Performance In Real Applications Research Articles

Unsupervised Test-Time Adaptation Learning for Effective Hyperspectral Image Super-Resolution With Unknown Degeneration.

Fusing a low-resolution hyperspectral image (HSI) with a high-resolution (HR) multi-spectral image has provided an effective way for HSI super-resolution (SR). The key lies on inferring the posteriori of the latent (i.e., HR) HSI using an appropriate image prior and the likelihood determined by the degeneration between the latent HSI and the observed images. However, in scenarios with complex imaging environments and various imaging scenes, the prior of HSIs can be prohibitively complicated and the degeneration is often unknown, which causes it difficult to accurately infer the posteriori of each latent HSI. To tackle this problem, we present an unsupervised test-time adaptation learning (UTAL) framework for HSI SR under unknown degeneration. Instead of directly modeling the complicated image prior, it first implicitly learns a content-agnostic prior shared across different images through supervisedly pre-training a mutual-guiding fusion module on extensive synthetic data. Then, it adapts the shared prior to those private characteristics in the latent HSI for posteriori inference through unsupervisedly learning a self-guiding adaptation module and a degeneration estimation network on two observed images in the test phase. Such a two-stage learning scheme models the complicated image prior in a divide-and-conquer manner, which eases the modeling difficulty and improves the prior accuracy. Moreover, the unknown degeneration can be estimated properly. Both of these two advantages empower us to accurately infer the posteriori of the latent HSI, thereby increasing the generalization performance in real applications. Additionally, in order to further mitigate the over-fitting in coping with more challenging cases (e.g., degenerations in both spectral and spatial domains are unknown) and speed up, we propose to meta-train UTAL on extensive synthetic SR tasks and solve it using an alternative optimization strategy such that UTAL learns to produce good generalization performance in real challenging cases with a small number of gradient descent steps. To verify the efficacy of UTAL, we evaluate it on HSI SR tasks with different unknown degenerations as well as some other HSI restoration tasks (e.g., compressive sensing), and report strong results superior to that of existing competitors.

A smartphone-integrated ratiometric fluorescent platform based on europium (III)-functionalized metal-organic frameworks for quantitative and visual detection of tetracycline

Food safety and environmental pollution caused by tetracycline antibiotics (TCs) are of great concern for public health worldwide. To realize on-site, real-time, ultrasensitive visual detection of tetracycline is an urgent need. Herein, a ratiometric fluorescent probe has been constructed by grafting Cit-Eu3+ on the amino-silanes-modified metal–organic framework for the detection of tetracycline. Under exciting at 330 nm,the red emission at 617 nm of Eu3+ was significantly enhanced by the antenna effect upon adding tetracycline, while the intrinsic fluorescence quenching at 425 nm of the probe ascribes to the inner filter effect, resulting in a reversible signal response. Under optimum conditions, the probe exhibits a visualized fluorescence evolution from blue to red with a linear range of 0.1–60 μM, and a limit of detection as low as 24.6 nM. Furthermore, a test strip was further fabricated by dropping NH2-MIL(Al)@SiO2-Cit-Eu3+ on filter paper, which can be used for on-site of tetracycline conveniently by using a smartphone. Moreover, the proposed probe has also been successfully applied for TCs detection in spiked honey and tap water sample with satisfactory recoveries in the range from 91.21–102.97 %, demonstrating the potential real application performance. This the smart sensing platform lays a foundation for the rapid screening of TCs in food and environmental matrices.

A novel high sensitive, specificity duplex enzyme-activated differentiating probes PCR method for the SNP detection and differentiation of MS-H vaccine strains from wild-type Mycoplasma synoviae strains

