Choreography-driven microservice composition has provided a better way to integrate components in the Cyber-physical-Social System (CPSS). Choreography is a global contract that specifies interactions among microservices participating in a composite service. After modeling a choreography, a problem arises here is whether the choreography specification at design time can be implemented correctly by generated microservices that interact with each other via exchanging messages. In this paper, we propose a novel approach for choreography analysis. Specifically, a choreography is specified using a Labeled Transition Systems (LTSs); then, the microservices participating in a composite service can be generated from the given choreography via projection and ε-remove; finally, the analysis of the choreography can be checked for both synchronous and asynchronous compositions using refinement checking. Our approach is completely automated under the support of our developed tool and the Process Analysis Toolkit (PAT) tool.

A highly sensitive fiber optics twist sensor is proposed and experimentally demonstrated using elliptical-core few-mode fiber (e-FMF). With the help of a fixed-phase plate for conversion from ${\mathrm{LP}}_{11}$ to ${\mathrm{LP}}_{01}$ mode, the twist angle can be linearly mapped to the spatial rotation of ${\mathrm{LP}}_{11}$ mode profile and consequently discriminated by monitoring the optical power variation at the standard single-mode fiber (SSMF) output. When the optical power at the e-FMF output is 10 mW, the twist angle within the range of $\pm 39°$ can be successfully detected with a sensitivity of more than 20 μW/°. Meanwhile, the twist direction can be identified simultaneously. In particular, when the twist angle ranges from $-12.5°$ to 20.1°, the sensitivity is higher than 100 μW/°. Both temperature-insensitive operation from 20°C to 150°C and e-FMF length insensitive operation are experimentally verified.

Traffic flow prediction plays a critical role in reducing traffic congestion in transportation systems. However, accurate traffic flow prediction becomes challenging due to the impact of complex spatio-temporal (ST) correlations and the diversity of ST correlations. When modeling complicated ST correlations, researchers usu did not take the diversity of ST correlations into consideration, resulting in poor prediction accuracy. In this paper, we propose ST-InNet, a deep spatio-temporal Inception network for collectively predicting traffic flow in each city region. Specifically, ST-InNet employs two Inception networks to simultaneously capture various spatial and temporal correlations of traffic data, including temporal closeness, temporal periodicity, nearby spatial dependencies, and distant spatial dependencies. For the diversity of spatial correlations, ST-InNet presents an improved variant of an Inception module to explicitly capture the different contributions of spatial correlations for each region. For the diversity of temporal correlations, ST-InNet designs a fusion component to explicitly model the varying contributions of temporal correlations on prediction. The experiments are conducted on a real-world traffic dataset in Nanjing, demonstrating that ST-InNet outperforms five state-of-the-art baselines in short-term and long-term traffic flow predictions with an average accuracy improvement of 32.09% and 30.97%, respectively.

Collaborative business processes gather a set of business processes with complementary competencies and knowledge to cooperate to achieve more business successes. To ensure their successful implementation, correctness is a key issue that needs to be addressed during their development. To this end, we propose a novel correctness enforcement approach for supporting the development of collaborative business processes. In this approach, given an original process specified by Petri nets, we first propose an algorithm for automatically detecting its correctness. Then, in case the original process is partially correct, we prune its reachability graph to obtain its core, which is a reduced reachability graph that doesn't cover invalid states. Finally, a set of controllers is yielded from the core through coordination mapping (i.e., inserting some coordination activities into controllers), and then an enforced process is built by the composition of the original process and the controllers. Our approach is implemented as an analysis module called cetool in the PIPE (Platform Independent Petri Net Editor) and it is validated on a set of real-world cases. The results show the effectiveness and efficiency of the proposed approach.

When an emergency occurs, disposal needs to be built to reduce the risk imposed on life, property, and environment. Generally, the disposal is organized as a cross-organization emergency response process (CERP). To achieve better-emergency response services, its correctness analysis is an important task that needs to be dealt with at design time. In this article, we propose a novel correctness analysis approach for CERPs. Given a CERP, this approach first decomposes it into a set of instance nets. Then, it excludes the invalid instance nets (each corresponds to an incomplete process instance) and adopts the stubborn set to check the structural correctness of each valid instance net without considering resource factors, as well as introduces a structure-based resource analysis (SRA) method to determine whether the resources in it are sufficient. Finally, it determines the correctness of the CERP by comparing the numbers of the correct instance nets and all valid instance nets. If the CERP is incorrect, it returns the correct instance nets, which capture the parts of the CERP that can be executed correctly. This approach is evaluated on an actual data set, and the comparison results show that it outperforms the state-of-the-art technique in terms of effectiveness and efficiency.