Flexible Deployment Research Articles

Recent Advances and Innovations in SAP S/4HANA Cloud and SAP BTP and SAP AI: Integration Strategies and Latest Developments

This article presents a comprehensive analysis of recent advancements and integration strategies in SAP S/4HANA Cloud and SAP Business Technology Platform (BTP), examining their combined impact on enterprise digital transformation. The article explores the architectural evolution of these platforms, focusing on their core components, integration frameworks, and deployment flexibility across on-premises, cloud, and hybrid environments. Through detailed examination of industry-specific implementations in retail, healthcare, and manufacturing sectors, the article demonstrates how organizations leverage these platforms to achieve operational excellence and innovation. The article investigates the technical infrastructure of SAP BTP, including its Platform-as-a-Service capabilities, development environments, and artificial intelligence integration, while evaluating the business intelligence and analytics capabilities that enable real-time decision-making. Special attention is given to the commercial models and economic implications of adopting these technologies, including consumption-based and subscription pricing strategies. The article concludes by identifying emerging trends and future developments, providing valuable insights for organizations planning or executing their digital transformation initiatives. This comprehensive article analysis reveals how the integration of SAP S/4HANA Cloud and BTP creates a robust foundation for enterprise innovation, while highlighting critical considerations for successful implementation and adoption.

Design and implementation of a scalable and high-throughput EEG acquisition and analysis system

Recent advances in neuroscience, neuromorphic intelligence, and brain–computer interface (BCI) technologies have created a need for fast, efficient, and convenient electroencephalogram (EEG) data acquisition systems. However, the existing equipment was limited in its flexibility, restricting non-invasive studies to research or medical settings. To address this issue, low-cost, compact EEG acquisition devices have been developed, allowing for frequent and flexible brain data acquisition in various scenarios. This paper introduces a scalable and high-throughput EEG signal acquisition and analysis system based on field-programmable gate array (FPGA) technology. The proposed system offers electrode scalability, on-chip computing, and optional wireless functionality extension. These features are achieved through the design of a highly scalable underlying EEG acquisition module and an FPGA central module that enables software-defined high-throughput expansion and high-speed data exchange between software and hardware. The paper presents two implementation cases that demonstrate the potential of the proposed system. The first case introduces a wearable wireless EEG system, enabling the deployment of effective and user-friendly steady-state visual evoked potential (SSVEP)-BCI applications in consumer-grade scenarios. The second case integrates an FPGA central module with multiple basic EEG acquisition modules to construct a high-throughput BCI system for cost-effective and real-time EEG data acquisition and processing. This configuration allows for flexible deployment in research and clinical applications, including attention index, SSVEP, motor imagery (MI), and emotion recognition. This combination further demonstrates the potential of scalable EEG systems and emphasizes the need for further integration or chipization. These implementations validate the feasibility of compact and efficient EEG devices and highlight the promising applications of scalable BCI system in various fields.

Fault-tolerant topology construction and down-link rate maximization in air-ground integrated networks

Due to the advantages in flexible deployment, fast communication recovery and high quality of service (QoS), unmanned aerial vehicles (UAVs) have been widely used in wireless communications and networking. However, existing works have not sufficiently solved the problem of reliable and survivable connectivity of UAV networks. In this paper, we investigate the deployment of multiple UAVs, cooperating with a ground mobile station (GMS), to provide wireless coverage for ground users. Under the constraints of satisfying different QoS of users and the resource limitation of UAVs, our aim is to minimize the number of deployed UAVs and maximize the sum down-link rate of all users. In order to ensure the survivability of the deployed UAV networks, we also constraint that each UAV has at least two disjoint paths to GMS to form a fault-tolerant topology. Unfortunately, the formulate problem is intractable and cannot be solved directly. To solve this problem, we decouple the original problem into two subproblems: (1) minimized fault-tolerant topology construction concerning user demands; (2) maximized down-link rate with access policy optimization. Then, we propose a heuristic link-cost minimization method and a potential-game-based user rate maximization method to solve the two subproblems, respectively. The effectiveness of the solution is validated through simulations. Meanwhile, ours also outperforms some baselines in minimized UAVs, down-link transmission rate as well as running time.