Mycoplasma synoviae (MS) is a contagious pathogen that poses a significant threat to the poultry industry. Detection plays an important role in the prevention and control of MS, particularly in differentiating between wild-type MS and live attenuated vaccine strains for vaccination selection and culling of animals with wild-type only. The live attenuated ts+ vaccine strain MS-H is recognized as the most effective and widely used vaccine. In this study, we have developed a method called double enzyme-activated differentiation probes PCR (DEA-probes PCR) for the differentiation of MS-H vaccine strain from wild-type strain by targeting the single nucleotide polymorphism (SNP) of the 367th nucleotide in the Obg gene sequence. We developed 2 modified probes with the ribonucleotide insert. When the probe perfectly complements with the target, the ribonuclease H2 (RNase H2) will cleave the ribonucleotide, resulting in the generation of fluorescent signal. With a detection limit of 5.8 copies/µL, the DEA-probes PCR method demonstrates 100% specificity in distinguishing wild-type MS from MS-H strains in 1 h. The method demonstrated great performance in real application of 100 superior palate cleft swab samples from chickens in poultry farms. Twenty-eight samples were detected as MS positive, consistent with the results of the Chinese industry standard method. Additionally, our method was able to distinguish 19 wild-type MS strains from 9 MS-H vaccine strains. The DEA-probes PCR method is rapid, specific and sensitive for SNP detection, overcoming the misidentification in MS detection and differentiation. It can be also applied to the differentiation of infected from vaccinated animals (DIVA) for other pathogens.

SFDA-CD: A Source-Free Unsupervised Domain Adaptation for VHR Image Change Detection

Deep models may have disappointing performance in real applications due to the domain shifts in data distributions between the source and target domain. Although a few unsupervised domain adaptation methods have been proposed to make the pre-train models effective on target domain datasets, constraints like data privacy, security, and transmission limits restrict access to VHR remote sensing images, making existing unsupervised domain adaptation methods almost ineffective in specific change detection areas. Therefore, we propose a source-free unsupervised domain adaptation change detection structure to complete specific change detection tasks, using only the pre-trained source model and unlabelled target data. The GAN-based source generation component is designed to generate synthetic source data, which, to some extent, reflects the distribution of the source domain. Moreover, these data can be utilised in model knowledge transfer. The model adaptation component facilitates knowledge transfer between models by minimising the differences between deep features, using AAM (Attention Adaptation Module) to extract the difference between high-level features, meanwhile we proposed ISM (Intra-domain Self-supervised Module) to train target model in a self-supervised strategy in order to improve the knowledge adaptation. Our SFDA-CD framework demonstrates superior accuracy over existing unsupervised domain adaptation change detection methods, which has 0.6% cIoU and 1.5% F1 score up in cross-regional tasks and 1.4% cIoU and 1.9% F1 score up in cross-scenario tasks, proving that it can effectively reduce the domain shift between the source and target domains even without access to source data. Additionally, it can facilitate knowledge transfer from the source model to the target model.

Self-Training Based Few-Shot Node Classification by Knowledge Distillation

Self-training based few-shot node classification (FSNC) methods have shown excellent performance in real applications, but they cannot make the full use of the information in the base set and are easily affected by the quality of pseudo-labels. To address these issues, this paper proposes a new self-training FSNC method by involving the representation distillation and the pseudo-label distillation. Specifically, the representation distillation includes two knowledge distillation methods (i.e., the local representation distillation and the global representation distillation) to transfer the information in the base set to the novel set. The pseudo-label distillation is designed to conduct knowledge distillation on the pseudo-labels to improve their quality. Experimental results showed that our method achieves supreme performance, compared with state-of-the-art methods. Our code and a comprehensive theoretical version are available at https://github.com/zongqianwu/KD-FSNC.

Study of the Errors in Interpolated Fast Fourier Transform for Interferometric Applications

Frequency estimation is often the basis of various measurement techniques, among which optical distance measurement stands out. One of the most used techniques is interpolated fast Fourier transform due to its simplicity, combined with good performance. In this work, we study the limits of this technique in the case of real signals, with reference to a particular interferometric technique known as self-mixing interferometry. The aim of this research is the better understanding of frequency estimation performances in real applications, together with guidance on how to improve them in specific optical measurement techniques. An optical rangefinder, based on self-mixing interferometry, has been realized and characterized. The simulation results allow us to explain the limits of the interpolated fast Fourier transform applied to the realized instrument. Finally, a method for overcoming them is proposed by decorrelating the errors between the measurements, which can provide a guideline for the design of frequency-modulated interferometric distance meters.

