Search

Ant colony optimization (ACO) algorithm is widely used in the instant delivery order scheduling because of its distributed computing capability. However, the order delivery efficiency decreases when different logistics statuses are faced. In order to improve the performance of ACO, an adaptive ACO algorithm based on real-time logistics features (AACO-RTLFs) is proposed. First, features are extracted from the event dimension, spatial dimension, and time dimension of the instant delivery to describe the real-time logistics status. Five key factors are further selected from the above three features to assist in problem modeling and ACO designing. Second, an adaptive instant delivery model is built considering the customer’s acceptable delivery time. The acceptable time is calculated by emergency order mark and weather conditions in the event dimension feature. Third, an adaptive ACO algorithm is proposed to obtain the instant delivery order schedules. The parameters of the probability equation in ACO are adjusted according to the extracted key factors. Finally, the Gurobi solver in Python is used to perform numerical experiments on the classical datasets to verify the effectiveness of the instant delivery model. The proposed AACO-RTLF algorithm shows its advantages in instant delivery order scheduling when compared to the other state-of-the-art algorithms.

Herein, a novel controllable and nondestructive semiconductor doping technique is proposed by introducing defects in the h-BN/GeSe van der Waals heterostructure. A perfect n-/p-type channel layer can be achieved through charge transfer between the defective h-BN substrate layer and the GeSe channel layer. The effect of this modulation doping strategy on the carrier mobility of the channel layers is also investigated. In the case of the h-BN/GeSe heterostructure with the introduction of boron vacancies, the electron mobility of 2D GeSe in the x(y) direction is 1479.11 (1343.95) cm2V–1s–1, and the hole mobility in the x(y) direction is 1031.88 (864.44) cm2V–1s–1. As for producing nitrogen vacancies in the h-BN/GeSe heterostructure, the electron mobility of 2D GeSe in the x(y) direction is predicted to be as high as 1643.77 (1678.14) cm2V–1s–1, and the hole mobility in the x(y) direction is about 1129.51 (1563.50) cm2V–1s–1, respectively. In contrast, the electron (hole) mobility in the x-direction is dramatically decreased to 705.29 (630.85) cm2V–1s–1, and the electron (hole) mobility in the y-direction is only 701.40 (481.37) cm2V–1s–1for the GeSe layer by using the traditional semiconductor doping method. The nondestructive doping strategy provides an effective method to modulate two-dimensional semiconductor channel materials while avoiding lattice damage, thus resulting in much higher carrier mobility. It indicates that the novel semiconductor doping technique has a great promising application in electronic and optoelectronic devices.

Deep neural networks play an important role in the recognition of waste electrical appliances. However, deep neural network components still lack reliability in decision-making features. To address this problem, a sparse convolutional model with semantic expression (SCMSE) is proposed. First, a low-rank sparse semantic expression component, combining the benefits of residual networks and sparse representation, is adapted to enhance sparse feature extraction and semantic expression. Second, a reliable network architecture is obtained by iterating the optimal sparse solution, enhancing semantic expression. Finally, the results of visualization experiments on the waste electrical appliances dataset demonstrate that the proposed SCMSE can obtain excellent semantic performance.

The reviews written by users in E-commerce platform have been fully exploited by product-related question answering systems, which ignore the product descriptions with valuable information to improve the system performance, especially for objective questions. In this paper, we propose a model named as Sentiment-enhanced Answer Generation and product Descriptions Fusing (SAGDF) for Product-related Question Answering task. The valid information from user reviews and product descriptions are learned jointly for answer generation. Importantly, the sentiment analysis task is performed initially to make the model judge the sentiment tendency correctly for answer accuracy. The review encoder of the model is fine-tuned on the large-scale Amazon review dataset to implement the sentiment analysis task. In addition, we build the dataset named AmazonQARD and it contains both reviews and corresponding product descriptions. The proposed model is trained on AmazonQARD and it processes user reviews individually and integrates product descriptions to constantly correct the generated answers iteratively. Experimental results demonstrate that SAGDF significantly outperforms the other baseline systems. [ABSTRACT FROM AUTHOR]

