Multiple Subsystems Research Articles

Privacy-preserving federated machine learning modeling and predictive control of heterogeneous nonlinear systems

Privacy preservation in data-driven modeling of a heterogeneous nonlinear system with multiple subsystems has become vitally important since communication data is vulnerable to cyber-attacks. This work develops a federated learning (FL) modeling and model predictive control (MPC) method for heterogeneous nonlinear systems with multiple subsystems to address privacy preservation and heterogeneity issues. The FL framework with two different neural network structures is developed to aggregate the submodels trained locally for the subsystems into a global model without sharing the local data with each other. Subsequently, a theoretical bound on the generalization error of the FL models is established using information theory. The closed-loop stability criteria of heterogeneous nonlinear systems under the FL-based MPC scheme are developed in an information-theoretical manner. Finally, a chemical process network is applied to demonstrate the effectiveness of the proposed FL modeling and FL-based MPC methods.

Agent-Based System for Continuous Control and its Application to Activated Sludge Process

This paper presents a concept of architecture and ontology layouts for development of multiagent model-based predictive control systems. The presented architecture provides guidelines to simplify development of agent-based systems and improve its maintainability. The proposed multiagent system (MAS) layout is split into multiple subsystems that include agents dedicated to performing assigned tasks. MAS implementation was prepared which can use provided algorithms, actuators and can react to changes in its environment to reach the best available control quality. An example of MAS based on the proposed architecture is shown in application of dissolved oxygen (DO) concentration control in a laboratory activated sludge setup with biological reactor. For that application, MAS incorporates agent-based controllers from Boundary-Based Predictive Controllers (BBPC) family. Presented experiments prove flexibility, resilience and online reconfiguration ability of the proposed multiagent system.

Applying Dynamical Systems Theory to Improve Personalized Medicine Following Mild Traumatic Brain Injury.

A sizable proportion of patients with mild traumatic brain injury (mTBI) have persistent symptoms and functional impairments months to years following injury. This phenomenon is continually observed despite an explosion of research and interest in improving mTBI clinical outcomes over the last two decades. All pharmacological clinical trials to date have failed to demonstrate improved outcomes for mTBI. One possible explanation for these continued failures is an overly myopic approach to treating mTBI (i.e., testing the effect of a single drug with a specific mechanism on a group of people with highly heterogenous injuries). Clinical presentation and prognosis of mTBI vary considerably between patients, and yet we continue to assess group-level effects of a homogenized treatment. We need to utilize an equally complex treatment approach to match the extraordinary complexity of the human brain. Dynamical systems theory has been used to describe systems composed of multiple subsystems who function somewhat independently but are ultimately interconnected. This theory was popularized in the motor control literature as an overarching framework for how the mind and body connect to interact and move through the environment. However, the human body can be viewed as a dynamical system composed of multiple subsystems (i.e., organ systems) who have isolated functions, which are also codependent on the health and performance of other interconnected organ systems. In this perspective piece, we will use the example of mTBI in the obese patient to demonstrate how broadening our approach to treatment of the individual (and not necessarily the injury) may ultimately yield improved outcomes. Furthermore, we will explore clinical and pre-clinical evidence demonstrating multiple system interactions in the context of obesity and TBI and discuss how expanding our understanding of the mechanistic interplay between multiple organ systems may ultimately provide a more personalized treatment approach for this mTBI patient subpopulation.

Real-Time Multi-Sensor Joint Fault Diagnosis Method for Permanent Magnet Traction Drive Systems Based on Structural Analysis.

Sensor faults are one of the most common faults that cause performance degradation or functional loss in permanent magnet traction drive systems (PMTDSs). To quickly diagnose faulty sensors, this paper proposes a real-time joint diagnosis method for multi-sensor faults based on structural analysis. Firstly, based on limited monitoring signals on board, a structured model of the system was established using the structural analysis method. The isolation and detectability of faulty sensors were analyzed using the Dulmage-Mendelsohn decomposition method. Secondly, the minimum collision set method was used to calculate the minimum overdetermined equation set, transforming the higher-order system model into multiple related subsystem models, thereby reducing modeling complexity and facilitating system implementation. Next, residual vectors were constructed based on multiple subsystem models, and fault detection and isolation strategies were designed using the correlation between each subsystem model and the relevant sensors. The validation results of the physical testing platform based on online fault data recordings showed that the proposed method could achieve rapid fault detection and the localization of multi-sensor faults in PMTDS and had a good application value.

