Search

This paper studies congestion-aware route-planning policies for intermodal Autonomous Mobility-on-Demand (AMoD) systems, whereby a fleet of autonomous vehicles provides on-demand mobility jointly with public transit under mixed traffic conditions (consisting of AMoD and private vehicles). First, we devise a network flow model to jointly optimize the AMoD routing and rebalancing strategies in a congestion-aware fashion by accounting for the endogenous impact of AMoD flows on travel time. Second, we capture the effect of exogenous traffic stemming from private vehicles adapting to the AMoD flows in a user-centric fashion by leveraging a sequential approach. Since our results are in terms of link flows, we then provide algorithms to retrieve the explicit recommended routes to users. Finally, we showcase our framework with two case-studies considering the transportation sub-networks in Eastern Massachusetts and New York City, respectively. Our results suggest that for high levels of demand, pure AMoD travel can be detrimental due to the additional traffic stemming from its rebalancing flows. However, blending AMoD with public transit, walking and micromobility options can significantly improve the overall system performance by leveraging the high-throughput of public transit combined with the flexibility of walking and micromobility.

Differential protection, as the key protection element in the power transformers, has always been threatened with sending false trips subjected to external transient disturbances. As a result, differential protection needs an additional block to distinguish between internal faults and external transient disturbances. The protection system should i) be able to perform based on raw data, ii) be able to learn fully temporal features and sudden changes in the transient signals, and iii) impose no assumption on noise. To address these challenges, a fast recurrent neural network, namely fast gated recurrent neural network (FGRNN). By removing the reset gate in the gated recurrent unit (GRU), the proposed network is capable of learning abrupt changes in addition to significantly reducing the computational time. Furthermore, a loss function based on an information theory concept is formulated in this paper to enhance the learning ability as well as robustness against non-Gaussian/Gaussian noises. A generalized form of mutual information is also adopted to form a noise model-free loss function, then incorporated with the designed deep network. Simulated and experimental examinations engaging various external factors, in addition to a comparison between the proposed fast GRNN, GRU, and seven firmly-established methods indicates the faster and more reliable performance of the proposed algorithm. Post-print / Final draft

Participants in electricity markets are becoming more proactive because of the fast development of DERs and DSM, which also boosts the emergence of P2P market mechanisms. Moreover, the market is also required to operate in a real-time scheme in response to changes in generation and load to maintain power balance. Therefore, a practicable real-time P2P market mechanism is in urgent need. However, it is technically challenging to deploy P2P mechanisms in real-time, since they most often involve a heavy computation burden, while the time available for negotiation in real-time is very short. Our core contribution is to design a novel asynchronous online optimization framework to enable the real-time P2P market negotiation mechanism, which can greatly reduce the computation and communication burden from two aspects. First, a novel online consensus ADMM algorithm is proposed, which can greatly reduce the computation complexity since only one iteration is performed for each agent in every time period. Second, the market operates in an asynchronous mode so that all agents can freely trade without waiting for idle neighboring agents. The sublinear regret upper bound is proved for our online algorithm, which indicates that social welfare can be maximized in the long run on time average.

The rising demand for high quality display has ensued active research in high dynamic range (HDR) imaging, which has the potential to replace the standard dynamic range imaging. This is due to HDR’s features like accurate reproducibility of a scene with its entire spectrum of visible lighting and color depth. But this capability comes with expensive capture, display, storage and distribution resource requirements. Also, display of HDR images/video content on an ordinary display device with limited dynamic range requires some form of adaptation. Many adaptation algorithms, widely known as tone mapping (TM) operators, have been studied and proposed in the last few decades. In this paper, we present a comprehensive survey of 60 TM algorithms that have been implemented on hardware for acceleration and real-time performance. In this state-of-the-art survey, we will discuss those TM algorithms which have been implemented on GPU [1]–[12], FPGA [13]–[47], and ASIC [48]–[60] in terms of their hardware specifications and performance. Output image quality is an important metric for TM algorithms. From our literature survey we found that, various objective quality metrics have been used to demonstrate the quality of those algorithms hardware implementation. We have compiled those metrics used in this survey [61], [62], and analyzed the relationship between hardware cost, image quality and computational efficiency. Currently, machine learning-based (ML) algorithms have become an important tool to solve many image processing tasks, and this paper concludes with a discussion on the future research directions to realize ML-based TM operators on hardware.

Big Data (BD)-driven business intelligence (BI) is considered to be a new development stage within industrial engineering management to achieve higher business value creation. The article provides extensive research of BD-driven approaches to identify strategic knowledge and value-creating components within Internet of Things (IoT) manufacturing. Due to previous research studies focused mostly on partial solutions and lack a holistic view, this article topic is still far from being sufficiently explored and resolved. The article presents the results of an extensive research study of contemporary professional literature with a specific aim to provide a more holistic and systematical view on the current state and future trends in this issue. To solve this high complex research problem, both quantitative and qualitative research methodology approaches are used. The article is primarily based on a systematic literature review covering 187 essential and 36 additional current research papers within the Web of Science and Scopus database from 2012 to the present. Research findings identify the seven key strategic elements determining that Big Data analytics (BDA) can become a real and tremendous business value creation driver within IoT intelligent manufacturing. These research results provide important conclusions and implications for challenging future investigations into BDA and BI systems in the context of advancing the Industry 4.0 revolution. In conclusion, we propose a final suggestion in the form of a strategic future research chain from IoT through BDA to value creation based on BD intelligence within IoT manufacturing, whereas seven strategic elements might play a crucial. Author, Internal Grant Agency of Tomas Bata University in Zlin [IGA/FaME/2020/009-Process]

