Load Estimation Algorithm Research Articles

Cognitive Workload Estimation in Conditionally Automated Vehicles Using Transformer Networks Based on Physiological Signals

Though driving automation promises to improve driving safety, drivers are still required to be ready to retake control in conditionally automated vehicles, which are defined by the Society of Automotive Engineers (SAE) as SAE L3 vehicles. Thus, drivers’ states can still affect driving safety in SAE L3 vehicles. Previous research found that a high cognitive load may impair drivers’ takeover performance. Thus, it is still necessary to estimate drivers’ cognitive load in SAE L3 vehicles. However, existing driver cognitive load estimation algorithms mostly focus on vehicles with a lower level of driving automation (e.g., SAE L0), which may not be relevant when estimating driver states in SAE L3 vehicles, given that drivers’ responsibilities are different, and several commonly used measures (e.g., driving performance) are unavailable when drivers are not continuously controlling the vehicle. Further, previous driver cognitive load estimation algorithms rarely considered the temporal information in the input features. Thus, we proposed a deep-learning algorithm to estimate driver cognitive load in SAE L3 vehicles, which integrated multiple physiological features (i.e., electrocardiogram, electrodermal activity, respiration) and considered the temporal correlation of the data using a transformer-encoder-based network. The performance of our algorithm was compared with baseline models on an open data set. Results showed that our algorithm outperformed baseline models and achieved an accuracy of 94.4% using within-subject data partition (proportionally splitting data from the same subject into the training and testing data sets) and an accuracy of 89% using across-subjects data partition (dividing the training and testing data sets based on individual subjects).

Sampling frequency, load estimation and the disproportionate effect of storms on solute mass flux in rivers

Riverine discharge (Q) and dissolved concentrations (C) dictate solute mass export from watersheds. Commonly Q is tracked at a much higher frequency than C for most major solutes, leading to the necessity of load estimation algorithms which are often based on sparse data. The result is that the disproportionate effects of short-duration events (e.g., storms) on solute mass fluxes are poorly known. Here we use novel lab-in-the-field instrumentation to compare high temporal-resolution (∼30 min to 7 h) datasets of major ion chemistry collected over a year of continuous monitoring in three watersheds ranging over four orders of magnitude in drainage area. In these diverse settings, we quantify the errors associated with common load estimation algorithms and reduced sampling frequencies. When sample frequencies are coarsened, the mass flux of solutes which are diluted by storm events (i.e., Ca2+, Mg2+, Na+, Cl− and SO42−) are systematically overestimated, while nutrients which become mobilized by these events (K+ and NO3−) are underestimated. This is most pronounced in the largest river, and strongly tied to the increasing likelihood that storm events are missed as sampling frequencies decrease. Coarsening our high-resolution data to monthly sampling frequency yields an average overestimate of 8 % for Na+ and an average underestimate of 32.5 % for K+ across the three watersheds, illustrating clear implications for estuary and coastal water eutrophication, chemical weathering budgets, and agricultural land management practices. SynopsisA new ‘lab-in-the-field’ technology produces continuous high-frequency records of the full suite of major ions in rivers. These data highlight the disproportionate effect of large storms on catchment solute exports and the error associated with temporally coarse monitoring.

Load Estimation Based Dynamic Access Protocol for Satellite Internet of Things

In recent years, the Internet of Things (IoT) industry has become a research hotspot. With the advancement of satellite technology, the satellite Internet of Things is further developed along with a new generation of information technology and commercial markets. However, existing random access protocols cannot cope with the access of a large number of sensors and short burst transmissions. The current satellite Internet of Things application scenarios are divided into two categories, one has only sensor nodes and no sink nodes, and the other has sink nodes. A time-slot random access protocol based on Walsh code is proposed for the satellite Internet-of-Things scenario with sink nodes. In this paper, the load estimation algorithm is used to reduce the resource occupancy rate in the case of medium and low load, and a dynamic Walsh code slot random access protocol is proposed to select the appropriate Walsh code length and frame length h. The simulation results show that the slotted random access protocol based on Walsh code can effectively improve the throughput of the system under high load. The introduction of load estimation in the case of medium and low load can effectively reduce the resource utilization of the system, and ensure that the performance of the access protocol based on Walsh codes does not deteriorate. However, in the case of high load, a large resource overhead is still required to ensure the access performance of the system.