Facile synthesis of KMnCl3 halide perovskite based composites with rGO and fullerene (C60) for efficient supercapacitor electrodes

Recently, the family of halide perovskite materials drawn significant attention of scientific community for next generation energy storage devices because of their outstanding features, such as high ionic and electronic conductivity. However, besides energy conversion, their use for energy storage is found to be limited. In this study, an efficient antisolvent approach were employed to synthesize the halide perovskites KMnCl3, and their composites, i.e.; KMnCl3/rGO and KMnCl3/C60, for supercapacitor electrodes. XRD spectra confirm the phase purity with orthorhombic phase, while FE-SEM revealed the porous type morphology of rGO and C60 based composite, facilitating the smooth and fast ions transportation at the electrode. EDX spectra confirmed the presence of the constituent elements. I-V measurements confirmed the high conductivity and low resistivity for rGO and fullerene (C60) based composite, supporting the EIS analysis having low solution and polarization resistance. BET analysis exhibit the mesoporous nature of the fullerene (C60) based sample with surface area (25.3412 m2/g), pore radius (45.3023 nm), and pore volume (0.0038 cc/g), respectively. Further, the CV test confirmed the pesudocapacitive nature, with outstanding stability 95 % over 4000th charging-discharging cycles. GCD test also demonstrated that fullerene (C60) based electrode have high specific capacitance, high power density and energy density (936.67 F/g, 3.1 W/kg, 150.58 Wh/Kg) as compared to other electrodes. The scalable synthesis of halide perovskite-based composites can be effectively used as next generation supercapacitor electrode with enhanced electrochemical performance for real applications in future.

A transformer-based neural network framework for full names prediction with abbreviations and contexts

With the rapid spread of information, abbreviations are used more and more common because they are convenient. However, the duplication of abbreviations can lead to confusion in many cases, such as information management and information retrieval. The resultant confusion annoys users. Thus, inferring a full name from an abbreviation has practical and significant advantages. The bulk of studies in the literature mainly inferred full names based on rule-based methods, statistical models, the similarity of representation, etc. However, these methods are unable to use various grained contexts properly. In this paper, we propose a flexible framework of Multi-attention mask Abbreviation Context and Full name language model, named MACF to address the problem. With the abbreviation and contexts as the inputs, the MACF can automatically predict a full name by generation, where the contexts can be variously grained. That is, different grained contexts ranging from coarse to fine can be selected to perform such complicated tasks in which contexts include paragraphs, several sentences, or even just a few keywords. A novel multi-attention mask mechanism is also proposed, which allows the model to learn the relationships among abbreviations, contexts, and full names, a process that makes the most of various grained contexts. The three corpora of different languages and fields were analyzed and measured with seven metrics in various aspects to evaluate the proposed framework. According to the experimental results, the MACF yielded more significant and consistent outputs than other baseline methods. Moreover, we discuss the significance and findings, and give the case studies to show the performance in real applications.

Unequal Error Protection-based Rate-Splitting precoding for VLC systems: BER analysis

Rate-Splitting Multiple Access (RSMA), as a promising next-generation multiple access technique, can be integrated with Visible Light Communication (VLC) to address the challenge of accommodating multiple users under limited modulation bandwidth of Light Emitting Diodes (LEDs). However, most of the current works about RSMA assume perfect Successive Interference Cancellation (SIC) during the decoding procedure and neglect the error propagation problem due to SIC errors, which will greatly affect the performance in real applications. In view of this, we consider the design of Rate-Splitting (RS) precoder for downlink Multi-User Multiple-Input Single-Output (MU-MISO) VLC systems in the presence of SIC errors. For the first time in the literature, we derive analytic Bit Error Rate (BER) expressions in this case and analyze the error performance of a conventional RS precoder, which unveils the error performance degradation due to SIC errors. To mitigate this effect and improve the robustness of the system, we propose a novel RS precoding scheme by providing Unequal Error Protection (UEP) for common and private streams, which is achieved by changing an error protection factor. By this means, the transmission power is flexibly allocated to the common and private symbol stream, which can reduce the error probability as a whole. Simulation results indicate that the proposed RS precoder can provide significant error performance gains (up to 82.9%) over the baseline.

Survey on Sketch-to-photo Translation

Sketch-based understanding is involved in human communication and cognitive development, making it essential in visual perception. A specific task in this domain is sketch-to-photo translation, where a model produces realistic images from simple drawings. To this end, large paired training datasets are commonly required, which is impractical in real applications. Thus, this work studies conditional generative models for sketch-to-photo translation, overcoming the lack of training datasets by a self-supervised approach that produces sketch-photo pairs from a target catalog. Our study shows the benefit of cycle-consistency loss and UNet architectures that, together with the proposed dataset generation, improve performance in real applications like eCommerce. Our results also reveal the weakness of conditional DDPMs for generating images resembling the input sketch, even though they achieve a high FID score.