A novel trusted hardware-based scalable security framework for IoT edge devices

The Internet of Things (IoT) devices are pervasively deployed and embedded into our daily lives. Over several years, the massive assimilation of IoT devices has given rise to smart cities, smart factories, smart farms, etc. While IoTs can collect immense amounts of user and environmental information, the lack of adequate security measures is among the major concerns about information security and privacy. With the ever-increasing presence of IoTs, information flow between IoT devices in a single or multi-layered network is becoming increasingly vulnerable to attacks. Although several software-based solutions have been developed over the years that improve the security of resource-constrained IoT devices, there are limited efforts on hardware-oriented IoT security solutions. This paper proposes a Trusted HArdware-based Scalable Secure Architecture (THASSA) for IoT Edge systems. Leveraging standard cryptographic algorithms, THASSA provides a secure mechanism for data transfer and off-loads cryptography operations to trusted hardware. The modularized THASSA architecture allows devices to be added or removed without user intervention. Also, THASSA could be scaled to multiple subsystems using multiple trusted hardware to form IoT clusters with secure data path(s) for mission-critical applications. An experimental study has verified the correctness and effectiveness of THASSA.

Nonlinear dynamics of postural control system under visual-vestibular habituation balance practice: evidence from EEG, EMG and center of pressure signals.

Human postural control system is inherently complex with nonlinear interaction among multiple subsystems. Accordingly, such postural control system has the flexibility in adaptation to complex environments. Previous studies applied complexity-based methods to analyze center of pressure (COP) to explore nonlinear dynamics of postural sway under changing environments, but direct evidence from central nervous system or muscular system is limited in the existing literature. Therefore, we assessed the fractal dimension of COP, surface electromyographic (sEMG) and electroencephalogram (EEG) signals under visual-vestibular habituation balance practice. We combined a rotating platform and a virtual reality headset to present visual-vestibular congruent or incongruent conditions. We asked participants to undergo repeated exposure to either congruent (n = 14) or incongruent condition (n = 13) five times while maintaining balance. We found repeated practice under both congruent and incongruent conditions increased the complexity of high-frequency (0.5-20 Hz) component of COP data and the complexity of sEMG data from tibialis anterior muscle. In contrast, repeated practice under conflicts decreased the complexity of low-frequency (<0.5 Hz) component of COP data and the complexity of EEG data of parietal and occipital lobes, while repeated practice under congruent environment decreased the complexity of EEG data of parietal and temporal lobes. These results suggested nonlinear dynamics of cortical activity differed after balance practice under congruent and incongruent environments. Also, we found a positive correlation (1) between the complexity of high-frequency component of COP and the complexity of sEMG signals from calf muscles, and (2) between the complexity of low-frequency component of COP and the complexity of EEG signals. These results suggested the low- or high-component of COP might be related to central or muscular adjustment of postural control, respectively.

A Novel Algorithm for Cyber Security Analysis for Supply Chain Security

The Cyber Supply Chain (CSC) system is a multifaceted system with multiple subsystems carrying out distinct functions. The inherent vulnerabilities and threats from any portion of the system that can be exploited at any point in the supply chain make supply chain security difficult. This can cause a severe disruption on the overall business continuity. Thus, it is critical for organizations to comprehend and assess the risks in order to implement the appropriate supply chain security management measures. In order to analyse and forecast the risks based on the features of Cyber Threat Intelligence (CTI), we have combined CTI with Machine Learning (ML) approaches. To demonstrate the applicability of our approach, CTI data is gathered and a number of ML algorithms, i.e., Logistic Regression (LG), Support Vector Machine (SVM), Random Forest (RF) and Decision Tree (DT), are used to develop predictive analytics using the Microsoft Malware Prediction dataset. KEYWORDS: Cyber Supply Chain, Malware, Cyber Threat Intelligence, Machine Learning.

