Time series classification is an important research topic in machine learning and data mining communities, since time series data exists in many application domains. Recent studies have shown that machine learning algorithms could benefit from good feature representation, explaining why deep learning has achieved breakthrough performance in many tasks. In deep learning, the convolutional neural network (CNN) is one of the most well-known approaches, since it incorporates feature representation and classification task in a unified network architecture. Although CNN has been successfully applied to image and text domains, it is still a challenge to apply CNN to time series data. This work proposes a tensor scheme along with a novel deep learning architecture called multivariate convolutional neural network (MVCNN) for time series classification, in which the proposed architecture considers multivariate and lag-features characteristics. We evaluate our proposed method with prognostics and health management (PHM) 2015 challenge data, and compare with several algorithms. The experimental results indicate that the proposed method outperforms the other alternatives using the prediction score, which is the evaluation metric used by the PHM Society 2015 Data Challenge. Besides performance evaluation, we provide detailed analysis about the proposed method.

In the past decades, many optimization methods have been devised and applied to job shop scheduling problem (JSSP) to find the optimal solution. Many methods assumed that the scheduling results were applied to static environments, but the whole environments in the real world are always dynamic. Moreover, many unexpected events such as machine breakdowns and material problems may be present to adversely affect the initial job scheduling. This work views JSSP as a sequential decision making problem and proposes to use deep reinforcement learning to cope with this problem. The combination of deep learning and reinforcement learning avoids handcraft features as used in traditional reinforcement learning, and it is expected that the combination will make the whole learning phase more efficient. Our proposed model comprises actor network and critic network, both including convolution layers and fully connected layer. Actor network agent learns how to behave in different situations, while critic network helps agent evaluate the value of statement then return to actor network. This work proposes a parallel training method, combining asynchronous update as well as deep deterministic policy gradient (DDPG), to train the model. The whole network is trained with parallel training on a multi-agent environment and different simple dispatching rules are considered as actions. We evaluate our proposed model on more than ten instances that are present in a famous benchmark problem library – OR library. The evaluation results indicate that our method is comparative in static JSSP benchmark problems, and achieves a good balance between makespan and execution time in dynamic environments. Scheduling score of our method is 91.12% in static JSSP benchmark problems, and 80.78% in dynamic environments.

The job-shop scheduling problem (JSSP) is one of the best-known combinatorial optimization problems and is also an essential task in various sectors. In most real-world environments, scheduling is complex, stochastic, and dynamic, with inevitable uncertainties. Therefore, this article proposes a novel framework based on graph neural networks (GNNs) and deep reinforcement learning (DRL) to deal with the dynamic JSSP (DJSSP) with stochastic job arrivals and random machine breakdowns by minimizing the makespan. In the proposed framework, JSSP is formulated as a Markov decision process (MDP) and is associated with a disjunctive graph to encode the information of jobs and machines as nodes and arcs. We propose a GNN architecture to perform representation learning by transforming graph states into node embeddings. Then, the agent takes actions using a parameterized policy in terms of policy learning. Operations are used as actions, and an effective reward is well designed to guide the agent. We train our proposed method using proximal policy optimization (PPO), which helps minimize the loss function while ensuring that the deviation is relatively small. Extensive experiments show that the proposed method can achieve excellent results considering different criteria: efficiency, effectiveness, robustness, and generalizability. Once the proposed method is trained, it can directly schedule new JSSPs of different sizes and distributions in static benchmark tests, showing its excellent generalizability and effectiveness compared to another DRL-based method. Furthermore, the proposed method simultaneously maintains the win rate (a quantitative metric) and the scheduling score (a qualitative metric) when scheduling in dynamic environments.

In this paper, we design and develop a movie-rating and review-summarization system in a mobile environment. The movie-rating information is based on the sentiment-classification result. The condensed descriptions of movie reviews are generated from the feature-based summarization. We propose a novel approach based on latent semantic analysis (LSA) to identify product features. Furthermore, we find a way to reduce the size of summary based on the product features obtained from LSA. We consider both sentiment-classification accuracy and system response time to design the system. The rating and review-summarization system can be extended to other product-review domains easily.

The unpredictability of seizures is often considered by patients to be the most problematic aspect of epilepsy, so this work aims to develop an accurate epilepsy seizure predictor, making it possible to enable devices to warn patients of impeding seizures. To develop a model for seizure prediction, most studies relied on Electroencephalograms (EEGs) to capture physiological measurements of epilepsy. This work uses the two domains of EEGs, including frequency domain and time domain, to provide two different views for the same data source. Subsequently, this work proposes a multi-view convolutional neural network framework to predict the occurrence of epilepsy seizures with the goal of acquiring a shared representation of time-domain and frequency-domain features. By conducting experiments on Kaggle data set, we demonstrated that the proposed method outperforms all methods listed in the Kaggle leader board. Additionally, our proposed model achieves average area under the curve (AUCs) of 0.82 and 0.89 on two subjects of CHB-MIT scalp EEG data set. This work serves as an effective paradigm for applying deep learning approaches to the crucial topic of risk prediction in health domains.