Search

Effective querying of data in the road networks is an important problem in the Internet of vehicles. Aggregate nearest neighbor queries can return the objects that minimizes an aggregate distance function on road networks considering a set of query points in the Internet of vehicles. And ${k}$ aggregate nearest neighbor query ( ${k}$ - ANN) is a complicate version for the basic one. The existing ${k}$ - ANN queries lack effective model to deal with the uncertain data and the existing query methods cannot be applied to solve the problem of ( ${k}$ - ANN) query on uncertain data directly. Therefore, in this paper, a probabilistic threshold ${k}$ - ANN query method based on uncertain Voronoi diagram is proposed. The method includes three phases: processing phase, pruning phase and refinement phase. The processing phase is to compute the minimum covered circle of the query dataset which is prepared for the pruning phase. In pruning phase, the different pruning algorithms are proposed for the corresponding three aggregate function of aggregate nearest neighbor query. The data points that cannot be the result are pruned and the candidate set is obtained. In refinement phase, the sets composed of ${k}$ data points in candidate set whose probabilities are not less than the user-specified threshold are stored into the result set and returned to the user. Experiments are performed to evaluate the effectiveness and superiority of these algorithms on probabilistic threshold k-ANN query.

Chemo-photothermal treatment is one of the most efficient strategies for cancer therapy. However, traditional drug carriers without near-infrared absorption capacity need to be loaded with materials behaving photothermal properties, as it results in complicated synthesis process, inefficient photothermal effects and hindered NIR-mediated drug release. Herein we report a facile synthesis of a polyethylene glycol (PEG) linked liposome (PEG-liposomes) coated doxorubicin (DOX)-loaded ordered mesoporous carbon (OMC) nanocomponents (PEG-LIP@OMC/DOX) by simply sonicating DOX and OMC in PEG-liposomes suspensions. The as-obtained PEG-LIP@OMC/DOX exhibits a nanoscale size (600 ± 15 nm), a negative surface potential (−36.70 mV), high drug loading (131.590 mg/g OMC), and excellent photothermal properties. The PEG-LIP@OMC/DOX can deliver loaded DOX to human MCF-7 breast cancer cells (MCF-7) and the cell toxicity viability shows that DOX unloaded PEG-LIP@OMC has no cytotoxicity, confirming the PEG-LIP@OMC itself has excellent biocompatibility. The NIR-triggered release studies demonstrate that this NIR-responsive drug delivery system enables on-demand drug release. Furthermore, cell viability results using human MCF-7 cells demonstrated that the combination of NIR-based hyperthermal therapy and triggered chemotherapy can provide higher therapeutic efficacy than respective monotherapies. With these excellent features, we believe that this phospholipid coating based multifunctional delivery system strategy should promote the application of OMC in nanomedical applications.

Crowdsourcing is an effective way to collect plenty of labeled data. Rather than just relying on feedback from the crowd, active learning can intentionally request informative instances to be annotated in surveillance applications. Previous work that combines crowdsourcing with active learning focuses on the scenario with the expert being responsible for the most matching task in common communication surveillance. Compared with similar methods, we propose an innovative approach based on the active cross-query learning scheme, allowing each ordinary worker instead of domain experts to label part of the selected query samples, especially in the networks of smart surveillance. By using the balanced incomplete block design (BIBD), each labeling task is repeated several times to complete the cross-query learning. The generated consensus labels are iteratively added to the existing labeled datasets for training the classifier. Experiments conducted on three real-world datasets with our algorithms demonstrate that our method ensures model accuracy and label quality in terms of text classification compared with the several state-of-the art algorithms.

Introducing negative items into sentences can shift the polarity of emotional words and leads to misclassification. Therefore, dealing with the negative item is indispensable to the analysis of the polarity of tweets. This paper first uses the combination of Conjunction Analysis (CA) technology and Punctuation Mark Identification (PMI) technology to detect negation cue and its scope. Besides, we propose the OL-DAWE model, which uses Data Augmentation(DA) technology to generate opposed tweets according to the original tweet. The model extends the training data set, and test data set and learns the original and opposed sides of the tweet in the training module. When predicting the polarity of tweets, the OL-DAWE model considers the positive degree (negative degree) of the original tweet and the negative degree (positive degree) of its opposed tweet. We conduct experiments on two real-world data sets. We prove the effectiveness of our combined technology in negation processing and show that the OL-DAWE model in the polarity sentiment analysis of tweets is better than the baseline for its simplicity and high efficiency.