SeO2-infused grain boundaries effectively improve rate and stability performance of Li-rich manganese-based layered cathode materials

For polycrystalline lithium-rich manganese-based layered oxides (LMLO), the presence of porous microstructures always leads to the greater oxygen release and lower conductivity, impairing their rate and cycling stability performance for real applications. Here, by temperature-controlled annealing, we propose a facile and scalable method to infuse molten SeO2 into the intracrystalline grain boundary of the polycrystalline Li1.2Mn0.54Ni0.13Co0.13O2 (LMNCO) particles. Then the uniform surface and double nanolayer structure composed of interconnected Li2SeO4 and robust Li2NixCoyO4 are revealed on primary particles. Accordingly, SeO2-infused LMNCO(Se-LMNCO) gains an upraised rate performance with 97 % capacity retenting rate after charge and discharge under 0.1–5 C then returned to 0.1 C and an improved cycling stability with a capacity retention of 80.0 % over 200 cycles at 1 C (1 C=250 mAh g−1). Our work highlights the significance of surface engineering inside the secondary LMLO particles and the improvement of electrochemical rate and stability performance toward lithium-ion batteries with LMLO electrode.

Ultrahigh insulation resistivity potential under colossal permittivity SrTiO3 based ceramics via controlling oxygen backfill

Effects of annealing atmosphere on the dielectric properties of Sr1-xErxTiO3 ceramics (x = 0–0.014) were systematically investigated in this paper. In x = 0.012 ceramic samples annealed in air, the stable insulation resistivity of over 109 Ω • cm (DC 0–150 V), the CP (16,635 @ 1 kHz, 16,822 @ 1 MHz), and the ultralow dielectric loss (0.006 @ 1 kHz, 0.02 @ 1 MHz) are achieved. Through a thorough examination of dielectric responses, X-ray photoelectron spectroscopy (XPS), UV–visible absorption spectrum, and complex impedance data, it is demonstrated that the defect dipoles [TiTi′−VO··−TiTi′], [ErSr·−TiTi′],[2ErTi′−VO··], [TiTi′−VO·], [ErTi′−VO·] and [ErSr·−ErTi′] form in Sr1-xErxTiO3 (when x = 0.012) ceramic annealed under flowing air. We innovatively used variable temperature in situ resistance monitoring equipment to simulate the industrial environment, the insulating properties and the microscopic mechanism of oxygen vacancy diffusion of ceramics were investigated under different voltages and temperatures, which is of great significance to achieve more desirable colossal permittivity, ultra-low dielectric loss and insulation resistivity performance for real applications.

Establishing the energy content of natural gas residential consumption : example with Belgian field-test applications

In the context of the much-needed energy transition, monitoring of residential energy appliances is more and more common in order to evaluate (and improve) their field-test performance in real applications. Many residential heating appliances use natural gas as energy source : residential gas boilers, gas engine heat pumps, gas absorption heat pumps; fuel cell-based cogeneration units, internal combustion engine cogeneration units, etc. Unfortunately, for simplicity and costs reasons, only the volume of the consumed natural is measured at the inlet of the monitored residential heating appliance. This volume, and the equivalent energy level that it contains and that is required for efficiency calculations, is affected by the atmospheric pressure and the temperature at the field-test site, as well as by the always varying natural gas composition. This paper demonstrates the method that has been used in Belgian field-test studies conducted on residential heating appliances to establish the energy content of the consumed natural gas.

A comprehensive study on flocculation of anionic dyes using the bioflocculant produced by Bacillus thuringiensis: Kinetics, affecting factors, and perspectives.

