Search Results (17)

Against the backdrop of global low-carbon transition, the integrated development of electricity and carbon markets demands higher efficiency in the optimal operation of virtual power plants (VPPs) and distribution networks, yet conventional trading mechanisms face limitations such as inadequate recognition of differentiated contributions and inequitable benefit allocation. To address these challenges, this paper proposes a collaborative optimal trading mechanism for VPP clusters and distribution networks in an electricity–carbon coupled market environment by first establishing a joint operation framework to systematically coordinate multi-agent interactions, then developing a bi-level optimization model where the upper level formulates peer-to-peer (P2P) trading plans for electrical energy and carbon allowances through cooperative gaming among VPPs while the lower level optimizes distribution network power flow and feeds back the electro-carbon comprehensive price (EACP). By introducing an asymmetric Nash bargaining model for fair benefit distribution and employing the Alternating Direction Method of Multipliers (ADMM) for efficient computation, case studies demonstrate that the proposed method overcomes traditional models’ shortcomings in contribution evaluation and profit allocation, achieving 2794.8 units in cost savings for VPP clusters while enhancing cooperation stability and ensuring secure, economical distribution network operation, thereby providing a universal technical pathway for the synergistic advancement of global electricity and carbon markets. Full article

In the contemporary global educational environment, the automatic assessment of students’ online engagement has garnered widespread attention. A substantial number of studies have demonstrated that facial expressions are a crucial indicator for measuring engagement. However, due to the asymmetry inherent in facial expressions and the varying degrees of deviation of students’ faces from a camera, significant challenges have been posed to accurate emotion recognition in the online learning environment. To address these challenges, this work proposes a novel VGG-SwishNet model, which is based on the VGG-16 model and aims to enhance the recognition ability of asymmetric facial expressions, thereby improving the reliability of student engagement assessment in online education. The Swish activation function is introduced into the model due to its smoothness and self-gating mechanism. Its smoothness aids in stabilizing gradient updates during backpropagation and facilitates better handling of minor variations in input data. This enables the model to more effectively capture subtle differences and asymmetric variations in facial expressions. Additionally, the self-gating mechanism allows the function to automatically adjust its degree of nonlinearity. This helps the model to learn more effective asymmetric feature representations and mitigates the vanishing gradient problem to some extent. Subsequently, this model was applied to the assessment of engagement and provided a visualization of the results. In terms of performance, the proposed method achieved high recognition accuracy on the JAFFE, KDEF, and CK+ datasets. Specifically, under 80–20% and 10-fold cross-validation (CV) scenarios, the recognition accuracy exceeded 95%. According to the obtained results, the proposed approach demonstrates higher accuracy and robust stability. Full article

Face verification and identification traditionally follow a symmetric matching approach, where the same model (e.g., ResNet-50 vs. ResNet-50) generates embeddings for both gallery and query images, ensuring compatibility. However, real-world scenarios often demand asymmetric matching, especially when query devices have limited computational resources or employ heterogeneous models (e.g., ResNet-50 vs. SwinTransformer). This asymmetry can degrade face recognition performance due to incompatibility between embeddings from different models. To tackle this asymmetric face recognition problem, we introduce the Learnable Anchor Embedding (LAE) model, which features two key innovations: the Shared Learnable Anchor and a Light Cross-Attention Mechanism. The Shared Learnable Anchor is a dynamic attractor, aligning heterogeneous gallery and query embeddings within a unified embedding space. The Light Cross-Attention Mechanism complements this alignment process by reweighting embeddings relative to the anchor, efficiently refining their alignment within the unified space. Extensive evaluations of several facial benchmark datasets demonstrate LAE’s superior performance, particularly in asymmetric settings. Its robustness and scalability make it an effective solution for real-world applications such as edge-device authentication, cross-platform verification, and environments with resource constraints. Full article

Makeup modifies facial textures and colors, impacting the precision of face anti-spoofing systems. Many individuals opt for light makeup in their daily lives, which generally does not hinder face identity recognition. However, current research in face anti-spoofing often neglects the influence of light makeup on facial feature recognition, notably the absence of publicly accessible datasets featuring light makeup faces. If these instances are incorrectly flagged as fraudulent by face anti-spoofing systems, it could lead to user inconvenience. In response, we develop a face anti-spoofing database that includes light makeup faces and establishes a criterion for determining light makeup to select appropriate data. Building on this foundation, we assess multiple established face anti-spoofing algorithms using the newly created database. Our findings reveal that the majority of these algorithms experience a decrease in performance when faced with light makeup faces. Consequently, this paper introduces a general face anti-spoofing algorithm specifically designed for light makeup faces, which includes a makeup augmentation module, a batch channel normalization module, a backbone network updated via the Exponential Moving Average (EMA) method, an asymmetric virtual triplet loss module, and a nearest neighbor supervised contrastive module. The experimental outcomes confirm that the proposed algorithm exhibits superior detection capabilities when handling light makeup faces. Full article