Active learning has been widely utilized to reduce the labeling cost of supervised learning. By selecting specific instances to train the model, the performance of the model was improved within limited steps. However, rare work paid attention to the effectiveness of active learning on it. In this paper, we proposed a deep active learning model with bidirectional encoder representations from transformers (BERT) for text classification. BERT takes advantage of the self-attention mechanism to integrate contextual information, which is beneficial to accelerate the convergence of training. As for the process of active learning, we design an instance selection strategy based on posterior probabilities Margin, Intra-correlation and Inter-correlation (MII). Selected instances are characterized by small margin, low intra-cohesion and high inter-cohesion. We conduct extensive experiments and analytics with our methods. The effect of learner is compared while the effect of sampling strategy and text classification is assessed from three real datasets. The results show that our method outperforms the baselines in terms of accuracy.

Black phosphorus (BP) has attracted increasing attention for cancer therapy because of its good biocompatibility and biodegradability and high photothermal conversion efficiency. Here, we developed...

A novel nanosensor is developed for selective and highly sensitive detection of phytic acid (PA) based on small-sized conjugated polyelectrolyte dots (Pdots) fabricated from a new conjugated polymer (P1) by a modified reprecipitation method. P1 featuring a π-delocalized backbone bearing meta-substituted pyridyl groups can be endowed with enhanced flexibility and hence is beneficial for the synthesis of ultrasmall Pdots (i.e. Pdot-1, ∼3.8 nm in average diameter) as well as for the binding of Fe3+, thus leading to the obvious fluorescence quenching of Pdot-1 (∼444 nm) in the presence of Fe3+ via an electron transfer (ET) process. In addition, phytic acid with six phosphate groups exhibits strong chelating ability. When phytic acid is added, phytic acid readily binds to Fe3+ and the fluorescence of Pdot-1 around 444 nm can be recovered, rendering the supersensitive and selective sensing of PA. Under the optimum conditions, this ultra-small Pdot-based nanoprobe favors the fluorescent determination of PA with the detection limit as low as 10 nM. Particularly, Pdot-1 with bright blue fluorescence exhibits low cytotoxicity. Furthermore, the small-sized and biocompatible Pdot-1 can be applied to the sensitive fluorescence assay for PA in cell extracts and the efficient imaging of PA in live cells.

Numerous applications of recommender systems can provide us a tool to understand users. A group recommender reflects the analysis of multiple users’ behavior, and aims to provide each user of the group with the things they involve according to users’ preferences. Currently, most of the existing group recommenders ignore the interaction among the users. However, in the course of group activities, the interactive preferences will dramatically affect the success of recommenders. The problem becomes even more challenging when some unknown preferences of users are partly influenced by other users in the group. An interaction-based method named GRIP (Group Recommender Based on Interactive Preference) is presented which can use group activity history information and recommender post-rating feedback mechanism to generate interactive preference parameters. To evaluate the performance of the proposed method, it is compared with traditional collaborative filtering on the MovieLens dataset. The results indicate the superiority of the GRIP recommender for multi-users regarding both validity and accuracy.

Low drug loading, premature drug leakage, and intratumoral genetic heterogeneity are three main challenges that hinder the successful nanotherapeutics-based oncotherapy, as they provide insufficient therapeutic efficacy, systematic adverse effects, and multidrug resistance, respectively. To address these challenges, we herein develop near-infrared (NIR) laser-sensitive DNA-modified hollow mesoporous silica nanoparticles (HMSNs) with dual cargo loading for chemo-photothermal combined treatment of tumors. Starting from the zeolitic imidazolate framework-8 (ZIF-8) template, a layer of mesoporous silica is coated on ZIF-8 (ZIF-8@MSNs), and subsequently the template is self-degraded under acidic conditions to obtain HMSNs. It is demonstrated that the as-made HMSNs possesses a well-defined morphology, large hollow cavities, and abundant mesoporous structures. After loading of indocyanine green into HMSNs’ core (ICG@HMSNs), the DNA strands, which are composed by sequential cytosine-guanine (CG) base pairs, are t...

