Search

Sequential recommendation is the mainstream approach in the field of click-through-rate (CTR) prediction for modeling users’ behavior. This behavior implies the change of the user’s interest, and the goal of sequential recommendation is to capture this dynamic change. However, existing studies have focused on designing complex dedicated networks to capture user interests from user behavior sequences, while neglecting the use of auxiliary information. Recently, knowledge graph (KG) has gradually attracted the attention of researchers as a structured auxiliary information. Items and their attributes in the recommendation, can be mapped to knowledge triples in the KG. Therefore, the introduction of KG to recommendation can help us obtain more expressive item representations. Since KG can be considered a special type of graph, it is possible to use the graph neural network (GNN) to propagate the rich information contained in the KG into the item representation. Based on this idea, this paper proposes a recommendation method that uses KG as auxiliary information. The method first propagates the knowledge information in the KG using GNN to obtain a knowledge-rich item representation. Then the temporal features in the item sequence are extracted using a transformer for CTR prediction, namely the Knowledge Graph-Aware Deep Interest Extraction network (KGDIE). To evaluate the performance of this model, we conducted extensive experiments on two real datasets with different scenarios. The results showed that the KGDIE method could outperform several state-of-the-art baselines. The source code of our model is available at . [ABSTRACT FROM AUTHOR]

Graph convolutional neural networks have been successfully applied to collaborative filtering to capture high-quality user-item representations. Despite their remarkable performance, there are still limitations that hinder further improvement of recommender systems. Most existing recommendation systems utilize implicit feedback data for model training, but such data inevitably contains adversarial interaction noise. The conventional graph-based collaborative filtering method fails to effectively filter out this noise, and instead amplifies its impact, resulting in degraded model performance. To address this issue, we propose a robustness-enhanced collaborative filtering graph neural network model that does not rely on explicit noise filtering. Our approach involves simulating user-item interactions that do not exist in practice as adversarial interaction noise using random noise. To mitigate the impact of this noise in hidden feedback, we replace them with randomly selected partial nodes based on the principle of mutual information maximization. Our model has been extensively experimented on three public datasets (MovieLens-1 M, Yelp, and Ta-feng) and achieves performance improvements of about 5%, 10%, and 14%, respectively, compared to the state-of-the-art baseline model. In particular, in model robustness experiments, our model achieves significant performance improvements of about 13% and 17% in Yelp and Ta-feng. A comprehensive experimental study shows that our proposed method is reasonably effective and interpretable. [ABSTRACT FROM AUTHOR]

Developing highly active materials that efficiently utilize solar spectra is crucial for photocatalysis, but still remains a challenge. Here, we report a new donor-acceptor (D-A) covalent organic framework (COF) with a wide absorption range from 200 nm to 900 nm (ultraviolet-visible-near infrared light). We find that the thiophene functional group is accurately introduced into the electron acceptor units of TpDPP-Py (TpDPP: 5,5'-(2,5-bis(2-ethylhexyl)−3,6-dioxo-2,3,5,6-tetrahydropyrrolo [3,4-c]pyrrole-1,4-diyl)bis(thiophene-2-carbaldehyde), Py: 1,3,6,8-tetrakis(4-aminophenyl)pyrene) COFs not only significantly extends its spectral absorption capacity but also endows them with two-photon and three-photon absorption effects, greatly enhancing the utilization rate of sunlight. The selective coupling of benzylamine as the target reactant is used to assess the photocatalytic activity of TpDPP-Py COFs, showing high photocatalytic conversion of 99% and selectivity of 98% in 20 min. Additionally, the TpDPP-Py COFs also exhibit the universality of photocatalytic selective coupling of other imine derivatives with ~100% conversion efficiency. Overall, this work brings a significant strategy for developing COFs with a wide absorption range to enhance photocatalytic activity. Creating highly active materials that effectively harness solar spectra is essential for photocatalysis, though challenging. Here the authors introduce a novel donor-acceptor covalent organic framework with a broad absorption range of 200 nm to 900 nm, achieving efficient artificial photocatalytic amine coupling. [ABSTRACT FROM AUTHOR]

