scholarly journals A Survey of Deep Active Learning

2022 ◽  
Vol 54 (9) ◽  
pp. 1-40
Author(s):  
Pengzhen Ren ◽  
Yun Xiao ◽  
Xiaojun Chang ◽  
Po-Yao Huang ◽  
Zhihui Li ◽  
...  
Keyword(s):  
Active Learning ◽  
Rapid Development ◽  
Internet Technology ◽  
High Quality ◽  
Powerful Learning ◽  
Learning Capabilities ◽  
Comprehensive Survey ◽  
Massive Number ◽  
The Cost ◽  
To Receive

Active learning (AL) attempts to maximize a model’s performance gain while annotating the fewest samples possible. Deep learning (DL) is greedy for data and requires a large amount of data supply to optimize a massive number of parameters if the model is to learn how to extract high-quality features. In recent years, due to the rapid development of internet technology, we have entered an era of information abundance characterized by massive amounts of available data. As a result, DL has attracted significant attention from researchers and has been rapidly developed. Compared with DL, however, researchers have a relatively low interest in AL. This is mainly because before the rise of DL, traditional machine learning requires relatively few labeled samples, meaning that early AL is rarely according the value it deserves. Although DL has made breakthroughs in various fields, most of this success is due to a large number of publicly available annotated datasets. However, the acquisition of a large number of high-quality annotated datasets consumes a lot of manpower, making it unfeasible in fields that require high levels of expertise (such as speech recognition, information extraction, medical images, etc.). Therefore, AL is gradually coming to receive the attention it is due. It is therefore natural to investigate whether AL can be used to reduce the cost of sample annotation while retaining the powerful learning capabilities of DL. As a result of such investigations, deep active learning (DeepAL) has emerged. Although research on this topic is quite abundant, there has not yet been a comprehensive survey of DeepAL-related works; accordingly, this article aims to fill this gap. We provide a formal classification method for the existing work, along with a comprehensive and systematic overview. In addition, we also analyze and summarize the development of DeepAL from an application perspective. Finally, we discuss the confusion and problems associated with DeepAL and provide some possible development directions.

scholarly journals LeafGo: Leaf to Genome, a quick workflow to produce high-quality De novo genomes with Third Generation Sequencing technology

2021 ◽  
Author(s):  
Patrick Driguez ◽  
Salim Bougouffa ◽  
Karen Carty ◽  
Alexander Putra ◽  
Kamel Jabbari ◽  
...  
Keyword(s):  
De Novo ◽  
Rapid Development ◽  
Plant Genome ◽  
Plant Genomics ◽  
High Quality ◽  
High Molecular Weight Dna ◽  
Tissue Samples ◽  
Sequencing Technologies ◽  
The Cost ◽  
New Generation

AbstractRecent years have witnessed a rapid development of sequencing technologies. Fundamental differences and limitations among various platforms impact the time, the cost and the accuracy for sequencing whole genomes. Here we designed a complete de novo plant genome generation workflow that starts from plant tissue samples and produces high-quality draft genomes with relatively modest laboratory and bioinformatic resources within seven days. To optimize our workflow we selected different species of plants which were used to extract high molecular weight DNA, to make PacBio and ONT libraries for sequencing with the Sequel I, Sequel II and GridION platforms. We assembled high-quality draft genomes of two different Eucalyptus species E. rudis, and E. camaldulensis to chromosome level without using additional scaffolding technologies. For the rapid production of de novo genome assembly of plant species we showed that our DNA extraction protocol followed by PacBio high fidelity sequencing, and assembly with new generation assemblers such as hifiasm produce excellent results. Our findings will be a valuable benchmark for groups planning wet- and dry-lab plant genomics research and for high throughput plant genomics initiatives.

scholarly journals INTELLIGENT MODE OF ELECTRONIC COMMERCE BASED ON DATA MINING TECHNOLOGY

2018 ◽  
Vol 48 (4) ◽  
pp. 267-272
Author(s):  
Z. L. WU ◽  
D. WANG ◽  
Y. T. SU ◽  
H. M. LI
Keyword(s):  
System Reliability ◽  
Penetration Rate ◽  
Rapid Development ◽  
External Environment ◽  
Internet Technology ◽  
Distribution Model ◽  
Factors Affecting ◽  
Internet Users ◽  
Intelligent Logistics ◽  
The Cost