This review article discusses the definition and implementation of brain–computer interface (BCI) system relying on brain connectivity (BC) and machine learning/deep learning (DL) for motor imagery (MI)-based applications. During the past few years, many approaches have been explored in terms of types of neurological sources of information, feature extraction, and intention prediction for BCI applications. Two novel aspects are becoming increasingly interesting for the BCI community: BC modeling and DL. The former aims at describing the interactions among different brain regions as connectivity patterns that reflect the dynamics of information flow either at rest or when performing a task. The latter is becoming pervasive for its capability of modeling and predicting complex data, where a huge amount of information is involved. In this scenario, we conducted a systematic literature review on BCI studies that led to the selection of 34 articles meeting all the required criteria. This provides evidence of the rapid growth of the topic over the past few years, though being still in its infancy. The last part of this article is dedicated to this new frontier of BCI that we call MI BC-based computer interfaces highlighting the potential of BC features. This, jointly with DL as enabling technology, has the potential of improving the performance of electroencephalography-based systems.

[EN] Floods are expected to increase in the coming years due to global warming. The early identification of water-based disasters can be lifesaving, and the challenge is to identify appropriate and timely warning measures. Social-media tools such as Twitter provide citizens with a real-time communication channel for reporting problems related to our environment, which allows humans to act as social sensors. In this article, we show the main results and lessons learned from the research project WATERoT, funded by the Spanish government. In this project, we designed a social sensing application (called WATERSensing) for the prevention and evaluation of water-related disasters with the participation of individuals through social networks. This tool crawls microtexts from different social networks such as Twitter, RSS feeds, or Telegram, which are analyzed with natural language processing techniques. A case study of Storm Gloria, a Mediterranean storm that heavily affected eastern Spain in January 2020, is presented to evidence that the system can correlate data from social media with actual events. We demonstrate that the analysis of different sources of information opens up new opportunities in the development of warning systems for the prevention, early identification, and management of natural disasters., This work was supported in part by the Spanish Ministry of Science and Innovation under Grant RYC2018-025580-I, Grant RTI2018-096384-B-I00, Grant RTC-2017-6389-5, and Grant RTC2019007159-5; in part by the Fundacion Seneca del Centro de Coordinacion de la Investigacion de la Region de Murcia under Project 20813/PI/18; and in part by the European Union's Horizon 2020 Research and Innovation Programme under Grant 101017861.

We present a systematic evaluation and optimization of a complex bio-medical signal processing application on the BrainWave prototype system, targeted towards ambulatory EEG monitoring within a tiny power budget of 1 mW. The considered BrainWave processor is completely programmable, while maintaining energy-efficiency by means of a Coarse-Grained Reconfigurable Array (CGRA). This is demonstrated through the mapping and evaluation of a state-of-the-art non-convulsive epileptic seizure detection algorithm, while ensuring real-time operation and seizure detection accuracy. Exploiting the CGRA leads to an energy reduction of 73.1%, compared to a highly tuned software implementation (SW-only). A total of 9 complex kernels were benchmarked on the CGRA, resulting in an average 4.7 × speedup and average 4.4 × energy savings over highly tuned SW-only implementations. The BrainWave processor is implemented in 28-nm FDSOI technology with 80 kB of Foundry-provided SRAM. By exploiting near-threshold computing for the logic and voltage-stacking to minimize on-chip voltage-conversion overhead, additional 15.2% and 19.5% energy savings are obtained, respectively. At the Minimum-Energy-Point (MEP) (223 μW, 8 MHz) we report a measured state-of-the-art 90.6% system conversion efficiency, while executing the epileptic seizure detection in real-time.

Artificial Neural Networks (ANNs) are increasingly being used within safety-critical Cyber-Physical Systems (CPSs). They are often co-located with traditional embedded software, and may perform advisory or control-based roles. It is important to validate both the timing and functional correctness of these systems. However, most approaches in the literature consider guaranteeing only the functionality of ANN based controllers. This issue stems largely from the implementation strategies used within common neural network frameworks -- their underlying source code is often simply unsuitable for formal techniques such as static timing analysis. As a result, developers of safety-critical CPS must rely on informal techniques such as measurement based approaches to prove correctness, techniques that provide weak guarantees at best. In this work we address this challenge. We propose a design pipeline whereby neural networks trained using the popular deep learning framework Keras are compiled to functionally equivalent C code. This C code is restricted to simple constructs that may be analysed by existing static timing analysis tools. As a result, if compiled to a suitable time-predictable platform all execution bounds may be statically derived. To demonstrate the benefits of our approach we execute an ANN trained to drive an autonomous vehicle around a race track. We compile the ANN to the Patmos time-predictable controller, and show that we can derive worst case execution timings., 4 pages, 2 figures. IEEE Embedded Systems Letters, 2020