Abstract The reverse osmosis (RO) process is a well-established desalination technology, wherein energy-efficient techniques and advanced process control methods significantly reduce production costs. This study proposes an optimal real-time management method to minimize the total daily operation cost of an RO desalination plant, integrating a storage tank system to meet varying daily freshwater demand. Utilizing the dynamic model of the RO process, a cascade structure with two reinforcement learning (RL) agents, namely the deep deterministic policy gradient (DDPG) and deep Q-Network (DQN), is developed to optimize the operation of the RO plant. The DDPG agent, manipulating the high-pressure pump, controls the permeate flow rate to track a reference setpoint value. Simultaneously, the DQN agent selects the optimal setpoint value and communicates it to the DDPG controller to minimize the plant’s operation cost. Monitoring storage tanks, permeate flow rates, and water demand enables the DQN agent to determine the required amount of permeate water, optimizing water quality and energy consumption. Additionally, the DQN agent monitors the storage tank’s water level to prevent overflow or underflow of permeate water. Simulation results demonstrate the effectiveness and practicality of the designed RL agents.

Abstract With the COVID-19 outbreak, schools and universities have massively adopted online learning to ensure the continuation of the learning process. However, in such setting, instructors lack efficient mechanisms to evaluate the learning gains and get insights about difficulties learners encounter. In this research work, we tackle the problem of predicting learner performance in online learning using a deep learning-based approach. Our proposed solution allows stakeholders involved in the online learning to anticipate the learner outcome ahead of the final assessment hence offering the opportunity for proactive measures to assist the learners. We propose a two-pathway deep learning model to classify learner performance using their interaction during the online sessions in the form of clickstreams. We also propose to transform these time series of clicks into images using the Gramian Angular Field. The learning model makes use of the available extra demographic and assessment information. We evaluate our approach on the Open University Learning Analytics Dataset. Comprehensive comparative study is conducted with evaluation against state-of-art approaches under different experimental settings. We also demonstrate the importance of including extra demographic and assessment data in the prediction process.

Remote monitoring systems analyze the environment dynamics in different smart industrial applications, such as occupational health and safety, and environmental monitoring. Specifically, in Industrial Internet of Things (IIoT) systems, the huge number of devices and the expected performance put pressure on resources, such as computational, network, and device energy. Distributed training of machine and deep learning (ML/DL) models for intelligent industrial IoT applications is very challenging for resource limited devices over heterogeneous wireless networks (HetNets). Hierarchical federated learning (HFL) performs training at multiple layers offloading the tasks to nearby multiaccess edge computing (MEC) units. In this article, we propose a novel energy-efficient HFL framework enabled by wireless energy transfer (WET) and designed for heterogeneous networks with massive multiple-input–multiple-output (MIMO) wireless backhaul. Our energy-efficiency approach is formulated as a mixed-integer nonlinear programming (MINLP) problem, where we optimize the HFL device association and manage the wireless transmitted energy. However due to its high complexity, we design a heuristic resource management algorithm, namely, H2RMA, that respects energy, channel quality, and accuracy constraints, while presenting a low-computational complexity. We also improve the energy consumption of the network using an efficient device scheduling scheme. Finally, we investigate device mobility and its impact on the HFL performance. Our extensive experiments confirm the high performance of the proposed resource management approach in HFL over HetNets, in terms of training loss and grid energy costs.

In this article, the deployment of federated learning (FL) is investigated in an energy harvesting wireless network in which the base stations (BSs) employs massive multiple-input–multiple-output (MIMO) to serve a set of users powered by independent energy harvesting sources. Since a certain number of users may not be able to participate in FL due to interference and energy constraints, a joint energy management and user scheduling problem in FL over wireless systems is formulated. This problem is formulated as an optimization problem whose goal is to minimize the FL training loss via optimizing user scheduling. To find how the transmit power, the number of scheduled users and user association, affect the training loss, the FL convergence rate is first analyzed. Given this analytical result, the original optimization problem can be decomposed, simplified, and solved. Simulation results show that the proposed user scheduling and user association algorithm can reduce training loss compared to a standard FL algorithm.