Indocyanine green (ICG) is the only near-infrared (NIR) dye approved by the United States Food and Drug Administration (FDA). Although it is highly desirable, some bottlenecks still remain in clinical applications, such as poor photostability, poor thermal stability, and lack of target specificity. To solve these problems, a zeolitic imidazolate framework-8 (ZIF-8)-based ICG theranostic agent was constructed by one-pot synthesis for fluorescence imaging and photothermal therapy (PTT). The as-synthesized ICG@ZIF-8 nanoparticles (NPs) displayed ultrahigh loading capacity, superior photothermal stability, good anti-photobleaching ability, good biocompatibility, efficient cellular uptake, and favourable photothermal killing capacity for human hepatocarcinoma SMMC-7721 cells. Importantly, in vivo experiments showed that ICG@ZIF-8 NPs accurately and sensitively detected tumors by fluorescence molecular imaging. The PTT results indicated that ICG@ZIF-8 NPs efficiently induced a local ablation effect under a single NIR laser irradiation. The tumor was completely suppressed, and no tumor recurrence or treatment-induced toxicity was observed. The described particles have the potential to act as a promising platform for cancer theranostic nanomedicine.

Twitter produces various colloquial tweets as an open communication platform. Previous research shows the frequency of negative sentences in spoken sentences is twice that of written texts. Negative items in negative sentences can shift the polarity of words with feelings, and leads to wrong classification. Therefore, negation processing is essential for the sentiment classification of tweets generated by Twitter. On the basis of considering the importance of negation which is often ignored in previous work, this paper firstly combines the technique of Conjunction Analysis (CA) with the technique of Punctuation Mark Identification (PMI) to detect the negation clue and its scope more accurately. In addition, We propose the OL-DAWE model. The model uses Data Augmentation (DA) approach to generate the opposed tweet according to the original tweet. The model extends learnable data and learns its polarity from both of positive and negative aspects of a tweet. In predicting the polarity of a tweet, the OL-DAWE model takes the positive (negative) degree of the original tweet into account, and also considers the negative (positive) degree of the opposed tweet. We conduct two experiments on two real-world data sets and analyze the experimental results from the perspectives of accuracy and robustness. We prove the effectiveness of our combined technology in negation processing and show that our OL-DAWE model in the polarity sentiment analysis of tweets is better than the baseline for its simplicity and high efficiency.

Microblogging sentiment analysis aims at exploring people’s opinion on social networks such as Twitter and Weibo. Existing work mainly focus on the English corpus based on Distant Supervision, which ignores the noise data in corpus and internationalization. The field of Weibo sentiment analysis lacks a large-scale and complete corpus for application and evaluation. In this work, we formulate the problem of corpus construction into an Information Retrieval problem and construct a Weibo sentiment analysis corpus called Senti-weibo. We also release a weibo pre-processing toolkit in order to unify the pre-processing rules of Weibo text. Eventually, we apply these works to implement a real-time Weibo sentiment analysis platform: S2AP, which serves to analyze and track the sequential sentiment of Weibo topics.

With the widespread use of big data, knowledge graph has become a new hotspot. It is used in intelligent question answering, recommendation system, map navigation and so on. Constructing a knowledge graph includes ontology construction, annotated data, relation extraction, and ontology inspection. Relation extraction is to solve the problem of entity semantic linking, which is of great significance to many natural language processing applications. Research related to relation extraction has gained momentum in recent years, necessitating a comprehensive survey to offer a bird’s-eye view of the current state of relation extraction. In this paper, we discuss the development process of relation extraction, and classify the relation extraction algorithms in recent years. Furthermore, we discuss deep learning, reinforcement learning, active learning and transfer learning. By analyzing the basic principles of supervised learning, unsupervised learning, semi-supervised learning and distant supervision, we elucidate the characteristics of different relation extraction algorithms, and give the potential research directions in the future.

Sentiment analysis of micro-blog topic aims to explore people’s attitudes towards a topic or event on social networks. Most existing research analyzed the micro-blog sentiment by traditional algorithms such as Naive Bayes and SVM based on the manually labelled data. They do not consider timeliness of data and inwardness of the topics. Meanwhile, few Chinese micro-blog sentiment analysis based on large-scale corpus is investigated. This paper focuses on the analysis of sequential sentiment based on a million-level Chinese micro-blog corpora to mine the features of sequential sentiment precisely. Distant supervised learning method based on micro-blog expressions and sentiment lexicon is proposed and fastText is used to train word vectors and classification model. The timeliness of analysis is guaranteed on the premise of ensuring the accuracy of classifier. The experiment shows that the accuracy of the classifier reaches 92.2%, and the sequential sentiment analysis based on this classifier can accurately reflect the emotional trend of micro-blog topics.