Improving Fault Diagnosis of the Drilling Permanent Magnet Synchronous Motor (DPMSM) in Harsh Environments: A Novel Approach Using Object-Oriented Bayesian Network (OOBN)

The drilling permanent magnet synchronous motor (DPMSM) contains multiple subsystems with identical structures and has a high probability of failure because the downhole working conditions are harsh. Therefore, the quick localization of faults is difficult to determine although the fault type may be identified in time. The system diagnostic model based on the Bayesian network (BN) can be used for fault diagnosis and localization for components in subsystems, but it is difficult to build and modify due to the complex system in practice. New methods are necessary to reduce the difficulty of building and modifying models. In this study, object-oriented ideas are introduced into the BN to establish a system diagnostic model based on an Object-oriented Bayesian network (OOBN) for the DPMSM. First, the fault diagnostic models for subsystems based on BN are established, respectively. Then, submodels of forward and backward based on BN are instantiated as instance nodes. Next, instance nodes are connected through input nodes and output nodes to establish the OOBN-based system diagnosis model. Finally, the system diagnosis model is validated by sensitivity analysis and the effectiveness is discussed in Cases. The system diagnosis model can effectively reduce the difficulties of modeling and modifying.

Unlocking near-whole-brain, layer-specific functional connectivity with 3D VAPER fMRI

Abstract Neuroscientific investigations at the cortical layer level not only enrich our knowledge of cortical micro-circuitry in vivo, but also help bridge the gap between macroscopic (e.g., conventional fMRI, behavior) and microscopic (e.g., extracellular recordings) measures of brain function. While laminar fMRI studies have extensively explored the evoked cortical response in multiple subsystems, the investigation of the laminar component of functional networks throughout the entire brain has been hindered due to constraints in high-resolution layer-fMRI imaging methodologies. Our study addresses this gap by introducing an innovative layer-specific 3D VAPER (integrated VASO and Perfusion contrast) technique in humans at 7 T, for achieving fMRI at high resolution (800 µm isotropic), high specificity (not biased toward unspecific vein signals as BOLD), high sensitivity (robust measurement at submillimeter resolution), high spatial accuracy (analysis in native fMRI space), near-whole-brain coverage (cerebellum not included), and eventually extending layer fMRI to more flexible connectivity-based experiment designs. To demonstrate its effectiveness, we collected 0.8-mm isotropic fMRI data during both resting-state and movie-watching scenarios, established a layer-specific functional connectivity analysis pipeline from individual to group levels, and explored the role of different cortical layers in maintaining functional networks. Our results revealed distinct layer-specific connectivity patterns within the default mode, somatomotor, and visual networks, as well as at the global hubness level. The cutting-edge technique and insights derived from our exploration into near-whole-brain layer-specific connectivity provide unparalleled understanding of the organization principles and underlying mechanisms governing communication between different brain regions.

Artificial-intelligence-enabled dynamic demand response system for maximizing the use of renewable electricity in production processes

AbstractThe transition towards renewable electricity provides opportunities for manufacturing companies to save electricity costs through participating in demand response programs. End-to-end implementation of demand response systems focusing on manufacturing power consumers is still challenging due to multiple stakeholders and subsystems that generate a heterogeneous and large amount of data. This work develops an approach utilizing artificial intelligence for a demand response system that optimizes industrial consumers’ and prosumers’ production-related electricity costs according to time-variable electricity tariffs. It also proposes a semantic middleware architecture that utilizes an ontology as the semantic integration model for handling heterogeneous data models between the system’s modules. This paper reports on developing and evaluating multiple machine learning models for power generation forecasting and load prediction, and also mixed-integer linear programming as well as reinforcement learning for production optimization considering dynamic electricity pricing represented as Green Electricity Index (GEI). The experiments show that the hybrid auto-regressive long-short-term-memory model performs best for solar and convolutional neural networks for wind power generation forecasting. Random forest, k-nearest neighbors, ridge, and gradient-boosting regression models perform best in load prediction in the considered use cases. Furthermore, this research found that the reinforcement-learning-based approach can provide generic and scalable solutions for complex and dynamic production environments. Additionally, this paper presents the validation of the developed system in the German industrial environment, involving a utility company and two small to medium-sized manufacturing companies. It shows that the developed system benefits the manufacturing company that implements fine-grained process scheduling most due to its flexible rescheduling capacities.

