Search

As a powerful tool for synthesizing information from multiple studies, meta-analysis has gained high popularity in many disciplines. Conclusions stemming from meta-analyses are often used to direct theory development, calibrate sample size planning, and guide critical decision-making and policymaking. However, meta-analyses can be conflicted, misleading, and irreproducible. One of the reasons for meta-analyses to be misleading is the improper handling of measurement unreliability. We show that even when there is no publication bias, the current meta-analysis procedures would frequently detect nonexistent effects, and provide severely biased estimates and intervals with coverage rates far below the intended level. In this study, an effective approach to correcting for unreliability is proposed and evaluated via simulation studies. Its sensitivity to the violation of the homogeneous reliability and residual correlation assumption is also tested. The proposed method is illustrated using a real meta-analysis on the relationship between extroversion and subjective well-being. Substantial differences in meta-analytic results are observed between the proposed method and existing methods. Further, although not specifically designed for aggregating effect sizes with various measures, the proposed method can be used to fulfill the purpose. The study ends with discussions on the limitations and guidelines for implementing the proposed approach. (PsycInfo Database Record (c) 2021 APA, all rights reserved).

Spreadsheet-based tools provide a simple yet effective way of calculating values, which makes them the number-one choice for building and formalizing simple models for budget planning and many other applications.A cell in a spreadsheet holds one specific value and gives a discrete, overprecise view of the underlying model. Therefore, spreadsheets are of limited use when investigating the immanent uncertainties of such models and answering what-if questions. Existing extensions typically require a complex modeling process that cannot be smoothly embedded in a tabular layout.In Fuzzy Spreadsheet, a cell can hold and display the distribution of values. This integrated uncertainty handling immediately conveys sensitivity and robustness information. The fuzzification of the cells enables calculations not only with precise values but with distributions, and probabilities. We conservatively added and carefully crafted visuals to maintain the look and feel of a traditional spreadsheet while facilitating what-if analyses.Given a user-specified reference cell, Fuzzy Spreadsheet automatically extracts and visualizes contextually relevant information, such as impact, uncertainty, and degree of neighborhood, for the selected and related cells.To evaluate its usability and the perceived mental effort required, we conducted a user study.The results show that our approach outperforms traditional spreadsheets in terms of answer correctness, response time, and perceived mental effort for almost all tasks tested.

Measuring and improving the efficiency of a sustainable supply chain in an effective way for strategic decision making is important in the business world. In this article, an alternative coherent data envelopment analysis (CoDEA) with a representation of the intramural structure is established for evaluating the efficiency of a sustainable supply chain. The proposed CoDEA model not only maintains the traditional value of data envelopment analysis (DEA) in its “black box” approach, which avoids the intermediate measures among different nodes in the supply chain, but also overcomes some main pitfalls in previously developed DEA models. The usefulness of the proposed model is illustrated in both simple and complex supply chain situations, yielding reasonable efficiency scores as compared with those from the existing methods. Moreover, the dummy decision-making unit (DMU) introduced in CoDEA offers additional benefits in the scenario of a small supply chain. The approach allows the implicit rule that requires three times the ratio between the total measurement factors and total DMUs to be always satisfied, providing a higher discriminatory power of CoDEA. Based on the case studies covering both simple and complex supply chains, the results and sensitivity analysis ascertain that the proposed CoDEA model is a flexible and reasonable alternative with a good efficiency evaluation, contributing toward an efficient and sustainable supply chain management process pertaining to sustainable strategy or policy recommendations.

Nano-electro-mechanical (NEMS) systems are compacted to be of dimension less than a micron by MEMS. Extremely high fundamental frequencies can be reached in this size regime while at the same time maintaining extremely elevated mechanical sensitivity (minute strength constant). This powerful mixture of attribute directly translate in to elevated strength sensitivities, ultra-low power operability's, and the capability to cause functional nonlinearities by very diffident controlling powers. Current paper addressed NEMS in this overview and will detail numerous of their stimulating original application. At the threshold for this new domain, however, there is a steep entry fee: modern innovation is key to realizing NEMS ' full potential. Some of the foundations of MEMS ' methods would obviously not usefully fit into the NEMS system. The main problem is the dimensions of the systems relative to the circuits in which they will be embedded, its excessive volume-to-surface ratio and its alternative “characteristic operating range.” These create some of the main challenges currently facing the development of NEMS. The majority of well-known of these is the requirement for: Very sensitive, elevated values of bandwidth dislocation transducer; unprecedented controls of quality of surface and adsorbents; new mode of capable Nano-scale actuations; and new surface as well as bulk Nano-machining approaches that are precise, robust and routinely reproducible.

COVID-19 is one of the biggest pandemics that the world is facing today, and every day, we are coming up with new challenges in this area. Still, much research is already going on to overcome this pandemic, and we also get succeeded to some extent. Diverse sources such as MRI, CT scanning, blood samples, X-ray image, and many more are available to detect COVID-19. Thus, it can be easily said that through image processing, the classification of COVID-19 can be done. In this study, the COVID-19 detection is done by classifying with the use of a type of convolutional neural network termed a detail-oriented capsule network. Chest CT scan imaging for the prediction of COVID-19 and non-COVID-19 are classified in the present paper using a Detailed Oriented capsule network (DOCN). Accuracy, specificity, and sensitivity are parameters used for model evaluation. The proposed model has achieved 98% accuracy, 81% sensitivity, and 98.4% specificity.

Road surface irregularities not only has an impact on consistency of road, but also affects driver safety, automobile mechanical stability, and fuel consumption. To order to evaluate road roughness and spot potholes, many solutions have been suggested to remotely track the road surface quality. Some of these methods use an embedded mobile accelerometer to take a crowd sensing view to feel the surface of road. Although crowd sensing has various advantages such as ubiquity and less cost, it has some sensitivity to the problems generated by structures made by human, actions of the driver, and characteristics of the road surface which cannot be identified road anomalies. For this purpose, this paper suggests method of deep learning which helps us (a) to identify the different types of surface of road and (b) to differentiate potholes automatically from destabilizations in the crowd sensing-based application sense arising from speed bumps or driver behavior. This paper study and implement different deep learning frameworks in particular: convolutionary neural networks, LSTM networks, and computational structures for reservoirs. The tests were performed using knowledge from the real world, and the results revealed good precision in solving both of the problems.

