Unconstrained Conditions Research Articles

Stochastic inventory control models for single item replenishment with variable demand under constrained and unconstrained conditions

Stochastic inventory control models for single item replenishment with variable demand under constrained and unconstrained conditions

Pen-based vibrotactile feedback rendering of surface textures under unconstrained acquisition conditions

Haptic rendering of surface textures enhances user immersion of human–computer interaction. However, strict input conditions and measurement methods limit the diversity of rendering algorithms. In this regard, we propose a neural network-based approach for vibrotactile haptic rendering of surface textures under unconstrained acquisition conditions. The method first encodes the interactions based on human perception characteristics, and then utilizes an autoregressive-based model to learn a non-linear mapping between the encoded data and haptic features. The interactions consist of normal forces and sliding velocities, while the haptic features are time–frequency amplitude spectrograms by short-time Fourier transform of the accelerations corresponding to the interactions. Finally, a generative adversarial network is employed to convert the generated time–frequency amplitude spectrograms into the accelerations. The effectiveness of the proposed approach is confirmed through numerical calculations and subjective experiences. This approach enables the rendering of a wide range of vibrotactile data for surface textures under unconstrained acquisition conditions, achieving a high level of haptic realism.

Prediabetes detection in unconstrained conditions using wearable sensors

Prediabetes detection in unconstrained conditions using wearable sensors

Investigation of the energy release characteristics and damage of thermobaric explosive under unconstrained conditions

To investigate the energetic release attributes and damage potential of a specific thermobaric explosive at atmospheric pressure, we had employed a pressure testing system, high-speed camera system, and thermal imager to elucidate the impact of explosive mass on the energetic release characteristics. Our findings underscored that thermobaric explosive can significantly enhance the after-burning effect. We noted a discernible positive relationship among the magnitude of the explosive force, post-detonation combustion effects, and the inherent quality of the given explosive. In addition, the resultant overpressure from the shockwave, positive pressure-area impulse, and the duration of the positive pressure, all markedly exceeded those produced by TNT, exhibiting increases of 38.9 %, 51.48 %, and 7 %, respectively. To quantify their explosive potency, empirical formulae were derived to account for the shock wave parameters of thermobaric explosive. Under equivalent mass conditions, the peak thermal radiation flux per unit area from thermobaric explosive substantially exceeded that of TNT. When the PROBIT (probability unit) model and the overpressure-impulse criteria were utilized to ascertain the damage potential of the respective explosives on human targets and structures, it emerged that TBX imparted superior destructive effects. This analysis underpinned the foundational assessment concerning the blast hazard presented by TBX.

Physical properties and anisotropy of sandstone during freeze-thaw cycle under unidirectional constraint

To investigate the evolution of physical properties of sandstone under unidirectional constraint during freeze-thaw cycles, an experimental device was specifically designed. Unidirectional constraint freeze-thaw tests were performed on sandstone specimens. The study analyzed variations in the dry mass, saturated mass, and longitudinal wave velocity of the sandstone both before and after undergoing freeze-thaw cycles, as well as examining the evolution of resistivity throughout the process. Results revealed that an increase in the number of freeze-thaw cycles leads to a gradual increase in the saturated mass of sandstone, while its dry mass consistently decreases, irrespective of whether it is subjected to constraint or not. The change rates of both dry mass and saturated mass were found to be significantly lower under unidirectional constraint compared to that without constraint. With more freeze-thaw cycles, a decline in longitudinal wave velocity was noted. Under unconstrained conditions, no significant direction dependence in longitudinal wave velocity was detected. However, under unidirectional constraint, there was a smaller decrease in the longitudinal wave velocity along the direction of constraint compared to other directions. This indicates that constraint mitigates frost heave damage. In the temperature rise and maintenance stages, resistivity initially dropped, then increased prior to stabilizing at a constant value. Conversely, in temperature decrease and maintenance stages, resistivity first rose, then dipped before ultimately rising again. Temperature primarily influenced resistivity by affecting the ion movement velocity within pore water and the connectivity of the conductive network.

