Recurrent neural network (RNN) and long short-term memory (LSTM) have achieved great success in processing sequential multimedia data and yielded state-of-the-art results in speech recognition, digital signal processing, video processing, and text data analysis. In this paper, we propose a novel action recognition method by processing the video data using convolutional neural network (CNN) and deep bidirectional LSTM (DB-LSTM) network. Firstly, deep features are extracted from every sixth frame of the videos which helps reduce the redundancy and complexity. Next, the sequential information among frame features is learnt using DB-LSTM network, where multiple layers are stacked together in both forward pass and backward pass of DB-LSTM to increase its depth. The proposed method is capable of learning long term sequences and can process lengthy videos by analyzing features for a certain time interval. Experimental results show significant improvements in action recognition using the proposed method on three benchmark datasets including UCF-101, YouTube 11 Actions, and HMDB51 compared to state-of-the-art action recognition methods.

Electric energy forecasting domain attracts researchers due to its key role in saving energy resources, where mainstream existing models are based on Gradient Boosting Regression, Artificial Neural Networks, Extreme Learning Machine and Support Vector Machine. These models encounter high-level of non-linearity between input data and output predictions and limited adoptability in real-world scenarios. Meanwhile, energy forecasting domain demands more robustness, higher prediction accuracy and generalization ability for real-world implementation. In this paper, we achieve the mentioned tasks by developing a hybrid sequential learning-based energy forecasting model that employs Convolution Neural Network and Gated Recurrent Units into a unified framework for accurate energy consumption prediction. The proposed framework has two major phases: (1) data refinement and (2) training, where the data refinement phase applies preprocessing strategies over raw data. In the training phase, CNN features are extracted from input dataset and fed in to GRU, that is selected as optimal and observed to have enhanced sequence learning abilities after extensive experiments. The proposed model is an effective alternative to the previous hybrid models in terms of computational complexity as well prediction accuracy, due to the representative features’ extraction potentials of CNNs and effectual gated structure of multi-layered GRU. The experimental evaluation over existing energy forecasting datasets reveal the better performance of our method in terms of preciseness and efficiency. The proposed method achieved the smallest error rate on individual Appliances Energy prediction and household electric power consumption datasets, when compared to other baseline models.

Convolutional neural networks (CNNs) have yielded state-of-the-art performance in image classification and other computer vision tasks. Their application in fire detection systems will substantially improve detection accuracy, which will eventually minimize fire disasters and reduce the ecological and social ramifications. However, the major concern with CNN-based fire detection systems is their implementation in real-world surveillance networks, due to their high memory and computational requirements for inference. In this paper, we propose an original, energy-friendly, and computationally efficient CNN architecture, inspired by the SqueezeNet architecture for fire detection, localization, and semantic understanding of the scene of the fire. It uses smaller convolutional kernels and contains no dense, fully connected layers, which helps keep the computational requirements to a minimum. Despite its low computational needs, the experimental results demonstrate that our proposed solution achieves accuracies that are comparable to other, more complex models, mainly due to its increased depth. Moreover, this paper shows how a tradeoff can be reached between fire detection accuracy and efficiency, by considering the specific characteristics of the problem of interest and the variety of fire data.

This paper presents a method for speech emotion recognition using spectrograms and deep convolutional neural network (CNN). Spectrograms generated from the speech signals are input to the deep CNN. The proposed model consisting of three convolutional layers and three fully connected layers extract discriminative features from spectrogram images and outputs predictions for the seven emotions. In this study, we trained the proposed model on spectrograms obtained from Berlin emotions dataset. Furthermore, we also investigated the effectiveness of transfer learning for emotions recognition using a pre-trained AlexNet model. Preliminary results indicate that the proposed approach based on freshly trained model is better than the fine-tuned model, and is capable of predicting emotions accurately and efficiently.