Biomedical Question Answering aims to extract an answer to the given question from a biomedical context. Due to the strong professionalism of specific domain, it's more difficult to build large-scale datasets for specific domain question answering. Existing methods are limited by the lack of training data, and the performance is not as good as in open-domain settings, especially degrading when facing to the adversarial sample. We try to resolve the above issues. First, effective data augmentation strategies are adopted to improve the model training, including slide window, summarization and round-trip translation. Second, we propose a model weighting strategy for the final answer prediction in biomedical domain, which combines the advantage of two models, open-domain model QANet and BioBERT pre-trained in biomedical domain data. Finally, we give adversarial training to reinforce the robustness of the model. The public biomedical dataset collected from PubMed provided by BioASQ challenge is used to evaluate our approach. The results show that the model performance has been improved significantly compared to the single model and other models participated in BioASQ challenge. It can learn richer semantic expression from data augmentation and adversarial samples, which is beneficial to solve more complex question answering problems in biomedical domain.

With the appearance of a huge number of reusable electronic products, the precise value evaluation has become an urgent problem to be solved in the recycling process. Traditional methods rely on manual intervention mostly. In order to make the model more suitable for the dynamic updating, this paper proposes the reinforcement learning based electronic products value prediction model, and it integrates market information to achieve timely and stable prediction results. The basic attributes and depreciation attributes of the product are modeled by two parallel neural networks separately to learn the different effects for prediction. Most importantly, the double deep Qnetwork is adopted to fuse market information by reinforcement learning strategy, and the training on the old product data can be used to predict the following appeared product, which alleviates the cold start problem. Experiments on the real mobile phone recycling platform data verify that the model has achieved higher accuracy and it has a better generalization ability.

Aiming at solving the problem that it is challenging to choose the appropriate price adjustment strategy according to the market fluctuations, an adaptive price adjustment method based on dual deep fuzzy networks (DDFN) is designed. First, a price adjustment model based on DDFN is established. Through interactively learning the recycling market environment, the description of the mapping relationship between the market environment information and the price adjustment action is realized. Second, based on a greedy strategy to calculate the optimal price adjustment action, it is possible to make small adjustments based on the preliminary estimated value of the waste mobile phone, and complete the judgment of the mobile phone recycling price. Third, based on the market feedback, the gradient descent algorithm is used to update parameters of the model to improve the performance. The proposed adaptive price adjustment method based on DDFN is applied to the actual transaction process, and the results show that the proposed method can ensure the accuracy and reliability of the adjustment results of the mobile phone recycling price.

Model recognition of second-hand mobile phones has been considered as an essential process to improve the efficiency of phone recycling. However, due to the diversity of mobile phone appearances, it is difficult to realize accurate recognition. To solve this problem, a mobile phone recognition method based on bilinear-convolutional neural network (B-CNN) is proposed in this paper. First, a feature extraction model, based on B-CNN, is designed to adaptively extract local features from the images of secondhand mobile phones. Second, a joint loss function, constructed by center distance and softmax, is developed to reduce the interclass feature distance during the training process. Third, a parameter downscaling method, derived from the kernel discriminant analysis algorithm, is introduced to eliminate redundant features in B-CNN. Finally, the experimental results demonstrate that the B-CNN method can achieve higher accuracy than some existing methods.

Biomedical machine reading comprehension aims to extract the answer to the given question from complex biomedical passages, which requires the machine to have the ability to process strong comprehension on natural language. Recent progress has made on this task, but still severely restricted by the insufficient training data due to the domain-specific nature. To solve this problem, we propose a hierarchical question-aware context learning model trained by the multi-task transfer learning algorithm, which can capture the interaction between the question and the passage layer by layer, with multi-level embeddings to strengthen the ability of the language representation. The multi-task transfer learning algorithm leverages the advantages of different machine reading comprehension tasks to improve model generalisation and robustness, pre-training on multiple large-scale open-domain data sets and fine-tuning on the target-domain training set. Moreover, data augmentation is also adopted to create new training samples with various expressions. The public biomedical data set collected from PubMed provided by BioASQ is used to evaluate the model performance. The results show that our method is superior to the best recent solution and achieves a new state of the art.