Effects of Speech Characteristics on Electroglottographic and Instrumental Acoustic Voice Analysis Metrics in Women With Structural Dysphonia Before and After Treatment.

Literature suggests a dependency of the acoustic metrics, smoothed cepstral peak prominence (CPPS) and harmonics-to-noise ratio (HNR), on human voice loudness and fundamental frequency (F0). Even though this has been explained with different oscillatory patterns of the vocal folds, so far, it has not been specifically investigated. In the present work, the influence of three elicitation levels, calibrated sound pressure level (SPL), F0 and vowel on the electroglottographic (EGG) and time-differentiated EGG (dEGG) metrics hybrid open quotient (OQ), dEGG OQ and peak dEGG, as well as on the acoustic metrics CPPS and HNR, was examined, and their suitability for voice assessment was evaluated. In a retrospective study, 29 women with a mean age of 25 years (± 8.9, range: 18-53) diagnosed with structural vocal fold pathologies were examined before and after voice therapy or phonosurgery. Both acoustic and EGG signals were recorded simultaneously during the phonation of the sustained vowels /ɑ/, /i/, and /u/ at three elicited levels of loudness (soft/comfortable/loud) and unconstrained F0 conditions. A linear mixed-model analysis showed a significant effect of elicitation effort levels on peak dEGG, HNR, and CPPS (all p < .01). Calibrated SPL significantly influenced HNR and CPPS (both p < .01). Furthermore, F0 had a significant effect on peak dEGG and CPPS (p < .0001). All metrics showed significant changes with regard to vowel (all p < .05). However, the treatment had no effect on the examined metrics, regardless of the treatment type (surgery vs. voice therapy). The value of the investigated metrics for voice assessment purposes when sampled without sufficient control of SPL and F0 is limited, in that they are significantly influenced by the phonatory context, be it speech or elicited sustained vowels. Future studies should explore the diagnostic value of new data collation approaches such as voice mapping, which take SPL and F0 effects into account.

De-occlusion and recognition of frontal face images: a comparative study of multiple imputation methods

AbstractIncreasingly, automatic face recognition algorithms have become necessary with the development and extensive use of face recognition technology, particularly in the era of machine learning and artificial intelligence. However, the presence of unconstrained environmental conditions degrades the quality of acquired face images and may deteriorate the performance of many classical face recognition algorithms. Due to this backdrop, many researchers have given considerable attention to image restoration and enhancement mechanisms, but with minimal focus on occlusion-related and multiple-constrained problems. Although occlusion robust face recognition modules, via sparse representation have been explored, they require a large number of features to achieve correct computations and to maximize robustness to occlusions. Therefore, such an approach may become deficient in the presence of random occlusions of relatively moderate magnitude. This study assesses the robustness of Principal Component Analysis and Singular Value Decomposition using Discrete Wavelet Transformation for preprocessing and city block distance for classification (DWT-PCA/SVD-L1) face recognition module to image degradations due to random occlusions of varying magnitudes (10% and 20%) in test images acquired with varying expressions. Numerical evaluation of the performance of the DWT-PCA/SVD-L1 face recognition module showed that the use of the de-occluded faces for recognition enhanced significantly the performance of the study recognition module at each level (10% and 20%) of occlusion. The algorithm attained the highest recognition rate of 85.94% and 78.65% at 10% and 20% occlusions respectively, when the MICE de-occluded face images were used for recognition. With the exception of Entropy where MICE de-occluded face images attained the highest average value, the MICE and RegEM result in images of similar quality as measured by their Absolute mean brightness error (AMBE) and peak signal to noise ratio (PSNR). The study therefore recommends MICE as a suitable imputation mechanism for de-occlusion of face images acquired under varying expressions.

Vein segmentation and visualization of upper and lower extremities using convolution neural network.

