Over the last years deep learning methods have been shown to outperform previous state-of-the-art machine learning techniques in several fields, with computer vision being one of the most prominent cases. This review paper provides a brief overview of some of the most significant deep learning schemes used in computer vision problems, that is, Convolutional Neural Networks, Deep Boltzmann Machines and Deep Belief Networks, and Stacked Denoising Autoencoders. A brief account of their history, structure, advantages, and limitations is given, followed by a description of their applications in various computer vision tasks, such as object detection, face recognition, action and activity recognition, and human pose estimation. Finally, a brief overview is given of future directions in designing deep learning schemes for computer vision problems and the challenges involved therein.

Energy disaggregation, or Non-Intrusive Load Mon-itoring (NILM), describes various processes aiming to identify the individual contribution of appliances, given the aggregate power signal. In this paper, a non-causal adaptive context-aware bidirec-tional deep learning model for energy disaggregation is intro-duced. The proposed model, CoBiLSTM, harnesses the represen-tational power of deep recurrent Long Short-Term Memory (LSTM) neural networks, while fitting two basic properties of NILM problem which state of the art methods do not appropri-ately account for: non-causality and adaptivity to contextual fac-tors (e.g. seasonality). A Bayesian-optimized framework is intro-duced to select the best configuration of the proposed regression model, driven by a self-training adaptive mechanism. Further-more, the proposed model is structured in a modular way to ad-dress multi-dimensionality issues that arise when the number of appliances increases. Experimental results indicate the proposed method’s superiority compared to the current state of the art.

Non-intrusive load monitoring (NILM) is the task of disaggregating the total power consumption into its individual sub-components. Over the years, signal processing and machine learning algorithms have been combined to achieve this. Many publications and extensive research works are performed on energy disaggregation or NILM for the state-of-the-art methods to reach the desired performance. The initial interest of the scientific community to formulate and describe mathematically the NILM problem using machine learning tools has now shifted into a more practical NILM. Currently, we are in the mature NILM period where there is an attempt for NILM to be applied in real-life application scenarios. Thus, the complexity of the algorithms, transferability, reliability, practicality, and, in general, trustworthiness are the main issues of interest. This review narrows the gap between the early immature NILM era and the mature one. In particular, the paper provides a comprehensive literature review of the NILM methods for residential appliances only. The paper analyzes, summarizes, and presents the outcomes of a large number of recently published scholarly articles. Furthermore, the paper discusses the highlights of these methods and introduces the research dilemmas that should be taken into consideration by researchers to apply NILM methods. Finally, we show the need for transferring the traditional disaggregation models into a practical and trustworthy framework.

The inspection, assessment, maintenance and safe operation of the existing civil infrastructure consists one of the major challenges facing engineers today. Such work requires either manual approaches, which are slow and yield subjective results, or automated approaches, which depend upon complex handcrafted features. Yet, for the latter case, it is rarely known in advance which features are important for the problem at hand. In this paper, we propose a fully automated tunnel assessment approach; using the raw input from a single monocular camera we hierarchically construct complex features, exploiting the advantages of deep learning architectures. Obtained features are used to train an appropriate defect detector. In particular, we exploit a Convolutional Neural Network to construct high-level features and as a detector we choose to use a Multi-Layer Perceptron due to its global function approximation properties. Such an approach achieves very fast predictions due to the feedforward nature of Convolutional Neural Networks and Multi-Layer Perceptrons.

In this paper, we propose a Stack Auto-encoder (SAE)-Driven and Semi-Supervised (SSL)-Based Deep Neural Network (DNN) to extract buildings from relatively low-cost satellite near infrared images. The novelty of our scheme is that we employ only an extremely small portion of labeled data for training the deep model which constitutes less than 0.08% of the total data. This way, we significantly reduce the manual effort needed to complete an annotation process, and thus the time required for creating a reliable labeled dataset. On the contrary, we apply novel semi-supervised techniques to estimate soft labels (targets) of the vast amount of existing unlabeled data and then we utilize these soft estimates to improve model training. Overall, four SSL schemes are employed, the Anchor Graph, the Safe Semi-Supervised Regression (SAFER), the Squared-loss Mutual Information Regularization (SMIR), and an equal importance Weighted Average of them (WeiAve). To retain only the most meaning information of the input data, labeled and unlabeled ones, we also employ a Stack Autoencoder (SAE) trained under an unsupervised manner. This way, we handle noise in the input signals, attributed to dimensionality redundancy, without sacrificing meaningful information. Experimental results on the benchmarked dataset of Vaihingen city in Germany indicate that our approach outperforms all state-of-the-art methods in the field using the same type of color orthoimages, though the fact that a limited dataset is utilized (10 times less data or better, compared to other approaches), while our performance is close to the one achieved by high expensive and much more precise input information like the one derived from Light Detection and Ranging (LiDAR) sensors. In addition, the proposed approach can be easily expanded to handle any number of classes, including buildings, vegetation, and ground.