The portfolio problem is a hot issue in the field of quantitative trading. An Integrated Deep Reinforcement Learning Portfolio Model (IDRLPM) was proposed to address the shortcomings of existing deep reinforcement learning-based portfolio models that cannot achieve adaptive trading strategies and effectively utilize supervised information. Firstly, multi-agent method was used to construct multiple base agents and design reward functions with different trading styles to represent different trading strategies. Secondly, integrated learning method was used to fuse the features of strategy network of the base agents to obtain the integrated agent adaptive to market environment. Then, a trend prediction network based on Convolutional Block Attention Module (CBAM) was embedded in the integrated agent, and the output of the trend prediction network guided integrated strategy network to adaptively select the proportion of trades. Finally, under the alternating iterative training of supervised deep learning and reinforcement learning, IDRLPM effectively utilized supervised information from training data to enhance model profitability. The Sharpe Ratio (SR) of IDRLPM reaches 1.87 and 1.88, and the Cumulative Return (CR) reaches 2.02 and 1.34 in Shanghai Stock Exchange (SSE) 50 constituent stocks and China Securities Index (CSI) 500 constituent stocks; compared with the Ensemble Deep Reinforcement Learning (EDRL) trading model, the SR improves by 105% and 55%, and the CR improves by 124% and 79%. The experimental results show that IDRLPM can effectively solve the portfolio problem.
Aiming at the problem of high matching cost in the existing complex event matching processing methods, a complex event matching algorithm ReCEP was proposed, which uses event buffers (ordered event lists) for recursive traversal. Different from the existing method that uses automaton to match on the event stream, this method decomposes the constraints in the complex event query mode into different types, and then recursively verifies the different constraints on the ordered list. Firstly, according to the query mode, the related event instances were cached according to the event type. Secondly, the query filtering operation was performed to the event instances on the ordered list, and an algorithm based on recursive traversal was given to determine the initial event instance and obtain candidate sequence. Finally, the attribute constraints of the candidate sequence were further verified. Experimental testing and analysis results based on simulated stock transaction data show that compared with the current mainstream matching methods SASE and Siddhi, ReCEP algorithm can effectively reduce the processing time of query matching, has overall performance better than both of the two methods, and has the query matching efficiency improved by more than 8.64%. It can be seen that the proposed complex event matching method can effectively improve the efficiency of complex event processing.
Damage to sensors in Industrial Internet of Things (IIoT) system due to continuous use and normal wear leads to hidden anomalies in the collected and recorded sensing data. To solve this problem, an anomaly detection algorithm based on Local Sensitive Bloom Filter (LSBF) model was proposed, namely LSBFAD. Firstly, the Spatial Partition based Fast Johnson-Lindenstrauss Transform (SP-FJLT) was used to perform hash mapping to the data, then the Mutual Competition (MC) strategy was used to reduce noise, and finally the Bloom filter was constructed by 0-1 coding. In simulation experiments conducted on three benchmark datasets including SIFT, MNIST and FMA, the false detection rate of LSBFAD algorithm is less than 10%. Experimental results show that compared with the current mainstream anomaly detection algorithms, the proposed anomaly detection algorithm based on LSBF has higher Detection Rate (DR) and lower False Alarm Rate (FAR) and can be effectively applied to anomaly detection of IIoT data.
Parameter-free locality preserving projection does not need to set parameters and has stable performance, but the algorithm cannot effectively maintain the local structure of the sample and ignores the role of non-local samples. Moreover, this method exists the Small Size Sample (SSS) problem. A complete parameter-free local neighborhood preserving and non-local maximization algorithm was proposed. In order to make full use of the nearest neighbor samples and non-nearest neighbor samples, which were divided by whether the distance between two samples is no more than 0.5 or not, the neighbor scatter matrix and non-nearest neighbor scatter matrix were constructed. Then, the objective function of the algorithm was to seek a set of projection vectors such that the neighbor scatter matrix was maximized and non-nearest neighbor scatter matrix was minimized simultaneously. As to solve the objective function, the high dimensional samples were projected to a low dimensional subspace by Principal Component Analysis (PCA) algorithm, which was proved without lossing any effective discriminant information according to two theorems. In order to solve the SSS problem, the objective function was converted to differential form. The experimental results on face database and palmprint database illustrate that the proposed method outperforms Parameter-free locality preserving projection with average recognition rate, which proves the effectiveness of the proposed algorithm.
To solve the security problems between the reader and the server of mobile Radio Frequency IDentification (RFID) caused by wireless transmission, a two-way authentication protocol based on pseudo-random function was provided. It satisfied the EPC Class-1 Generation-2 industry standards, and mutual certifications between tags, readers and servers were achieved. The security of this protocol was also proved by using GNY logic. It can effectively resist track, replay and synchronization attack etc.; simultaneously, its main calculations are transferred to the server, thereby reducing the calculations and cost of the tag.
Concerning gender tendency hidden in microblog messages posted by microblog users, a novel approach based on rough set theory was proposed to identify microblog user gender. In the proposed approach, a new Representation Model based on Tolerance Rough Set (TRSRM) was devised, which can effectively represent gender characteristics of microblog messages. The experimental results show that the accuracy rate of the proposed approach is 7% higher than frequency model approach by testing messages of 1000 real microblog users, and so the TRSRM achieves better recognition performance.