Weakly supervised temporal action localization with proxy metric modeling

Temporal localization is crucial for action video recognition. Since the manual annotations are expensive and time-consuming in videos, temporal localization with weak video-level labels is challenging but indispensable. In this paper, we propose a weakly-supervised temporal action localization approach in untrimmed videos. To settle this issue, we train the model based on the proxies of each action class. The proxies are used to measure the distances between action segments and different original action features. We use a proxy-based metric to cluster the same actions together and separate actions from backgrounds. Compared with state-of-the-art methods, our method achieved competitive results on the THUMOS14 and ActivityNet1.2 datasets.     

Cryptanalysis of Two Signature Schemes for IoT and Mobile Health Systems

Wireless Personal Communications - Recently, Lee et al. (Sensors 20(14): 3983, 2020) proposed a certificateless aggregate arbitrated signature scheme CLAAS for IoT environments. Addobea et...     

Friendly spectrum jamming against MIMO eavesdropping

Wireless Networks - Friendly spectrum jamming is a flexible scheme to establish secure communications among heterogeneous wireless devices without the need of encryption. Previous works have...     

Adaptive full order sliding mode control for electronic throttle valve system with fixed time convergence using extreme learning machine

Neural Computing and Applications - This paper proposes a novel extreme learning machine (ELM)-based fixed time adaptive trajectory control for electronic throttle valve system with uncertain...     

A novel cause analysis approach of grey reasoning Petri net based on matrix operations

Cause analysis makes great contributions to identifying the priorities of the causes in fault diagnosis system. A fuzzy Petri net (FPN) is a preferable model for knowledge representation and reasoning and has become an effective fault diagnosis tool. However, the existing FPN has some limitations in cause analysis. It is criticized for the inability to fully consider incomplete and unknown knowledge in uncertain situations. In this paper, an enhanced grey reasoning Petri net (EGRPN) based on matrix operations is presented to address the limitations and improves the flexibility of the existing FPN. The proposed EGRPN model uses grey numbers to handle the greyness and inaccuracy of uncertain knowledge. Then, the EGRPN inference algorithm is executed based on the matrix operations, which can express the relevance of uncertain events in the form of grey numbers and improve the reliability of the knowledge reasoning process. Finally, industrial examples of cause diagnosis are used to illustrate the feasibility and reliability of the EGRPN model. The experimental results show that the new EGRPN model is promising for cause analysis.

     

Social-path embedding-based transformer for graduation development prediction

As the education of students attracts more and more attention, the task of graduation development prediction has gradually become a hot topic in academia and industry. The task of graduation development prediction aims to predict the employment category of students in advance via academic achievement data, which can help administrators understand students’ learning status and set up a reasonable learning plan. However, existing research ignores the potential impact of social relationships on students’ graduation development choices. To fully explore social relationships among students, we propose a Social-path Embedding-based Transformer Neural Network (SPE-TNN) for the task of graduation development prediction in this paper. Specifically, SPE-TNN is divided into the Social-path selection layer, the Social-path embedding layer, the Transformer layer, and the Multi-layer projection layer. Firstly, the Social-path selection layer is designed to find social relationships that impact graduation development and embed them into the student’s performance features through the Social-path embedding layer. Secondly, the Transformer layer is adopted to balance the weights of the students’ features. Finally, the Multi-layer projection layer is used to achieve the student graduation development prediction. Experimental results on the real-world datasets show that SPE-TNN outperforms the existing popular approaches.

     

Study on the preparation and microstructure of a single-crystal hollow turbine blade

This paper studied the structural design of a ceramic core and a blade, ceramic core localization, shell preparation, casting process, core leaching technology, and the heat treatment process of a single-crystal hollow turbine blade. The results show that the single-crystal structure solidification sequence of the blade platform is consistent with the cooling sequence and the pulling-out direction of the blade. The primary dendrites were obviously enlarged with the increase of the blade thickness owing to the change in the local cooling rate. Besides, the γ′ phase had a high uniform size distribution ranging from 0.40 to 0.60?µm after heat treatment, and the cubic degree was more homogeneous in comparison with the as-cast microstructure, which are favorable for the superalloy structure. Moreover, γ′ phase size gradually increased and its quantity gradually reduced owing to the increase of the wall thickness in the growth direction.     

Passive Picoinjection Enables Controlled Crystallization in a Droplet Microfluidic Device

Segmented flow microfluidic devices offer an attractive means of studying crystallization processes. However, while they are widely employed for protein crystallization, there are few examples of their use for sparingly soluble compounds due to problems with rapid device fouling and irreproducibility over longer run‐times. This article presents a microfluidic device which overcomes these issues, as this is constructed around a novel design of “picoinjector” that facilitates direct injection into flowing droplets. Exploiting a Venturi junction to reduce the pressure within the droplet, it is shown that passive injection of solution from a side‐capillary can be achieved in the absence of an applied electric field. The operation of this device is demonstrated for calcium carbonate, where highly reproducible results are obtained over long run‐times at high supersaturations. This compares with conventional devices that use a Y‐junction to achieve solution loading, where in‐channel precipitation of calcium carbonate occurs even at low supersaturations. This work not only opens the door to the use of microfluidics to study the crystallization of low solubility compounds, but the simple design of a passive picoinjector will find wide utility in areas including multistep reactions and investigation of reaction dynamics.