Explore the vast range of titles available.

Federated learning (FL) is a distributed model for deep learning that integrates client-server architecture, edge computing, and real-time intelligence. FL has the capability of revolutionizing machine learning (ML) but lacks in the practicality of implementation due to technological limitations, communication overhead, non-IID (independent and identically distributed) data, and privacy concerns. Training a ML model over heterogeneous non-IID data highly degrades the convergence rate and performance. The existing traditional and clustered FL algorithms exhibit two main limitations, including inefficient client training and static hyperparameter utilization. To overcome these limitations, we propose a novel hybrid algorithm, namely, genetic clustered FL (Genetic CFL), that clusters edge devices based on the training hyperparameters and genetically modifies the parameters clusterwise. Then, we introduce an algorithm that drastically increases the individual cluster accuracy by integrating the density-based clustering and genetic hyperparameter optimization. The results are bench-marked using MNIST handwritten digit dataset and the CIFAR-10 dataset. The proposed genetic CFL shows significant improvements and works well with realistic cases of non-IID and ambiguous data. An accuracy of 99.79% is observed in the MNIST dataset and 76.88% in CIFAR-10 dataset with only 10 training rounds.

In this review, we intend to present a complete literature survey on the conception and variants of the recent successful optimization algorithm, Harris Hawk optimizer (HHO), along with an updated set of applications in well-established works. For this purpose, we first present an overview of HHO, including its logic of equations and mathematical model. Next, we focus on reviewing different variants of HHO from the available well-established literature. To provide readers a deep vision and foster the application of the HHO, we review the state-of-the-art improvements of HHO, focusing mainly on fuzzy HHO and a new intuitionistic fuzzy HHO algorithm. We also review the applications of HHO in enhancing machine learning operations and in tackling engineering optimization problems. This survey can cover different aspects of HHO and its future applications to provide a basis for future research in the development of swarm intelligence paths and the use of HHO for real-world problems.

In recent years, multi-access edge computing (MEC) has become a promising technology used in 5G networks based on its ability to offload computational tasks from mobile devices (MDs) to edge servers in order to address MD-specific limitations. Despite considerable research on computation offloading in 5G networks, this activity in multi-tier multi-MEC server systems continues to attract attention. Here, we investigated a two-tier computation-offloading strategy for multi-user multi-MEC servers in heterogeneous networks. For this scenario, we formulated a joint resource-allocation and computation-offloading decision strategy to minimize the total computing overhead of MDs, including completion time and energy consumption. The optimization problem was formulated as a mixed-integer nonlinear program problem of NP-hard complexity. Under complex optimization and various application constraints, we divided the original problem into two subproblems: decisions of resource allocation and computation offloading. We developed an efficient, low-complexity algorithm using particle swarm optimization capable of high-quality solutions and guaranteed convergence, with a high-level heuristic (i.e., meta-heuristic) that performed well at solving a challenging optimization problem. Simulation results indicated that the proposed algorithm significantly reduced the total computing overhead of MDs relative to several baseline methods while guaranteeing to converge to stable solutions.

Covert communication is critical to guarantee a strong security and secure user privacy. In this work, we consider adversary’s noise and channel uncertainties and analyze their impact on adversary’s optimum detection performance and the throughput of covert messages. We determine the throughput of covert messages and its gain and loss by having adversary’s channel uncertainty and fading channel, respectively. The results show that fading is essential to hide information, particularly for low noise uncertainty or at high SNR. The improvement of adversary’s optimum detection performance, hence the covert throughput, under channel uncertainty is more significant for larger noise uncertainty. The covert throughput is gained by having channel uncertainty roughly 12–19% when the noise uncertainty is about 1–2 dB.

This paper contributes to the understanding of the recent urban development of Ho Chi Minh City, Vietnam. Previous studies have aimed at quantifying the city’s spatial growth yet have disregarded its inherent morphological and socio-economic heterogeneity. To overcome this knowledge gap, we employ an urban structure type approach for the spatially explicit quantification of urbanisation patterns for the period 2010–⁠2020, categorising 77,000 blocks across the entire administrative area of 2095 km2. The approach allows us to understand the basic underlying processes of urbanisation, both quantitatively and qualitatively, and the main growth corridors along the rural–urban gradient. By contextualizing and combining our findings within current literature and official planning reports, we discern between traditional urban growth and the contemporary new town development patterns, highlighting their driving forces and policy implications. Incremental plot-by-plot development along the northwest development corridor is observed as the principal mode of urban development, whilst bypass urbanisation is seen along both the eastern and southern development corridors. Our block-based results highlight the city’s key growth challenges and provide insights on a scale that is meaningful for official spatial and infrastructure planning, and periodic analysis and monitoring. As far as the authors are aware, this is the first time that an urban structure type approach was applied to understand the rapid urban growth dynamics of an emerging megacity in Southeast Asia.