Bioflocculants have received more and more attention as alternatives to chemical flocculants because of their innocuousness, environmental friendliness, and high effectiveness. This study aims to investigate various factors that influence the performance of the novel bioflocculant produced by Bacillus thuringiensis (BF-TWB10) and analyze its adsorption kinetics to optimize its flocculation performance for real applications. The best-fit kinetic model was pseudo-second order with R2 = 0.999. The effects of pretreatment temperature, pH, and the presence of cations on flocculation were assessed. Further investigations of flocculation, including zeta potential analysis and particle size analysis, were also conducted. Thermal pretreatment of BF-TWB10 or the presence of divalent cations could stimulate the decolorization efficiency of the bioflocculant. BF-TWB10 manifested outstanding dye removal performances with over 90% for all tested anionic dyes at pH2 and 3. Its decolorization efficiency on anionic dyes decreased with the increase of pH values. Zeta potential analysis revealed that the electrostatic repulsion between anionic dyes decreased after the addition of BT-TWB10 and further diminished by adjusting the reaction mixture to pH2 before flocculation, suggesting the occurrence of adsorption bridging and charge neutralization. These findings proposed that BF-TWB10 might be a promising bioflocculant for the removal of dyes in textile wastewater. PRACTITIONER POINTS: Bioflocculant BF-TWB10 shows outstanding performance in flocculation. Adsorption process follows pseudo-second-order kinetic model. Flocculation process is pH-responsive. High-temperature pretreatment or divalent cations enhance its flocculation performance. The analyses suggest the occurrence of charge neutralization and adsorption bridging.

An Image-Based Framework for Measuring the Prestress Level in CFRP Laminates: Experimental Validation.

Image-based methods have been applied to support structural monitoring, product and material testing, and quality control. Lately, deep learning for compute vision is the trend, requiring large and labelled datasets for training and validation, which is often difficult to obtain. The use of synthetic datasets is often applying for data augmentation in different fields. An architecture based on computer vision was proposed to measure strain during prestressing in CFRP laminates. The contact-free architecture was fed by synthetic image datasets and benchmarked for machine learning and deep learning algorithms. The use of these data for monitoring real applications will contribute towards spreading the new monitoring approach, increasing the quality control of the material and application procedure, as well as structural safety. In this paper, the best architecture was validated during experimental tests, to evaluate the performance in real applications from pre-trained synthetic data. The results demonstrate that the architecture implemented enables estimating intermediate strain values, i.e., within the range of training dataset values, but it does not allow for estimating strain values outside those range. The architecture allowed for estimating the strain in real images with an error ∼0.5%, higher than that obtained with synthetic images. Finally, it was not possible to estimate the strain in real cases from the training performed with the synthetic dataset.

Regularized Estimation in High-Dimensional Vector Auto-Regressive Models Using Spatio-Temporal Information

A Vector Auto-Regressive (VAR) model is commonly used to model multivariate time series, and there are many penalized methods to handle high dimensionality. However in terms of spatio-temporal data, most methods do not take the spatial and temporal structure of the data into consideration, which may lead to unreliable network detection and inaccurate forecasts. This paper proposes a data-driven weighted l1 regularized approach for spatio-temporal VAR model. Extensive simulation studies are carried out to compare the proposed method with four existing methods of high-dimensional VAR model, demonstrating improvements of our method over others in parameter estimation, network detection and out-of-sample forecasts. We also apply our method on a traffic data set to evaluate its performance in real application. In addition, we explore the theoretical properties of l1 regularized estimation of VAR model under the weakly sparse scenario, in which the exact sparsity can be viewed as a special case. To the best of our knowledge, this direction has not been considered yet in the literature. For general stationary VAR process, we derive the non-asymptotic upper bounds on l1 regularized estimation errors under the weakly sparse scenario, provide the conditions of estimation consistency, and further simplify these conditions for a special VAR(1) case.

Multiscale spatial temporal attention graph convolution network for skeleton-based anomaly behavior detection

Anomaly behavior detection plays a significant role in emergencies such as robbery. Although a lot of works have been proposed to deal with this problem, the performance in real applications is still relatively low. Here, to detect abnormal human behavior in videos, we propose a multiscale spatial temporal attention graph convolution network (MSTA-GCN) to capture and cluster the features of the human skeleton. First, based on the human skeleton graph, a multiscale spatial temporal attention graph convolution block (MSTA-GCB) is built which contains multiscale graphs in temporal and spatial dimensions. MSTA-GCB can simulate the motion relations of human body components at different scales where each scale corresponds to different granularity of annotation levels on the human skeleton. Then, static, globally-learned and attention-based adjacency matrices in the graph convolution module are proposed to capture hierarchical representation. Finally, extensive experiments are carried out on the ShanghaiTech Campus and CUHK Avenue datasets, the final results of the frame-level AUC/EER are 0.759/0.311 and 0.876/0.192, respectively. Moreover, the frame-level AUC is 0.768 for the human-related ShanghaiTech subset. These results show that our MSTA-GCN outperforms most of methods in video anomaly detection and we have obtained a new state-of-the-art performance in skeleton-based anomaly behavior detection.