With the rapid development of Internet technology, the penetration rate of Internet in China has exceeded 50 %, and more and more Internet users have chosen to shop online. Based on the analysis of the current situation of e-commerce development, this paper analyzes the influencing factors affecting the reliability of e-commerce logistics from the aspects of information technology, facilities and equipment, personnel operation and external environment. Additionally, it constructs the E-commerce intelligent logistics reliability distribution model and simulates the example. The research results show that, when the maximum and minimum reliability and complexity are not considered, the priority of improving the important high unit has a great impact on the reliability of the whole system. An increase in unit reliability can lead to an increase in system reliability and an increase in cost. When the reliability is increased to a certain extent, the continued increase will greatly increase the cost, and the cost of increasing the system unit reliability is greatly increased.

scholarly journals Cost-savings achieved in two semesters through the adoption of open educational resources

2014 ◽  
Vol 15 (2) ◽  
Author(s):  
John Levi Hilton III ◽  
T. Jared Robinson ◽  
David Wiley ◽  
J. Dale Ackerman
Keyword(s):  
Higher Education ◽  
Student Loans ◽  
Cost Savings ◽  
The United States ◽  
Open Educational Resources ◽  
Educational Resources ◽  
High Quality ◽  
The Cost ◽  
Quality Learning ◽  
To Receive

<p>Textbooks represent a significant portion of the overall cost of higher education in the United States. The burden of these costs is typically shouldered by students, those who support them, and the taxpayers who fund the grants and student loans which pay for textbooks. Open educational resources (OER) provide students a way to receive high-quality learning materials at little or no cost to students. We report on the cost savings achieved by students at eight colleges when these colleges began utilizing OER in place of traditional commercial textbooks.</p>

scholarly journals Mapping the Sharing Economy in China

2020 ◽  
Vol 12 (16) ◽  
pp. 6333
Author(s):  
Chan Liu ◽  
Raymond K. H. Chan ◽  
Maofu Wang ◽  
Zhe Yang
Keyword(s):  
Global Economy ◽  
Rapid Development ◽  
Sharing Economy ◽  
Essential Elements ◽  
Mobile Internet ◽  
Internet Technology ◽  
Short Term ◽  
Bona Fide ◽  
The Government ◽  
Idle Capacity

Harnessing the rapid development of mobile internet technology, the sharing economy has experienced unprecedented growth in the global economy, especially in China. Likely due to its increasing popularity, more and more businesses have adopted this label in China. There is a concern as to the essential meaning of the sharing economy. As it is difficult to have a universally accepted definition, we aim to map the sharing economy and demystify the use of it in China in this paper. We propose seven organizing essential elements of the sharing economy: access use rights instead of ownership, idle capacity, short term, peer-to-peer, Internet platforms mediated, for monetary profit, and shared value orientation. By satisfying all or only parts of these elements, we propose one typology of sharing economy, and to differentiate bona fide sharing economy from quasi- and pseudo-sharing economy. Finally, there are still many problems that need to be solved urgently in the real sharing economy from the perspective of the government, companies and individuals.

scholarly journals ALPINE: Active Link Prediction Using Network Embedding

2021 ◽  
Vol 11 (11) ◽  
pp. 5043
Author(s):  
Xi Chen ◽  
Bo Kang ◽  
Jefrey Lijffijt ◽  
Tijl De Bie
Keyword(s):  
Active Learning ◽  
Protein Interactions ◽  
Link Prediction ◽  
Prediction Accuracy ◽  
Real Data ◽  
Network Embedding ◽  
Protein Protein Interactions ◽  
Additional Information ◽  
The Cost ◽  
Active Link

Many real-world problems can be formalized as predicting links in a partially observed network. Examples include Facebook friendship suggestions, the prediction of protein–protein interactions, and the identification of hidden relationships in a crime network. Several link prediction algorithms, notably those recently introduced using network embedding, are capable of doing this by just relying on the observed part of the network. Often, whether two nodes are linked can be queried, albeit at a substantial cost (e.g., by questionnaires, wet lab experiments, or undercover work). Such additional information can improve the link prediction accuracy, but owing to the cost, the queries must be made with due consideration. Thus, we argue that an active learning approach is of great potential interest and developed ALPINE (Active Link Prediction usIng Network Embedding), a framework that identifies the most useful link status by estimating the improvement in link prediction accuracy to be gained by querying it. We proposed several query strategies for use in combination with ALPINE, inspired by the optimal experimental design and active learning literature. Experimental results on real data not only showed that ALPINE was scalable and boosted link prediction accuracy with far fewer queries, but also shed light on the relative merits of the strategies, providing actionable guidance for practitioners.