Gwydion: Efficient auto-scaling for complex containerized applications in Kubernetes through Reinforcement Learning

Containers have reshaped application deployment and life-cycle management in recent cloud platforms. The paradigm shift from large monolithic applications to complex graphs of loosely-coupled microservices aims to increase deployment flexibility and operational efficiency. However, efficient allocation and scaling of microservice applications is challenging due to their intricate inter-dependencies. Existing works do not consider microservice dependencies, which could lead to the application’s performance degradation when service demand increases. As dependencies increase, communication between microservices becomes more complex and frequent, leading to slower response times and higher resource consumption, especially during high demand. In addition, performance issues in one microservice can also trigger a ripple effect across dependent services, exacerbating the performance degradation across the entire application. This paper studies the impact of microservice inter-dependencies in auto-scaling by proposing Gwydion, a novel framework that enables different auto-scaling goals through Reinforcement Learning (RL) algorithms. Gwydion has been developed based on the OpenAI Gym library and customized for the popular Kubernetes (K8s) platform to bridge the gap between RL and auto-scaling research by training RL algorithms on real cloud environments for two opposing reward strategies: cost-aware and latency-aware. Gwydion focuses on improving resource usage and reducing the application’s response time by considering microservice inter-dependencies when scaling horizontally. Experiments with microservice benchmark applications, such as Redis Cluster (RC) and Online Boutique (OB), show that RL agents can reduce deployment costs and the application’s response time compared to default scaling mechanisms, achieving up to 50% lower latency while avoiding performance degradation. For RC, cost-aware algorithms can reduce the number of deployed pods (2 to 4), resulting in slightly higher latency (300μs to 6 ms) but lower resource consumption. For OB, all RL algorithms exhibit a notable response time improvement by considering all microservices in the observation space, enabling the sequential triggering of actions across different deployments. This leads to nearly 30% cost savings while maintaining consistently lower latency throughout the experiment. Gwydion aims to advance auto-scaling research in a rapidly evolving dynamic cloud environment.

Performance of optically pumped magnetometer magnetoencephalography: validation in large samples and multiple tasks.

Objective
Current commercial magnetoencephalography (MEG) systems detect neuro-magnetic signals using superconducting quantum interferometers devices (SQUIDs), which require liquid helium as cryogen and have many limitations during operation. In contrast, optical pumped magnetometers (OPMs) technology provides a promising alternative to conventional SQUID-MEG. OPMs can operate at room temperature, offering benefits such as flexible deployment and lower costs. However, the validation of OPM-MEG has primarily been conducted on small sample sizes and specific regions of interest in the brain, lacking comprehensive validation for larger sample sizes and assessment of whole-brain. 
Approach
We recruited 100 participants, including healthy and neurological disorders individuals. Whole-brain OPM-MEG and SQUID-MEG data were recorded sequentially during auditory (n = 50) and visual (n = 50) stimulation experiments. By comparing the task-evoked responses of the two systems, we aimed to validate the performance of the next-generation OPM-MEG. 
Main results
The results showed that OPM-MEG enhanced the amplitude of task-related responses and exhibited similar magnetic field patterns and neural oscillatory activity as SQUID-MEG. There was no difference in the task-related latencies measured by the two systems. The signal-to-noise ratio was lower for the OPM-MEG in the auditory experiment, but did not differ in the visual experiment, suggesting that the results may be task-dependent. 
Significance
These results demonstrate that OPM-MEG, as an alternative to traditional SQUID-MEG, shows superior response amplitude and comparable performance in capturing brain dynamics. This study provides evidence for the effectiveness of OPM-MEG as a next-generation neuroimaging technique.