Hierarchical core-shell NiCoSe2@nickel cobalt layered double hydroxide nanocomposite as high-performance electrode materials for asymmetric supercapacitors

As an efficient energy storage device, supercapacitors have exhibited excellent charge storage capacity and stable cycling performance. However, the lower energy density makes it difficult to meet the performance requirements in practical applications. Here, a core-shell structure of NiCoSe2@NiCo-LDH was synthesized on carbon cloth by a two-step method. The NiCoSe2@NiCo-LDH composite as electrode of supercapacitor exhibited a specific capacitance of 2609.1 mF cm−2 (1242.4F g−1) in three-electrode system, which was far higher than that of the NiCoSe2 electrode material, maintaining 85 % of the original capacity after 2000 cycles. The NiCoSe2@NiCo-LDH and activated carbon materials were further assembled to an asymmetric supercapacitor to verify their performance of real applications. The device exhibited a specific capacity of 912.5 mF cm−2 at a current density of 2 mA cm−2 and maintained 96.19 % of its original capacity after 2000 cycles, demonstrating its application potential.

Toward Smart Multizone HVAC Control by Combining Context-Aware System and Deep Reinforcement Learning

Building energy consumption accounts for a large figure of total energy consumption and keeps a rapid increase. Energy for heating, ventilation, and air conditioning (HVAC) is the main contribution. To save energy with maintaining comfort, control methods have been studied, including rule-based methods, model predictive control, and deep reinforcement learning (DRL). While their performance in real applications can be restricted by the highly nonstationary building environment caused by factors like weather conditions. Especially, for multizone HVAC control with multiple controllers, variation of the controller policy causes potential nonstationarity for each other. Current solutions to the nonstationarity based on model-based methods add complexity for building modeling and decrease the control efficiency. In addition, although massive data are available with the development of the Internet of Things (IoT) in smart buildings, high-level exploitation of data in the context-aware system is not yet explored to detect environment changes for smart building control. To this end, we propose a novel context-aware model-free DRL method called Trans-Context soft actor–critic (SAC) for multizone HVAC control, which combines a transformer-encoder-based context-aware system and the state-of-the-art DRL algorithm SAC. The context-aware system disentangles the nonstationarity by learning context data from IoT sensors. Besides, Trans-Context SAC is a model-free method without the need for building modeling. We evaluate Trans-Context SAC in a simulation-based case study on a multizone commercial building. Results demonstrate that Trans-Context SAC can achieve up to 15.9% of energy saving compared to other baselines with maintaining thermal comfort. Besides, Trans-Context SAC obtains the generalization for unseen environments.

Side substitution on benzothiadiazole-based hole transporting materials with a D–A–D molecular configuration for efficient perovskite solar cells

A series of benzothiadiazole-based Donor-Acceptor-Donor (D-A-D) typed hole-transporting materials (HTMs) are designed through introducing electron-withdrawing fluorine group and electron-donating alkoxy group into the core of benzothiadiazole (BT). The energy level alignment, electronic properties, absorption, and hole transport properties of these materials are explored comprehensively using First-principle calculations. As compared with the reference molecule BT, three other substituted molecules have lower HOMO energy levels and lower reorganization energy. Especially, two fluorine substituted hole-transporting materials BT-1F and BT-2F possess planar molecular configuration, suitable energy level, indicating that fluorine substitution is beneficial to the increase of open circuit voltage of device. Moreover, the hole transporting mobility, solubility and stability of all designed molecules are also estimated, which are important items to determine the cost and performance in real application of solar cells. Calculated results show that hole mobility of monofluorinated molecule BT-1F displays relatively higher hole mobility owing to efficient intermolecular interactions. Therefore, molecule BT-1F is likely to be highly efficient HTMs because of its excellent hole mobility and solubility. The present work demonstrates that fluorination engineering on core acceptors in D-A-D typed HTMs is an effective strategy to tune the photovoltaic performance of perovskite solar cells.