The study focused on developing a reliable real-time venous localization, identification, and visualization framework based upon deep learning (DL) self-parametrized Convolution Neural Network (CNN) algorithm for segmentation of the venous map for both lower and upper limb dataset acquired under unconstrained conditions using near-infrared (NIR) imaging setup, specifically to assist vascular surgeons during venipuncture, vascular surgeries, or Chronic Venous Disease (CVD) treatments. A portable image acquisition setup has been designed to collect venous data (upper and lower extremities) from 72 subjects. A manually annotated image dataset was used to train and compare the performance of existing well-known CNN-based architectures such as ResNet and VGGNet with self-parameterized U-Net, improving automated vein segmentation and visualization. Experimental results indicated that self-parameterized U-Net performs better at segmenting the unconstrained dataset in comparison with conventional CNN feature-based learning models, with a Dice score of 0.58 and displaying 96.7 % accuracy for real-time vein visualization, making it appropriate to locate veins in real-time under unconstrained conditions. Self-parameterized U-Net for vein segmentation and visualization has the potential to reduce risks associated with traditional venipuncture or CVD treatments by outperforming conventional CNN architectures, providing vascular assistance, and improving patient care and treatment outcomes.

Investigation of Crystallization Growth Characteristics of Mg(OH)2 Crystals under Unconstrained Conditions.

Utilizing MgO as the precursor and deionized water as the solvent, this study synthesized nanoparticles of Mg(OH)2 via hydrothermal methods, aiming to control its purity, particle size, and morphology by understanding its growth under non-uniform nucleation. Characterization of crystal morphology and structure was conducted through scanning electron microscopy and X-ray diffraction, while laser particle size detection assessed the secondary particle size distribution. The study focused on how MgO's hydrothermal process conditions influence Mg(OH)2 crystal growth, particularly through ion concentration and release rate adjustments to direct crystal growth facets. These adjustments shifted the dominant growth plane, enhancing the peak intensity ratio I001/I101 from 1.03 to 2.14, thereby reducing surface polarity and secondary aggregation of crystals. The study of the physicochemical properties of the same sample at different times revealed the pattern of crystal dissolution and recrystallization. A 2 h hydrothermal reaction notably altered the particle size distribution, with a decrease in particles sized 0.2~0.4 μm and an increase in those sized 0.4~0.6 μm, alongside new particles over 1 μm, indicating a shift toward uniformity through dissolution and recrystallization. Optimal conditions (6% magnesium oxide concentration, 160 °C, 2 h) led to the synthesis of highly dispersed, uniformly sized magnesium hydroxide, showcasing a simple, eco-friendly, and high-yield process.

Insight into single-helix intelligent shape memory polymer cables: modeling and optimization under finite sliding contact

This pioneering study focuses on the finite element analysis (FEA) of thermomechanical properties of shape memory polymer (SMP) wire ropes and their components under both small- and finite-sliding contact deformation. To validate the FEA, we need to validate both geometric modeling and non-linear material behavior. Owing to intricate geometry, as well as excessive wire interactions in the structure, this part is studied by simulating a 1 × 37 steel wire rope and then comparing it with existing experimental data. To evaluate the response of non-linear material behavior, we employ the available numerical results to model the thermomechanical property of an SMP rectangular bar under a uniaxial test and then verify both constrained and unconstrained recovery behavior. After rigorous validation, two configurations of 1 × 7 and 1 × 27 SMP cables are modeled based on the thermo-visco-hyperelastic constitutive framework for acrylate polymer systems. Upon exerting an axially tensile load on these 1 × 7 and 1 × 27 SMP wire ropes, the response of force and shape recovery, as well as the normal and shear stress distributions, are measured under constrained and unconstrained conditions. For a deeper physical understanding, the influences of different temperature rates (5 and 1 °C min−1), inter-wire sliding frictional coefficient (0.1–0.6), and multiple-shape programming on the stress-strain-temperature relations of these SMP cables are also investigated. Furthermore, based on optimizing two cable factors of diameter and helix angle, and using the design of experiments method, the specific energy of a 1 × 6 SMP cable is maximized. Under different thermomechanical loadings, this study tries to cast light on the remarkable features and possible potential applications of these newly developed SMP actuators which may foster unparalleled advancements in various industries.