This paper presents a practical optimum design solution of prismatic simply supported prestressed concrete girders that are subjected to uniformly distributed static loads. While assuming linear elastic behaviour and employing working stresses method, the optimum values of two design variables, namely the cross-sectional dimensions and the prestressing force, are formulated as a nonlinear optimization model. Optimum values of the design variables are computed to satisfy either a minimum weight or a minimum cost objective function. To solve the nonlinear programming models, a program named Non-Linear Programming Prestressed Concrete Optimizer (NLPRECO) was coded in MATLAB® programming environment. Some illustrative design problems were solved using NLPRECO and their results are demonstrated herein. Sensitivity analysis of the optimized design variables, to variations in design parameters, was also investigated and the results are presented. Results show substantial improvement over the regular un-optimized solutions and moderate improvement over a linear programming optimization solutions.

In the future, wind power is expected to become widely used due to its environmentally friendly and sustainable nature. Recent advancements in technology have also allow for the efficient use of this energy in the form of electrical power. Increased research has resulted in the development of wind turbines as energy converters. For the safety and proper operation of wind turbines, condition monitoring is imperative. According to Condition Monitoring (CM), the most common rotating equipment failure is found in wind turbines is a lack of good bearing grease. Using machine learning techniques, we've performed a CM of the wind turbine and validated our methods with fault-seeded data from a previous test. We isolate two primary characteristics from the data: kurtosis, which measures the non-Gaussianity, and then we rate it based on the kurtosis measure (NGS). In order to identify malfunctioning data, the robustness of this method is then checked using an “anomaly detection” to carry out the classification. This research shows that anomaly detection produces a better result in terms of accuracy and sensitivity as compared to SVMs.

Waste electrical and electronics equipment (WEEE) recyclers have become a boon for countries as they assist to reduce carbon emissions by recycling the WEEE in the most ecofriendly way. The evaluation and choice of optimal WEEE recycling partner is a significant and multifaceted decision for the managerial experts because of the involvement of several qualitative and quantitative criteria. Thus, the aim of the article is to propose a novel methodology by integrating a combined compromise solution approach and similarity measure within the context of single-valued neutrosophic sets (SVNSs) and, then, used to solve the decision-making problem. In this approach, the criteria weights are evaluated by a new procedure based on a similarity measure. For this, a novel similarity measure is introduced for SVNSs and also presented its efficiency over existing similarity measures. To investigate the efficiency and practicality of the introduced approach, a case study of WEEE recycling partner selection is taken under the SVNSs environment. Finally, comparison and sensitivity analysis are made to check the robustness and stability of the developed methodology. The outcomes of this article exemplify that the developed approach is more suitable and well consistent with existing approaches.

Dimensionality reduction is commonly used for identifying and analyzing patterns in the visual analysis of multi-dimensional datasets. The selection of subspaces is a core building block in projecting high-dimensional data to low-dimensional space, which is usually illustrated as a scatterplot for analysts to easily understand and explore. This process involves human prior knowledge and domain-specific requirements. Thus, quantifying and tracking the changes of projections across subspaces remain challenging. Existing methods can neither quantify the subsets-based changes of dimensionality reduction results when switching subspaces nor automatically and comprehensively display overall and subtle differences among dimensionality reduction results.To address this, we developed EvoSets, a novel visual analytics system designed to help users understand how subspaces affect dimensionality reduction results. The effects are quantified based on subsets' distribution to tracking the sensitivity of dimensionality reduction results across subspaces. System supports the exploration of the overall evolution of the dimensionality reduction results for helping users track the convergence and divergence behavior changes of subsets based on an extended Bubble Sets visualization. Similarities are intuitively illustrated, and dissimilarities are highlighted among projections based on layout constraints. The usefulness and effectiveness are evaluated with a user study and two case studies on multi-dimensional datasets.

A sensitivity study is presented to evaluate the influence of different parameters on the simulation of an underground excavation in the Callovo-Oxfordian (COx) argillaceous formation performed in the Meuse/Haute-Marne underground research laboratory. An elasto-viscoplastic constitutive law representing the characteristic behaviour of indurated mudrocks and stiff clays has been employed. It incorporates anisotropy, strain-softening, creep deformations and dependence of permeability on damage. In addition, a non-local formulation, able to simulate localised deformations objectively, has been incorporated in the analyses. The following features affecting the excavation have been studied: initial stress, strength and stiffness anisotropy, strength parameters, hydraulic and hydromechanical parameters, and scale effects. A simulation reported in a companion paper provides the base case for benchmarking. The results are compared in terms of extent and configuration of the excavation fractured zone, vertical and horizontal tunnel convergences, and the development and evolution of pore pressures in the rock. From the comparisons, an enhanced understanding of the hydromechanical mechanisms associated with underground excavations in COx claystone, and other similar argillaceous materials, has been achieved. We are grateful for the financial and technical assistance of the French national radioactive waste management agency (Andra) to the work presented. The technical assistance of Plaxis is also gratefully acknowledged. The first author has been supported by a Conacyt scholarship (Reg. No. 270190).

Attentional biases toward negative information are implicated in various emotional disorders. The literature probing this relationship relies on assumptions that the tasks used to measure attentional biases are sensitive to the negative emotional qualities of stimuli; but are such assumptions justified? We assessed the degree to which two widely used tasks-the dot probe and emotion-induced blindness-displayed sensitivity to gradations in valence and arousal ratings for negative emotional pictures. For emotion-induced blindness (the failure to see a target that follows an emotional distractor in a rapidly presented sequence of items), there was strong evidence of sensitivity to gradations in both valence and arousal. In contrast, there was moderate to strong evidence that the dot probe (a spatial attention task where latency to respond to a target depends on whether it appears at or away from the location of an emotional stimulus) was insensitive to gradations in valence and arousal, although there was some evidence of its sensitivity to emotional versus neutral stimuli overall. That said, in the dot probe, response latency regardless of spatial relationship between the target and the emotional image appeared sensitive to gradations in stimulus emotionality. Together, these findings suggest that such sensitivity may be characteristic of nonspatial, rather than spatial, aspects of attention. Implications for attentional bias studies are discussed. Notably, the finding that emotion-induced blindness was sensitive to gradations in ratings of emotional pictures supports claims that the effect arises due to stimulus emotionality rather than simply differences in visual features of pictures (e.g., color, brightness, complexity). (PsycInfo Database Record (c) 2022 APA, all rights reserved).