GAN for Load Estimation and Traffic-Aware Network Selection for 5G Terminals

In the face of the user-centric access network architecture adopted by the fifth-generation (5G) mobile communication network terminals, the communication capability of terminals faces significant challenges. In this case, the combination of 5G and artificial intelligence (AI) has become a significant trend to meet the various communication needs of terminal devices. Toward the problem that the data analysis and decision making for cell load estimation are primarily accomplished on the access side of the network, terminals can only passively access the network, but cannot predict the load estimation on the access side of the network in advance and cannot make network selection decisions in real time. In this article, we propose a cell load estimation algorithm based on a generative adversarial network (GAN) for 5G mobile communication networks, which considers estimating the cell load according to the wireless information measured by the terminals. The algorithm effectively estimates the cell load at the terminal side, which reflects the intelligence of the terminals and solves the problems of low data transmission rate, high signaling cost, and time delay in the existing techniques for load estimation schemes at the network side, assisting users in making a real-time decision. The performance is evaluated through the system-level simulation, and the results indicate that the proposed model improves load estimation accuracy, simultaneously improving the network throughput and reducing the packet queuing delay, suitable for different heterogeneous network scenarios.

Field investigation of novel self-sensing asphalt pavement for weigh-in-motion sensing

The integration of weigh-in-motion (WIM) sensors within highways or bridge structural health monitoring systems is becoming increasingly popular to ensure structural integrity and users safety. Compared to standard technologies, smart self-sensing materials and systems present a simpler sensing setup, a longer service life, and increased durability against environmental effects. Field deployment of such technologies requires characterization and design optimization for realistic scales. This paper presents a field investigation of the vehicle load-sensing capabilities of a newly developed low-cost, eco-friendly and high durability smart composite paving material. The novel contributions of the work include the design and installation of a full-scale sensing pavement section and of the sensing hardware and software using tailored low-cost electronics and a learning algorithm for vehicle load estimation. The outcomes of the research demonstrate the effectiveness of the proposed system for traffic monitoring of infrastructures and WIM sensing by estimating the gross weight of passing trucks within a 20% error during an autonomous sensing period of two months.

Yield and Maturity Estimation of Apples in Orchards Using a 3-step Deep Learning-based Method

Yield and maturity estimation of apples in orchards before harvest is essential for labor resource management. Current yield and maturity estimation are usually manually conducted, which is neither accurate nor efficient. In this paper, a 3-step deep learning–based approach for yield estimation and maturity classification is presented to address these issues. The proposed framework included an optimized detection network to count the visible fruits from both sides of a tree, a classification network to filter out mis-detected objects and perform maturity estimation, and a fruit load estimation algorithm to obtain the total fruit count of a tree. Images from three differ-ent apple orchards were collected to evaluate the performance of the proposed method. According to a series of comparative experiments, the proposed method outperformed several detection networks regarding the counting accuracy, indicating that an optimized architecture of the detection network combined with a fine classification network is necessary for enhanced precision of yield estimation. The presented workflow can be readily extended to other fruit crops for automation yield and maturity estimation featuring high efficiency and accuracy.

The Fixed Point Iteration of Positive Concave Mappings Converges Geometrically if a Fixed Point Exists: Implications to Wireless Systems

We prove that the fixed point iteration of arbitrary positive concave mappings with nonempty fixed point set converges geometrically for any starting point. We also show that positivity is crucial for this result to hold, and the concept of (nonlinear) spectral radius of asymptotic mappings provides us with information about the convergence factor. As a practical implication of the results shown here, we rigorously explain why some power control and load estimation algorithms in wireless networks, which are particular instances of the fixed point iteration, have shown geometric convergence in simulations. These algorithms have been typically derived by considering fixed point iterations of the general class of standard interference mappings, so the possibility of sublinear convergence rate could not be ruled out in previous studies, except in special cases that are often more restrictive than those considered here.

A Novel Computation Method for Tag Estimates in DFSA-based RFID Systems

In this paper, we propose a novel computation method for tag estimation in the dynamic framed slotted ALOHA (DFSA) protocol, based on Vogt’s estimate (VE). The estimation target is system load λ and tag estimate N̂ is computed from the estimated values of λ, instead of the direct approach taken in the existing method. Starting from the definition of VE, we derive a single concise equation for the estimate. For the numerical solution, we present a load estimation algorithm, which turns out to be computationally very efficient. The computational complexity is roughly O(10 log<SUB>10</SUB> N<SUB>max</SUB>), in contrast to O(N<SUB>max</SUB>) in the existing method for maximum possible number of tags, N<SUB>max</SUB>. Through computer simulations, we show that the proposed method indeed yields estimation results almost identical to those by the existing method in most cases.