Effective management of urban traffic is important for any smart city initiative. Therefore, the quality of the sensory traffic data is of paramount importance. However, like any sensory data, urban traffic data are prone to imperfections leading to missing measurements. In this paper, we focus on inter-region traffic data completion. We model the inter-region traffic as a spatiotemporal tensor that suffers from missing measurements. To recover the missing data, we propose an enhanced CANDECOMP/PARAFAC (CP) completion approach that considers the urban and temporal aspects of the traffic. To derive the urban characteristics, we divide the area of study into regions. Then, for each region, we compute urban feature vectors inspired from biodiversity which are used to compute the urban similarity matrix. To mine the temporal aspect, we first conduct an entropy analysis to determine the most regular time-series. Then, we conduct a joint Fourier and correlation analysis to compute its periodicity and construct the temporal matrix. Both urban and temporal matrices are fed into a modified CP-completion objective function. To solve this objective, we propose an alternating least square approach that operates on the vectorized version of the inputs. We conduct comprehensive comparative study with two evaluation scenarios. In the first one, we simulate random missing values. In the second scenario, we simulate missing values at a given area and time duration. Our results demonstrate that our approach provides effective recovering performance reaching 26% improvement compared to state-of-art CP approaches and 35% compared to state-of-art generative model-based approaches.

In this paper, the deployment of federated learning (FL) is investigated in an energy harvesting wireless network in which the base station (BS) is equipped with a massive multiple-input multiple-output (MIMO) system and a set of users powered by independent energy harvesting sources to cooperatively perform FL. Since a certain number of users may not be served due to interference and energy constraints, a joint energy management and user scheduling problem is considered. This problem is formulated as an optimization problem whose goal is to minimize the FL training loss via optimizing user scheduling. To determine the effect of various wireless factors (transmit power and number of scheduled users) on training loss, the convergence rate of the FL algorithm is analyzed. Given this analytical result, the original user scheduling and energy management optimization problem can be decomposed, simplified and solved. Simulation results show that the proposed algorithm can reduce training loss compared to a standard FL algorithm.

Training centralized machine learning (ML) models becomes infeasible in wireless networks due to the increasing number of internet of things (IoT) and mobile devices and the prevalence of the learning algorithms to adapt tasks in dynamic situations with heterogeneous networks (HetNets) and battery limited devices. Hierarchical federated learning (HFL) has been proposed as a promising learning that can preserve the data privacy of the wireless devices, tackle the communication bottlenecks in wireless networks, and improve the energy effi-ciency. We propose a novel energy-efficient HFL framework for HetNets with massive multiple-input multiple-output (MIMO) wireless backhaul enabled by wireless energy transfer (WET). We formulate a joint energy management and device association optimization problem in HFL over HetNets subject to maximal divergence constraints. Next, an optimal solution is developed, but with high complexity. To reduce the complexity, a heuristic algorithm for HFL over HetNets with energy, channel quality, and accuracy constraints, is developed in order to minimize the grid energy consumption cost and preserve the value of loss function, which captures the HFL performance. Simulation results show the efficiency of the proposed resource management approach in the HFL context in terms of grid power consumption cost and training loss.

The widespread of smart devices equipped with high sensing capabilities opened the door to the new paradigm of mobile crowdsourcing. This paradigm relies on the crowd contribution and participation to collect data and relevant information. The abstraction of mobile crowdsourcing as a service has become easier and more seamless thanks to the availability, low-cost and fast access to cloud services. In this context, it is important to satisfy a request for a crowdsourced service, at a given time and place, as soon as possible. Nevertheless, maintaining a balance between the supply and demand of crowdsourced services in a geographic area is challenging given the mobility of both service requesters and providers. Motivated by this requirement, we propose a forecasting approach to infer the supply demand gap of crowdsourced services in a given geographic area. Instead of relying on raw data for prediction, we devise a technique to generate predictors from the raw gap data using topological data analysis to exploit the topological and underlying geometric structures. Our forecasting strategy is conducted in a multiview fashion, that is, we devise the historical time horizon into immediate, near and distant time. Then, using topological analysis, we derive three key features: topological similarity, Betti numbers and the Distance To Measure value (DTM). These features, along with additional context information including weather and temperature, are used to infer the supply-demand gap value using state-of-art prediction approach. Our experiments show that the proposed multiview topological analysis is effective for supply-demand prediction with both clean and noisy data.