Stretchable neuromorphic optoelectronics present tantalizing opportunities for intelligent vision applications that necessitate high spatial resolution and multimodal interaction. Existing neuromorphic devices are either stretchable but not reconcilable with multifunctionality, or discrete but with low-end neurological function and limited flexibility. Herein, we propose a defect-tunable viscoelastic perovskite film that is assembled into strain-insensitive quasi-continuous microsphere morphologies for intrinsically stretchable neuromorphic vision-adaptive transistors. The resulting device achieves trichromatic photoadaptation and a rapid adaptive speed (<150 s) beyond human eyes (3 ~ 30 min) even under 100% mechanical strain. When acted as an artificial synapse, the device can operate at an ultra-low energy consumption (15 aJ) (far below the human brain of 1 ~ 10 fJ) with a high paired-pulse facilitation index of 270% (one of the best figures of merit in stretchable synaptic phototransistors). Furthermore, adaptive optical imaging is achieved by the strain-insensitive perovskite films, accelerating the implementation of next-generation neuromorphic vision systems.Wearable neuromorphic optoelectronics require stretchable photosensitive materials and multifunctional integration. Here, authors develop intrinsically stretchable neuromorphic vision-adaptive transistors for skin-like neuromorphic vision systems. [ABSTRACT FROM AUTHOR]

Challenges associated with stretchable optoelectronic devices, such as pixel size, power consumption and stability, severely brock their realization in high-resolution digital imaging. Herein, we develop a universal detachable interface technique that allows uniform, damage-free and reproducible integration of micropatterned stretchable electrodes for pixel-dense intrinsically stretchable organic transistor arrays. Benefiting from the ideal heterocontact and short channel length (2 μm) in our transistors, switching current ratio exceeding 106, device density of 41,000 transistors/cm2, operational voltage down to 5 V and excellent stability are simultaneously achieved. The resultant stretchable transistor-based image sensors exhibit ultrasensitive X-ray detection and high-resolution imaging capability. A megapixel image is demonstrated, which is unprecedented for stretchable direct-conversion X-ray detectors. These results forge a bright future for the stretchable photonic integration toward next-generation visualization equipment. Pixel size, power consumption, and stability of stretchable optoelectronic devices limit their application in digital imaging. Bian et al. developed a universal detachable interface technique for damage-free micropattern, reproducible transfer and ideal heterocontact of intrinsically stretchable electrodes. [ABSTRACT FROM AUTHOR]

Nanoclusters with atomically precise structures and discrete energy levels are considered as nanoscale semiconductors for artificial intelligence. However, nanocluster electronic engineering and optoelectronic behavior have remained obscure and unexplored. Hence, we create nanocluster photoreceptors inspired by mantis shrimp visual systems to satisfy the needs of compact but multi-task vision hardware and explore the photo-induced electronic transport. Wafer-scale arrayed photoreceptors are constructed by a nanocluster-conjugated molecule heterostructure. Nanoclusters perform as an in-sensor charge reservoir to tune the conductance levels of artificial photoreceptors by a light valve mechanism. A ligand-assisted charge transfer process takes place at nanocluster interface and it features an integration of spectral-dependent visual adaptation and circular polarization recognition. This approach is further employed for developing concisely structured, multi-task, and compact artificial visual systems and provides valuable guidelines for nanocluster neuromorphic devices. All-in-one multi-task photoperception is desirable for artificial vision systems. Wen et al. present wafer-scale high density integration of artificial photoreceptors that combine photoadaptation and circular polarized light vision, enabled by chiral-nanocluster-conjugated molecule heterostructures. [ABSTRACT FROM AUTHOR]

Nanoscale polymeric thin films are widely used in diverse modern applications, where a satisfactory mechanical performance is a requirement to their full functionality. The mechanical response of polymer films is strongly affected by the size effects under nanoconfinement; however, the mechanism of such response in terms of molecular configurations and chain conformations has yet to be determined. In this work, we reveal the conformational origin of the stiffening behavior of crosslinked polymeric nanofilms via coarse-grained molecular dynamics and tailored experiments. We find that the biaxial modulus changes follow the alteration of polymer conformations, decoupled from size and thickness. We propose a theory to quantitatively link the elastic properties of the polymers to the distribution of their chain end-to-end distances, predicting a stiffening effect on uncoiled chains. Finally, we use such insight to obtain several PDMS nano-films of the same thickness but with a variability of two orders of magnitudes in their moduli. The mechanical response of polymer films is affected by size effects under nanoconfinement, but the mechanism of such response in terms of molecular configurations and chain conformations has proven elusive. The authors reveal the conformational origin of the stiffening behavior in crosslinked polymeric nanofilms via simulations and experiments. [ABSTRACT FROM AUTHOR]