A revision of the mechanism of mechanical-to-vibrational energy transfer in crystals of energetic materials undergone impact loading is proposed. The new approach takes into account previous inaccuracies of normalization of the number of couplings between phonon overtones and conformational vibrational fundamentals (ζ), which is critical for comparison of molecules that differ greatly in the number of atoms. Moreover, it introduces two very important damping factors, namely a and b. The a factor allows differentiation of the phonon overtones by their coupling strength; the lower the overtone interacts, the stronger the coupling is. Meanwhile, the b factor is aimed to distinguish the coupling strength itself. This factor is the denominator in the exponent of a Gaussian-type function and determines the rate at which the coupling strength decays with the rise of difference between the interacting phonon overtones and conformational vibrational fundamentals. After a careful regression analysis of ζ against impact sensitivities (h50) of 30 common nitroexplosives, we have determined the numerical values of these damping factors as a = 2.5 and b = 40 cm–1. The proposed approach is extrapolated on the vibrational spectra of 21 crystalline energetic materials with Z' ≥ 1 and a general applicability along with limitations of the method are discussed for the family of nitroexplosives and nitrogen-rich (cyclo-pentazolate and 5,5′-bitetrazole) energetic salts as an example.

The circuit parameters mismatches of input-parallel output-parallel (IPOP) dual active bridge (DAB) converter modules will cause power imbalances of the system. To solve this problem, this paper presents a simple sensorless current sharing control based on dual-phase-shift (DPS) modulation method. First, the full process operation mode of IPOP DAB is analyzed. Then, the power balance mechanism of the IPOP DAB converter is discussed, and a sensorless current sharing control method is proposed. The core principle of the proposed method is based on the perturbation algorithm to estimate the parameter mismatches of each DAB cell. Once the parameter mismatches are known, the phase shifts that achieve current sharing are calculated. The implementation scheme based on CAN Bus is given, and sensitivity and stability analysis of the proposed method are conducted. Finally, the simulation and experimental results verify the effectiveness of the proposed control strategy.

The development of an efficient and fast cryptosystem has become significant with the widespread use of internet and advancements in networking technology. A colour image encryption/decryption technique using image block generation from block-based Sequency-based Mapped Real Transform (SMRT) is introduced in this paper to achieve this goal. The encryption architecture uses a confusion-diffusion approach and begins by partitioning individual colour components of plain image into fixed-size blocks. This is followed by XOR operation between generated diffusion keys and the image blocks to achieve diffusion. SMRT of the diffused image block is found and confusion induced by image block operations. Encrypted image is obtained through inverse SMRT and compilation of encrypted colour components. The proposed cryptosystem demonstrates excellent features including high sensitivity, complex keystream, strong security, high encryption and decryption efficiency and simple structure.

Accurate rotor position estimation is important to ensure the high-performance operation of position sensorless permanent magnet synchronous motor (PMSM) drives. To suppress the estimated rotor position harmonic error (ERPHE) caused by inverter nonlinearities, flux spatial harmonics, and the current measurement error in high-frequency signal injection based schemes, an adaptive iterative learning control based online suppression method is proposed in this paper. This method constructs a P-type iterative learning rotor position observer with the forgetting factor to obtain the tracking error and generate the compensation value in real time. The stability, the convergence, and the parameter sensitivity of this observer are analyzed in detail. To improve the suppression effect of the ERPHE for different loads and speeds, an iterative learning gain self-tuning strategy is investigated. The proposed method does not require the offline detection and the discrimination of harmonic frequencies, which has strong suppression ability for different harmonic error components. The effectiveness is verified by experiments on a 2.2-kW interior PMSM drive platform.

Online condition monitoring of winding insulation has been proved to be an effective means to improve the reliability of an inverter-fed machine, but little work has been done on the insulation of line-end coil subjected to much higher transient voltage stress with a higher risk of premature insulation break down. In this paper, the inverter self-excited high-frequency switching oscillations are utilized for the line-end coil insulation condition monitoring. To improve the condition monitoring sensitivity and its robustness to dynamic operating conditions, a switching oscillation mode decomposition (SOMD) method is proposed. Firstly, the condition-sensitive mode, i.e. high-frequency common-mode (HFCM) current is selected and separated by the variation mode decomposition (VMD) algorithm among three dominant modes in switching oscillation current. Then, the amplitude-frequency features of HFCM current are extracted for condition monitoring. Finally, the overall insulation condition of three-phase line-end coils and the degree of asymmetric degradation are quantitatively evaluated by the frequency and amplitude features respectively. Experimental work was carried out and the results demonstrate the good performance of high sensitivity, good robustness, and non-contract safety.

Antisocial behavior has been linked to an increased tolerance of painful stimuli; however, there is evidence that pain behavior is multidetermined. The current study used pain measures from 3 different modalities (pain tolerance, pain ratings, electrocortical reactivity) and assessed triarchic traits of boldness and meanness to clarify the dispositional basis of associations between pain processing and antisocial behavior. High boldness was significantly associated with blunted early neural response to painful and nonpainful stimuli as well as increased pain tolerance. High meanness was associated with blunted elaborative processing of painful images, lower ratings of perceived pain for self and others, and increased pain tolerance. Meanness also accounted for variance shared between pain processing and antisocial behavior. Findings demonstrate that boldness and meanness contribute to pain processing in different ways and suggest that meanness may uniquely account for the association between blunted pain processing and antisocial behavior. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

A coastal sensitivity index (CSI) is a measure of the sensitivity of a coastline to its physical environment, which provides information useful for coastal management. Traditionally, a CSI is calculated as the mathematical aggregation of coastal sensitivity indicators, which may include factors such as coastal material, relief, and wave energy. The indicators differ depending on study area, but generally are assigned a score ranging from one to five in order of increasing sensitivity. These scores are then aggregated using either the square root of the product mean (the “classic” method) or the geometric mean. Both of these methods are limited by mathematical assumptions, lack of comparability, and the need for empirical validation. In this study, we applied an alternative nonparametric method of calculation, known as μ-statistics, to Canada's marine coasts to provide an improved measure of coastal sensitivity. μ-statistics, which offer a mathematically sound method of aggregating ordinal indicators, have a number of theoretical advantages over the classic and geometric mean methods. In practice, when applied to Canada’s marine coasts, we find that the μ-statistics method (1) compresses the mid-range variability in the resulting sensitivity index, (2) accentuates positive and negative distribution tails, and (3) minimizes propagated errors by 190% and 50%, respectively, compared with the classic and geometric mean methods. Additionally, the μ-statistics method has a theoretical foundation that relieves the necessity to empirically validate the aggregating assumptions and relies only on the assumptions inherent in the scoring method. μ-statistics thus provide a new, rigourous method for the calculation of coastal sensitivity indices when the underlying variables have ordinal scores.

