Multiple Time Slots Research Articles

Geohash coding-powered deep learning network for vessel trajectory prediction using clustered AIS data in maritime Internet of Things industries

The increasing traffic flow and frequent navigational activities in maritime transportation raise accidents, such as collision and grounding. To mitigate such safety issues, high precision and stable vessel trajectory prediction play an essential role in developing accident prevention techniques in maritime Internet of Things (IoT) industries. However, vessel trajectory prediction is a challenge because conventional deep learning technologies struggle to capture complex changes in vessel trajectories. To address this challenge, this study designs a novel prediction method (namely DBSCAN-GeoCLSTM) comprising two steps. The first step employs the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm to perform clustering analysis on trajectories. The second step feds trajectory data from different categories into a Long Short-Term Memory (LSTM) optimization network with Geohash Coding (called GeoCLSTM netework) for training. This GeoCLSTM network encodes the trajectory points using Geohash Coding to construct one-hot vectors, which captures the positional correlation information among trajectory points. The GeoCLSTM model further introduces a dimensionality reduction module by converting the one-hot vectors into feature vectors. Subsequently, the GeoCLSTM model employs LSTM to use these feature vectors from multiple consecutive time slots to accurately predict trajectory data. Results of comparative experiments demonstrate that the proposed DBSCAN-GeoCLSTM method achieved accurate and stable predictions, and outperformed eight state-of-the-art methods in the vessel trajectory prediction task.

A Consensus-based Traffic Prediction for Time Series Data in SDN

Objective: This research proposes a methodology for improving real-time traffic prediction by constructing dataset from the live traffic in Software-Defined Networks (SDNs). Methods: This work applies time-series based machine learning models such as XGBoost Regressor, LSTM, and Seasonal ARIMA, on the collected and preprocessed traffic data from SDN switches. Findings: Simulation shows that the percentage of error parameters that depict accuracy and goodness of fit for traffic predictions are still weak and needs improvement, as these predictions have the potential to compose new policies for the dynamic environment. Novelty: The consensus method is applied to forecast future network traffic across multiple time slots as consensus strengthens the decisions. Keywords: Software defined networking, Traffic prediction, Consensus, Machine learning, Time series data

Patent transformation prediction: When a patent can be transformed

Patent transformation is a pivotal pathway for realizing technological advancements, and patent transformation prediction is a potential strategy for improving the patent transformation rate. Existing automated patent transformation prediction models do not predict the transformation time, causing invalid conclusions for these valid patents. In this study, we propose a patent transformation prediction model to predict patent transformation time. (1) To obtain patent features in different time periods, the years elapsed since the patent application are segmented into multiple time slots; (2) For each patent, we extract static features and dynamic features of each time slot after constructing and embedding a dynamic graph of the patent; (3) The features for each time slot are concatenated as the input of the dynamic model which utilizes a neural network to predict the patent transformation of the time slot. We measure the model in diverse domains, each of which includes 10,000 patent transformation data. The experimental results show that precision, recall, and F1 scores are approximately 80% for predicting patent transformation in the next 3 years. Additionally, our study yields some novel findings: (1) later applied patents have a higher transformation speed; (2) over 90% of patent transformations occur within 13 years since the patent application; (3) dynamic features, especially dynamic structured features, have a significantly greater impact on patent transformation prediction compared to static features; (4) our model performs stably on different experiment data.

Effect of time of day on outcomes in elective surgery: asystematic review.

The timing of elective surgery could affect clinical outcome because of diurnal rhythms of patient physiology as well as surgical team performance. Waiting times for elective surgery are increasing in many countries, leading to increasing interest in undertaking elective surgery in the evening or at night. We aimed to systematically review the literature on the effect of the timing of elective (but not urgent or emergency) surgery on mortality, morbidity and other clinical outcomes. We searched databases for relevant studies combining the terms 'circadian rhythm' and 'anaesthesia/surgery'. Additional relevant articles were found by hand-searching the references. All studies were screened for bias. Included studies examined daytime vs. evening/night-time surgery, morning vs. afternoon surgery, multiple timeslots or used time as a continuous variable. Nineteen retrospective cohort studies, one prospective cohort study and one randomised controlled trial were included (n = 798,914). Evening/night-time elective surgery was associated with a higher risk of mortality when compared with daytime procedures in three studies (n = 611,230), with odds ratios (95%CI) for mortality ranging from 1.35 (1.16-1.56) to 3.98 (1.54-10.30), while no differences were found in three other studies (n = 142,355). No differences were found for morning vs. afternoon surgery (four studies, n = 3277). However, most studies had a low quality of evidence due to their retrospective nature and because not all studies corrected for patient characteristics. Moreover, the studies were heterogeneous in terms of the reported time slots and clinical outcomes. We found that evening/night-time elective surgery is associated with a higher risk of mortality compared with daytime surgery. However, the quality of evidence was graded as low, and thus, future prospective research should publish individual patient data and standardise outcome measures to allow firm conclusions and facilitate interventions.