A multi-featured expression recognition model incorporating attention mechanism and object detection structure for psychological problem diagnosis

Expression is the main method for judging the emotional state and psychological condition of the human body, and the prediction of changes in facial expressions can effectively determine the mental health of a person, thus avoiding serious psychological or psychiatric disorders due to early negligence. From a computer vision perspective, most researchers have focused on studying facial expression analysis, and in some cases, body posture is also considered. However their performance is more limited under unconstrained natural conditions, which requires more information to be used in human emotion analysis. In this paper, we design an Adaptive Multi-End Fusion Attention Mechanism suitable for extracting human body information based on the deep learning framework, depending on human expressions, postures and the environment they are in and add it to an object detection model to obtain the information we need from different regions of the human body and face and features of different sizes and use fusion networks for feature fusion and classification, and from different test methods to confirm that this fusion approach for expression recognition and prediction is feasible. This model achieves an average accuracy of 34.51 % in the Emotic contextual expression recognition dataset.

Cognitive effort detection for tele-robotic surgery via personalized pupil response modeling.

Gaze tracking and pupillometry are established proxies for cognitive load, giving insights into a user's mental effort. In tele-robotic surgery, knowing a user's cognitive load can inspire novel human-machine interaction designs, fostering contextual surgical assistance systems and personalized training programs. While pupillometry-based methods for estimating cognitive effort have been proposed, their application in surgery is limited by the pupil's sensitivity to brightness changes, which can mask pupil's response to cognitive load. Thus, methods considering pupil and brightness conditions are essential for detecting cognitive effort in unconstrained scenarios. To contend with this challenge, we introduce a personalized pupil response model integrating pupil and brightness-based features. Discrepancies between predicted and measured pupil diameter indicate dilations due to non-brightness-related sources, i.e., cognitive effort. Combined with gaze entropy, it can detect cognitive load using a random forest classifier. To test our model, we perform a user study with the da Vinci Research Kit, where 17 users perform pick-and-place tasks in addition to auditory tasks known to generate cognitive effort responses. We compare our method to two baselines (BCPD and CPD), demonstrating favorable performance in varying brightness conditions. Our method achieves an average true positive rate of 0.78, outperforming the baselines (0.57 and 0.64). We present a personalized brightness-aware model for cognitive effort detection able to operate under unconstrained brightness conditions, comparing favorably to competing approaches, contributing to the advancement of cognitive effort detection in tele-robotic surgery. Future work will consider alternative learning strategies, handling the difficult positive-unlabeled scenario in user studies, where only some positive and no negative events are reliably known.

Transformer-Augmented Network With Online Label Correction for Facial Expression Recognition

Facial expression recognition (FER) in the wild is extremely challenging due to occlusions, variant head poses under unconstrained conditions and incorrect annotations (e.g., label noise). In this paper, we aim to improve the performance of in-the-wild FER with Transformers and online label correction. Different from pure CNNs based methods, we propose a Transformer-augmented network (TAN) to dynamically capture the relationships within each facial patch and across the facial patches. Specifically, the TAN translates a number of facial patch images into a set of visual feature sequences by a backbone convolutional neural network. The intra-patch Transformer is subsequently utilized to capture the most discriminative features within each visual feature sequence. The position-disentangled attention mechanism of the intra-patch Transformer is proposed to better incorporate the positional information for feature sequences. Furthermore, we propose the inter-patch Transformer to model the dependencies across these feature sequences. More importantly, we present the online label correction (OLC) framework to correct suspicious hard labels and accumulate soft labels based on the predictions of the model, which strengthens the robustness of our model against label noise. We validate our method on several widely-used datasets (RAF-DB, FERPlus, AffectNet), realistic occlusion and pose variation datasets, and synthetic noisy datasets. Extensive experiments on these benchmarks demonstrate that the proposed method performs favorably against state-of-the-art methods. The source code will be made publicly available.