High-gain nature of extended state observer (ESO), which forms an integral part of active disturbance rejection control (ADRC) technique, results in the following limitations: (1) Sensitivity to high-frequency measurement noise which limits closed-loop performance in practical applications. (2) Escalation of observer gains up-to a power $\bm{n+1}$ of observer bandwidth, which complicates numerical implementation when system order $(\bm{n})$ or observer bandwidth is large. To overcome these limitations, a low-power higher-order ESO (LHESO) is proposed in the present work for practical application of ADRC scheme in noisy environment. Moreover, a recently proposed cascade ESO (CESO), designed for noise suppression, is analyzed in the frequency-domain to reveal an underlying similarity with higher-order ESO, which is not reported in literature. Presented analysis justifies the performance improvement obtained over conventional ESO and provides a guideline for selecting the number of cascade levels based on the expected nature of disturbance. Case study performed on a DC-DC boost converter illustrates the practical advantages of proposed scheme over CESO in terms of improved immunity to high-frequency measurement noise, precise regulation in presence of time-varying disturbance, low observer gains that facilitate numerical implementation and ease of tuning due to a single observer parameter.

Triangle count is a critical parameter in mining relationships among people in social networks. However, directly publishing the findings obtained from triangle counts may bring potential privacy concern, which raises great challenges and opportunities for privacy-preserving triangle counting. In this paper, we choose to use differential privacy to protect triangle counting for large scale graphs. To reduce the large sensitivity caused in large graphs, we propose a novel graph projection method that can be used to obtain an upper bound for sensitivity in different distributions. In particular, we publish the triangle counts satisfying the node-differential privacy with two kinds of histograms: the triangle count distribution and the cumulative distribution. Moreover, we extend the research on privacy preserving triangle counting to one of its applications, the local clustering coefficient. Experimental results show that the cumulative distribution can fit the real statistical information better, and our proposed mechanism has achieved better accuracy for triangle counts while maintaining the requirement of differential privacy.

Indirect Field Oriented Control (IFOC) can provide an excellent dynamic response in Three Phase Induction Motor (TIM) drives and is widely used in the industry. Still, as a considerable part of the electrical energy is used to drive motors, intense research has been carried out to reduce the energy consumption of the induction motor drives and improve their efficiency. In this paper, a high-efficiency Smooth-IFOC (SIFOC) scheme is proposed and implemented experimentally with improved current controllers and the Loss Model Control (LMC) technique, which achieves up to 41% reduction in energy consumption compared to the traditional IFOC approach. The main contribution is the new Adaptive LMC (ALMC) control scheme, which includes two recursive adaptation algorithms to minimize the LMC technique sensitivity to the variation of the motor parameters. The algorithms are derived considering MRAS concept and both active (P) and reactive (Q) power to estimate the stator and rotor bandwidths, which are used to update the ALMC controller. The SIFOC-ALMC approach is verified experimentally, with up to 7.2% energy savings compared to SIFOC-LMC. Moreover, since the traditional IFOC controller is sensitive to rotor bandwidth variation, estimating this parameter improves the robustness of the SIFOC drive system.

Stiffened panels have been widely utilized in fuselages and wings as critical load-bearing components. These structures are prone to be damaged under long-term and extreme loads, and their health monitoring has been a common concern. The guided wave-based monitoring method is regarded as an efficient approach to detect the damage in stiffened plates because of its wide monitoring range and high sensitivity to micro-damage. Efficient simulation of wave propagation can theoretically demonstrate the detection mechanism of the method. In this study, a Time-Domain Spectral Finite Element Method (TD-SFEM) is adopted to study the wavefield in stiffened plates, where continuous Absorbing Layers with Increasing Damping (ALID) strategy is proposed to circumvent the disturbance of reflected waves on boundaries. After the convergence analysis, the developed TD-SFEM with ALID is validated by the finite element method first. Then, wave scattering and the influence of the stiffener are investigated in detail by comparing the results with the non-stiffened structure. Finally, the effects of the parameters of the stiffener, such as the height and width, on wave propagation are studied, respectively. The results illustrate that the proposed TD-SFEM with ALID is an efficient approach to study the wave propagation in the stiffened plate and can reveal the mechanism of influence of the stiffener. It is found that the height of the stiffener changes the interference of wavefield in the plate, while the effects of the width are mainly in wave scattering and mode conversion.

As a typical mechatronics system, the battery manufacturing chain becomes a hot research topic because it directly determines electrode quality, further affecting manufactured battery performance. Due to the complexity of battery manufacturing, an effective sensitivity analysis solution that could quantify variable importance or correlations and explore impact variables toward resulting the electrode quality is urgently needed. This article scrutinizes the effects of component parameters from the mixing stage on the manufactured results of Li-ion battery electrode via classification modeling. Specifically, an effective RUBoost-based ensemble learning framework is proposed to compensate for class imbalance issue and well classify three key quality indicators including the electronic conductivity, thickness, and half-cell capacity for both LiFePO $_4$- and Li$_4$ Ti$_5$O$_{12}$-based electrode. Experimental results reveal that the proposed models could well handle the class imbalance issues and accurately classify/predict the qualities of the manufactured electrode. Moreover, the importance weights of variables and the correlations of variable pairs could be effectively quantified. Due to the superiority in terms of accuracy, interpretability, and data-driven nature, the proposed ensemble learning approach could not only help to conduct reliable multiclassification of manufactured electrode but also benefit smarter battery manufacturing.

Introducing bond wire diagnosis for multichip IGBT modules is key to the health monitoring of modular multilevel converters (MMCs), which allows for improved field robustness, reliability, and reduced maintenance cost. This paper leverages the crosstalk phenomenon during switching transitions to detect the chip open-circuit faults caused by the bond wire lift-off using typical half-bridge IGBT modules in a multichip-parallel configuration. The cycle-controlled, non-intrusive measurement is conducted under normal operation, when the device under test is at off-state and its complementary switch is during switching transitions. Two specialized health sensitive parameters arising from the dynamic gate loop waveforms are identified and evaluated, including 1) the gate voltage VGE(t3) when the declining collector voltage reaches zero, and 2) the negative peak gate voltage VGE(t4). The sensitivity and stability of these two parameters are compared through theoretical analysis, circuit simulation and practical verification. The results show that VGE(t4) is more suitable for online monitoring, while VGE(t3) is more sensitive than VGE(t4). With managed complexity in gate drives, this proposed health awareness approach is feasible in the submodules of MMC applications, but it can also be used in other power converter topologies incorporating the half-bridge structure.