Sequential models based on deep learning are widely used in sequential recommendation task, but the increase of model parameters results in a higher latency in the inference stage, which limits the real-time performance of the model. In order to make the model strike a balance between efficiency and effectiveness, the knowledge distillation technology is adopted to transfer the pre-trained knowledge from the large teacher model to the small student model. We propose a multi-stage knowledge distillation method based on interest knowledge, including interest representation knowledge and interest drift knowledge. In the process of knowledge transfer, expert distillation is designed to transform the knowledge dimension of student model to alleviate the loss of original knowledge information. Specially, curriculum learning is introduced for multi-stage knowledge learning, which further makes the teacher model effectively transfer the knowledge to the student model with limited ability. The proposed method on three real-world datasets including MovieLen-1M, Amazon Game and Steam datasets. The experimental results demonstrate that our method is superior to the other compared distillation method significantly and multi-stage learning makes the student model achieve the knowledge step by step for improvement. [ABSTRACT FROM AUTHOR]

Precise “bottom-up” synthesis by surface-assisted chemical reaction provides advanced approaches for the fabrication of two-dimensional (2D) robust covalent nanostructures, which are bound to contain defects due to the irreversible properties of covalent bonds. The further introduction of metal–organic coordination interactions possessing self-correction abilities and yielding comparable stabilities would be a strategically advanced supplement for the construction of well-ordered complex covalent networks. In this report, the on-surface synthesis of Au-coordinated bipyrenes and polypyrenes is achieved on Au(111) by a combination of triggering surface-assisted dehalogenative coupling and capture of Au adatoms. The resulting nanostructures are characterized using a scanning tunneling microscope and X-ray photoelectron spectroscopy analysis and further verified by density functional theory calculations. Quinone group functionality present in the pyrene precursor molecules is the key by which the formation of O–Au–O coordination bonds is facilitated, in turn forcing the expulsion of bromine atoms from the thus formed 2D nanostructures.

In two-dimensional (2D) systems, high mobility is typically achieved in low-carrier-density semiconductors and semimetals. Here, we discover that the nanobelts of Weyl semimetal NbAs maintain a high mobility even in the presence of a high sheet carrier density. We develop a growth scheme to synthesize single crystalline NbAs nanobelts with tunable Fermi levels. Owing to a large surface-to-bulk ratio, we argue that a 2D surface state gives rise to the high sheet carrier density, even though the bulk Fermi level is located near the Weyl nodes. A surface sheet conductance up to 5–100 S per □ is realized, exceeding that of conventional 2D electron gases, quasi-2D metal films, and topological insulator surface states. Corroborated by theory, we attribute the origin of the ultrahigh conductance to the disorder-tolerant Fermi arcs. The evidenced low-dissipation property of Fermi arcs has implications for both fundamental study and potential electronic applications.

Visual recognition technologies based on deep learning have been gradually playing an important role in various resource recovery fields. However, in the field of metal resource recycling, there is still a lack of intelligent and accurate recognition of metallic products, which seriously hinders the operation of the metal resource recycling industry chain. In this article, a convolutional neural network with dual attention mechanism and multi-branch residual blocks is proposed to realize the recognition of metallic products with a high accuracy. First, a channel-spatial dual attention mechanism is introduced to enhance the model sensitivity on key features. The model can focus on key features even when extracting features of metallic products with too much confusing information. Second, a deep convolutional network with multi-branch residual blocks as the backbone while embedding a dual-attention mechanism module is designed to satisfy deeper and more effective feature extraction for metallic products with complex characteristic features. To evaluate the proposed model, a waste electrical and electronic equipment (WEEE) dataset containing 9266 images in 18 categories and a waste household metal appliance (WHMA) dataset containing 11,757 images in 23 categories are built. The experimental results show that the accuracy reaches 94.31% and 95.88% in WEEE and WHMA, respectively, achieving high accuracy and high quality recycling.

Data sparseness brings significant challenges to the research of recommender systems. It becomes more severe for neighborhood-based collaborative filtering. We introduce the trust relation computing of the sociology field. Instead of the traditional similarity computing method, the trust degree is integrated for the nearest neighbor selection. The trust network is constructed by the expansion of different path length, and the trust value between the users can be obtained by the trust transmission rules. To verify the effectiveness of our method, we give the experiments on different techniques for rating prediction, including Pearson based method, the User position similarity (UPS) based method and the trust with Pearson and UPS. We also give the t-test result. The implementation of the experiment on the Epinions data set shows that the proposed method can improve the system performance significantly.

