93 % for multispecies classification and 84,89 % for binary classification (animal/background). These models performed better than the other tested tools for the multispecies classification but not for the binary classification. Finally, the models developed could be used under certain conditions to assist in the analysis of camera traps data. The results obtained are promising. Le monde actuel est menacé par une crise de la biodiversité dramatique. Il devient donc primordial de surveiller les populations animales et végétales qui habitent les écosystèmes de la Terre. Dans ce sens, les pièges photographiques sont des caméras qui capturent des images ou des vidéos lorsqu'elles détectent un mouvement. Ces caméras sont de plus en plus utilisées dans le monde scientifique et pourraient devenir un outil essentiel dans des systèmes de surveillance de la faune et de la flore. Elles possèdent notamment l'avantage d'être très peu intrusives et de pouvoir être installées dans des endroits reculés et difficilement accessibles. Le point faible de cette technologie est qu'elle génère une quantité très importante de données. L'analyse de ces dernières par l'homme est donc très chronophage et fastidieuse. Une solution pourrait être apportée à ce problème grâce à l'utilisation de l'apprentissage profond. Celui-ci permet d'entraîner des réseaux de neurones profonds afin d'automatiser une tâche habituellement réalisée par l'homme. Certaines approches d'apprentissage profond ont permis d'atteindre de meilleurs résultats lors la résolution de problèmes complexes. L'objectif principal de ce travail est donc d'utiliser l'apprentissage profond afin d'automatiser la reconnaissance d'espèces animales dans des vidéos de pièges photographiques installés dans les forêts tropicales d'Afrique centrale. Pour ce faire, trois jeux de données ont été constitués et 22 classes ont été définies. Différentes architectures de modèles ont ensuite été testées. Ces dernières sont composées de réseaux de neurones convolutifs (ResNet à deux dimensions et à trois dimensions) et de réseaux de neurones récurrents (mémoire convolutive à long court terme (ConvLSTM) et mémoire à long court terme (LSTM)). Ce travail aborde également la comparaison de différents outils qui ont été développés afin de classifier automatiquement des données de pièges photographiques. Les meilleurs modèles entraînés ont atteint, sur un jeu de données de test, une exactitude globale de 67,93 % pour la classification multi-espèces et de 84,89 % pour la classification binaire (animal / arrière-plan). Ces modèles ont mieux performés que les autres outils testés, pour la classification multi-espèces mais pas pour la classification binaire. Enfin, les modèles développés pourraient être utilisés sous certaines conditions dans le but d'aider à l'analyse des données de pièges photographiques. Les résultats obtenus sont prometteurs.

camera trap --- tropical forest --- deep learning --- convolutional neural network --- convolutional long short-term memory --- classification --- wildlife --- piège photographique --- forêt tropicale --- apprentissage profond --- réseau de neurones convolutifs --- mémoire convolutive à long court terme --- classification --- faune sauvage --- Ingénierie, informatique & technologie > Multidisciplinaire, généralités & autres

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

This reprint introduces advanced prediction models focused on power load forecasting. Models based on artificial intelligence and more traditional approaches are shown, demonstrating the real possibilities of use to improve prediction in this field. Models of LSTM neural networks, LSTM networks with a SESDA architecture, in even LSTM-CNN are used. On the other hand, multiple seasonal Holt-Winters models with discrete seasonality and the application of the Prophet method to demand forecasting are presented. These models are applied in different circumstances and show highly positive results. This reprint is intended for both researchers related to energy management and those related to forecasting, especially power load.

Research & information: general --- Physics --- Prophet model --- Holt–Winters model --- long-term forecasting --- peak load --- prophet model --- multiple seasonality --- time series --- demand --- load --- forecast --- DIMS --- irregular --- galvanizing --- short-term electrical load forecasting --- machine learning --- deep learning --- statistical analysis --- parameters tuning --- CNN --- LSTM --- short-term load forecast --- Artificial Neural Network --- deep neural network --- recurrent neural network --- attention --- encoder decoder --- online training --- bidirectional long short-term memory --- multi-layer stacked --- neural network --- short-term load forecasting --- power system