The Coronavirus Disease (COVID-19) was declared a pandemic disease by the World Health Organization (WHO), and it has not ended so far. Since the infection rate of the COVID-19 increases, the computational approach is needed to predict patients infected with COVID-19 in order to speed up the diagnosis time and minimize human error compared to conventional diagnoses. However, the number of negative data that is higher than positive data can result in a data imbalance situation that affects the classification performance, resulting in a bias in the model evaluation results. This study proposes a new oversampling technique, i.e., TRIM-SBR, to generate the minor class data for diagnosing patients infected with COVID-19. It is still challenging to develop the oversampling technique due to the data’s generalization issue. The proposed method is based on pruning by looking for specific minority areas while retaining data generalization, resulting in minority data seeds that serve as benchmarks in creating new synthesized data using bootstrap resampling techniques. Accuracy, Specificity, Sensitivity, F-measure, and AUC are used to evaluate classifier performance in data imbalance cases. The results show that the TRIM-SBR method provides the best performance compared to other oversampling techniques.

Recently, reconfigurable intelligent surface (RIS) has attracted continuous attention in wireless communications. Because the normal incidence condition of electromagnetic waves cannot always be satisfied in practical applications, the angular insensitivity in RISs has become an important issue. The angular sensitivity in RISs may lead to the failure of RIS-assisted wireless communication networks that rely on the reciprocity of wireless channels. In this work, an angle-insensitive 3-bit RIS meta-atom is proposed. By introducing metallic vias in the substrate of programmable meta-atoms, the interference induced by multiple reflections in the multilayered structure is restrained, and the decoupling between adjacent meta-atoms makes the metasurface insensitive to the incident angle. Hence the angular insensitivity can be achieved. An RIS is fabricated using the proposed angleinsensitive programmable meta-atom with metallic vias, which is capable of maintaining stable phase and amplitude responses at oblique incidences. Both simulated and measured results show stable angle performance. A maximum of 3150 phase range and eight digital coding states with 450 stable interval are obtained for wide incidence angles from 00 to 600. Finally, numerical simulations and experimental results of anomalous reflections are performed to verify the angular reciprocity of the proposed RIS, which is important in wireless communications.

With the objective to eliminate the input current sensor in a totem-pole boost power factor corrector (TPFC) for its low-cost design, a novel discretized sampling-based robust control scheme is proposed in this work. The proposed control methodology proves to be beneficial due to its ease of implementation and its ability to support high frequency operation, while being able to eliminate one sensor, and thus enhancing reliability and cost-effectiveness. In addition to that, detailed closed loop stability analysis is carried out for the controller in discrete domain to ascertain brisk dynamic operation when subjected to sudden load fluctuations. To establish the robustness of the proposed control scheme, a detailed sensitivity analysis of the closed loop performance metrics with respect to undesired changes and inherent uncertainty in system parameters is presented in this paper. A comparison with the state-of-the-art (SOA) methods is provided, and conclusive results in terms of better dynamic performance are also established. To verify and elaborate on the specifics of the proposed scheme, a detailed simulation study is conducted, and the results show 25% reduction in response time as compared to SOA approaches. A 500W boost PFC prototype is developed and tested with the proposed control scheme to evaluate the steady state and dynamic performance.

(Aim) To detect COVID-19 patients more accurately and more precisely, we proposed a novel artificial intelligence model. (Methods) We used previously proposed chest CT dataset containing four categories: COVID-19, community-acquired pneumonia, secondary pulmonary tuberculosis, and healthy subjects. First, we proposed a novel VGG-style base network (VSBN) as backbone network. Second, convolutional block attention module (CBAM) was introduced as attention module into our VSBN. Third, an improved multiple-way data augmentation method was used to resist overfitting of our AI model. In all, our model was dubbed as a 12-layer attention-based VGG-style network for COVID-19 (AVNC) (Results) This proposed AVNC achieved the sensitivity/precision/F1 per class all above 95%. Particularly, AVNC yielded a micro-averaged F1 score of 96.87%, which is higher than 11 state-of-the-art approaches. (Conclusion) This proposed AVNC is effective in recognizing COVID-19 diseases.

Cow behavior recognition systems support the assessment of cows’ condition by providing their behavior information. Accelerometers are particularly suited for a non-invasive solution for the development of these monitoring systems. They are cheap and simple in setting up and providing high-performance recognition when using machine learning algorithms. The activity complexity of animals brings challenges in real context applications because different behaviors may have similar acceleration data. The reason is that they contain similar gestures, for example, feeding and standing. In our previous work, we proposed a cows’ behavior classifier based on leg-mounted acceleration data. The distinguishing of similar behaviors, such as feeding and standing, is limited by the data. This study presents a new efficient cow behavior recognition system based on combining leg-mounted and collar-mounted accelerometers. Significantly, the acceleration data from these two sensors were synchronized. Therefore, we can substantially expand the amount of information for classification purposes. Our approach identifies four cow behaviors: walking, feeding, lying, and standing. Random Forest algorithm with our extracted features (root mean square, standard deviation, and mean) and 16-second data window (a sample/second) offer excellent performance when identifying all concerning behaviors: feeding (0.914 accuracy, 0.884 sensitivity, 0.956 positive predictive value), lying (0.998, 0.996, 1), standing (0.88, 0.928, 0.842), and walking (0.998, 0.996, 0.998). These performances are better than other existing works, especially in our experiments with free-grazing cows.