Facial expression recognition plays an increasingly important role in daily life, and it is used in several areas of human–computer interaction, such as robotics, assisted driving, and intelligent tutoring systems. However, the current mainstream methods are based on the whole face, and do not consider the existence of expression asymmetry between the left and right half-face. Hence, the accuracy of facial expression recognition needs to be improved. In this paper, we propose a half-face self-attention weighted approach called HSAW. Using statistical analysis and computer vision techniques, we found that the left half-face contains richer expression features than the right half-face. Specifically, we employed a self-attention mechanism to assign different weights to the left and right halves of the face. These weights are combined with convolutional neural network features for improved facial expression recognition. Furthermore, to attack the presence of uncertain categories in the dataset, we introduce adaptive re-labeling module, which can improve the recognition accuracy. Extensive experiments conducted on the FER2013 and RAF datasets have verified the effectiveness of the proposed method, which utilizes fewer parameters. Full article

A novel chitosan (CS) functionalized optical fiber sensor with a bullet-shaped hollow cavity was proposed in this work for the trace concentration of Pb²⁺ ion detection in the water environment. The sensor is an optical fiber Mach–Zehnder interferometer (MZI), which consists of a sequentially spliced bullet-shaped hollow-core fiber (HCF), thin-core fiber, and another piece of spliced bullet-shaped HCF. The hollow-core fiber is caused to collapse by adjusting the amount of discharge to form a tapered hollow cavity with asymmetric end faces. The bullet-like hollow cavities act as beam expanders and couplers for optical fiber sensors, which were symmetrically spliced at both ends of a section of thin core fiber. The simulation and experiments show that the bullet-like hollow-core tapered cavity excites more cladding modes and is more sensitive to variation in the external environment than the planar and spherical cavities. The ion-imprinted chitosan (IIP-CS) film was fabricated with Pb²⁺ ion as a template and uniformly coated on the surface for specific recognition of Pb²⁺. Experimental verification confirms that the developed sensor can achieve high-sensitivity Pb²⁺ ion detection, with a sensitivity of up to −12.68 pm/ppm and a minimum Pb²⁺ ion detection concentration of 5.44 ppb Meanwhile, the sensor shows excellent selectivity, repeatability, and stability in the ion detection process, which has huge potential in the direction of heavy metal ion detection in the future. Full article

Occlusion or posture change of the face in natural scenes has typical asymmetry; however, an asymmetric face plays a key part in the lack of information available for facial expression recognition. To solve the problem of low accuracy of asymmetric facial expression recognition, this paper proposes a fusion of channel global features and a spatial local information expression recognition network called the “Channel–Spatial Integration Network” (CSINet). First, to extract the underlying detail information and deepen the network, the attention residual module with a redundant information filtering function is designed, and the backbone feature-extraction network is constituted by module stacking. Second, considering the loss of information in the local key area of face occlusion, the channel–spatial fusion structure is constructed, and the channel features and spatial features are combined to enhance the accuracy of occluded facial recognition. Finally, before the full connection layer, more local spatial information is embedded into the global channel information to capture the relationship between different channel–spatial targets, which improves the accuracy of feature expression. Experimental results on the natural scene facial expression data sets RAF-DB and FERPlus show that the recognition accuracies of the modeling approach proposed in this paper are 89.67% and 90.83%, which are 13.24% and 11.52% higher than that of the baseline network ResNet50, respectively. Compared with the latest facial expression recognition methods such as CVT, PACVT, etc., the method in this paper obtains better evaluation results of masked facial expression recognition, which provides certain theoretical and technical references for daily facial emotion analysis and human–computer interaction applications. Full article

Next-generation advanced driver-assistance systems (ADASs) are a promising direction for intelligent transportation systems. To achieve intelligent security monitoring, it is imperative that vehicles possess the ability to accurately comprehend driver maneuvers amidst diverse driver behaviors and complex driving scenarios. Existing CNN-based and transformer-based driver maneuver recognition methods face challenges in effectively capturing global and local features across temporal and spatial dimensions. This paper proposes a Spatial–Temporal Joint Attention Network (STA-Net) to realize high-efficient temporal and spatial feature extractions in driver maneuver recognition. First, we introduce a two-stream architecture for a concurrent analysis of in-cabin driver behaviors and out-cabin environmental information. Second, we propose a Multi-Scale Transposed Attention (MSTA) module and Multi-Scale Feedforward Network (MSFN) to extract features at multiple scales, addressing receptive field inadequacies and combining high-level and low-level information. Third, to address the information redundancy in multi-scale features, we propose a Cross-Spatial Attention Module (CSAM) and Multi-Scale Cross-Spatial Fusion Module (MCFM) to select essential features. Additionally, we introduce an asymmetric loss function to effectively tackle the issue of sample imbalance across diverse categories of driving maneuvers. The proposed method demonstrates a remarkable accuracy of 90.97% and an F1 score of 89.37% on the Brain4Cars dataset, surpassing the performance of the methods compared. These results substantiate the fact that our approach effectively enhances driver maneuver recognition. Full article