Effects of cognitive flexibility on dynamics of emotion regulation and negative affect in daily life

ABSTRACT Background Cognitive flexibility is a key factor underlying emotion regulation (ER) and mental health. However, the impact of cognitive flexibility on flexible deployment of ER strategies in changing contexts remains unknown. This study investigated the effects of cognitive flexibility on two noteworthy ER constructs (strategy use and flexibility) and examined downstream impacts on negative affect. Methods Healthy adult participants (N = 202) completed a 10-day experience sampling protocol. Cognitive flexibility, daily ER (including flexibility and ten specific strategies) and negative affect in daily life were measured. We conducted multilevel regression and mediation models to examine associations among cognitive flexibility, daily ER, and negative affect in daily life. Results Higher cognitive flexibility predicted higher ER flexibility – indicated by strategy – situation fit, use of meta-ER skills and between-strategy variability – as well as higher use of reappraisal and problem solving, but lower use of worry. Mediation analyses suggested that enhanced ER flexibility and reduced use of worry linked cognitive flexibility to reduced negative affect. Conclusions Overall, findings have important implications for understanding the effects of cognitive flexibility on rigid versus flexible ER in ever-changing situations.

An investigation on energy-saving scheduling algorithm of wireless monitoring sensors in oil and gas pipeline networks

With the rapid development of the oil and gas industry, monitoring the safety and efficiency of pipeline networks has become particularly important. In this context, Wireless Sensor Networks (WSNs) are widely used for monitoring oil and gas pipelines due to their flexible deployment and cost-effectiveness. However, since sensor nodes typically rely on limited battery power, extending the network’s lifecycle and improving energy utilization efficiency have become focal points of research. Therefore, this paper proposes an energy-saving scheduling algorithm based on transformer networks, aimed at optimizing energy consumption and data transmission efficiency of wireless monitoring sensors in oil and gas pipelines. Firstly, this study designs a deep learning-based Transformer model that learns from historical data on energy consumption patterns and environmental variables to predict the energy and data transmission needs of each sensor node. Secondly, based on the prediction results, this algorithm employs a dynamic scheduling strategy that automatically adjusts the sensor’s operational mode and communication frequency according to the node’s energy status and task urgency. Additionally, we have validated the effectiveness of the proposed algorithm through field tests and simulation experiments. According to the experimental results, our model has higher efficiency in energy saving. Compared with Convolutional Neural Networks, Recurrent Neural Networks and Graph Neural Networks, the total energy consumption of sensor networks under the model scheduling in this paper was reduced by 6.7%, 33.4% and 26.3%, respectively. Our algorithms improve the energy efficiency and stability of the monitoring system and provide important technical support for future intelligent pipeline monitoring systems. We hope this paper will inspire future scientific research in this field.

Joint Computation Offloading and Trajectory Optimization for Edge Computing UAV: A KNN-DDPG Algorithm

Unmanned aerial vehicles (UAVs) are widely used to improve the coverage and communication quality of wireless networks and assist mobile edge computing (MEC) due to their flexible deployments. However, the UAV-assisted MEC systems also face challenges in terms of computation offloading and trajectory planning in the dynamic environment. This paper employs deep reinforcement learning to jointly optimize the computation offloading and trajectory planning for UAV-assisted MEC system. Specifically, this paper investigates a general scenario where multiple pieces of user equipment (UE) offload tasks to a UAV equipped with a MEC server to collaborate on a complex job. By fully considering UAV and UE movement, computation offloading ratio, and blocked relations, a joint computation offloading and trajectory optimization problem is formulated to minimize the maximum computational delay. Due to the non-convex nature of the problem, it is converted into a Markov decision process, and solved by the deep deterministic policy gradient (DDPG) algorithm. To enhance the exploration capability and stability of DDPG, the K-nearest neighbor (KNN) algorithm is employed, namely KNN-DDPG. Moreover, the prioritized experience replay algorithm, where the constant learning rate is replaced by the decaying learning rate, is utilized to enhance the converge. To validate the effectiveness and superiority of the proposed algorithm, KNN-DDPG is compared with the benchmark DDPG algorithm. Simulation results demonstrate that KNN-DDPG can converge and achieve 3.23% delay reduction compared to DDPG.