An Environment-Aware Adaptive Data-Gathering Method for Packet-Level Index Modulation in LPWA.

Low-power wide-area (LPWA) is a communication technology for the IoT that allows low power consumption and long-range communication. Additionally, packet-level index modulation (PLIM) can transmit additional information using multiple frequency channels and time slots. However, in a competitive radio access environment, where multiple sensors autonomously determine packet transmission, packet collisions occur when transmitting the same information. The packet collisions cause a reduction in the throughput. A method has been proposed to design a mapping table that shows the correspondence between indexes and information using a packet collision minimization criterion. However, the effectiveness of this method depends on how the probability of the occurrence of the information to be transmitted is modeled. We propose an environment-aware adaptive data-gathering method that identifies the location of factors affecting sensor information and constructs a model for the probability of the occurrence of sensor information. The packet collision rate of the environment-aware adaptive data-gathering method was clarified through computer simulations and actual experiments on a 429 MHz LPWA. We confirm that the proposed scheme improves the packet collision rate by 15% in the computer simulation and 30% in the experimental evaluation, respectively.

Mitigating AC and DC Interference in Multi-ToF-Camera Environments.

Multi-camera interference (MCI) is an important challenge faced by continuous-wave time-of-flight (C-ToF) cameras. In the presence of other cameras, a C-ToF camera may receive light from other cameras' sources, resulting in potentially large depth errors. We propose stochastic exposure coding (SEC), a novel approach to mitigate MCI. In SEC, the camera integration time is divided into multiple time slots. Each camera is turned on during a slot with an optimal probability to avoid interference while maintaining high signal-to-noise ratio (SNR). The proposed approach has the following benefits. First, SEC can filter out both the AC and DC components of interfering signals effectively, which simultaneously achieves high SNR and mitigates depth errors. Second, time-slotting in SEC enables 3D imaging without saturation in the high photon flux regime. Third, the energy savings due to camera turning on during only a fraction of integration time can be utilized to amplify the source peak power, which increases the robustness of SEC to ambient light. Lastly, SEC can be implemented without modifying the C-ToF camera's coding functions, and thus, can be used with a wide range of cameras with minimal changes. We demonstrate the performance benefits of SEC with thorough theoretical analysis, simulations and real experiments, across a wide range of imaging scenarios.

Strategies to improve customer service in delivery time slot management

AbstractIn several online retail contexts, such as grocery retailing, customers have to be present at the moment of delivery, that is, an attended home delivery service is in place. This requirement adds new challenges to this channel, often leading to narrow profitability. From an operations perspective, this service is performed with the retailer offering multiple time slots for the customer to choose from. Retailers target a cost‐efficient delivery process that also accounts for customers' preferences by properly managing the options to show to customers, that is, time slot management. This study analyzes a dynamic slotting problem, that is, choosing the best slots to show for each customer, which is close to many practical cases pursuing a customer service orientation. We study two new strategies to improve customer service while satisfying cost‐efficiency goals: (i) enforcing a constraint on the minimum number or percentage of slots to show to customers and (ii) integrating multiple days when tackling this challenging problem. Our results show under which conditions these proposed strategies can lead to win‐win situations for both customer service and profit.

Over-the-Air Computation With Multiple Receivers: A Space-Time Approach

The emerging concept of Over-the-Air (OtA) computation has shown great potential for achieving resource-efficient data aggregation across large wireless networks. However, current research in this area has been limited to the standard many-to-one topology, where multiple nodes transmit data to a single receiver. In this study, we address the problem of applying OtA computation to scenarios with multiple receivers, and propose a novel communication design that exploits joint precoding and decoding over multiple time slots. To determine the optimal precoding and decoding vectors, we formulate an optimization problem that aims to minimize the mean squared error of the desired computations while satisfying the unbiasedness condition and power constraints. Our proposed multi-slot design is shown to be effective in saving communication resources (e.g., time slots) and achieving smaller estimation errors compared to the baseline approach of separating different receivers over time.