Ear images are easy to capture, and ear features are relatively stable and can be used for identification. The ear images are all asymmetric, and the asymmetry of the ear images collected in the unconstrained environment will be more pronounced, increasing the recognition difficulty. Most recognition methods based on hand-crafted features perform poorly in terms of recognition performance in the face of ear databases that vary significantly in terms of illumination, angle, occlusion, and background. This paper proposes a feature fusion human ear recognition method based on channel features and dynamic convolution (CFDCNet). Based on the DenseNet-121 model, the ear features are first extracted adaptively by dynamic convolution (DY_Conv), which makes the ear features of the same class of samples more aggregated and different types of samples more dispersed, enhancing the robustness of the ear feature representation. Then, by introducing an efficient channel attention mechanism (ECA), the weights of important ear features are increased and invalid features are suppressed. Finally, we use the Max pooling operation to reduce the number of parameters and computations, retain the main ear features, and improve the model’s generalization ability. We performed simulations on the AMI and AWE human ear datasets, achieving 99.70% and 72.70% of Rank-1 (R1) recognition accuracy, respectively. The recognition performance of this method is significantly better than that of the DenseNet-121 model and most existing human ear recognition methods. Full article

The chirality of biopolymers and its emergence from the racemic prebiotic world is one of the key mysteries of science. There are many versions on how the total chiral balance breaking occurred, but they all face an insoluble challenge—the impossibility of a total shift of the chiral balance towards the formation of biopolymers based only on D-sugars and L-amino acids. A possible solution to this problem lies in the asymmetric autocatalysis on chiral crystals. Since the reaction is heterogeneous, it is important to study the features of adsorption on the surface of crystals. In this paper, the adsorption of limonene, α-pinene, and menthol enantiomers on γ-glycine and CsCuCl₃ crystals was studied. Single-crystal X-ray crystallography, SEM, and porosimetry were used as auxiliary methods. The t-test was used to determine the reliability of chiral recognition. It was shown that both crystals were capable of chiral recognition at high coverages. The mechanism of supramolecular chiral recognition was identical to that of the chiral crystals studied previously. However, neither γ-glycine nor CsCuCl₃ showed chiral recognition with respect to all enantiomers. In fact, γ-glycine crystals showed recognition for limonene enantiomers, and very high recognition in the case of menthol enantiomers. CsCuCl₃ crystals showed the capability to recognize enantiomers of α-pinenes only. This led to the conclusion that the recognition of enantiomers by a supramolecular chiral surface is not universal. Full article

A consortium system can leverage information to improve workflows, accountability, and transparency through setting up a backbone for these cross-company and cross-discipline solutions, which make it become a hot spot of market application. Users of a consortium system may register and log in different target domains to get the access authentications, so how to access resources in different domains efficiently to avoid the trust-island problem is a big challenge. Cross-domain authentication is a kind of technology that breaks trust islands and enables users to access resources and services in different domains with the same credentials, which reduces service costs for all parties. Aiming at the problems of traditional cross-domain authentication, such as complex certificate management, low authentication efficiency, and being unable to prevent the attack users’ accounts, a cross-domain authentication protocol based on face recognition is proposed in this paper. The protocol makes use of the decentralized and distributed characteristics of the consortium chain to ensure the reliable transmission of data between participants without trust relationships, and achieves biometric authentication to further solve the problem of account attack by applying a deep-learning face-recognition model. An asymmetric encryption algorithm is used to encrypt and store the face feature codes on the chain to ensure the privacy of the user’s face features. Finally, through security analysis, it is proved that the proposed protocol can effectively prevent a man-in-the-middle attack, a replay attack, an account attack, an internal attack, and other attacks, and mutual security authentication between different domains can be realized with the protocol. Full article