Representation learning of users and items is the core of recommendation, and benefited from the development of graph neural network (GNN), graph collaborative filtering (GCF) for capturing higher order connectivity has been successful in the recommendation domain. Nevertheless, the matrix sparsity problem in collaborative filtering and the tendency of higher order embeddings to smooth in GNN limit further performance improvements. Contrastive learning (CL) was introduced into GCF and alleviated these problems to some extent. However, existing methods usually require graph perturbation to construct augmented views or design complex CL tasks, which limits the further development of CL-based methods in the recommendation. We propose a simple CL framework that does not require graph augmentation, but is based on dropout techniques to generate contrastive views to address the aforementioned problem. Specifically, we first added dropout operation to the GNN computation, and then fed the same batch of samples twice into the network for computation. Using the randomness of dropout, a pair of views with random noise was obtained, and maximizing the similarity of the view pairs is set as an auxiliary task to complement the recommendation. In addition, we made a simple modification to the computation of the GNN to alleviate the information loss due to embedding smoothing by means of cross-layer connected graph convolution computation. We named our proposed method as Simple Contrastive Learning Graph Neural Network based on dropout (SimDCL). Extensive experiments on five public datasets demonstrate the effectiveness of the proposed SimDCL, especially on the Amazon Books and Ta-Feng datasets, where our approach achieves 44% and 43% performance gains compared to baseline. [ABSTRACT FROM AUTHOR]

Polymer nanowire (NW) organic field-effect transistors (OFETs) integrated on highly aligned large-area flexible substrates are candidate structures for the development of high-performance flexible electronics. This work presents a universal technique, coaxial focused electrohydrodynamic jet (CFEJ) printing technology, to fabricate highly aligned 90-nm-diameter polymer arrays. This method allows for the preparation of uniformly shaped and precisely positioned nanowires directly on flexible substrates without transfer, thus ensuring their electrical properties. Using indacenodithiophene-co-benzothiadiazole (IDT-BT) and poly(9,9-dioctylfluorene-co-benzothiadiazole) (F8-BT) as example materials, 5 cm2 arrays were prepared with only minute size variations, which is extremely difficult to do using previously reported methods. According to 2D-GIXRD analysis, the molecules inside the nanowires mainly adopted face-on π-stacking crystallite arrangements. This is quite different from the mixed arrangement of thin films. Nanowire-based OFETs exhibited a high average hole mobility of 1.1 cm2 V−1 s−1 and good device uniformity, indicating the applicability of CFEJ printing as a potential batch manufacturing and integration process for high-performance, scalable polymer nanowire-based OFET circuits. This technique can be used to fabricate various polymer arrays, enabling the use of organic polymer semiconductors in large-area, high-performance electronic devices and providing a new path for the fabrication of flexible displays and wearable electronics in the future. [ABSTRACT FROM AUTHOR]

In practice, the assessment and treatment of rail corrugation are quantitatively based on the corrugation depth. Wheel–rail vertical forces (WRVF), as a direct reflection of wheel–rail interaction, can give expression to the corrugation depth and thus serve as a key parameter for assessing the corrugation. In this paper, we propose an evaluation method for rail corrugation based on the WRVF. First, a 3D wheel–rail dynamic finite element (FE) model was developed with typical parameters of CRTS II slab track and CRH3 vehicle for high-speed railways in China. The accuracy of the model was then validated with the measured WRVF data in the field. Second, using the validated model, the time–frequency domain distribution of WRVF (vehicle speed: 300 km/h) was obtained with consideration of the corrugation wavelength in the range of 40–180 mm. The non-linear least squares method and rational equation were used to fit the function between the large value of WRVF and the corrugation depth value under the conditions of different corrugation wavelengths. Next, effects of the Pinned–Pinned resonance frequency and vibration mode on the fitted parameters were analysed, by which an indicator for corrugation treatment (grinding) was proposed. Finally, the indicator was applied in the monitoring of rail corrugation for high-speed railway lines in the field. The results show that the misjudgement rate of rail grinding decisions (using the proposed indicator) is low with the accuracy at 92.5%. The proposed method can provide a basis for the rail corrugation evaluation and grinding decisions-making. [ABSTRACT FROM AUTHOR]