Enhancing Cyber Supply Chain Security through Prophetic Analytics for Cyber Threats

The Cyber Provide series system a multifaceted system with a multiple subsystems carrying out distinct functions. The potential weaknesses and risks originating out of a segment and arrangement that will manipulated at some stage in the provide series. make supply chain security difficult As a result, it is critical for organizations to comprehend and assess the risks in order to implement the appropriate supply chain security management measures. Using machine learning (ML) techniques in conjunction with cyber threat intelligence (CTI), we have been able To examine and predict potential risks using the characteristics of CTI. This makes it possible to pinpoint the innate CSC vulnerabilities and implement the proper countermeasures for an overall increase in cyber security. In order to show the practicality of our method, we collect CTI data and use the Microsoft viruses forecast dataset to produce prophetic investigation using several machine learning (ML) algorithms, The test considers the pounce and TTP as capture variable, while the measures of compromise and vulnerabilities are considered as output parameters, incorporating Decision Tree, Random Forest, Support Vector Machine. KEY WORDS Cyber Supply Chain; Cyber warning surveillance; Predictive Analytics, Cyber Safety, Tactical Methods Process

Topics of Conflict Across Family Subsystems

The present study investigated topics of conflict across multiple family subsystems (i.e., the romantic couple, parent–adolescent, and parent–younger child) in present-day American families. Research questions were addressed from a nationwide sample of 593 adults parenting at least one child. Findings highlight the heightened severity of conflict in the couple relationship relative to equivalent topics appearing in parent–child subsystems as well as topics with greater conflict severity between parents and adolescents (e.g., being distant) and topics with greater severity between parents and younger children (e.g., food/picky eating). Salient sources of conflict in present-day families (e.g., technology/phone use in the parent–adolescent subsystem, mood and tempers in all subsystems) were also identified. Findings from the study illustrate ways in which conflict topics appear similarly and differently across distinct family subsystems as well as which conflict topics have changed in families over time and those that have remained constant.

Reliability Analysis of Highway Network Travel Time Based on Information Entropy Model and Electronic Toll Collection Data

Travel time reliability (TTR) holds significant importance as an evaluation index in the transportation industry. To simplify TTR calculations at the network level in engineering applications, this paper re-examines the highway network from the perspective of system theory, regards it as a road network system consisting of multiple subsystems, and proposes a framework for calculating the TTR of the highway network based on the information entropy model. The information entropy model is employed to quantify the level of disorder within the temporal distribution, thereby substituting the need for fitting or deducing the distribution function as practiced in conventional methodologies. The design of roadway indicators considers the social attributes of the transportation network, making reliability not solely dependent on temporal data. For the case study, we used data from the electronic toll collection gantry system on the Xi’an bypass highway. The results indicate that the TTR of the inner ring within the ring network is significantly higher than that of the outer ring. Furthermore, the reliability of the network is lower than that of any sub-section, during both peak and off-peak hours. The applicability of the proposed computational framework is demonstrated and the nature of the results is explored in comparisons with traditional metrics and time prediction attempts. The approach to the TTR evaluation problem from a novel perspective presented in this research omits the procedure of fitting the time distribution function and avoids being affected by its heterogeneity, making TTR calculation and extension more efficient and convenient.