Multi‐objective based container placement strategy in CaaS

AbstractIn contrast to a conventional virtual machine (VM), a container is a lightweight virtualization technology. Containers are becoming a prominent technology for cloud services because of their portable, scalable, and flexible deployments, especially in the Internet of Things (IoT), smart devices, and fog and edge computing. It is a type of operating system‐level virtualization in which the kernel allows multiple isolated containers to run independently. Container placement (CP) is a nontrivial problem in Container‐as‐a‐Service (CaaS). CP is mapping to a container over virtual machines (VMs) to execute an application. Designing an efficient CP strategy is complex due to several intertwined challenges. These challenges arise from a diverse spectrum of computing resources, like on‐demand and unpredictable fluctuations of IT resources by multiple tenants. In this article, we propose a modified sum‐based container placement algorithm called a multi‐objective optimization‐based container placement algorithm (MSBCPA). In the proposed algorithm, we have considered two metrics: makespan and monetary costs for optimizing available IT resources. We have conducted comprehensive simulation experiments to validate the effectiveness of the proposed algorithm over the CloudSim 4.0 simulator. The proposed optimization algorithm (MSBCPA) aims to minimize the makespan and the execution monetary costs simultaneously. In the simulation, we found that the execution cost and energy consumption cost reduce by 20% to 30% and achieve the best possible cost‐makespan trade‐offs compared to competing algorithms.

Comparative analysis of hybrid geothermal-solar systems and solar PV with battery storage: Site suitability, emissions, and economic performance

Renewable energy integration has become a critical focus in the global effort to reduce carbon emissions and diversify energy sources. In regions with distinct geographic features, such as Türkiye, combining different renewable technologies can offer enhanced energy security. This study investigates the site suitability and economic and environmental performance of hybrid geothermal-solar systems and solar PV systems with battery storage across the provinces of Osmaniye, Hatay, and Kilis, of Türkiye. Using the fuzzy-AHP method, site suitability is evaluated, addressing a key gap in comparing these systems' adaptability to varying geographic conditions. This study is the first to directly compare these two renewable energy technologies in terms of site suitability. The findings reveal significant differences in site suitability, with solar PV systems with battery storage demonstrating broader applicability across the region. The suitable sites (20–100 % suitability) cover 1260.82 km² for solar PV systems with battery storage and only 122.18 km² for hybrid geothermal-solar systems. In terms of environmental impact, hybrid geothermal-solar systems exhibit significantly lower carbon emissions, averaging 44.6 kg CO₂/MWh, compared to 123.8 kg CO₂/MWh for solar PV systems with battery storage. Economically, hybrid geothermal-solar systems also outperform with a lower levelized cost of electricity of $0.091 kWh versus $0.254 kWh for solar PV systems. These results highlight the environmental and economic advantages of hybrid geothermal-solar systems, while also emphasizing their limited scalability to regions with geothermal activity. Conversely, solar PV systems, despite their higher emissions and costs, offer greater flexibility and potential for widespread deployment.

Development and verification of an MC/MOC two-step scheme for neutronic analysis of FCM-fueled micro gas-cooled reactor

Gas-cooled microreactors are known for compact designs, high thermal-to-electric efficiencies, long refueling cycles, and flexible deployment capabilities, representing a groundbreaking solution to address the energy requisites of special scenarios. Fully ceramic microencapsulated (FCM) fuel is widely used in gas-cooled microreactors, bringing challenges to neutronic analysis methods. In this paper, an Monte Carlo/Method of Characteristics (MC/MOC) two-step scheme is developed and verified based on the reference case. In this scheme, the continuous-energy Monte Carlo calculations are used for reference calculation and multi-group cross-section generation. The multi-group Monte Carlo calculations are used for multi-group cross-section verification and the MOC solver verification. Fuel multi-group cross-sections are generated with the explicit fuel assembly model by continuous-energy Monte Carlo calculations, and structure multi-group cross-sections are generated with the simplified core model by continuous-energy Monte Carlo calculations. The core calculations are conducted with the MOC calculations. For verification, parameters such as power distribution, neutron spectrum, and control devices worth will be compared. Core calculation results show that the relative errors of MOC results are within −329 pcm, ±5%, ±6%, and ± 2 % for Keff, power distribution, neutron spectrum, and control device worth, separately. Moreover, the computation cost of MOC is only 6.6 % of the reference computation cost. The figure of merit results show that the MC-MOC scheme exhibits improved computational efficiency for neutronic analysis of FCM-fueled micro gas-cooled reactor.