Machine Learning Based Short Term Load Estimation in Commercial Buildings

Nowadays, there are many problems with the electricity system, such as increasing consumption, short-time overload during the intra-day, environmental problems caused by fossil fuel, and foreign-source dependency. Therefore, it is necessary to meet these increasing energy needs, minimize environmental impacts, and develop cost optimization solutions. In order to meet these requirements, it is necessary for the network to have a more dynamic structure and to have real-time monitoring and control systems. Furthermore, to develop the aforementioned system, it is necessary to estimate the load of the users in the system. Therefore, the developed artificial neural network-based load estimation algorithm is capable of high accuracy load estimates, and high precision data were obtained for use in the demand side management system

Bone Mechanoregulation Allows Subject-Specific Load Estimation Based on Time-Lapsed Micro-CT and HR-pQCT in Vivo.

Patients at high risk of fracture due to metabolic diseases frequently undergo long-term antiresorptive therapy. However, in some patients, treatment is unsuccessful in preventing fractures or causes severe adverse health outcomes. Understanding load-driven bone remodelling, i.e., mechanoregulation, is critical to understand which patients are at risk for progressive bone degeneration and may enable better patient selection or adaptive therapeutic intervention strategies. Bone microarchitecture assessment using high-resolution peripheral quantitative computed tomography (HR-pQCT) combined with computed mechanical loads has successfully been used to investigate bone mechanoregulation at the trabecular level. To obtain the required mechanical loads that induce local variances in mechanical strain and cause bone remodelling, estimation of physiological loading is essential. Current models homogenise strain patterns throughout the bone to estimate load distribution in vivo, assuming that the bone structure is in biomechanical homoeostasis. Yet, this assumption may be flawed for investigating alterations in bone mechanoregulation. By further utilising available spatiotemporal information of time-lapsed bone imaging studies, we developed a mechanoregulation-based load estimation (MR) algorithm. MR calculates organ-scale loads by scaling and superimposing a set of predefined independent unit loads to optimise measured bone formation in high-, quiescence in medium-, and resorption in low-strain regions. We benchmarked our algorithm against a previously published load history (LH) algorithm using synthetic data, micro-CT images of murine vertebrae under defined experimental in vivo loadings, and HR-pQCT images from seven patients. Our algorithm consistently outperformed LH in all three datasets. In silico-generated time evolutions of distal radius geometries (n = 5) indicated significantly higher sensitivity, specificity, and accuracy for MR than LH (p < 0.01). This increased performance led to substantially better discrimination between physiological and extra-physiological loading in mice (n = 8). Moreover, a significantly (p < 0.01) higher association between remodelling events and computed local mechanical signals was found using MR [correct classification rate (CCR) = 0.42] than LH (CCR = 0.38) to estimate human distal radius loading. Future applications of MR may enable clinicians to link subtle changes in bone strength to changes in day-to-day loading, identifying weak spots in the bone microstructure for local intervention and personalised treatment approaches.

An Intelligent Load Control-Based Random Access Scheme for Space-Based Internet of Things.

Random access is one of the most competitive multiple access schemes for future space-based Internet of Things (S-IoT) due to its support for massive connections and grant-free transmission, as well as its ease of implementation. However, firstly, existing random access schemes are highly sensitive to load: once the load exceeds a certain critical value, the throughput will drop sharply due to the increased probability of data collision. Moreover, due to variable satellite coverage and bursty traffic, the network load of S-IoT changes dynamically; therefore, when existing random access schemes are applied directly to the S-IoT environment, the actual throughput is far below the theoretical maximum. Accordingly, this paper proposes an intelligent load control-based random access scheme based on CRDSA++, which is an enhanced version of the contention resolution diversity slotted ALOHA (CRDSA) and extends the CRDSA concept to more than two replicas. The proposed scheme is dubbed load control-based three-replica contention resolution diversity slotted ALOHA (LC-CRDSA3). LC-CRDSA3 actively controls network load. When the load threatens to exceed the critical value, only certain nodes are allowed to send data, and the load is controlled to be near the critical value, thereby effectively improving the throughput. In order to accurately carry out load control, we innovatively propose a maximum likelihood estimation (MLE)-based load estimation algorithm, which estimates the load value of each received frame by making full use of the number of time slots in different states. On this basis, LC-CRDSA3 adopts computational intelligence-based time series forecasting technology to predict the load values of future frames using the historical load values. We evaluated the performance of LC-CRDSA3 through a series of simulation experiments and compared it with CRDSA++. Our experimental results demonstrate that in S-IoT contexts where the load changes dynamically, LC-CRDSA3 can obtain network throughput that is close to the theoretical maximum across a wide load range through accurate load control.