EPT-GCN: Edge propagation-based time-aware graph convolution network for POI recommendation

In location-based social networks (LBSNs), point-of-interest (POI) recommendation systems help users identify unvisited POIs by filtering large amounts of information. Accurate POI recommendations can effectively improve user satisfaction and save time in finding POIs. In recent years, the graph convolution network (GCN) technique, which enhances the representational ability of neural networks by learning the embeddings of users and items, has been widely adopted in recommendation systems to improve accuracy. Combining GCN with various information, such as time and geographical information, can further improve recommendation performance. However, existing GCN-based techniques simply adopt time information by modeling users’ check-in sequences, which is insufficient and ignores users’ time-based high-order connectivity. Note that time-based high-order connectivity refers to the relationship between indirect neighbors with similar preferences in the same time slot. In this paper, we propose a new time-aware GCN model to extract rich collaborative signals contained in time information. Our work is the first to divide user check-ins into multiple subgraphs, i.e., time slots, based on time information. We further propose an edge propagation module to adjust edge affiliation, where edges represent check-ins, to propagate user’s time-based preference to multiple time slots. The propagation module is based on an unsupervised learning algorithm and does not require additional ground-truth labels. Experimental results confirm that our method outperforms state-of-the-art GCN models in all baselines, improving Recall@5 from 0.0803 to 0.0874 (8.84%) on the Gowalla dataset and from 0.0360 to 0.0388 (7.78%) on the New York dataset. The proposed subgraph mining technique and novel edge-based propagation module have high scalability and can be applied to other subgraph construction models.

DRL-Based Computation Offloading With Queue Stability for Vehicular-Cloud-Assisted Mobile Edge Computing Systems

Computation offloading is considered as a promising method to improve computation performance of Intelligent Vehicles (IVs), where IVs can offload resource-hungry applications to Mobile Edge Computing (MEC) servers. However, due to the dynamic environment of Intelligent Transportation Systems, it's challenging to develop an effective offloading scheme that ensures stable operation of the system. Furthermore, IVs only offload tasks to MEC servers or parked vehicles, how to take full advantage of resources in a random traffic flow is a main challenge. In this paper, we propose a vehicular-cloud-assisted MEC network in urban cities to fully explore the idle resources and ensure the stability of task queue. Specifically, we develop a novel virtual platform based on deep neural network that predicts vehicles trajectory and creates vehicular cloud to integrate computation resources. We then design a vehicular-cloud-assisted offloading scheme that aims to maximize task throughput in continuous time slots subject to multi-constraint. To address the coupling among multiple variables and different time slots, we put forward a lightweight framework to apply the Lyapunov optimization in combination with deep reinforcement learning. In particular, we apply Lyapunov drift-plus-penalty approach to decompose the initial problem into per-slot subproblems and control the long-term task queue stability. To further reduce the computation complexity, we decouple the subproblem into three processes, and the deep Q-network is put forward to solve it. Extensive simulations demonstrate that under different task arrivals, our proposed scheme can achieve the task queue stability within 10 time slots with a low transmission power.

Maximizing Sensing and Computation Rate in Ad Hoc Energy Harvesting IoT Networks

This article considers the collection and processing of data by solar-powered servers operating in an Internet of Things (IoT) network. Specifically, these servers aim to cooperatively maximize the amount of data collected from devices and computed over multiple time slots. To achieve this aim, they must consider computation deadline, time-varying energy arrivals at sensor devices and other servers. To this end, this article outlines a mixed-integer linear program (MILP), which can be used to optimize the sensing time of sensor devices, offloading decision of each server, and the number of virtual machines (VMs) assigned to each device. Further, this article proposes a multiagent co-operative <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$Q$ </tex-math></inline-formula> -learning approach coupled with the Hungarian algorithm to assign VMs to devices. It allows servers to learn when to share their energy and VMs with neighbor servers using only noncausal energy and channel gain information. The simulation results show that the amount of processed data by co-operative <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$Q$ </tex-math></inline-formula> -learning is 93% that of MILP.

