A blind image super-resolution network guided by kernel estimation and structural prior knowledge.

The goal of blind image super-resolution (BISR) is to recover the corresponding high-resolution image from a given low-resolution image with unknown degradation. Prior related research has primarily focused effectively on utilizing the kernel as prior knowledge to recover the high-frequency components of image. However, they overlooked the function of structural prior information within the same image, which resulted in unsatisfactory recovery performance for textures with strong self-similarity. To address this issue, we propose a two stage blind super-resolution network that is based on kernel estimation strategy and is capable of integrating structural texture as prior knowledge. In the first stage, we utilize a dynamic kernel estimator to achieve degradation presentation embedding. Then, we propose a triple path attention groups consists of triple path attention blocks and a global feature fusion block to extract structural prior information to assist the recovery of details within images. The quantitative and qualitative results on standard benchmarks with various degradation settings, including Gaussian8 and DIV2KRK, validate that our proposed method outperforms the state-of-the-art methods in terms of fidelity and recovery of clear details. The relevant code is made available on this link as open source.

Optimizing Intermediate Adsorption over PdM (M=Fe, Co, Ni, Cu) Bimetallene for Boosted Nitrate Electroreduction to Ammonia.

Electrochemical reduction of nitrate to ammonia (NO3RR) is a promising and eco-friendly strategy for ammonia production. However, the sluggish kinetics of the eight-electron transfer process and poor mechanistic understanding strongly impedes its application. To unveil the internal laws, herein, a library of Pd-based bimetallene with various transition metal dopants (PdM (M=Fe, Co, Ni, Cu)) are screened to learn their structure-activity relationship towards NO3RR. The ultra-thin structure of metallene greatly facilitates the exposure of active sites, and the transition metals dopants break the electronic balance and upshift its d-band center, thus optimizing intermediates adsorption. The anisotropic electronic characteristics of these transition metals make the NO3RR activity in the order of PdCu>PdCo≈PdFe>PdNi>Pd, and a record-high NH3 yield rate of 295 mg h-1 mgcat -1 along with Faradaic efficiency of 90.9 % is achieved in neutral electrolyte on PdCu bimetallene. Detailed studies further reveal that the moderate N-species (*NO3 and *NO2) adsorption ability, enhanced *NO activation, and reduced HER activity facilitate the NH3 production. We believe our results will give a systematic guidance to the future design of NO3RR catalysts.

Using less annotation workload to establish a pathological auxiliary diagnosis system for gastric cancer.

Pathological diagnosis of gastric cancer requires pathologists to have extensive clinical experience. To help pathologists improve diagnostic accuracy and efficiency, we collected 1,514 cases of stomach H&E-stained specimens with complete diagnostic information to establish a pathological auxiliary diagnosis system based on deep learning. At the slide level, our system achieves a specificity of 0.8878 while maintaining a high sensitivity close to 1.0 on 269 biopsy specimens (147 malignancies) and 163 surgical specimens (80 malignancies). The classified accuracy of our system is 0.9034 at the slide level for 352 biopsy specimens (201 malignancies) from 50 medical centers. With the help of our system, the pathologists' average false-negative rate and average false-positive rate on 100 biopsy specimens (50 malignancies) are reduced to 1/5 and 1/2 of the original rates, respectively. At the same time, the average uncertainty rate and the average diagnosis time are reduced by approximately 22% and 20%, respectively.

Catalytic oxidation of VOCs over 3D@2D Pd/CoMn2O4 nanosheets supported on hollow Al2O3 microspheres.

Catalytic oxidation is a promising method for removing harmful volatile organic compounds (VOCs). Therefore, exploring high-efficiency catalysts for catalyzing VOCs is of great significance to the realization of an environment-friendly and sustainable society. Here, a series of 3D@2D constructed Al2O3@CoMn2O4 microspheres with a hollow hierarchical structure supporting Pd nanoparticles was successfully synthesized. The introduction of hollow Al2O3 for the in situ vertical growth of 2D CMO spinel materials constructs a well-defined core - shell hollow hierarchical structure, leading to larger specific surface area, more accessible active sites and promoted catalytic activity of support material. Additionally, theoretical calculations also indicate that the addition of Al2O3 as the support material strengthens the adsorption of toluene and oxygen on CoMn2O4, which promotes their activation. The dispersion of Pd further strengthens the low-temperature reducibility along with more active surface oxygen species and lower apparent activation energy. The optimum 1 wt% Pd/h-Al@4CMO catalyst possesses the lowest apparent activation energy for toluene of 77.4 kJ mol-1, showing the relatively best catalytic activity for VOC oxidation, reaching 100% toluene, benzene, and ethyl acetate conversion at 165, 160, and 155 °C, respectively. Meanwhile, the 1 wt% Pd/h-Al@4CMO sample possesses excellent catalytic stability, outstanding selectivity, and good moisture tolerance, which is an effective candidate for eliminating VOCs contaminants.

Pt-Co nanoparticles supported on hollow multi-shelled CeO2 as a catalyst for highly efficient toluene oxidation: Morphology control and the role of bimetal synergism.