Advancements in Deep-Learning-Based Object Detection in Challenging Environments

This article focuses on object detection in challenging environments, where objects of interest need to be detected in images captured under unconstrained conditions. These environments can include outdoor scenes with varying lighting, weather conditions, and background clutter. Object detection in such scenarios is crucial for applications like autonomous driving, surveillance, and industrial production inspection. The paper explores existing techniques for object detection in challenging environments and proposes novel solutions to enhance its performance. One key aspect emphasized in the paper is the need for relevant datasets to validate models under unconstrained scenarios. While several datasets already exist, the research identifies gaps in specific situations and addresses them by proposing new datasets, such as the Indian Lane Dataset for autonomous vehicles. The proposed object detection framework leverages spatial information to detect objects in challenging environments, and its performance is evaluated against benchmark datasets and the newly proposed datasets. A real-world application demonstrates significant improvements in object detection performance in natural environments.

FG-AGR: Fine-Grained Associative Graph Representation for Facial Expression Recognition in the Wild

Facial expression recognition (FER) in the wild is challenging due to various unconstrained conditions, i.e., occlusions and head pose variations. Previous methods tend to improve the performance of facial expression recognition through resorting to holistic methods or coarse local-based methods, while ignoring the local fine-grained feature structure knowledge and the correlation between features. In this paper, we propose a Fine-Grained Association Graph Representation (FG-AGR) framework which can capture the local fine-grained facial expression representation. Firstly, an Adaptive Salient Region Induction (ASRI) is designed for adaptively highlighting the local saliency regions of facial expressions combined with spatial location information. Based on this, a Local Fine-grained Feature Extraction (LFFE) based on Visual Transformers is introduced to further extract fine but discriminative fine-grained features of saliency regions. Thirdly, an Adaptive Graph Association Reasoning (AGAR) based on Graph Convolutional Network is constructed to learn associated fine-grained feature combinations. Extensive experiments demonstrate that our FG-AGR achieves superior performance compared to the state-of-the-art methods with 90.81% on RAF-DB, 64.91% on AffectNet-7, 60.69% on AffectNet-8 and 91.09% on FERPlus.

Palm Vein Recognition Under Unconstrained and Weak-Cooperative Conditions

Palm Vein Recognition Under Unconstrained and Weak-Cooperative Conditions

An unconstrained palmprint region of interest extraction method based on lightweight networks.

Accurately extracting the Region of Interest (ROI) of a palm print was crucial for subsequent palm print recognition. However, under unconstrained environmental conditions, the user's palm posture and angle, as well as the background and lighting of the environment, were not controlled, making the extraction of the ROI of palm print a major challenge. In existing research methods, traditional ROI extraction methods relied on image segmentation and were difficult to apply to multiple datasets simultaneously under the aforementioned interference. However, deep learning-based methods typically did not consider the computational cost of the model and were difficult to apply to embedded devices. This article proposed a palm print ROI extraction method based on lightweight networks. Firstly, the YOLOv5-lite network was used to detect and preliminarily locate the palm, in order to eliminate most of the interference from complex backgrounds. Then, an improved UNet was used for keypoints detection. This network model reduced the number of parameters compared to the original UNet model, improved network performance, and accelerated network convergence. The output of this model combined Gaussian heatmap regression and direct regression and proposed a joint loss function based on JS loss and L2 loss for supervision. During the experiment, a mixed database consisting of 5 databases was used to meet the needs of practical applications. The results showed that the proposed method achieved an accuracy of 98.3% on the database, with an average detection time of only 28ms on the GPU, which was superior to other mainstream lightweight networks, and the model size was only 831k. In the open-set test, with a success rate of 93.4%, an average detection time of 5.95ms on the GPU, it was far ahead of the latest palm print ROI extraction algorithm and could be applied in practice.