In this paper, a novel optical rotary sensor based on laser self-mixing interferometry is developed for the full-circle rotation measurement. The proposed sensor is convenient to use for it does not need any contact with the target or a cooperative mirror. A prototype is fabricated and tested. The measured results demonstrate a good performance compared with other optical rotary sensors, in terms of the 0.1 μrad resolution, the 2.33×10-4 linearity and 2 μrad stability over one hour. Additionally, the repeatability error is below 14.66 mrad under 9-group full-circle tests, which exhibits the potential to be instrumentalized reliably. Error analysis and limitation discussion have been also carried out. Although the accuracy needs further improvement compared with the best rotary sensor, this method has its unique advantages of high resolution, non-cooperative target sensing and electromagnetic immunity. Hence, the proposed optical rotary sensor provides a promising alternative in precise rotation measurement, tremor tracing and nano-motion monitoring.In this paper, a novel optical rotary sensor based on laser self-mixing interferometry is developed for the full-circle rotation measurement. The proposed sensor is convenient to use for it does not need any contact with the target or a cooperative mirror. A prototype is fabricated and tested. The measured results demonstrate a good performance compared with other optical rotary sensors, in terms of the 0.1 μrad resolution, the 2.33×10-4 linearity and 2 μrad stability over one hour. Additionally, the repeatability error is below 14.66 mrad under 9-group full-circle tests, which exhibits the potential to be instrumentalized reliably. Error analysis and limitation discussion have been also carried out. Although the accuracy needs further improvement compared with the best rotary sensor, this method has its unique advantages of high resolution, non-cooperative target sensing and electromagnetic immunity. Hence, the proposed optical rotary sensor provides a promising alternative in precise rotation measurement, tremor tracing and nano-motion monitoring.

High voltage DC (HVDC) grids have raised high-speed operation and high reliability requirement for relay protection. This paper aims at proposing a protection scheme with high operation speed, high sensitivity, and high reliability. Firstly, the symbolic expressions of the line-mode fault component traveling wave in case of the internal and external faults are derived, which consist of the traveling wave propagation term and the DC line boundary term. It is theoretically demonstrated that (i) the index of the traveling wave propagation term in case of internal faults is greater than that for the external faults, and (ii) the index is independent of fault impedance. Secondly, the Levenberg-Marquardt (LM) algorithm is introduced to extract the index and an index-based non-unit protection method as well as the protection scheme is proposed. The proposed method is theoretically robust and independent of fault impedance and fault type. In the validation, the fitting results have indicated that the symbolic expressions are correct and the extracted indices are effective to characterize the location of the faults. Numerous fault cases of different fault distances, fault impedances, and fault types have demonstrated that the proposed protection scheme has high sensitivity, high operation speed, and high reliability.

In real-life applications, monotonic classification is a widespread task, where the improvement of a particular input value cannot result in an inferior output. A common drawback of the existing algorithms for monotonic classification is their sensitivity to noise data which particularly refer to monotonicity violations in the monotonic circumstance. Motivated by weakening the impact of noises, the Fuzzy Monotonic K-Nearest Neighbor (FMKNN) is proposed in this paper, which constructs monotonic classifiers by taking advantage of the fuzzy dominance relation between a pair of instances, especially that between incomparable instances for the first time. Through tuning the thresholds of fuzzy dominance relation degrees, FMKNN intends to decrease the disturbance caused by noises which considerably affect the selection range of the K-Nearest Neighbors in different extent. The experimental results show that the best average improvement degrees of FMKNN in terms of the KNN-based and non-KNN-based classifiers on all the involved datasets arrive at 28%, 11% and 29% with respect to ACCU, MAE and NMI, respectively, which demonstrates the superiority of our proposed FMKNN over other state-of-the-art monotonic classifiers including the Monotonic Fuzzy K-Nearest Neighbor (MFKNN) which disperses the impact of noise data by converting crisp class labels into class membership vectors.

Personalized mobile healthcare integrated with various wearable devices has become a significant area of interest in the present era. In the current research work, a flexible, wearable and disposable paper-based continuous skin temperature monitoring sensor for early medical prognosis and accurate diagnosis of body temperature-related ailments, such as COVID-19, is proposed. Conventional screen-printing and drop-casting techniques were used to fabricate the proposed sensor using MWCNTs as the sensing material and paper as the substrate. The linearity, stability, repeatability and durability of the sensors were tested from 29°C (room temperature) to 60°C. A thin sheet of PET was laminated over the sensor surface to ascertain its stability toward environmental effects and physical movements, and a response time of ~13 s and a recovery time of ~38 s with a sensitivity of -0.0685% °C-1 were recorded. The efficacy of the proposed sensor was ascertained by placing it at different body locations on a human subject and comparing it with a standard thermocouple and IR sensor. The sensor even helped to effectively distinguish minimal temperature variations between various regions of the body. Furthermore, the feasibility of the fabricated temperature sensor as a temperature-based tactile sensor for robotics/artificial skin applications and as a noncontact breath monitoring device for use in personalized healthcare monitoring applications was investigated.

This paper presents a novel configuration of the eddy current speed sensor to measure the rotating speed of iron rods and shafts up to 3000 rpm. The proposed eddy current speed sensor has an axial airgap structure with one excitation coil and two antiserially connected pick up coils. The speed sensor is mounted in the end shaft part region. Different solid iron materials for rotating shaft are considered in the measurements and calculations to evaluate solid iron material effect on the eddy current speed sensor performance. 2D and 3D finite element method is utilized for the performance analysis of the speed sensor. Also, a 2D analytical method is developed for parametric analysis. A copper rod is also used to compare the speed sensor with the rotating iron shaft and copper shaft. Finally, two thin copper discs with different diameters are mounted on the solid iron shaft and their influences on the eddy current speed sensor were evaluated and measured to increase sensitivity and decrease sensor dependency on the permeability of the solid iron shaft. The achieved nonlinearity errors are about 0.2%.

An accurate and reliable turbofan engine model which can describe its dynamic behavior within the full flight envelop and lifecycle plays a critical role in performance optimization, controller design and fault diagnosis. However, due to the performance differences caused by the tolerance of engine manufacturing and assembly, and performance degradation during continuously stringent environmental regulations, the model accuracy is severely reduced. In this paper, an adaptive modification method of turbofan engine nonlinear component-level model (CLM) based on long short-term memory neural network (LSTM NN) and hybrid optimization algorithm is pro-posed. First, a dynamic compensator with a combined LSTM NN architecture is constructed to compensate for the initial error between the experimental data and CLM of a turbofan engine on health condition. Then, a sensitivity analysis approach based on based on the entropy coefficient and technique for order preference by similarity to an ideal solution integrated evaluation is developed to choose the unmeasurable health parameters to be adjusted. Finally, a parallel hybrid optimization algorithm is developed to complete the adaptive model modification when the performance degrades. The proposed method is verified on a military low-bypass twin-spool turbofan engine, and experimental results show the effectiveness of the proposed method.

