Operational medium range flood forecasting systems are increasingly moving towards the adoption of ensembles of numerical weather predictions (NWP), known as ensemble prediction systems (EPS), to drive their predictions. We review the scientific drivers of this shift towards such ‘ensemble flood forecasting’ and discuss several of the questions surrounding best practice in using EPS in flood forecasting systems. We also review the literature evidence of the ‘added value’ of flood forecasts based on EPS and point to remaining key challenges in using EPS successfully.

Ensemble flood forecasting: A review

The Internet of Underwater Things (IoUT) is an emerging communication ecosystem developed for connecting underwater objects in maritime and underwater environments. The IoUT technology is intricately linked with intelligent boats and ships, smart shores and oceans, automatic marine transportations, positioning and navigation, underwater exploration, disaster prediction and prevention, as well as with intelligent monitoring and security. The IoUT has an influence at various scales ranging from a small scientific observatory, to a mid-sized harbor, and to covering global oceanic trade. The network architecture of IoUT is intrinsically heterogeneous and should be sufficiently resilient to operate in harsh environments. This creates major challenges in terms of underwater communications, whilst relying on limited energy resources. Additionally, the volume, velocity, and variety of data produced by sensors, hydrophones, and cameras in IoUT is enormous, giving rise to the concept of Big Marine Data (BMD), which has its own processing challenges. Hence, conventional data processing techniques will falter, and bespoke Machine Learning (ML) solutions have to be employed for automatically learning the specific BMD behavior and features facilitating knowledge extraction and decision support. The motivation of this article is to comprehensively survey the IoUT, BMD, and their synthesis. It also aims for exploring the nexus of BMD with ML. We set out from underwater data collection and then discuss the family of IoUT data communication techniques with an emphasis on the state-of-the-art research challenges. We then review the suite of ML solutions suitable for BMD handling and analytics. We treat the subject deductively from an educational perspective, critically appraising the material surveyed. Accordingly, the reader will become familiar with the pivotal issues of IoUT and BMD processing, whilst gaining an insight into the state-of-the-art applications, tools, and techniques. Finally, we analyze the architectural challenges of the IoUT, followed by proposing a range of promising direction for research and innovation in the broad areas of IoUT and BMD. Our hope is to inspire researchers, engineers, data scientists, and governmental bodies to further progress the field, to develop new tools and techniques, as well as to make informed decisions and set regulations related to the maritime and underwater environments around the world.

/pdf/internet-of-underwater-things-and-big-marine-data-analytics-19j7i05tj5.pdf

Internet of Underwater Things and Big Marine Data Analytics—A Comprehensive Survey

Structural crack detection using deep convolutional neural networks

Nowadays, deep learning has been increasingly applied in real-world scenarios involving the collection and analysis of sensitive data, which often causes privacy leakage. Differential privacy is widely recognized in the majority of traditional scenarios for its rigorous mathematical guarantee. However, it is uncertain to work effectively in the deep learning model. In this paper, we introduce the privacy attacks facing the deep learning model and present them from three aspects: membership inference, training data extraction, and model extracting. Then we recall some basic theory about differential privacy and its extended concepts in deep learning scenarios. Second, in order to analyze the existing works that combine differential privacy and deep learning, we classify them by the layers differential privacy mechanism deployed, such as input layer, hidden layer, and output layer, and discuss their advantages and disadvantages. Finally, we point out several key issues to be solved and provide a broader outlook of this research direction.

/pdf/differential-privacy-preservation-in-deep-learning-1bf3fnywlq.pdf

Differential Privacy Preservation in Deep Learning: Challenges, Opportunities and Solutions

The recent development of big data analytics (BDA) and the Internet of Things (IoT) technologies create a huge opportunity for both disaster management systems and disaster-related authorities (emergency responders, police, public health, and fire departments) to acquire state-of-the-art assistance and improved insights for accurate and timely decision-making. The motivation behind this research is to pave the way for effective utilization of the available opportunities that the BDA and IoT collaboratively offer to predict, understand and monitor disaster situations. Most of the conventional disaster management systems lack the support for multiple new data sources and real-time big data processing tools that can assist decision makers with quick and accurate results. This paper highlights the importance of BDA and IoT for disaster management and investigates recent studies directed towards the same. We classify a thematic taxonomy with several related attributes and inspect the prevalent solutions to propose a conceptual reference model for the deployment of BDA- and IoT-based disaster management environments. The reference model with its proposed integrated parameters can provide guidelines to harvest, transmit, manage, and analyze disaster data from various data sources to deliver updated and valuable information for disaster management. We also enumerate some important use cases from a disaster management perspective. Finally, we highlight the main research challenges that need to be addressed in such an important field of research.