Energy and exergy analysis of a novel solar-powered passive multi-stage osmosis desalination system for sustainable water production

Climate change and population growth constantly exacerbate global water scarcity, and seawater desalination technology is crucial to addressing this crisis. Conventional fossil-fuel desalination poses environmental and economic challenges, especially in remote, water-scarce regions. Renewable energy offers sustainable options for seawater desalination; however, most related technologies face challenges in flexible deployment. Among passive technologies, interfacial evaporation still confronts issues of salt accumulation impacting desalination efficiency. Therefore, this study investigates a novel solar-powered passive multi-stage osmosis device that emulates mangroves’ transpiration and natural osmosis processes. Harnessing solar energy, it employs hydrophilic nanoporous membranes for water movement and evaporation and an osmosis membrane for solute retention, aiming for efficient seawater desalination without external power and pressure. Energy and exergy analyses reveal key efficiency factors. Results reveal significant pressure gradients across the osmosis membrane as a challenge. Optimizing salinity and adjusting the area ratio of the nanoporous membrane to the osmosis membrane is vital for stability and performance. Moreover, potential increases in water production from 0.97 kg/m2/h to 3.53 kg/m2/h with a five-stage setup, though benefits diminish with additional stages due to heat/exergy losses. The exergy efficiency increases from 0.14 % for a five-stage device to 0.18 % for a ten-stage system. This study demonstrates the solar-powered passive multi-stage osmosis device’s dependence on solar flux and highlights the importance of optimizing the air gap thickness and insulation to boost efficiency.

A novel energy-efficiency framework for UAV-assisted networks using adaptive deep reinforcement learning

In the air-to-ground transmissions, the lifespan of the network is based on the “unmanned aerial vehicle's (UAV)” life span because of the limited battery capacity. Thus, the enhancement of energy efficiency and the outage of the ground candidate’s minimization are significant factors of the network functionality. UAV-aided transmission can highly enhance the spectrum efficacy and coverage. Because of their flexible deployment and the high maneuverability, the UAVs can be the best alternative for the situations where the “Internet of Things (IoT)” systems utilize more energy to attain the essential information rate, when they are far away from the terrestrial base station. Therefore, it is significant to win over the few troubles in the conventional UAV-aided efficiency approaches. Thus, this proposed work is aimed to design an innovative energy efficiency framework in the UAV-assisted network using a reinforcement learning mechanism. The energy efficiency optimization in the UAV offers better wireless coverage to the static and mobile ground user. Presently, reinforcement learning techniques effectively optimize the energy efficiency rate of the system by employing the 2D trajectory mechanism, which effectively removes the interference rate attained in the nearby UAV cells. The main objective of the recommended framework is to maximize the energy efficiency rate of the UAV network by performing the joint optimization using UAV 3D trajectory, with the energy utilized during interference accounting, and connected user counts. Hence, an efficient Adaptive Deep Reinforcement Learning with Novel Loss Function (ADRL-NLF) framework is designed to provide a better energy efficiency rate to the UAV network. Moreover, the parameter of ADRL is tuned using the Hybrid Energy Valley and Hermit Crab (HEVHC) algorithm. Various experimental observations are performed to observe the effectualness rate of the recommended energy efficiency model for UAV-based networks over the classical energy efficiency framework in UAV Networks.

Joint optimization for service-caching, computation-offloading, and UAVs flight trajectories over rechargeable UAV-aided MEC using hierarchical multi-agent deep reinforcement learning

Due to the high mobility, high chance of line-of-sight (LoS) transmission, and flexible deployment, unmanned aerial vehicles (UAVs) have been used as mobile edge computing (MEC) servers to provide ubiquitous computation services to mobile users (MUs). However, the limited energy storage, caching capacity, and computation resources of UAVs bring new challenges for UAV-aided MEC, e.g., how to recharge UAVs and how to jointly optimize service-caching, computation-offloading, and UAVs flight trajectories. To overcome the above-mentioned difficulties, in this paper we study the joint optimization for service-caching, computation-offloading, and UAVs flight trajectories for UAV-aided MEC, where multiple rechargeable UAVs cooperatively provide MEC services to a number of MUs. First, we formulate an energy minimization problem to minimize all MUs' energy consumptions by taking into account the mobility of MUs and the energy replenishment of UAVs. Then, using the hierarchical multi-agent deep reinforcement learning (HMDRL), we develop a two-timescale based joint service-caching, computation-offloading, and UAVs flight trajectories scheme, called HMDRL-Based SCOFT. Using HMDRL-Based SCOFT, we derive UAVs' service-caching policies in each time frame, and then derive UAVs flight trajectories and MUs' computation-offloading in each time slot. Finally, we validate and evaluate the performances of our proposed HMDRL-Based SCOFT scheme through extensive simulations, which show that our developed scheme outperforms the other baseline schemes to converge faster and greatly reduce MUs' energy consumptions.