Attention-based neural networks for trust evaluation in online social networks

Trust relationship prediction has gained a lot of interest in online social networks as it allows users to escape complex analysis in decision-making. However, most existing work fail to consider two kinds of complementary crucial user data, users' trusted neighbors and temporal continuity of user behaviors, simultaneously. In this paper, we analyze the complementarity between the crucial user data mentioned above and design an attention-based neural networks model, GainTrust, to aggregate the two kinds of user data for trust relationship prediction task. Specifically, we firstly map the users' trust neighbors and behavioral records into the same feature space by designing heterogeneous network embedding layer. Then, we develop multi-layer Long Short-Term Memory (LSTM) network to further learn the time series features of users over multiple time slots. Finally, after integrating time series features with trusted neighborhood features, we design two-level multi-head attention mechanism to obtain global trust features for trust evaluation among users. A series of extensive experiments are conducted on two real-world datasets and the results demonstrate the effectiveness of the proposed approach.

Multiuser Computation Offloading for Long-Term Sequential Tasks in Mobile Edge Computing Environments

Mobile edge computing has shown its potential in serving emerging latency-sensitive mobile applications in ultra-dense 5G networks via offloading computation workloads from the remote cloud data center to the nearby network edge. However, current computation offloading studies in the heterogeneous edge environment face multifaceted challenges: Dependencies among computational tasks, resource competition among multiple users, and diverse long-term objectives. Mobile applications typically consist of several functionalities, and one huge category of the applications can be viewed as a series of sequential tasks. In this study, we first proposed a novel multiuser computation offloading framework for long-term sequential tasks. Then, we presented a comprehensive analysis of the task offloading process in the framework and formally defined the multiuser sequential task offloading problem. Moreover, we decoupled the long-term offloading problem into multiple single time slot offloading problems and proposed a novel adaptive method to solve them. We further showed the substantial performance advantage of our proposed method on the basis of extensive experiments.

Deep Reinforcement Learning Driven UAV-Assisted Edge Computing

Unmanned aerial vehicles (UAVs) are playing a critical role in provisioning instant connectivity and computational needs of Internet of Things Devices (IoTDs), especially in crisis and disaster management. In this work, we focus on optimizing trajectories of UAVs along which IoTDs are served with communication and computing resources in multiple time slots. The Quality of Experience (QoE) of an IoTD depends on its latency performance; we thus aim to maximize the average aggregate QoE of all IoTDs overall time slots. However, this is a nonconvex, nonlinear, and mixed discrete optimization problem, which is difficult to solve and obtain the optimal solution. We thus propose two deep reinforcement learning algorithms to solve this problem by considering UAV path planning, user assignment, bandwidth, and computing resource assignment. We compare the performance of our proposed algorithms through simulations with three baseline cases: 1) with fixed UAV locations; 2) without UAVs; and 3) the fixed UAV trajectories. We demonstrate that the deep reinforcement learning algorithms perform better than all baseline cases.

Wireless Information Surveillance Over Multiple Time Slots

Proactive eavesdropping via joint jamming and relaying has been proposed to improve the legitimate surveillance performance. However, how will it perform over multiple time slots compared to proactive eavesdropping via jamming remains unknown. To answer this question, proactive eavesdropping via joint jamming and relaying over multiple time slots is investigated with full and causal channel state information (CSI). The problem for maximizing the average eavesdropping rate subject to the peak and average transmit power constraints is investigated, and the online and offline algorithms are proposed. Simulation results confirm that the proposed algorithms are low complex and practically optimal. It is shown that compared to proactive eavesdropping via jamming, the joint jamming and relaying always performs better with full CSI, and performs better with causal CSI when the average transmit power constraint is loose.

Incremental incentive mechanism design for diversified consumers in demand response

Demand response has been proven to be an effective way to improve energy utilization efficiency. It is notable that the diversified characteristics of residential consumers, which many greatly affect its performance in demand response, have not been fully considered in existing incentive mechanisms. In this paper, an incremental incentive mechanism for incentive-based demand response (IBDR) is proposed, in which consumers obtain different incentives according to the increment of response, so that the incentive can follow the change of consumers' marginal cost. We theoretically illustrate that the proposed incremental incentive mechanism can effectively improve the profit of load service entity (LSE), as well as the benefit of highly flexible consumers, compared with other existing incentive mechanism. In practice, LSE's bidding strategy in the day ahead market is affected by the intraday IBDR strategy that cannot be known in advance. In order to solve the bidding problem with incomplete information in the day ahead market, we propose an asynchronous double-interaction deep reinforcement learning (DRL) algorithm to maximize LSE’s cumulative profit of multiple time slots throughout the day. Numerical simulation results show that the proposed mechanism can improve the consumers' response depth while reducing the unit incentive cost, and the proposed DRL algorithm has relatively stable and satisfactory performance even in highly uncertain environment.

