scholarly journals FreshJoin: An Efficient and Adaptive Algorithm for Set Containment Join

2019 ◽  
Vol 4 (4) ◽  
pp. 293-308 ◽  
Author(s):  
Jizhou Luo ◽  
Wei Zhang ◽  
Shengfei Shi ◽  
Hong Gao ◽  
Jianzhong Li ◽  
...  
Keyword(s):  
Adaptive Algorithm ◽  
State Of The Art ◽  
Real Life ◽  
Adaptive Parameter ◽  
Set Containment ◽  
Inverted Indices ◽  
Space Cost ◽  
High Space ◽  
The Universe ◽  
Scientific Fields

Abstract This paper revisits set containment join (SCJ) problem, which uses the subset relationship (i.e., $$\subseteq$$⊆) as condition to join set-valued attributes of two relations and has many fundamental applications in commercial and scientific fields. Existing in-memory algorithms for SCJ are either signature-based or prefix-tree-based. The former incurs high CPU cost because of the enumeration of signatures, while the latter incurs high space cost because of the storage of prefix trees. This paper proposes a new adaptive parameter-free in-memory algorithm, named as frequency-hashjoin or $${\mathsf {FreshJoin}}$$FreshJoin in short, to evaluate SCJ efficiently. $${\mathsf {FreshJoin}}$$FreshJoin builds a flat index on-the-fly to record three kinds of signatures (i.e., two least frequent elements and a hash signature whose length is determined adaptively by the frequencies of elements in the universe set). The index consists of two sparse inverted indices and two arrays which record hash signatures of all sets in each relation. The index is well organized such that $${\mathsf {FreshJoin}}$$FreshJoin can avoid enumerating hash signatures. The rationality of this design is explained. And, the time and space cost of the proposed algorithm, which provide a rule to choose $${\mathsf {FreshJoin}}$$FreshJoin from existing algorithms, are analyzed. Experiments on 16 real-life datasets show that $${\mathsf {FreshJoin}}$$FreshJoin usually reduces more than 50% of space cost while remains as competitive as the state-of-the-art algorithms in running time.

scholarly journals A Multi-Branch U-Net for Steel Surface Defect Type and Severity Segmentation

Metals ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. 870
Author(s):  
Robby Neven ◽  
Toon Goedemé
Keyword(s):  
Process Parameters ◽  
Visual Inspection ◽  
Steel Surface ◽  
Surface Defect ◽  
State Of The Art ◽  
Sheet Steel ◽  
Real Life ◽  
Single Task ◽  
Severity Estimation ◽  
Task Model

Automating sheet steel visual inspection can improve quality and reduce costs during its production. While many manufacturers still rely on manual or traditional inspection methods, deep learning-based approaches have proven their efficiency. In this paper, we go beyond the state-of-the-art in this domain by proposing a multi-task model that performs both pixel-based defect segmentation and severity estimation of the defects in one two-branch network. Additionally, we show how incorporation of the production process parameters improves the model’s performance. After manually constructing a real-life industrial dataset, we first implemented and trained two single-task models performing the defect segmentation and severity estimation tasks separately. Next, we compared this to a multi-task model that simultaneously performs the two tasks at hand. By combining the tasks into one model, both segmentation tasks improved by 2.5% and 3% mIoU, respectively. In the next step, we extended the multi-task model using sensor fusion with process parameters. We demonstrate that the incorporation of the process parameters resulted in a further mIoU increase of 6.8% and 2.9% for the defect segmentation and severity estimation tasks, respectively.

New Multi-View Classification Method with Uncertain Data

2021 ◽  
Vol 16 (1) ◽  
pp. 1-23
Author(s):  
Bo Liu ◽  
Haowen Zhong ◽  
Yanshan Xiao
Keyword(s):  
Learning Strategy ◽  
State Of The Art ◽  
Uncertain Data ◽  
Real Life ◽  
Support Vector ◽  
Classification Methods ◽  
Complementary Information ◽  
Novel Approach ◽  
Svm Model ◽  
Iterative Framework