A Preamble Re-utilizing Access Scheme for Machine-Type Communications with Optimal Access Class Barring

The existing long term evolution networks originally designed for human-to-human communications are hard to tackle numerous and bursty random access requests from emerging machine-type communication devices (MTCDs). In this paper, we propose a novel preamble re-utilizing random access scheme for stationary MTCDs with optimal access class barring (ACB), which is based on joint ACB and timing advance (TA) model. By adopting load estimation algorithm, evolved node B (eNB) can detect the preamble collisions in the first step of random access procedure. Therefore, the eNB merely schedules physical uplink shared channel to the successful preambles according to standard random access procedure. The MTCDs that did not pass the first ACB check re-utilize the resources scheduled by the idle and collided preambles to access with a second optimal ACB. Analytical and simulation results manifest that our proposed scheme notably outperforms the conventional joint ACB and TA scheme in terms of four metrics: throughput, access delay, probability of preamble collision and resource efficiency.

Effects of sampling strategies and estimation algorithms on total nitrogen load determination in a small agricultural headwater watershed

Monitoring data collected from rivers are used to support assessments of the quality of the river environment and help decision makes formulate appropriate management plans. Therefore, accurate and precise estimates of constituent fluxes in streams and rivers are important. However, seasonal errors have not received enough attention and the published results have rarely been verified by other methods. In this study, the error associated with sampling frequencies (3 daily, weekly, 2 weekly, 4 weekly, 6 weekly, 8 weekly) and seven load estimation algorithms were examined. Seasonal and annual total N loads were estimated and wavelet coherence was used as a reference. In order to reduce the contingency of the results, three years data were used and total N (with 17.53% particulate N, 58.70% NO3−-N and 23.77% other dissolved N fractions) was chosen to reflect water quality parameters. Results indicated that 2 weekly sampling frequency and algorithm F (linear interpolation) are sufficient for evaluating the characters of annual total N load in Fengyu River Watershed with 5% RMSE (root-mean-square error). There was a large RMSE (3.97–44.66%) in summer with a high CV (coefficient variation) (35.2%) for total N concentration. These results can serve as a useful reference for decision makes who need to establish monitoring programmes in watersheds with similar characteristics.

Event-Triggered Optimal Active Power Control in Islanded Microgrid With Variable Demand and Time-Varying Communication Topology

For islanded microgrids, traditional droop-based control leads to frequency deviation and low economic efficiency. To resolve this issue, a novel event-triggered optimal active power control strategy, which achieves frequency regulation and economic operation in a fully distributed way, is proposed in this paper. Frequency deviations are monitored and used to trigger the load estimation algorithm to track changes in power demand. Based on estimated demand values, a distributed economic dispatch (ED) algorithm, which only requires that the communication topology satisfies the jointly connected condition, is proposed to calculate the optimal generation references for the generators. The ED algorithm has the finite-time convergence property, which is rigorously proved by Lyapunov theory, LaSalle’s invariance principle and homogeneous property. Based on optimal generation references, the parameters of droop controller are reset in real time, which makes microgrid achieve frequency restoration and economic operation simultaneously. Finally, several case studies are presented to illustrate the effectiveness of the proposed control strategy.

An R package for estimating river compound load using different methods

The load quantification of solutes and suspended materials in rivers provides meaningful ecological information about watershed functionality. High-frequency measurements of flow are often available, whereas concentration data are commonly recorded at low frequencies. Different calculation methods have been developed by various authors to provide unbiased load estimation. We provide a new R package (RiverLoad) that implements several of the most widely used load estimation algorithms. The package provides an easy-to-use tool to rapidly calculate the load for various compounds and to compare different methods. The package also supplies additional functions to easily organize and analyze the data. A bootstrapping was performed on two example datasets to illustrate the reliability of the methods at different sampling frequencies. The RiverLoad package should make it easier to obtain load data and to compare different estimation algorithms. However, attention must be paid when selecting the method to avoid consistent error in the load estimation.