Experiments aimed at searching for variations in the fine-structure constant α are based on spectroscopy of transitions in microscopic bound systems, such as atoms and ions, or resonances in optical cavities. The sensitivities of these systems to variations in α are typically on the order of unity and are fixed for a given system. For heavy atoms, highly charged ions and nuclear transitions, the sensitivity can be increased by benefiting from the relativistic effects and favorable arrangement of quantum states. This article proposes a new method for controlling the sensitivity factor of macroscopic physical systems. Specific concepts of optical cavities with tunable sensitivity to α are described. These systems show qualitatively different properties from those of previous studies of the sensitivity of macroscopic systems to variations in α, in which the sensitivity was found to be fixed and fundamentally limited to an order of unity. Although possible experimental constraints attainable with the specific optical cavity arrangements proposed in this article do not yet exceed the present best constraints on α variations, this work paves the way for developing new approaches to searching for variations in the fundamental constants of physics.

Detecting faces and identifying their emotional expressions are essential for social interaction. The importance of expressions has prompted suggestions that some emotionally-relevant facial features may be processed unconsciously, and it has been further suggested that this unconscious processing yields preferential access to awareness. Evidence for such preferential access has predominantly come from reaction times in the Breaking Continuous Flash Suppression (b-CFS) paradigm, which measures how long it takes different stimuli to overcome interocular suppression. For instance, it has been claimed that fearful expressions break through suppression faster than neutral expressions. However, in the b-CFS procedure, observers can decide how much information they receive before committing to a report, so although their responses may reflect differential detection sensitivity, they may also be influenced by differences in decision criteria, stimulus identification, and response production processes. Here, we employ a procedure that directly measures sensitivity for both face detection and identification of facial expressions, using predefined exposure durations. We apply diverse psychophysical approaches – forced-choice localisation, presence/absence detection, and staircase-based threshold measurement; across six experiments, we find that emotional expressions do not alter detection sensitivity to faces as they break through CFS. Our findings constrain the possible mechanisms underlying previous findings: faster reporting of emotional expressions’ breakthrough into awareness is unlikely to be due to the presence of emotion affecting perceptual sensitivity; the source of such effects is likely to reside in one of the many other processes that influence response times.

As a common phenomenon, overtaking behaviour is frequently observed on pedestrian flow, which not only reshapes pedestrian flow but also generates adverse impacts on pedestrian safety to some extent. Prior research focused on unidirectional pedestrian modelling, especially with overtaking behaviour, is limited. Moreover, pedestrian behaviour in the context of COVID-19 is rarely investigated. Inspired by the social force model, this paper proposes a dynamic sensitivity model for unidirectional pedestrian flow, which is able to describe the overtaking behaviour and analyse the potential impact of COVID-19 on pedestrian behaviour. In the proposed model, dynamic sensitivity and attention field of pedestrians are introduced to embody the effects of individual characteristics and surrounding environments on pedestrian behaviours. To calibrate the model and evaluate the effects of COVID-19 pandemic on pedestrian dynamics, real-life data collected by video recordings in Nanjing, China is used in this study. The simulation results indicate that the dynamic sensitivity model is able to reflect the variance of the adaptive velocity and route choice of overtaking pedestrians on unidirectional pedestrian flow. Our research findings show that the social distance during COVID-19 is higher than the value under normal conditions, and the majority of pedestrians tend to follow the suggested social distancing rules during COVID-19. Moreover, the overtaking pedestrians violate the suggested social distancing rules more frequently than the rest pedestrians.

This study investigates the adoption of proximity mobile payment services (PMPS) using, for the first time, an extended version of the decomposed theory of planned behaviour (DTPB) and considering both the linear and non-linear relationships depicted in the proposed model. Based on a two-stage hybrid analytic methodology, the proposed model was validated empirically using a sample of 951 participants. First, partial least squares (PLS) regression was used to identify the significant drivers of PMPS acceptance predictors. Artificial neural networks (ANN) were then used to rank the relative influence of the significant adoption drivers obtained in the previous step. The PLS results indicate that the extended DTPB provides a solid theoretical framework for studying the adoption of PMPS. The results of the PLS-ANN sensitivity analysis confirmed the PLS results regarding the importance of the determinants' of normative and controlling customers’ beliefs, although there were some contradictions concerning the determination of customer attitudes and behavioural intentions towards PMPS usage. The results are discussed and implications are offered.

Switched capacitor circuits exhibit dynamic topology and operate on clock phase dependent charge transfer. A circuit simulator that can directly compute branch charges by retaining capacitors and closed switch branches while excluding open switch branches based on clock is proposed in this work. Topological/graph-based formulation is used for charge level analyses of ideal switched capacitor circuits. The simulator supports time, frequency, noise and sensitivity analyses of switched capacitor circuits for any number of clock phases. The compact linear difference equation can compute time responses in a straightforward manner while frequency analysis is based on the impulse response of the circuit. Adjoint network concept is used to perform noise and sensitivity analyses for computing noise spectrum and differential derivatives respectively. The same formulation holds good for the adjoint equivalent network also since the network topology and incidence matrix almost remains same. Simulation results are presented for sample circuits to demonstrate the performance of the proposed simulator. Time and frequency responses have been compared with SWITCAP while noise and sensitivity responses with a commercial simulator.

The advancements in smart grid technologies had brought forth the prospect of self-healing distribution grid through intentional islanding, aided by the steadily rising penetration of inverter-based distributed generations (IBDGs). Adaptive protection is the key enabler for this resilient grid architecture. For cost-effectiveness, overcurrent relays (OCRs) with adaptive features had been proposed, often with the sensitivity problem due to low short-circuit current magnitude from the IBDG taken into consideration and largely addressed. However, apart from this widely discussed sensitivity problem, there is an underlying issue on selectivity of the OCR which is frequently disregarded when designing an adaptive overcurrent protection scheme for IBDG dominated microgrid. This selectivity problem is mainly caused by the current diversion to load during fault, which is often disregarded when performing OCR grading for a conventional grid. In this paper, this selectivity problem of the OCR is discussed in depth through a comparative study of conventional grid and a modern IBDG dominated grid. The coordination time interval margin violations problems are demonstrated through theoretical calculations and real-time hardware-in-the-loop experiments. This research aims to provide better insights into the selectivity problem as a step towards achieving a cost-effective yet reliable overcurrent-based adaptive protection for IBDG dominated microgrid.

This article focuses on global finite-time output feedback stabilization for uncertain nonlinear systems with unknown measurement sensitivity. The existence of the continuous measurement error resulting from limited accuracy of sensors invalidates the existing design strategies depending on the use of the precise output in the construction of an observer, which highlights the contribution of this article. Essentially, different from related works, we propose a new finite-time convergent observer by avoiding the use of the information on nonlinearities. By combining the homogeneous domination with the addition of a power integrator method, an output feedback controller composed of multiple nested sign functions is successfully developed. Finally, the effectiveness of the presented scheme is exhibited by a numerical example.