Large area and highly aligned polymer semiconductor sub-microwires were fabricated using the coaxial focused electrohydrodynamic jet printing technology. As indicated by the results, the sub-microwire arrays have smooth morphology, well reproducibility and controllable with a width of ~110 nm. Analysis shows that the molecular chains inside the sub-microwires mainly exhibited edge-on arrangement and the π-stacking direction (010) of the majority of crystals is parallel to the long axis of the sub-microwires. Sub-microwires based organic field effect transistors showed high mobility with an average of 1.9 cm2 V−1 s−1, approximately 5 times higher than that of thin film based organic field effect transistors. In addition, the number of sub-microwires can be conveniently controlled by the printing technique, which can subsequently concisely control the performance of organic field effect transistors. This work demonstrates that sub-microwires fabricated by the coaxial focused electrohydrodynamic jet printing technology create an alternative path for the applications of high-performance organic flexible device. Here, the authors fabricate large area and highly aligned polymer semiconductor sub-microwires arrays via coaxial focused electrohydrodynamic jet printing technology, achieving high on/off ratio and average mobility that is 5x higher than that of thin film based organic field effect transistors. [ABSTRACT FROM AUTHOR]

Recent advances in organic electronics of novel materials and optoelectronic devices spark great interest in the design and synthesis of high-performance polymer semiconductors. During the last decade, isoindigo (IID) and its derivatives have sprung up as common electron-deficient building blocks and obtained extensive applications in organic field-effect transistors (OFETs). In this review, we first present the current status, basic principles, and general material design strategies for OFETs. Then, multiple IID-type acceptors, mature synthetic routes to monomers, and typical IIDs-based conjugated polymers are summarized. We also introduce side-chain engineering and cutting-edge applications, like stretchable transistors, sensing, active-matrix driving, etc., of the classic copolymer poly(isoindigo-co-bithiophene). Green polymerization approaches towards conjugated polymers incorporating IIDs are subsequently discussed for efficient polymerization. Finally, we conclude this review and propose in-depth prospects with respect to material synthesis and device applications. Undoubtedly, IIDs-based conjugated polymers would occupy a significant position in the future of organic electronics, due to diverse building blocks, mature synthetic pathways, tunable side chains, and unique optoelectronic properties. [ABSTRACT FROM AUTHOR]

Flexible electronics have suggested tremendous potential to shape human lives for more convenience and pleasure. Strenuous efforts have been devoted to developing flexible organic field-effect transistor (FOFET) technologies for rollable displays, bendable smart cards, flexible sensors and artificial skins. However, these applications are still in a nascent stage for lack of standard high-performance material stacks as well as mature manufacturing technologies. In this review, the material choice and device design for FOFET devices and circuits, as well as the demonstrated applications are summarized in detail. Moreover, the technical challenges and potential applications of FOFETs in the future are discussed. [ABSTRACT FROM AUTHOR]

With the train speed and axle load increasing, excessive stresses are produced and transmitted to the ballast layer, inducing rapid ballast degradation. To solve this issue, the under sleeper pads (USPs) have been widely applied between sleepers and ballast particles as the elastic layer. In this research, laboratory tests using half-sleeper track were carried out to study the ballast bed performance with or without the USPs under static and cyclic loading. Results show that applying the USPs reduces the track stiffness and can decrease the settlement. However, installing the USPs increases the ballast bed acceleration and the sleeper vertical acceleration. The contact areas of sleeper-ballast with USPs are over 5 times as those without USPs. The USPs assist reducing ballast degradation mainly by avoiding the ballast particle breakage at the sleeper-ballast interface and can increase the stress distribution at the longitudinal direction. [ABSTRACT FROM AUTHOR]

