COWO: towards real-time spatiotemporal action localization in videos

Purpose The purpose of this paper is to provide a fast and accurate network for spatiotemporal action localization in videos. It detects human actions both in time and space simultaneously in real-time, which is applicable in real-world scenarios such as safety monitoring and collaborative assembly. Design/methodology/approach This paper design an end-to-end deep learning network called collaborator only watch once (COWO). COWO recognizes the ongoing human activities in real-time with enhanced accuracy. COWO inherits from the architecture of you only watch once (YOWO), known to be the best performing network for online action localization to date, but with three major structural modifications: COWO enhances the intraclass compactness and enlarges the interclass separability in the feature level. A new correlation channel fusion and attention mechanism are designed based on the Pearson correlation coefficient. Accordingly, a correction loss function is designed. This function minimizes the same class distance and enhances the intraclass compactness. Use a probabilistic K-means clustering technique for selecting the initial seed points. The idea behind this is that the initial distance between cluster centers should be as considerable as possible. CIOU regression loss function is applied instead of the Smooth L1 loss function to help the model converge stably. Findings COWO outperforms the original YOWO with improvements of frame mAP 3% and 2.1% at a speed of 35.12 fps. Compared with the two-stream, T-CNN, C3D, the improvement is about 5% and 14.5% when applied to J-HMDB-21, UCF101-24 and AGOT data sets. Originality/value COWO extends more flexibility for assembly scenarios as it perceives spatiotemporal human actions in real-time. It contributes to many real-world scenarios such as safety monitoring and collaborative assembly.

A Comprehensive Evaluation of Internet-of-Things Platforms

Internet of things (IoT) has attracted researchers in recent years as it has a great potential to solve many emerging problems. An IoT platform is missioned to operate as a horizontal key element for serving various vertical IoT domains such as structure monitoring, smart agriculture, healthcare, miner safety monitoring, smart home, and healthcare. In this chapter, the authors propose a comprehensive analysis of IoT platforms to evaluate their capabilities. The selected metrics (features) to investigate the IoT platforms are “ability to serve different domains,” “ability to handle different data formats,” “ability to process unlimited size of data from various context,” “ability to convert unstructured data to structured data,” and “ability to produce complex reports.” These metrics are chosen by considering the reporting capabilities of various IoT platforms, big data concepts, and domain-related issues. The authors provide a detailed comparison derived from the metric analysis to show the advantages and drawbacks of IoT platforms.

The Importance of Direct Patient Reporting of Adverse Drug Reactions in the Safety Monitoring Process

All medicinal products authorized in the European Union are subjects of constant drug-safety monitoring processes. It is organized in a pharmacovigilance system that is designed to protect human health and life by the detection, analysis and prevention of adverse drug reactions (ADRs) and other drug-related problems. The main role of the aforementioned system is to collect and analyze adverse drug reaction reports. Legislation introduced several years ago allowed patients, their legal representatives and caregivers to report adverse drug reactions, which caused them to be an additional source of safety data. This paper presents the analysis of EudraVigilance data related to adverse drug reactions provided by patients, their representatives, as well as those obtained from healthcare professionals related to medicines which belong to M01A anti-inflammatory and antirheumatic products, a non-steroid group. The objective of the study was to identify the changes in the number and structure of adverse reaction reporting after the introduction of pharmacovigilance (PV) obligations in EU. A review of scientific literature was also conducted to assess the differences in adverse reactions reported by patients or their representatives and by healthcare professionals. We also identified other factors which, according to literature review, influenced the number of adverse reaction reports provided by patients. Analysis of data collected from the EudraVigilance showed that from 2011 to 2013 the number of reports made by patients and their caregivers increased by approx. 24 percentage points, and then, from 2014, it constituted around 30% of the total of reported reactions every year, so patient reporting is an important part of pharmacovigilance system and a source of drugs’ safety information throughout their use in healthcare practice. Additionally, there was no interrelationship between the seriousness of reported adverse reactions and the overall number of patient reports when compared to reports form healthcare professionals.

Outlier Detection Based on Multivariable Panel Data and K-Means Clustering for Dam Deformation Monitoring Data

A dam is a super-structure widely used in water conservancy engineering fields, and its long-term safety is a focus of social concern. Deformation is a crucial evaluation index and comprehensive reflection of the structural state of dams, and thus there are many research papers on dam deformation data analysis. However, the accuracy of deformation data is the premise of dam safety monitoring analysis, and original deformation data may have some outliers caused by manual errors or instruments aging after long-time running. These abnormal data have a negative impact on the evaluation of dam structural safety. In this study, an analytical method for detecting outliers of dam deformation data was established based on multivariable panel data and K-means clustering theory. First, we arranged the original spatiotemporal monitoring data into the multivariable panel data format. Second, the correlation coefficients between the deformation signals of different measuring points were studied based on K-means clustering theory. Third, the outlier detection rules were established through the changes of the correlation coefficients. Finally, the proposed model was applied to the Jinping-I Arch Dam in China which is the highest dam in the world, and results indicate that the detection method has high accuracy detection ability, which is valuable in dam safety monitoring applications.