Learning How to Transfer From Uplink to Downlink via Hyper-Recurrent Neural Network for FDD Massive MIMO

In order to unlock the full advantages of massive multiple-input multiple-output (MIMO) in the downlink, the base station (BS) must leverage information about the downlink fading channels. However, in frequency division duplex (FDD) systems, full channel reciprocity does not hold, and acquiring information about the downlink channels generally requires downlink pilot transmission followed by uplink feedback. Prior work proposed to design pilot transmission, feedback, and channel state information (CSI) estimation, or directly downlink beamforming, via deep learning in an end-to-end manner. While previous work only used downlink pilots in a single slot, in this work, we introduce an enhanced end-to-end design that leverages partial uplink-downlink reciprocity and temporal correlation of the fading processes by utilizing jointly downlink and uplink pilots across multiple time slots. The proposed method is based on a novel deep learning architecture – HyperRNN – that combines hypernetworks and recurrent neural networks (RNNs) to optimize the transfer of long-term invariant channel features from uplink to downlink. Simulation results demonstrate that the HyperRNN achieves a lower normalized mean square error (NMSE) performance in terms of channel estimation, and that it attains a larger achievable sum-rate when applied to multi-user beamforming, as compared to the state of the art.

Research on wireless spectrum allocation and utility evaluation of cross-domain multi-slot radio

The existing spectrum use authorization adopts the large-period and large-area allocation mode, and users exclusively use the right to use the spectrum, resulting in the idle spectrum of multiple time slots and regions and a low utilization rate. This paper proposes a cross-domain, multi-slot Wireless Spectrum Allocation Mechanism (CMWSA) from a fine-grained spatiotemporal perspective. The bilateral spectrum auction model includes the buyer’s location, the start and end time, and the interference radius in the auction information, and the multi-spectrum buyer virtual grouping algorithm is designed. By classifying the spectrum and constructing the interference matrix, a cross-domain, multi-slot, spatiotemporal reuse Wireless Spectrum auction mechanism is proposed to improve the utilization of the idle spectrum and increase users’ satisfaction. Simulation results show that CMWSA can improve the spectrum utilization rate of secondary users, meet the diverse needs of secondary users, and improve the spectrum reuse rate.

Simple Clock Drift Estimation and Compensation for Packet-Level Index Modulation and Its Implementation in LoRaWAN

Low-power wide-area network (LPWAN), which includes the long-range wide-area network (LoRaWAN) protocol, is an enabling technology that satisfy low power consumption and long-range communication. In many applications of LPWAN, an end node (EN) transmits data at regular intervals. Based on this, we had previously proposed the concept of packet-level index modulation (PLIM) to increase the number of information bits transmitted by one data packet. In PLIM, the generation interval between two consecutive packets is split into multiple time slots. Each EN transmits its packet in a specific combination of time slot and frequency channel, which represents the index, to convey additional information bits. To retrieve additional information, the gateway (GW) detects the time slot in which the data packet is being transmitted. Therefore, accurate synchronization between EN and GW is essential. However, clock drift occurs due to the inexpensive real-time clock oscillator on each EN, which results in timing misalignment between each node and the GW. This article proposes a simple clock drift estimation and compensation method for the PLIM. An experimental measurement is performed to model the clock drift. The numerical results obtained using the clock drift model show that it can accurately detect the time slot index under the influence of clock drift. Furthermore, PLIM is implemented on a commercial LoRaWAN node and GW to demonstrate its practicability.

Multi-Agent Reinforcement Learning for a Random Access Game

This work investigates a random access (RA) game for a time-slotted RA system, where <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$N$</tex-math></inline-formula> players choose a set of slots of a frame and each frame consists of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$M$</tex-math></inline-formula> multiple time slots. We obtain the pure strategy Nash equilibria (PNEs) of this RA game, where slots are fully utilized as in the centralized scheduling. As an algorithm to realize a PNE (Pure strategy Nash Equilibrium), we propose an Exponential-weight algorithm for Exploration and Exploitation (EXP3)-based multi-agent (MA) learning algorithm, which has the computational complexity of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$O(N N_{\max }^{2} T)$</tex-math></inline-formula> . EXP3 is a bandit algorithm designed to find an optimal strategy in a multi-armed bandit (MAB) problem that users do not know the expected payoff of each strategy. Our simulation results show that the proposed algorithm can achieve PNEs. Moreover, it can adapt to time-varying environments, where the number of players varies over time.