Residue concentrations of heavy metals, including As, Cd, Cr, Cu, Ni, Pb, and Zn, were determined in bottom ash, fly ash, and particulate matter (PM10) samples collected from five municipal incinerators in northern Vietnam to assess their occurrence, distribution characteristics, and potential risks. Concentrations and profiles of heavy metals are presented, showing the dominance of Zn in all types of samples. Highly volatile elements (Cd, Pb, and Zn) were found at elevated proportions in PM10 but not fly ash. The large difference in the heavy metal profiles could be explained by the variation of input raw materials, the absence of an appropriate cycle for the material feeding process, and post-combustion technology applied. Mass balance of heavy metals in the bottom ash, fly ash, and PM10 varied significantly between the investigated incinerators, largely due to the difference in incineration technology and air pollution control system. Emission factors and annual emissions were also estimated, indicating the highest value and amount in bottom ash, followed by PM10 and fly ash. Our results are among the first studies reporting contents and emissions of toxic elements in incinerated solid wastes in Vietnam.

One of the most promising approaches to address the mismatch between computation- intensive applications and computation-limited end devices is multi-access edge computing (MEC). To overcome the rapid increase in traffic volume and offload the traffic from macrocells, a massive number of small cells have been deployed, so-called heterogeneous networks (HetNets). Strongly motivated by the close integration of MEC and HetNets, in this paper, we propose an envisioned architecture of MEC-empowered HetNets, where both wireless and wired backhaul solutions are supported, flying base stations (BSs) can be equipped with MEC servers, and mobile users (MUs) need both communication and computation resources for their computationally heavy tasks. Subsequently, we provide the research progress summary of task offloading and resource allocation in the proposed MEC-empowered unmanned aerial vehicle (UAV)-assisted heterogeneous networks. We complete this article by spotlighting key challenges and open future directives for researches.

Breast cancer (BC) is one of the leading cancers in women. Recent progress has enabled BC to be cured with high efficiency. However, late detection or metastatic disease often renders the disease untreatable. Additionally, relapse is the main cause of death in BC patients. Breast cancer stem cells (BCSCs) are considered to cause the development of BC and are thought to be responsible for metastasis and relapse. This study aimed to target BCSCs using dendritic cells (DCs) to treat tumor-bearing humanized mice models. NOD/SCID mice were used to produce the humanized mice by transplantation of human hematopoietic stem cells. Human BCSCs were injected into the mammary fat pad to produce BC humanized mice. Both hematopoietic stem cells and DCs were isolated from the human umbilical cord blood, and immature DCs were produced from cultured mononuclear cells. DCs were matured by BCSC-derived antigen incubation for 48 hours. Mature DCs were vaccinated to BC humanized mice with a dose of 10(6) cells/mice, and the survival percentage was monitored in both treated and untreated groups. The results showed that DC vaccination could target BCSCs and reduce the tumor size and prolong survival. These results suggested that targeting BCSCs with DCs is a promising therapy for BC.

Forecasting discharge (Q) and water level (H) are essential factors in hydrological research and flood prediction. In recent years, deep learning has emerged as a viable technique for capturing the non-linear relationship of historical data to generate highly accurate prediction results. Despite the success in various domains, applying deep learning in Q and H prediction is hampered by three critical issues: a shortage of training data, the occurrence of noise in the collected data, and the difficulty in adjusting the model’s hyper-parameters. This work proposes a novel deep learning-based Q–H prediction model that overcomes all the shortcomings encountered by existing approaches. Specifically, to address data scarcity and increase prediction accuracy, we design an ensemble learning architecture that takes advantage of multiple deep learning techniques. Furthermore, we leverage the Singular-Spectrum Analysis (SSA) to remove noise and outliers from the original data. Besides, we exploit the Genetic Algorithm (GA) to propose a novel mechanism that can automatically determine the prediction model’s optimal hyper-parameters. We conducted extensive experiments on two datasets collected from Vietnam’s Red and Dakbla rivers. The results show that our proposed solution outperforms current techniques across a wide range of metrics, including NSE, MSE, MAE, and MAPE. Specifically, by exploiting the ensemble learning technique, we can improve the NSE by at least 2 % . Moreover, with the aid of the SSA-based data preprocessing technique, the NSE is further enhanced by more than 5 % . Finally, thanks to GA-based optimization, our proposed model increases the NSE by at least 6 % and up to 40 % in the best case.

Massive machine-type communication (mMTC) in 5G New Radio (5G-NR) or the Internet of Things (IoT) is a network of physical devices such as vehicles, smart meters, sensors, and smart appliances, which can communicate and interact in real time without human intervention. In IoT systems, the number of networked devices is expected to be in the tens of billions, while radio resources remain scarce. To connect the massive number of devices with limited bandwidth, it is crucial to develop new access solutions that can improve resource efficiency and reduce control overhead as well as access delay. The key idea is controlling the number of arrival devices that want to access the system, and then allowing only the strongest device (that has the largest channel gain and each device is able to check whether it is the strongest device) be able to transit to BS. In this paper, we consider a random access problem in massive MIMO context for the collision resolution, in which the access class barring (ACB) factor is dynamically adjusted in each time slot to maximize access success rate for the strongest-user collision resolution (SUCRe) protocol. We propose the dynamic ACB scheme to find optimal ACB factor in the next time slot and then apply SUCRe protocol to achieve a good performance. This method is called dynamic access class barring combined strongest-user collision resolution (DACB-SUCR). In addition, we investigate two different ACB schemes that consist of the fixed ACB and the traffic-aware ACB to compare with the proposed dynamic ACB. Analysis and simulation results demonstrate that, compared with SUCRe protocol, the proposed DACB-SUCR method can remarkably reduce pilot collision, and increase access success rate. It is also shown that the dynamic ACB gives better performance than the fixed ACB and the traffic-aware ACB.