/pdf/the-rising-role-of-big-data-analytics-and-iot-in-disaster-molkgfyjup.pdf

The Rising Role of Big Data Analytics and IoT in Disaster Management: Recent Advances, Taxonomy and Prospects

Traditional surveillance systems for observing water levels are often complex, costly, and time-consuming. In this paper, we developed a low-cost unmanned surveillance system consisting of remote measuring stations and a monitoring center. The system uses a map-based Web service, as well as video cameras, water level analyzers, and wireless communication routers necessary to display real-time water level measurements of rivers and reservoirs on a Web platform. With the aid of a wireless communication router, the water level information is transmitted to a server connected to the Internet via a cellular network. By combining complex water level information of different river basins, the proposed system can be used to forecast and prevent flood disasters. In order to evaluate the proposed system, we conduct experiments using three feasible methods, including the difference method, dictionary learning, and deep learning. The experimental results show that the deep learning-based method performs best in terms of accuracy and stability.

Deep Learning-Based Unmanned Surveillance Systems for Observing Water Levels

Intelligent intrusion detection based on federated learning aided long short-term memory

Automatic modulation classification (AMC) is one of the most critical technologies for non-cooperative communication systems. Recently, deep learning (DL) based AMC (DL-AMC) methods have attracted significant attention due to their preferable performance. However, the study of most of DL-AMC methods are concentrated in the single-input and single-output (SISO) systems, while there are only a few works on DL-based AMC methods in multiple-input and multiple-output (MIMO) systems. Therefore, we propose in this work a convolutional neural network (CNN) based zero-forcing (ZF) equalization AMC (CNN/ZF-AMC) method for MIMO systems. Simulation results demonstrate that the CNN/ZF-AMC method achieves better performance than the artificial neural network (ANN) with high order cumulants (HOC)-based AMC method under the condition of the perfect channel state information (CSI). Moreover, we also explore the impact of the imperfect CSI on the performance of the CNN/ZF-AMC method. Simulation results demonstrated that the classification performance is not only influenced by the imperfect CSI, but also associated with the number of the transmit and receive antennas.

Automatic Modulation Classification for MIMO Systems via Deep Learning and Zero-Forcing Equalization

With the development of wireless communications and internet of things (IoT), non-orthogonal multiple access (NOMA) has been considered as one of effective schemes to meet the rapidly growing user access requirements. Two types of NOMA, i.e., NOMA-2000 and power-domain NOMA (PD-NOMA), have been proposed in recent years. The first one is a superposition of a set of orthogonal frequency division multiple access (OFDMA) signals and a set of spread-spectrum multicarrier-code division multiple access (MC-CDMA) signals while the second one is a direct superposition of a MC-CDMA signal and an OFDMA signal. This paper proposes a dynamic user grouping method for classifying users and then compares the performance between NOMA-2000 and PD-NOMA over Rayleigh fading channels. Simulation results show that the PD-NOMA can always exhibit lower bit error rate (BER) than the NOMA-2000 under different signal-to-noise ratios. Under the Rayleigh fading environment, the performance of the PD-NOMA after user grouping is better than that of NOMA-2000.

/pdf/dynamic-user-grouping-based-noma-over-rayleigh-fading-2zgm08bduy.pdf

Dynamic User Grouping-Based NOMA Over Rayleigh Fading Channels

Decentralized edge computing techniques have been attracted strongly attentions in many applications of intelligent Internet of Things (IIoT). Among these applications, intelligent edge surveillance (INES) methods play a very important role to recognize object feature information automatically from surveillance video by virtue of edge computing together with image processing and computer vision. Traditional centralized surveillance techniques recognize objects at the cost of high latency, high cost and also require high occupied storage. In this paper, we propose a deep learning-based INES technique for a specific IIoT application. First, a depthwise separable convolutional strategy is introduced to build a lightweight deep neural network to reduce its computational cost. Second, we combine edge computing with cloud computing to reduce network traffic. Third, our proposed INES method is applied into the practical construction site for the validation of a specific IIoT application. The detection speed of the proposed INES reaches 16 frames per second in the edge device. After the joint computing of edge and cloud, the detection precision can reach as high as 89%. In addition, the operating cost at the edge device is only one-tenth of that of the centralized server. Experiment results are given to confirm the proposed INES method in terms of both computational cost and detection accuracy.

Yue Yin

Papers

Deep Learning-Based Unmanned Surveillance Systems for Observing Water Levels

Intelligent intrusion detection based on federated learning aided long short-term memory

Automatic Modulation Classification for MIMO Systems via Deep Learning and Zero-Forcing Equalization

Dynamic User Grouping-Based NOMA Over Rayleigh Fading Channels

Lightweight Deep Learning Based Intelligent Edge Surveillance Techniques