The emergence of the Internet of Things (IoT) and the tactile internet presents high-quality connectivity strengthened by next-generation networking to cover a vast array of smart systems. Quantum computing is another powerful enabler of the next technological revolution, which will improve the world tremendously, and it will continue to grow to cover an extensive array of important functions, in addition to it receiving recently great interest in the scientific scene. Because quantum computers have the potential to overcome various issues related to traditional computing, major worldwide technical corporations are investing competitively in them. However, along with its novel potential, quantum computing is introducing threats to cybersecurity algorithms, as quantum computers are able to decipher many complex mathematical problems that classical computers cannot. This research paper proposes a robust and performance-effective lattice-driven cryptosystem in the context of face recognition that provides lightweight intelligent bio-latticed cryptography, which will aid in overcoming the cybersecurity challenges of smart world applications in the pre- and post-quantum era and with sixth-generation (6G) networks. Since facial features are symmetrically used to generate encryption keys on the fly without sending or storing private data, our proposal has the valuable attribute of dramatically combining symmetric and asymmetric cryptography operations in the proposed cryptosystem. Implementation-based evaluation results prove that the proposed protocol maintains high-performance in the context of delay, energy consumption, throughput and stability on cellular network topology in classical Narrowband-Internet of Things (NB-IoT) mode. Full article

With the improved hardware storage capabilities and the rapid development of artificial intelligence image recognition technology, information is becoming image-oriented. Increasingly sensitive image data needs to be processed. When facing a large amount of real-time sensitive image data encryption and decryption, ensuring both the speed and the security is an urgent demand. This paper proposes an original triple-hybrid encryption system for a real-time sensitive image acquisition chip. This encryption system optimizes the symmetric encryption algorithm AES, asymmetric encryption algorithm ECC, and chip authentication algorithm PUF in pursuit of security, calculation speed, and to ensure that it is lightweight. The three optimized algorithms are further mixed and reused on the circuit level, to ensure mutual protection while making full use of their advantages. Apart from sensitive image protection at the algorithm level, the image chip itself is also protected by an innovative PUF chip authentication method that prevents it from being tampered with and copied. Triple-hybrid encryption system hardware implementation achieves a frequency of 132.5 MHz under the Virtex-5 FPGA with an area of 2834 Slices; with Virtex-7 FPGA, it reaches a frequency of 137.6 MHz with an area of 2716 Slices. The system is also implemented on SMIC 40 nm ASIC, and the clock frequency reaches 480 MHz and the area is 94,812.4 $\mathsf{\mu }$m${}^2$. In terms of computing speed, the peak image encryption speed is 6.15 Gb/s, which meets the real-time image encryption requirement. In terms of hardware resource usage, AES reduced the hardware area by 60.1% compared with the results in other literature, ECC reduced the hardware area by 43.4%, and the PUF hardware area decreased exponentially with the increase in information entropy. The implementation of the three algorithms is reasonable and cost-effective, and the mixture of algorithms does not increase the required capacity of the hardware resource. The triple-hybrid encryption system cooperates with the image acquisition subsystem, storage subsystem, and asynchronous clock subsystem through software control to realize a complete triple-hybrid encryption SoC chip solution, and was successfully taped-out under the SMIC 40 nm process with all constraints passed and a total area of 10.59 mm${}^2$. Full article

This paper analyses the contribution of residual network (ResNet) based convolutional neural network (CNN) architecture employed in two tasks related to plant phenotyping. Among the contemporary works for species recognition (SR) and infection detection of plants, the majority of them have performed experiments on balanced datasets and used accuracy as the evaluation parameter. However, this work used an imbalanced dataset having an unequal number of images, applied data augmentation to increase accuracy, organised data as multiple test cases and classes, and, most importantly, employed multiclass classifier evaluation parameters useful for asymmetric class distribution. Additionally, the work addresses typical issues faced such as selecting the size of the dataset, depth of classifiers, training time needed, and analysing the classifier’s performance if various test cases are deployed. In this work, ResNet 20 (V2) architecture has performed significantly well in the tasks of Species Recognition (SR) and Identification of Healthy and Infected Leaves (IHIL) with a Precision of 91.84% and 84.00%, Recall of 91.67% and 83.14% and F1 Score of 91.49% and 83.19%, respectively. Full article

This study set out to investigate whether and how aesthetic evaluations of different types of symmetric, as well as abstract vs. representational patterns are modulated by art expertise. To this end, we utilized abstract asymmetric, symmetric, and “broken” patterns slightly deviating from symmetry, as well as more representational patterns resembling faces (also symmetric or broken). While it has already been shown that symmetry preference decreases with art expertise, it was still unclear whether an already established relationship between art expertise and preference for abstract over representational art can be similarly found as a preference for abstract over representational patterns, as these are non-art objects. Nevertheless, we found profound differences in aesthetic preferences between art experts and laypersons. While art experts rated asymmetric patterns higher than laypersons, as expected, they rated face-like patterns lower than laypersons. Also, laypersons rated all other types of patterns higher than asymmetric patterns, while art experts rated the other patterns similar or lower than asymmetric patterns. We found this both for liking and for interest ratings. As no differences between art experts and laypersons were found regarding memory recognition of new and old patterns, this effect is not likely due to differences in memory performance. In sum, this study further extends our knowledge about the influence of art expertise on aesthetic appreciation. Full article