Development of an action programme tackling obesity-related behaviours in adolescents: a participatory system dynamics approach

System dynamics approaches are increasingly addressing the complexity of public health problems such as childhood overweight and obesity. These approaches often use system mapping methods, such as the construction of causal loop diagrams, to gain an understanding of the system of interest. However, there is limited practical guidance on how such a system understanding can inform the development of an action programme that can facilitate systems changes. The Lifestyle Innovations Based on Youth Knowledge and Experience (LIKE) programme combines system dynamics and participatory action research to improve obesity-related behaviours, including diet, physical activity, sleep and sedentary behaviour, in 10–14-year-old adolescents in Amsterdam, the Netherlands. This paper illustrates how we used a previously obtained understanding of the system of obesity-related behaviours in adolescents to develop an action programme to facilitate systems changes. A team of evaluation researchers guided interdisciplinary action-groups throughout the process of identifying mechanisms, applying the Intervention Level Framework to identify leverage points and arriving at action ideas with aligning theories of change. The LIKE action programme consisted of 8 mechanisms, 9 leverage points and 14 action ideas which targeted the system’s structure and function within multiple subsystems. This illustrates the feasibility of developing actions targeting higher system levels within the confines of a research project timeframe when sufficient and dedicated effort in this process is invested. Furthermore, the system dynamics action programme presented in this study contributes towards the development and implementation of public health programmes that aim to facilitate systems changes in practice.

Subgradient of Cycle-Based Aging Cost Function and Its Application in Optimal Operation of Battery Energy Storage System With Multiple Subsystems

Subgradient of Cycle-Based Aging Cost Function and Its Application in Optimal Operation of Battery Energy Storage System With Multiple Subsystems

Two Disparity Channels in Human Visual Cortex With Different Contrast and Blur Sensitivity.

Our goal is to describe the contrast and blur sensitivity of multiple horizontal disparity subsystems and to relate them to the contrast and spatial sensitivities of their monocular inputs. Steady-state visual evoked potential (SSVEP) amplitudes were recorded in response to dynamic random dot stereograms (DRDSs) alternating at 2 Hz between zero disparity and varying magnitudes of crossed disparity for disparity plane and disparity grating stimuli. Half-image contrasts ranged between 2.5% and 80% and over a range of Gaussian blurs from 1.4 to 12 arcmin. Separate experiments measured contrast and blur sensitivity for the monocular half-images. The first and second harmonics disparity responses were maximal for disparity gratings and for the disparity plane condition, respectively. The first harmonic of the disparity grating response was more affected by both contrast and blur than was the second harmonic of the disparity plane response, which had higher contrast sensitivity than the first harmonic. The corrugation frequency, contrast, and blur tuning of the first harmonic suggest that it reflects activity of neurons tuned to higher luminance spatial frequencies that are selective for relative disparity, whereas the second harmonic reflects the activity of neurons sensitive to absolute disparity that are driven by low monocular spatial frequencies. SSVEPs to DRDSs provide two objective neural measures of disparity processing, the first harmonic-whose stimulus preferences are similar to those of behavioral stereoacuity-and the second harmonic that represents an independent disparity-specific but not necessarily stereoscopic mechanism.

Effects of speech rate modifications on phonatory acoustic outcomes in Parkinson's disease.

Speech rate reduction is a global speech therapy approach for speech deficits in Parkinson's disease (PD) that has the potential to result in changes across multiple speech subsystems. While the overall goal of rate reduction is usually improvements in speech intelligibility, not all people with PD benefit from this approach. Speech rate is often targeted as a means of improving articulatory precision, though less is known about rate-induced changes in other speech subsystems that could help or hinder communication. The purpose of this study was to quantify phonatory changes associated with speech rate modification across a broad range of speech rates from very slow to very fast in talkers with and without PD. Four speaker groups participated: younger and older healthy controls, and people with PD with and without deep brain stimulation of the subthalamic nucleus (STN-DBS). Talkers read aloud standardized sentences at 7 speech rates elicited using magnitude production: habitual, three slower rates, and three faster rates. Acoustic measures of speech intensity, cepstral peak prominence, and fundamental frequency were measured as a function of speech rate and group. Overall, slower rates of speech were associated with differential effects on phonation across the four groups. While all talkers spoke at a lower pitch in slow speech, younger talkers showed increases in speech intensity and cepstral peak prominence, while talkers with PD and STN-DBS showed the reverse pattern. Talkers with PD without STN-DBS and older healthy controls behaved in between these two extremes. At faster rates, all groups uniformly demonstrated increases in cepstral peak prominence. While speech rate reductions are intended to promote positive changes in articulation to compensate for speech deficits in dysarthria, the present results highlight that undesirable changes may be invoked across other subsystems, such as at the laryngeal level. In particular, talkers with STN-DBS, who often demonstrate speech deterioration following DBS surgery, demonstrated more phonatory detriments at slowed speech rates. Findings have implications for speech rate candidacy considerations and speech motor control processes in PD.