scholarly journals Text Mining of Hazard and Operability Analysis Reports Based on Active Learning

Processes ◽  
2021 ◽  
Vol 9 (7) ◽  
pp. 1178
Author(s):  
Zhenhua Wang ◽  
Beike Zhang ◽  
Dong Gao
Keyword(s):  
Active Learning ◽  
Named Entity Recognition ◽  
Entity Recognition ◽  
Chemical System ◽  
Chemical Safety ◽  
High Quality ◽  
Data Set ◽  
Final Model ◽  
Named Entity ◽  
Sampling Algorithms

In the field of chemical safety, a named entity recognition (NER) model based on deep learning can mine valuable information from hazard and operability analysis (HAZOP) text, which can guide experts to carry out a new round of HAZOP analysis, help practitioners optimize the hidden dangers in the system, and be of great significance to improve the safety of the whole chemical system. However, due to the standardization and professionalism of chemical safety analysis text, it is difficult to improve the performance of traditional models. To solve this problem, in this study, an improved method based on active learning is proposed, and three novel sampling algorithms are designed, Variation of Token Entropy (VTE), HAZOP Confusion Entropy (HCE) and Amplification of Least Confidence (ALC), which improve the ability of the model to understand HAZOP text. In this method, a part of data is used to establish the initial model. The sampling algorithm is then used to select high-quality samples from the data set. Finally, these high-quality samples are used to retrain the whole model to obtain the final model. The experimental results show that the performance of the VTE, HCE, and ALC algorithms are better than that of random sampling algorithms. In addition, compared with other methods, the performance of the traditional model is improved effectively by the method proposed in this paper, which proves that the method is reliable and advanced.

scholarly journals Dynamical Analysis and Optimal Control for a SEIR Model Based on Virus Mutation in WSNs

Mathematics ◽  
2021 ◽  
Vol 9 (9) ◽  
pp. 929
Author(s):  
Guiyun Liu ◽  
Jieyong Chen ◽  
Zhongwei Liang ◽  
Zhimin Peng ◽  
Junqiang Li
Keyword(s):  
Optimal Control ◽  
Rapid Development ◽  
Hamiltonian Function ◽  
Propagation Model ◽  
Dynamical Analysis ◽  
Optimal Control Strategy ◽  
Epidemic Dynamics ◽  
Optimization Control ◽  
The Cost ◽  
The Pontryagin Maximum Principle

With the rapid development of science and technology, the application of wireless sensor networks (WSNs) is more and more widely. It has been widely concerned by scholars. Viruses are one of the main threats to WSNs. In this paper, based on the principle of epidemic dynamics, we build a SEIR propagation model with the mutated virus in WSNs, where E nodes are infectious and cannot be repaired to S nodes or R nodes. Subsequently, the basic reproduction number R0, the local stability and global stability of the system are analyzed. The cost function and Hamiltonian function are constructed by taking the repair ratio of infected nodes and the repair ratio of mutated infected nodes as optimization control variables. Based on the Pontryagin maximum principle, an optimal control strategy is designed to effectively control the spread of the virus and minimize the total cost. The simulation results show that the model has a guiding significance to curb the spread of mutated virus in WSNs.

scholarly journals Foundation Piles—A New Feature for Concrete 3D Printers

Materials ◽  
2021 ◽  
Vol 14 (10) ◽  
pp. 2545
Author(s):  
Marcin Hoffmann ◽  
Krzysztof Żarkiewicz ◽  
Adam Zieliński ◽  
Szymon Skibicki ◽  
Łukasz Marchewka
Keyword(s):  
3D Printing ◽  
Rapid Development ◽  
Construction Materials ◽  
Shallow Foundation ◽  
Soil Reinforcement ◽  
3D Printer ◽  
Permanent Formwork ◽  
3D Printers ◽  
New Feature ◽  
The Cost

Foundation piles that are made by concrete 3D printers constitute a new alternative way of founding buildings constructed using incremental technology. We are currently observing very rapid development of incremental technology for the construction industry. The systems that are used for 3D printing with the application of construction materials make it possible to form permanent formwork for strip foundations, construct load-bearing walls and partition walls, and prefabricate elements, such as stairs, lintels, and ceilings. 3D printing systems do not offer soil reinforcement by making piles. The paper presents the possibility of making concrete foundation piles in laboratory conditions using a concrete 3D printer. The paper shows the tools and procedure for pile pumping. An experiment for measuring pile bearing capacity is described and an example of a pile deployment model under a foundation is described. The results of the tests and analytical calculations have shown that the displacement piles demonstrate less settlement when compared to the analysed shallow foundation. The authors indicate that it is possible to replace the shallow foundation with a series of piles combined with a printed wall without locally widening it. This type of foundation can be used for the foundation of low-rise buildings, such as detached houses. Estimated calculations have shown that the possibility of making foundation piles by a 3D printer will reduce the cost of making foundations by shortening the time of execution of works and reducing the consumption of construction materials.