Mobile crowdsourcing has become easier thanks to the widespread of smartphones capable of seamlessly collecting and pushing the desired data to cloud services. However, the success of mobile crowdsourcing relies on balancing the supply and demand by first accurately forecasting spatially and temporally the supply-demand gap, and then providing efficient incentives to encourage participant movements to maintain the desired balance. In this paper, we propose Deep-Gap, a deep learning approach based on residual learning to predict the gap between mobile crowdsourced service supply and demand at a given time and space. The prediction can drive the incentive model to achieve a geographically balanced service coverage in order to avoid the case where some areas are over-supplied while other areas are under-supplied. This allows anticipating the supply-demand gap and redirecting crowdsourced service providers towards target areas. Deep-Gap relies on historical supply-demand time series data as well as available external data such as weather conditions and day type (e.g., weekday, weekend, holiday). First, we roll and encode the time series of supplydemand as images using the Gramian Angular Summation Field (GASF), Gramian Angular Difference Field (GADF) and the Recurrence Plot (REC). These images are then used to train deep Convolutional Neural Networks (CNN) to extract the low and high-level features and forecast the crowdsourced services gap. We conduct comprehensive comparative study by establishing two supply-demand gap forecasting scenarios: with and without external data. Compared to state-of-art approaches, Deep-Gap achieves the lowest forecasting errors in both scenarios.

In the context of mobile Health (mHealth) applications, data are prone to several sources of contamination which would lead to false interpretation and misleading classification results. In this paper, a robust deep learning approach with low rank model is proposed to classify mHealth vital signs. Further-more, we propose using the Schatten-p norm instead of the classic nuclear norm since it has shown better recovery performance for several applications. We conduct a comprehensive study where we compare our method to the state-of-art methods and evaluate its performance with respect to the key system parameters. Our findings show indeed that combining deep network with dictionary learning model is effective for vital signs classification even in presence of 50% corruption with 8% improvement over the closest performance.

The emergence of mobile health (mHealth) systems has risen the challenges and concerns due to the sensitivity of the data involved in such systems. It is essential to ensure that these data are well delivered to the health monitoring center for accurate and perfect diagnosis and follow-up. Due to the wireless network constraints, these requirements become more challenging. In this paper, we propose a deep learning approach for EEG data compression in mHealth system. We show that the stacked autoencoder neural network architecture is efficient for EEG data compression. We conduct a comprehensive comparative study that demonstrates the effectiveness of our system for EEG compression in addition to preserving the total energy consumption.

In this paper, we present a joint compression and classification approach of EEG and EMG signals using a deep learning approach. Specifically, we build our system based on the deep autoencoder architecture which is designed not only to extract discriminant features in the multimodal data representation but also to reconstruct the data from the latent representation using encoder-decoder layers. Since autoencoder can be seen as a compression approach, we extend it to handle multimodal data at the encoder layer, reconstructed and retrieved at the decoder layer. We show through experimental results, that exploiting both multimodal data intercorellation and intracorellation 1) Significantly reduces signal distortion particularly for high compression levels 2) Achieves better accuracy in classifying EEG and EMG signals recorded and labeled according to the sentiments of the volunteer.

In this paper, we propose a new cluster validity index (CVI) based on geometrical shape. Classic CVIs are based on a combination of separation and compactness measures and may include a measure of overlap between clusters. The proposed CVI combines measures of compactness and over-lap using n-sphere shape. We conducted experiments on several real data sets from the UCI repository and compared the performances of the proposed CVI with widely used CVIs. Results demonstrate that the proposed CVI performs better than the others even when used with complicated data sets.