Distributed beamforming design for UAV‐based integrated communication and jamming systems

AbstractThe integrated communication and jamming system is proposed by exploiting the diversity gain and flexible deployment of unmanned aerial vehicle (UAV)‐based distributed multiple input multiple output technology, which is expected to gain higher spectral efficiency and system scalability. This paper designs transmit beamforming of multiple UAVs so that they can simultaneously impose jamming signal to jamming targets and communication signal to communication users at the same frequency. The aim is to maximize the total jamming effect of all jamming targets while achieving a certain communication rate of communication users by optimizing the transmit beamforming matrices. Two cases are considered in which the UAV swarm works in clock synchronization and clock asynchronization. Specifically, the problem is formulated into a non‐convex optimization in the synchronous case. A near optimal solution is derived by decoupling the beamforming matrix into multi‐user interference suppression matrix and single‐user beamforming matrix. In the asynchronous case, the transmitter–receiver matching relation needs to consider and multiple optimization variables are highly coupled, penalty factors and intermediate variables to convert the optimization problem to convex programming are introduced. The simulation results show that the proposed beamforming design algorithm coordinates the communication and jamming signal rationally and outperforms the conventional beamforming design algorithms.

An ellipse-based locating method for flexible deployment of emergency UAVs

Unmanned Aerial Vehicles (UAVs), or drones, are gaining attention in emergency response for their rapid mobility in dynamic scenarios. Constrained by limited endurance and payload, UAVs typically operate in a ”depot-customer-depot” paradigm. Thus, optimally locating multiple depots is critical to achieving operational efficiency and flexibility. Traditional location models, which rely on circular coverage, fail to capture the actual reachable area for UAV round-trips between multiple depots within a given endurance range. This drawback restricts deployment flexibility or results in excessive redundancy, even making it impractical. To address this limitation, we introduce an ellipse-based locating method for flexible UAV deployment, inspired by UAV reachability and process flexibility in manufacturing. This approach attempts to optimize the redundancy of multi-depot coverage for demand points to achieve a better balance between deployment flexibility and resource requirements. To tackle the model’s computational challenge, we present an improved Benders decomposition algorithm that speeds up the solution process by analytically addressing subproblems and implementing dominance rules to manage the master problem’s size. Simulations show that the proposed model greatly improves the ability to handle uncertainties by incorporating slight redundancy in emergency resources, and the fulfillment rate of demand fluctuations is increased by 5%–20%, which shows the superiority of enhancing the mobility and flexibility of UAV deployment.

HCFormer: A Lightweight Pest Detection Model Combining CNN and ViT

Pests are widely distributed in nature, characterized by their small size, which, along with environmental factors such as lighting conditions, makes their identification challenging. A lightweight pest detection network, HCFormer, combining convolutional neural networks (CNNs) and a vision transformer (ViT) is proposed in this study. Data preprocessing is conducted using a bottleneck-structured convolutional network and a Stem module to reduce computational latency. CNNs with various kernel sizes capture local information at different scales, while the ViT network’s attention mechanism and global feature extraction enhance pest feature representation. A down-sampling method reduces the input image size, decreasing computational load and preventing overfitting while enhancing model robustness. Improved attention mechanisms effectively capture feature relationships, balancing detection accuracy and speed. The experimental results show that HCFormer achieves 98.17% accuracy, 91.98% recall, and a mean average precision (mAP) of 90.57%. Compared with SENet, CrossViT, and YOLOv8, HCFormer improves the average accuracy by 7.85%, 2.01%, and 3.55%, respectively, outperforming the overall mainstream detection models. Ablation experiments indicate that the model’s parameter count is 26.5 M, demonstrating advantages in lightweight design and detection accuracy. HCFormer’s efficiency and flexibility in deployment, combined with its high detection accuracy and precise classification, make it a valuable tool for identifying and classifying crop pests in complex environments, providing essential guidance for future pest monitoring and control.