B Correction to: Complex & Intelligent Systems b https://doi.org/10.1007/s40747-023-00974-z In the original publication, the author affiliation has published incorrectly. The correct affiliation is HongYu Tian belongs to "School of Physics and Electronic Engineering" and YuHao Xu, ZhenHai Wang, ZhiRu Wang, YunLong Guo, Rong Fan, Xing Wang belongs to "School of Information Science and Engineering". Publisher's Note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations. [Extracted from the article]

Stretchable organic field-effect transistors (STOFETs) employing organic semiconductors as active layers are highly attractive ongoing from health monitoring to biological research owing to some favorable advantages over their inorganic counterpart, including light weight, low cost, solution processing, high flexibility and simple adjustment of functionalities through molecular design. Although the development of STOFETs with original electrical performances under large mechanical deformation remain rudimentary, major efforts have recently been devoted to the investigation on STOFETs, and remarkable advances in stretchable components and novel fabrication methods have been achieved. A detailed overview of the advantages, challenges and current achievements in STOFETs was given including stretchable electrodes, semiconductors, dielectrics and substrates. Furthermore, conclusions and prospects for the future development of STOFETs with both high stretchability and superb electrical performances fabricated using intrinsically stretchable components are proposed. [ABSTRACT FROM AUTHOR]

Recommendation systems can interpret personal preferences and recommend the most relevant choices to the benefit of countless users. Attempts to improve the performance of recommendation systems have hence been the focus of much research in an era of information explosion. As users would like to ask about shopping information with their friend in real life and plentiful information concerning items can help to improve the recommendation accuracy, traditional work on recommending based on users' social relationships or the content of item tagged by users fails as recommending process relies on mining a user's historical information as much as possible. This paper proposes a new recommending model incorporating the social relationship and content information of items (SC) based on probabilistic matrix factorization named SC-PMF (Probabilistic Matrix Factorization with Social relationship and Content of items). Meanwhile, we take full advantage of the scalability of probabilistic matrix factorization, which helps to overcome the often encountered problem of data sparsity. Experiments demonstrate that SC-PMF is scalable and outperforms several baselines (PMF, LDA, CTR, SocialMF) for recommending. [ABSTRACT FROM AUTHOR]

We demonstrate a photo-electrochemical biosensor for the sensitive and specific detection of microRNA using BiS nanorods as a photoactive material and streptavidin as the unit that inhibits photocurrent. BiS nanorods were synthesized hydrothermally in organic phase and displayed excellent light-to-current conversion efficiency. The BiS was deposited on an indium tin oxide (ITO) slice and then modified with gold nanoparticles onto which biotinylated hairpin probe DNA was deposited as a monolayer. Following hybridization between the biotinylated probe DNA and the target microRNA, the stem-loop structure of the probe DNA was unfolded and the biotin directed outwards into the solution. Streptavidin was then added to bind to biotin via the strong streptavidin-biotin interactions. This causes the photocurrent of the modified ITO to decrease due to steric hindrance that blocks the transfer of electrons from added ascorbic acid to the surface of the electrode. The method has a detection limit as low as 3.5 fM of microRNA and can excellently discriminate even singly mismatched microRNA. The method was successfully applied to investigate the effect of abscisic acid on the expression level of microRNA-159a in seeds of Arabidopsis thaliana. We conclude that the assay presented here has a large potential as a method for quantification of microRNA and for studying the epigenetic regulation of flowering plants. [Figure not available: see fulltext.] [ABSTRACT FROM AUTHOR]

MicroRNAs (miRNAs), a class of small endogenous nonprotein-coding RNAs, regulate a wide range of biological processes, and their abnormal expressions are related to the growth and development of plants. Thus, a simple, rapid, and highly sensitive assay for miRNA detection is of great significance. In this work, a label-free and ultrasensitive assay for miRNA detection using protein cage nanoparticles has been developed. Apoferritin-encapsulated Cu nanoparticles (Cu-apoferritin) could be immobilized on the electrode through special reaction between amino and carboxyl. Hybridization event between the probe DNA and the target miRNA-159a is confirmed by electrochemical oxidation signal after Cu released into the detection buffer by adjusting the pH. This assay is highly selective and sensitive with a low detection limit of 3.5 fM. Moreover, the developed method can even discriminate single-base mismatched strand between the complementary targets. The effect of abscisic acid on the expression level of miRNA-159a in Arabidopsis thaliana seeds was also investigated. [ABSTRACT FROM AUTHOR]