Matching and optimization to minimize fuel consumption and NOx emission for a marine diesel engine with turbo-assisted exhaust gas recirculation

Exhaust gas recirculation (EGR) and two-stage turbocharging technology are widely used in marine diesel engines due to their advantages of reducing nitrogen oxides (NOx) emission and improving fuel economy respectively. The matching of EGR, two-stage turbocharging and diesel engine is significant to realize both advantages simultaneously. Turbo-assisted EGR (TA EGR) can achieve high EGR rate and lower fuel consumption due to a turbocharger driving EGR. In this study, a 1D model of the diesel engine with TA EGR coupling two-stage turbocharging system was established by GT-Power. A theoretical matching method was proposed based on the requirements of excess air coefficient and EGR rate. The matching laws of the coupling system were studied, and the preliminary matching results achieved good effects. A fully connected neural network was used as the optimization agent model of the 1D model, and the NSGA II algorithm was used to carry out the multi-parameter and multi-objective optimizing matching. Considering constrained and unconstrained conditions, independent optimizing matching was carried out under each single load, and the weighted brake specific fuel consumption (BSFC) and weighted NOx under all loads were taken as the target to carry out comprehensive optimizing matching. The results showed that the optimization performance is worse under constrained conditions, while TA EGR coupling adjustable two-stage turbocharging system can achieve comprehensive optimal BSFC and NOx, with weighted BSFC decreasing by 3.57% and weighted NOx decreasing by 75.28% compared with experimental results of the original engine.

Application of financial management in regional economic development based on VAR modeling

Abstract This paper constructs a vector autoregressive (VAR) model between the level of financial management and regional GDP. Through the Granger causality test, the panel data at the financial management level and regional economic phenomena are studied, and the empirical distributions in the stationary situation are given by combining the stochastic simulation method. The auxiliary regression equations are established separately for constrained and unconstrained conditions, and the test statistic is constructed to determine whether there is Granger causality between the variables. Finally, from the actual data, a one standard deviation shock is applied to LATS and LGDP, and a response model with a lag of 100 periods is chosen to obtain the impulse response of the level of financial management and regional economic growth. The results show that the impact of the regional economy on the level of financial management is zero in the first period and then increases continuously, reaching a maximum response of 0.0233 in the 49th period, which indicates that there is a bidirectional promotional effect between the level of financial management and the regional economy and that the effect is not very strong but lasts for a long time.

The Improved Method for Indoor 3D Pedestrian Positioning Based on Dual Foot-Mounted IMU System.

Micro-Electro-Mechanical System (MEMS) inertial sensors, characterized by their small size, low cost, and low power consumption, are commonly used in foot-mounted wearable pedestrian autonomous positioning systems. However, they also have drawbacks such as heading drift and poor repeatability. To address these issues, this paper proposes an improved pedestrian autonomous 3D positioning algorithm based on dual-foot motion characteristic constraints. Two sets of small-sized Inertial Measurement Units (IMU) are worn on the left and right feet of pedestrians to form an autonomous positioning system, each integrated with low-cost, low-power micro-inertial sensor chips. On the one hand, an improved adaptive zero-velocity detection algorithm is employed to enhance discrimination accuracy under different step-speed conditions. On the other hand, considering the dual-foot gait characteristics and the height difference feature during stair ascent and descent, horizontal position update algorithms based on dual-foot motion trajectory constraints and height update algorithms based on dual-foot height differences are, respectively, designed. These algorithms aim to re-correct the pedestrian position information updated at zero velocity in both horizontal and vertical directions. The experimental results indicate that in a laboratory environment, the 3D positioning error is reduced by 93.9% compared to unconstrained conditions. Simultaneously, the proposed approach enhances the accuracy, continuity, and repeatability of the foot-mounted IMU positioning system without the need for additional power consumption.