In order to reduce the couplings between the radial suspension forces and control currents caused by the asymmetry structure of the three-pole magnetic hybrid bearing (HMB) which driven by an inverter, a six-pole radial HMB is proposed. To improve the bearing capacity, reduce eddy current loss and volume of the six-pole radial HMB, an improved multi-objective particle swarm optimization (MOPSO) algorithm is proposed to optimize the parameters. At first, the structure and working principle of the six-pole radial HMB are introduced based on the equivalent magnetic circuit method. Then, the optimization objectives and optimization variables are determined and the number of multi-objective optimization parameters is reduced by sensitivity analysis. Next, the fitting function of suspension force is obtained by response surface method. Based on the theoretical analysis of the MOPSO, the linear decreasing inertia weight and the concept of hybridization are introduced to improve diversity and convergence of the MOPSO to get the Pareto optimal sets. Finally, simulation analysis and prototype experiment are carried out on the optimized six-pole radial HMB. The feasibility of the optimization method is verified by the results of simulation and experiment.

Path tracking plays an essential role in autonomous vehicles. To ensure tracking accuracy and improve tracking adaptability in different velocities, a path tracking strategy based on an improved model predictive control (MPC) method is presented in this research. First, a path tracking controller based on improved MPC based an online Updating algorithm is constructed. The update mechanism is triggered by using the cosine similarity, when the cosine similarity is lower than the predefined threshold value, making the state space and cost function of MPC match real-time conditions to rectify the sensitivity of MPC to vehicle speed. Additionally, to further enhance the controller's performance, a fuzzy control is employed to determine the horizon factor for optimizing the prediction horizon and control horizon online. Also, the weighting factors of the prediction horizon and control horizon are discussed to improve the adaptability at varying velocities. Next, the improved MPC controller is compared with the traditional MPC controller for a double lane change maneuver. The validation results demonstrate that the proposed strategy achieves good adaptability with satisfactory tracking accuracy at various velocities. Finally, the feasibility of the proposed strategy is verified in a real prototype vehicle test.

The deployment of connected, automated vehicles (CAVs) provides the opportunity to enhance the safety and efficiency of transportation systems. However, despite the rapid development of this technology, human-driven vehicles are predicted to predominate the vehicle fleet, compelling CAVs to be able to operate in a mixed traffic environment. The key to achieving a reliable and safe human-CAV collaboration in such environments is to characterize the interactions between the actors and incorporate the underlying decision-making mechanism of human drivers into CAVs' motion planning algorithms. Towards this goal and extending a previously developed game theoretical model, the present study proposes a decision-making dynamic to achieve more realistic models of human behavior when making conflicting maneuvers at intersections. A novel field test is conducted to extract the required modeling data directly from CAVs' perception system, facilitating the incorporation of the model into CAV navigation algorithms. Model validation and sensitivity analysis provided invaluable insights into the nature of human decisions and indicated that the proposed structure is robust to environmental uncertainties and can well capture the real-world behavior of human drivers in unprotected left-turn maneuvers. The derived knowledge can be directly used in CAV motion planning algorithms to provide the vehicle with more accurate predictions of human actions when operating in mixed traffic environments.

Every network contains different characteristics. In particular, microgrids have unique features compared to utility grids such as high resistance to reactance ratio(R/X). Consequently, both active and reactive current injection is likely to improve the dynamic voltage stability (DVS) of the islanded microgrids. Therefore, instead of injecting only reactive current, both active and reactive current is injected in the proposed voltage support(VS) strategy. Contrarily, without considering the distinctive characteristics of the network, other strategies with both active and reactive current injection provide fixed and uniform active and reactive current for all networks. To convey the distinctive features of network, voltage sensitivity subject to active and reactive current injection is used in the proposed VS strategy. As a consequence, unlike other strategies, the proposed strategy provides unique combination of active and reactive current for every network. The concept and derivation of the proposed strategy is described. Voltage sensitivity analysis is carried out to determine the sensitivity coefficients. The effectiveness of the proposed strategy is theoretically demonstrated and compared with other strategies. Case studies and result analysis on two islanded microgrids show that the proposed VS strategy for photovoltaic system is capable of enhancing the DVS of islanded microgrids compared to other strategies.

This article presents an improved equivalent-input-disturbance (EID) approach to handle unknown disturbances and plant uncertainties. The disturbances and uncertainties are treated as a lumped disturbance in an EID-based control system. The effect of the lumped disturbance is compensated by an EID estimator. A constraint between design parameters and uncertainties is imposed on the design of the estimator. In addition, there are insufficient analyses of the influence of uncertainties on the control performance and the stability of the system. A new filter is devised for an improved EID estimator in this article to remove the constraint. This ensures that the sensitivity of the system to disturbances at low frequencies can be freely decreased. An analysis of the system reveals that uncertainties not only influence disturbance-rejection and reference-tracking performance but also affect system stability. A sufficient stability criterion is derived with consideration of uncertainties. The validity of the presented method is demonstrated by simulation and experimental results.

Early detection of driver mental fatigue is one of the active areas of research in smart and intelligent vehicles. There are various methods, based on measuring the physiological characteristics of the driver utilising sensors and computer vision, proposed in the literature. In general, driver behaviour is unpredictable that can suddenly change the nature of driving and dynamics under mental fatigue. This results in sudden variations in driver body posture and head movement, with consequent inattentive behaviour that can end in fatal accidents and crashes. In the process of delineating the different driving patterns of driver states while active or influenced by mental fatigue, this paper contributes to advancing direct measurement approaches. In the novel approach proposed in this paper, driver mental fatigue and drowsiness are measured by monitoring driver's head posture motions using XSENS motion capture system. The experiments were conducted on 15 healthy subjects on a MATHWORKS driver-in-loop (DIL) simulator, interfaced with Unreal Engine 4 studio. A new modified bidirectional long short-term memory deep neural network, based on a rectified linear unit layer, was designed, trained and tested on 3D time-series head angular acceleration data for sequence-to-sequence classification. The results showed that the proposed classifier outperformed state-of-art approaches and conventional machine learning tools, and successfully recognised driver's active, fatigue and transition states, with overall training accuracy of 99.2%, sensitivity of 97.54%, precision and F1 scores of 97.38% and 97.46%, respectively. The limitations of the current work and directions for future work are also explored.