scholarly journals Acceptability of remote prescribing and postal delivery services for contraceptive pills and treatment of uncomplicated Chlamydia trachomatis

2020 ◽  
pp. bmjsrh-2020-200687
Author(s):  
Tom Nadarzynski ◽  
Ynez Symonds ◽  
Robert Carroll ◽  
Jo Gibbs ◽  
Sally Kidsley ◽  
...  
Keyword(s):  
Online Survey ◽  
Home Delivery ◽  
Transmitted Infection ◽  
Sexually Transmitted ◽  
Sti Testing ◽  
Contraceptive Pills ◽  
Remote Management ◽  
Delivery Services ◽  
The Cost ◽  
To Receive

ObjectivesThe digitalisation of sexual and reproductive health (SRH) services offers valuable opportunities to deliver contraceptive pills and chlamydia treatment by post. We aimed to examine the acceptability of remote prescribing and ‘medication-by-post’ in SRH.Study designAn online survey assessing attitudes towards remote management was distributed in three UK SRH clinics and via an integrated sexually transmitted infection (STI) postal self-sampling service. Logistic regressions were performed to identify potential correlates.ResultsThere were 1281 participants (74% female and 49% <25 years old). Some 8% of participants reported having received medication via post and 83% were willing to receive chlamydia treatment and contraceptive pills by post. Lower acceptability was observed among participants who were: >45 years old (OR 0.43 (95% CI 0.23–0.81)), screened for STIs less than once annually (OR 0.63 (0.42–0.93)), concerned about confidentiality (OR 0.21 (0.90–0.50)), concerned about absence during delivery (OR 0.09 (0.02–0.32)) or unwilling to provide blood pressure readings (OR 0.22 (0.04–0.97)). Higher acceptability was observed among participants who reported: previously receiving medication by post (OR 4.63 (1.44–14.8)), preference for home delivery over clinic collection (OR 24.1 (11.1–51.9)), preference for home STI testing (OR 10.3 (6.16–17.4)), ability to communicate with health advisors (OR 4.01 (1.03–15.6)) and willingness to: register their real name (OR 3.09 (1.43–10.6)), complete online health questionnaires (OR 3.09 (1.43–10.6)) and use generic contraceptive pills (OR 2.88 (1.21–6.83)).ConclusionsPostal treatment and entering information online to allow remote prescribing were acceptable methods for SRH services and should be considered alongside medication collection in pharmacies. These methods could be particularly useful for patients facing barriers in accessing SRH. The cost-effectiveness and implementation of these novel methods of service delivery should be further investigated.

Technology of animation in multimedia courseware of mechanical drawing

2021 ◽  
pp. 002072092098608
Author(s):  
Yucheng Shen ◽  
Wei Lu
Keyword(s):  
Divergent Thinking ◽  
Rapid Development ◽  
Development Trend ◽  
Internet Technology ◽  
Size Principle ◽  
Network Information ◽  
Teaching Platform ◽  
Multimedia Teaching ◽  
Multimedia Environment ◽  
Use Of Internet

With the rapid development of Internet technology in China, mechanical drawing plays a more and more important role in social development and practice. The main purpose is to use the course of mechanical drawing to accurately represent the appearance, size, principle and technology of the machine. It is often called the language of communication in the industry. In order to make mechanical drawing better applied and practiced, and to make maximum use of Internet technical resources, the establishment of multimedia courseware teaching mechanism is the development trend of mechanical drawing.In order to adapt to the trend of network information, based on the multimedia environment, this paper studies the application of animation technology in mechanical drawing teaching, and constructs a small multimedia teaching platform. Through the explanation of animation courseware, students can better understand the making and principle of mechanical drawing, and cultivate students' divergent thinking. The teaching platform combines teaching material knowledge with practice to deepen students' understanding of the basic content of mechanical drawing. Finally, the rationality and practicability of the system are analyzed by investigating the platform users. The results show that the application of animation technology in mechanical drawing teaching is reasonable and practical.

Sign in / Sign up

Export Citation Format

Share Document