The Monitoring System of Soil PH Factor Using IoT-Webserver-Android and Machine Learning: A Case Study

In Indonesia, the agriculture industry has been more reluctant than other sectors to adopt IoT, IT, and AI technology. Utilizing this technology will enable precision agriculture. This research aims to make and implement an IoT-Webserver-Android and Machine Learning-based soil PH factor monitoring tool system. The steps for making the tool system are divided into three subsystems. The first is a multiple sensors data acquisition subsystem, consisting of sensors for soil PH-Moisture, Temperature-Humidity, and Sunlight. The sensors are connected to the Arduino Uno microcontroller for serial communication with the ESP 8266 microcontroller for the Wi-Fi module. The second part is the monitoring subsystem with the local web application, which contains a MySQL database and a local web page. The third part is the monitoring subsystem with the Android application, which includes a real-time Firebase database and the application for real-time and mobile data display. The results have been implemented and display the expected outcomes. It is clear from the performance of the three subsystems. The outcomes of the tool system's data evaluation provide precise statistical values. Then, Machine Learning analysis generates accurate soil PH prediction models. It has been demonstrated that the monitoring system is applicable and has a favorable impact on data soil PH factor. The implication for the future is that this monitoring system should be added with Nitrogen-Phosphorus-Potassium sensors to measure soil nutrients. Also, the system added edge-analysis to be integrated in monitoring and analyzing soil nutrients.

Statistics of modal condensation in nonlinear multimode fibers

Optical pulses traveling through multimode optical fibers encounter the influence of both linear disturbances and nonlinearity, resulting in a complex and chaotic redistribution of power among different modes. In our research, we explore the phenomenon where multimode fibers reach stable states marked by the concentration of energy into both single and multiple sub-systems. We introduce a weighted Bose-Einstein law, demonstrating its suitability in describing thermalized modal power distributions in the nonlinear regime, as well as steady-state distributions in the linear regime. We apply the law to experimental results and numerical simulations. Our findings reveal that, at power levels situated between the linear and soliton regimes, energy concentration occurs locally within higher-order modal groups before transitioning to global concentration in the fundamental mode within the soliton regime. This research broadens the application of thermodynamic principles to multimode fibers, uncovering previously unexplored optical states that exhibit characteristics akin to optical glass.

Actuator fault detection and isolation in a class of nonlinear interconnected systems

In this paper, the problem of actuator fault detection and isolation is investigated for a class of nonlinear interconnected large-scale systems with modelling uncertainty and measurement noise, where each subsystem can have multiple inputs and multiple outputs (MIMO). The main contribution of this work is the derivation of a scheme that is able to diagnose single or multiple actuator faults in one or multiple subsystems. Each subsystem is monitored by a local diagnosis agent which contains the actuator fault detection module and the isolation module. The detection threshold in the fault detection module is generated through the use of a novel filtering technique, while the fault isolation module is realised by applying a reasoning-based decision logic based on a fault signature matrix. Fault propagation among subsystems is investigated and the results obtained allow for the identification of the subsystems that contain the faulty actuators. Finally, the effectiveness of the proposed actuator fault diagnosis method is demonstrated through a simulation example.