Integration of LoRa-enabled IoT infrastructure for advanced campus safety systems in Taiwan

Amid rising concerns about campus safety in Taiwan, particularly with the global trend towards smart cities, integrating the Internet of Things (IoT) into institutional security frameworks has become pivotal. The paper discusses the implementation of using iBeacons and Long Range (LoRa) technology to locating the student position and ensure his safety in the school campus. It uses Internet of Things (IoT) approach in real time to monitor and locate the student presence in the school compound. This paper unveils an innovative design for a campus security system that harnesses the LoRa technology. In the system, the students are equipped with devices containing Bluetooth Low Energy (BLE) beacons to capture and transmit real-time location data. The system response time to locating student in abnormal locations such as cornered and concealed areas is about one second. By extending this system to cover all individuals on campus, a closely monitored environment and areas is enabled that significantly bolstering the security measures. This not only furnishes a dynamic protective layer for educational institutions but also serves as a proactive deterrent against potential security breaches. Ultimately, this research underscores the transformative potential of merging IoT with campus security to ushering in a new era of student safety. LoRa technology offers advantages in battery life, cost-effectiveness, deployment flexibility, and network coverage etc. Therefore, this paper ultimately provides a method of how to utilize the LoRa technology to develop a campus security system. Unlike artificial intelligence (AI)-based image recognition, which raises concerns about privacy and human rights; the features of LoRa’s long-range communication and low power consumption make it a more suitable choice.

Softwarized and containerized microservices-based network management analysis with MSN

Microservice architecture is a service-oriented paradigm that enables the decomposition of cumbersome monolithic-based software systems. Using microservice design principles, it is possible to develop flexible, scalable, reusable, and loosely coupled software that could be containerized and deployed in a distributed edge/cloud environment. The flexible deployment of microservices in an edge environment increases system performance in terms due to dynamic service function placement and chaining possibly resulting in latency reduction, fault tolerance, scalability, efficient resource utilization, cost reduction, and energy consumption reduction. On the other hand, virtualization and containerization of microservices add processing and communication overheads. Therefore, to evaluate end-to-end microservices-based system performance, we need to have an end-to-end mathematical formulation of the overall microservice-based network system. Incorporating the virtualization overhead, here we provide end-to-end mathematical formulation considering system parameters: latency, throughput, computational resource usage, and energy consumption. We then evaluate the formulation in a testbed environment with the Microservice-based SDN (MSN) framework that decomposes the Software-defined Networking (SDN) controller in microservices with Docker Container. The final result validates the presented mathematical modeling of the system’s dynamic behavior which can be used to design a microservice-based system.

A generalist vision-language foundation model for diverse biomedical tasks.

Traditional biomedical artificial intelligence (AI) models, designed for specific tasks or modalities, often exhibit limited flexibility in real-world deployment and struggle to utilize holistic information. Generalist AI holds the potential to address these limitations due to its versatility in interpreting different data types and generating tailored outputs for diverse needs. However, existing biomedical generalist AI solutions are typically heavyweight and closed source to researchers, practitioners and patients. Here, we describe BiomedGPT, the first open-source and lightweight vision-language foundation model, designed as a generalist capable of performing various biomedical tasks. BiomedGPT achieved state-of-the-art results in 16 out of 25 experiments while maintaining a computing-friendly model scale. We also conducted human evaluations to assess the capabilities of BiomedGPT in radiology visual question answering, report generation and summarization. BiomedGPT exhibits robust prediction ability with a low error rate of 3.8% in question answering, satisfactory performance with an error rate of 8.3% in writing complex radiology reports, and competitive summarization ability with a nearly equivalent preference score to human experts. Our method demonstrates that effective training with diverse data can lead to more practical biomedical AI for improving diagnosis and workflow efficiency.