Operation load estimation of chain-like structures using fiber optic strain sensors

The recent advancements in sensing technologies allow us to record measurements from target structures at multiple locations and with relatively high spatial resolution. Such measurements can be used to develop data-driven methodologies for condition assessment, control, and health monitoring of target structures. One of the state-of-the-art technologies, Fiber Optic Strain Sensors (FOSS), is developed at NASA Armstrong Flight Research Center, and is based on Fiber Bragg Grating (FBG) sensors. These strain sensors are accurate, lightweight, and can provide almost continuous strain-field measurements along the length of the fiber. The strain measurements can then be used for real-time shape-sensing and operational load-estimation of complex structural systems. While several works have demonstrated the successful implementation of FOSS on large-scale real-life aerospace structures (i.e., airplane wings), there is paucity of studies in the literature that have investigated the potential of extending the application of FOSS into civil structures (e.g., tall buildings, bridges, etc.). This work assesses the feasibility of using FOSS to predict operational loads (e.g., wind loads) on chain-like structures. A thorough investigation is performed using analytical, computational, and experimental models of a 4-story steel building test specimen, developed at the University of Southern California. This study provides guidelines on the implementation of the FOSS technology on building-like structures, addresses the associated technical challenges, and suggests potential modifications to a load-estimation algorithm, to achieve a robust methodology for predicting operational loads using strain-field measurements.

Vibration Analysis for Monitoring of Ancient Tie-Rods

This paper presents an application of vibration analysis to the monitoring of tie-rods. An algorithm for the axial load estimation based on experimentally measured natural frequencies is introduced and its application to a case study is reported. The proposed model of a tie-rod incorporates elastic bed-type boundary conditions that represent the contact between stonework and the tie-rod. The weighed differences between experimentally and numerically determined frequencies are minimized with respect to the parameters of the model, the main being the axial load and the stiffness at the tie-rod/wall interface. Thus, the multidimensional optimization problem is solved. Results are analysed in comparison to a model with simple fixed-end boundary conditions. In addition, the analytical formulation of the problem is delivered.

A Performance Assessment Method for Main HVAC Equipment with Electricity Submetering Data

HVAC system is one of the biggest contributors to building energy use, and meanwhile a considerable part of energy is wasted due to the faulty operation of it. Hence, detecting and diagnosing HVAC system faults and improving energy efficiency are of large economic and environmental impact worldwide. However, the current study or application is highly limited by the scarcity of energy usage data, while in recent years electricity submeter was widely implemented and massive amounts of submetering data were accumulated in China. The aim of this paper is therefore to develop a performance assessment framework which is specifically designed for HVAC systems in such commercial buildings with electricity submetering data. This framework consists of three parts. 1) A HVAC terminal energy usage disaggregation algorithm and 2) a cooling load estimation algorithm are firstly performed to make up data deficiency. And then, 3) a diagnosis algorithm is proposed, which uses EPI generated from a Chinese standard (GB/T 17981-2007) as the benchmarks. Finally, a real case study in Shanghai is presented to illustrate the proposed framework and shows that the building operators can easily identify the poor performance area.

Development of a Plantar Load Estimation Algorithm for Evaluation of Forefoot Load of Diabetic Patients during Daily Walks Using a Foot Motion Sensor.

Forefoot load (FL) contributes to callus formation, which is one of the pathways to diabetic foot ulcers (DFU). In this study, we hypothesized that excessive FL, which cannot be detected by plantar load measurements within laboratory settings, occurs in daily walks. To demonstrate this, we created a FL estimation algorithm using foot motion data. Acceleration and angular velocity data were obtained from a motion sensor attached to each shoe of the subjects. The accuracy of the estimated FL was validated by correlation with the FL measured by force sensors on the metatarsal heads, which was assessed using the Pearson correlation coefficient. The mean of correlation coefficients of all the subjects was 0.63 at a level corridor, while it showed an intersubject difference at a slope and stairs. We conducted daily walk measurements in two diabetic patients, and additionally, we verified the safety of daily walk measurement using a wearable motion sensor attached to each shoe. We found that excessive FL occurred during their daily walks for approximately three hours in total, when any adverse event was not observed. This study indicated that FL evaluation method using wearable motion sensors was one of the promising ways to prevent DFUs.

State estimation of medium voltage distribution networks using smart meter measurements

Distributed generation and low carbon loads are already leading to some restrictions in the operation of distribution networks and higher penetrations of e.g. PV generation, heat pumps and electric vehicles will exacerbate such problems. In order to manage the distribution network effectively in this new situation, increased real-time monitoring and control will become necessary. In the future, distribution network operators will have smart meter measurements available to them to facilitate safe and cost-effective operation of distribution networks. This paper investigates the application of smart meter measurements to extend the observability of distribution networks. An integrated load and state estimation algorithm was developed and tested using residential smart metering measurements and an 11kV residential distribution network. Simulation results show that smart meter measurements, both real-time and pseudo measurements derived from them, can be used together with state estimation to extend the observability of a distribution network. The integrated load and state estimation algorithm was shown to produce accurate voltage magnitudes and angles at each busbar of the network. As a result, the algorithm can be used to enhance distribution network monitoring and control.