Due to the lack of parallel data in current grammatical error correction (GEC) task, models based on sequence to sequence framework cannot be adequately trained to obtain higher performance. We propose two data synthesis methods which can control the error rate and the ratio of error types on synthetic data. The first approach is to corrupt each word in the monolingual corpus with a fixed probability, including replacement, insertion and deletion. Another approach is to train error generation models and further filtering the decoding results of the models. The experiments on different synthetic data show that the error rate is 40% and that the ratio of error types is the same can improve the model performance better. Finally, we synthesize about 100 million data and achieve comparable performance as the state of the art, which uses twice as much data as we use.

This research investigates the fixed-time event-triggered fuzzy adaptive control for uncertain nonlinear systems with full-state constraints. Due to the difficulty of modeling and the inherent characteristics of mechanical structures, uncertainties and state constraints often arise in engineering applications, and the system may suffer from network congestion. Ignoring the effects of these constraints can affect the performance of the system. In addition, the system often requires high convergence speeds to increase productivity. To cope with these problems, this study investigates the fixed-time event-triggered fuzzy adaptive control method. First, special barrier Lyapunov functions (BLFs) are constructed to ensure that the full-state constraints are not violated. Furthermore, considering that the communication resources of practical systems are limited, a fuzzy based event-triggered mechanism (ETM) is designed. On this basis, a fixed-time fuzzy adaptive controller is constructed to achieve the fast convergence of the system. Finally, simulation results verify the feasibility. [ABSTRACT FROM AUTHOR]

Background and aims:Patients aged ≥75 years compose a high-risk subgroup for acute myocardial infarction (AMI). It is unknown whether myocardial perfusion in these patients is decreased compared with younger ones after primary percutaneous coronary intervention (PPCI), which may contribute to their worse prognosis. We compared epicardial and myocardial perfusions as well as short-term outcomes between elderly and younger patients undergoing PPCI. Methods:A total of 547 consecutive PPCI patients were prospectively enrolled; of these, 106 were elderly (≥75 yrs). Epicardial perfusion was evaluated by the Thrombolysis in Myocardial Infarction (TIMI) flow grade and corrected TIMI frame count (CTFC), and myocardial perfusion was evaluated by the TIMI myocardial perfusion grade (TMPG) and ST-segment resolution (STR). Results:Despite comparable epicardial perfusion pre- and post-PPCI, elderly patients had impaired myocardial perfusion after PPCI, as measured by reduced TMPG (35.9% vs14.5%, p=0.001) and absent STR (18.9% vs9.8%, p=0.009). After adjusting for clinical and angiographic risk profiles, multivariate analysis showed that age ≥75 years remained independently associated with reduced TMPG or absent STR. In the whole population, multivariate analysis revealed that both age ≥75 years and absent STR were independently associated with 3-month major adverse cardiac events (MACE). In the elderly subgroup, multivariate analysis identified absent STR as the strongest determinant of 3-month MACE. Conclusions:Age is associated with impaired myocardial perfusion, but not epicardial perfusion, after PPCI for AMI. To further improve the outcome of elderly AMI patients, efforts should be aimed at improving myocardial perfusion beyond epicardial recanalization.

Federated learning (FL) plays an important role in collaborative distributed modeling. However, most studies cannot address poor generalization of out-of-distribution (OoD) data. Efforts have been exerted to address data heterogeneity among participants, but yielding limited success. Here, we propose an information bottleneck based FL method (FedIB), which aims to build a model with better OoD generalization. We extract the domain-invariance of different source domains to mitigate the domain heterogeneity under the cross-silo scenarios. Next, given the scale imbalance, we balance the representation importance of different domains with reweighting a better invariance across multiple domains. In addition, the convergence of FedIB is analyzed. As opposed to aligning distributions or eliminating redundancy by previous methods, FedIB achieves better domain generalization explicitly by eliminating the pseudo-invariant features. Finally, we conduct extensive experiments on various datasets revealing that FedIB has superior performances facing OoD and scale imbalance scenarios in distributed modeling. • We extract domain-invariant representation via information bottleneck across different clients. • Pseudo-invariant features of different clients are eliminated in the form of mutual information. • We propose the reweighting technique to balance disturbances from data scales for a better approximation of domain invariance. invariance. [ABSTRACT FROM AUTHOR]