As recently illustrated, nanostructured glassy polymer films with exceptional thermal and kinetic stability can be formed via Matrix Assisted Pulsed Laser Evaporation (MAPLE) (Guo et al. in Nat. Mater. 11:337, ). Relative to the standard poly(methyl methacrylate) glass formed on cooling at standard rates, glasses prepared by MAPLE can be 40 % less dense and have a 40 K higher glass transition temperature ( T). Furthermore, the kinetic stability in the glassy state can be enhanced by 2 orders-of-magnitude. Here, we examine the stability of the structured morphology. We show that nanostructured glasses may be formed even when the substrate is held at temperatures greater than the polymer T during deposition. In addition, we discuss the origin of the enhanced stability and the mechanism of nanostructured film formation within the framework of the Zhigilei model. Finally, we compare the nanostructured morphology to the surface morphology of other MAPLE-deposited films in the literature. [ABSTRACT FROM AUTHOR]

Owing to the kinetic nature of the glass transition, the ability to significantly alter the properties of amorphous solids by the typical routes to the vitreous state is restricted. For instance, an order of magnitude change in the cooling rate merely modifies the value of the glass transition temperature (Tg) by a few degrees. Here we show that matrix-assisted pulsed laser evaporation (MAPLE) can be used to form ultrastable and nanostructured glassy polymer films which, relative to the standard poly(methyl methacrylate) glass formed on cooling at standard rates, are 40% less dense, have a 40?K higher Tg, and exhibit a two orders of magnitude enhancement in kinetic stability at high temperatures. The unique set of properties of MAPLE-deposited glasses may make them attractive in technologies where weight and stability are central design issues. [ABSTRACT FROM AUTHOR]

We demonstrate a simple and controllable way to synthesize large-area, few-layer graphene on iron substrates by an optimized chemical vapor deposition (CVD) method using a mixture of methane and hydrogen. Based on an analysis of the Fe-C phase diagram, a suitable procedure for the successful synthesis of graphene on Fe surfaces was designed. An appropriate temperature and cooling process were found to be very important in the synthesis of highly crystalline few-layer graphene. Graphene-based field-effect transistor (FET) devices were fabricated using the resulting few-layer graphene, and showed good quality with extracted mobilities of 300-1150 cm/(V·s). [InlineMediaObject not available: see fulltext.] [ABSTRACT FROM AUTHOR]

Controlling the densities of aligned single-walled carbon nanotube arrays (SWNTs) on ST-cut quartz is a critical step in various applications of these materials. However the growth mechanism for tuning SWNT density using the chemical vapor deposition (CVD) method is still not well understood, preventing the development of efficient ways to obtain the desired results. Here we report a general 'periodic' approach that achieves ultrahigh density modulation of SWNT arrays on ST-cut quartz substrates-with densities increased by up to ∼60 times compared with conventional methods using the same catalyst densities-by varying the CH gas 'off' time. This approach is applicable to a wide range of initial catalyst densities, substrates, catalyst types and growth conditions. We propose a general mechanism for the catalyst size-dependent nucleation of SWNTs associated with different free carbon concentrations, which explains all the observations. Moreover, the validity of the model is supported by systematic experiments involving the variation of key parameters in the 'periodic' CVD approach. [Figure not available: see fulltext.] [ABSTRACT FROM AUTHOR]

We report a simple method to produce graphene nanospheres (GNSs) by annealing graphene oxide (GO) solution at high-temperature with the assistance of sparks induced by the microwave absorption of graphite flakes dispersed in the solution. The GNSs were formed by rolling up of the annealed GO, and the diameters were mostly in the range 300-700 nm. The GNS exhibited a hollow sphere structure surrounded by graphene walls with a basal spacing of 0.34 nm. Raman spectroscopy and X-ray photoelectron spectroscopy of the GNSs confirmed that the GO was efficiently reduced during the fabrication process. The resulting GNSs may open up new opportunities both for fundamental research and applications, and this method may be extended to the synthesis of other nanomaterials and the fabrication of related nanostructures. [InlineMediaObject not available: see fulltext.] [ABSTRACT FROM AUTHOR]