A series of hollow multi-shelled CeO2 (HoMS-CeO2) support materials with tunable shell numbers were fabricated and applied to the catalytic oxidation of toluene. HoMS-CeO2 possess much higher catalytic activity (T90 = 236 ℃) than hollow CeO2 with only a single shell (h-CeO2) (T90 = 275℃). The porous multiple-shelled structure has a higher SBET, which strongly promotes gas distribution and provides more active sites. The superiority of this kind of structure was also verified by comparing h-Co3O4 and HoMS-Co3O4. Furthermore, Pt-Co bimetallic nanoparticles were loaded onto HoMS-CeO2. The synergistic effect between Pt and Co was verified by XPS and O2-TPD, which was observed to allow electron transfer between Pt and Co and thus regulate the electronic state of the Pt. Compared with Pt alone, Pt-Co bimetallic nanoparticles could stronglypromotethe activation of O2and oxygen mobility, as revealed by a much higher Oads content and a lower oxygen desorption temperature. Of the catalysts prepared in this study, the 1 wt% PtCo3/CeO2 catalyst was found to be the most suitable for toluene oxidation owing to its excellent activity (T90 = 158 ℃), long-term stability, and water resistance. Finally, in situ DRIFTS was employed to investigate mechanism during toluene oxidation and the possible reaction pathway was proposed.

Low Temperature Combustion of VOCs with Enhanced Catalytic Activity Over MnO2 Nanotubes Loaded with Pt and Ni-Fe Spinel.

MnO2 nanotubes loaded with Pt and Ni-Fe spinel were synthesized using simple hydrothermal and sol-gel techniques. After loading with Ni-Fe spinel, the specific surface area of the material increases 3-fold. This change helped to provide more active sites and facilitated the association between the catalyst and volatile organic compounds (VOCs). X-ray photoelectron spectroscopy determined that the adsorbed oxygen concentrations were all greatly increased after Pt loading, indicating that Pt promoted the adsorption of oxygen and so accelerated the combustion process. The performance of the catalyst after loading with 2 wt % Pt was greatly improved, such that the T90 for benzene decomposition was decreased to 113 °C. In addition, the 2% Pt/2Mn@NFO exhibited excellent low-temperature catalytic activity when reacting with low concentrations of toluene and ethyl acetate. This work therefore demonstrates a viable new approach to the development of Mn-based catalysts for the low temperature catalytic remediation of VOCs.

Auxiliary Diagnostic Method for Patellofemoral Pain Syndrome Based on One-Dimensional Convolutional Neural Network.

Early accurate diagnosis of patellofemoral pain syndrome (PFPS) is important to prevent the further development of the disease. However, traditional diagnostic methods for PFPS mostly rely on the subjective experience of doctors and subjective feelings of the patient, which do not have an accurate-unified standard, and the clinical accuracy is not high. With the development of artificial intelligence technology, artificial neural networks are increasingly applied in medical treatment to assist doctors in diagnosis, but selecting a suitable neural network model must be considered. In this paper, an intelligent diagnostic method for PFPS was proposed on the basis of a one-dimensional convolutional neural network (1D CNN), which used surface electromyography (sEMG) signals and lower limb joint angles as inputs, and discussed the model from three aspects, namely, accuracy, interpretability, and practicability. This article utilized the running and walking data of 41 subjects at their selected speed, including 26 PFPS patients (16 females and 10 males) and 16 painless controls (8 females and 7 males). In the proposed method, the knee flexion angle, hip flexion angle, ankle dorsiflexion angle, and sEMG signals of the seven muscles around the knee of three different data sets (walking data set, running data set, and walking and running mixed data set) were used as input of the 1D CNN. Focal loss function was introduced to the network to solve the problem of imbalance between positive and negative samples in the data set and make the network focus on learning the difficult-to-predict samples. Meanwhile, the attention mechanism was added to the network to observe the dimension feature that the network pays more attention to, thereby increasing the interpretability of the model. Finally, the depth features extracted by 1D CNN were combined with the traditional gender features to improve the accuracy of the model. After verification, the 1D CNN had the best performance on the running data set (accuracy = 92.4%, sensitivity = 97%, specificity = 84%). Compared with other methods, this method could provide new ideas for the development of models that assisted doctors in diagnosing PFPS without using complex biomechanical modeling and with high objective accuracy.

The behavior of surface acidity on photo-Fenton degradation of ciprofloxacin over sludge derived carbon: Performance and mechanism.

Sludge derived carbon (SC) has been widely used in advanced oxidation processes as an effective and economic catalyst. In this study, we applied surface modified SC for the first time to catalyze the heterogeneous photo-Fenton process with ciprofloxacin, a highly concerned emerging contaminant, as a model substance. H2SO4 was used to acidify the SCs under varying acid dosages, temperatures, and reaction time lengths. The surface acidity of SCs was quantitatively characterized with NH3-TPD. A strong correlation between the surface acidity and the catalytic activity was clearly demonstrated. The highest catalytic activity was obtained with SC whose acidity was 0.149 mmol·g-1 after being modified with 6 mol·L-1 H2SO4 at -20 ℃ for 24 h. In addition, XRD, XRF, BET, XPS, and HRTEM were also used to characterize the obtained SC. ·OH radicals were found to be the main reactive species by EPR. Ten transformation products were identified by GC-MS, based on which three possible reaction pathways were proposed.