Multi-view classification aims at designing a multi-view learning strategy to train a classifier from multi-view data, which are easily collected in practice. Most of the existing works focus on multi-view classification by assuming the multi-view data are collected with precise information. However, we always collect the uncertain multi-view data due to the collection process is corrupted with noise in real-life application. In this case, this article proposes a novel approach, called uncertain multi-view learning with support vector machine (UMV-SVM) to cope with the problem of multi-view learning with uncertain data. The method first enforces the agreement among all the views to seek complementary information of multi-view data and takes the uncertainty of the multi-view data into consideration by modeling reachability area of the noise. Then it proposes an iterative framework to solve the proposed UMV-SVM model such that we can obtain the multi-view classifier for prediction. Extensive experiments on real-life datasets have shown that the proposed UMV-SVM can achieve a better performance for uncertain multi-view classification in comparison to the state-of-the-art multi-view classification methods.

scholarly journals Drone Deep Reinforcement Learning: A Review

Electronics ◽  
2021 ◽  
Vol 10 (9) ◽  
pp. 999
Author(s):  
Ahmad Taher Azar ◽  
Anis Koubaa ◽  
Nada Ali Mohamed ◽  
Habiba A. Ibrahim ◽  
Zahra Fathy Ibrahim ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
State Of The Art ◽  
Real Life ◽  
Environment Monitoring ◽  
Simulated Environments ◽  
Infrastructure Inspection ◽  
Remote Sensing Mapping ◽  
And Control ◽  
The Military ◽  
Uav Navigation

Unmanned Aerial Vehicles (UAVs) are increasingly being used in many challenging and diversified applications. These applications belong to the civilian and the military fields. To name a few; infrastructure inspection, traffic patrolling, remote sensing, mapping, surveillance, rescuing humans and animals, environment monitoring, and Intelligence, Surveillance, Target Acquisition, and Reconnaissance (ISTAR) operations. However, the use of UAVs in these applications needs a substantial level of autonomy. In other words, UAVs should have the ability to accomplish planned missions in unexpected situations without requiring human intervention. To ensure this level of autonomy, many artificial intelligence algorithms were designed. These algorithms targeted the guidance, navigation, and control (GNC) of UAVs. In this paper, we described the state of the art of one subset of these algorithms: the deep reinforcement learning (DRL) techniques. We made a detailed description of them, and we deduced the current limitations in this area. We noted that most of these DRL methods were designed to ensure stable and smooth UAV navigation by training computer-simulated environments. We realized that further research efforts are needed to address the challenges that restrain their deployment in real-life scenarios.

scholarly journals Fabry Disease Therapy: State-of-the-Art and Current Challenges

2020 ◽  
Vol 22 (1) ◽  
pp. 206
Author(s):  
Olga Azevedo ◽  
Miguel Fernandes Gago ◽  
Gabriel Miltenberger-Miltenyi ◽  
Nuno Sousa ◽  
Damião Cunha
Keyword(s):  
Fabry Disease ◽  
State Of The Art ◽  
Large Body ◽  
Real Life ◽  
Clinical Manifestations ◽  
Substrate Reduction Therapy ◽  
Lysosomal Storage ◽  
New Therapies ◽  
Enzyme Replacement

Fabry disease (FD) is a lysosomal storage disorder caused by mutations of the GLA gene that lead to a deficiency of the enzymatic activity of α-galactosidase A. Available therapies for FD include enzyme replacement therapy (ERT) (agalsidase alfa and agalsidase beta) and the chaperone migalastat. Despite the large body of literature published about ERT over the years, many issues remain unresolved, such as the optimal dose, the best timing to start therapy, and the clinical impact of anti-drug antibodies. Migalastat was recently approved for FD patients with amenable GLA mutations; however, recent studies have raised concerns that “in vitro” amenability may not always reflect “in vivo” amenability, and some findings on real-life studies have contrasted with the results of the pivotal clinical trials. Moreover, both FD specific therapies present limitations, and the attempt to correct the enzymatic deficiency, either by enzyme exogenous administration or enzyme stabilization with a chaperone, has not shown to be able to fully revert FD pathology and clinical manifestations. Therefore, several new therapies are under research, including new forms of ERT, substrate reduction therapy, mRNA therapy, and gene therapy. In this review, we provide an overview of the state-of-the-art on the currently approved and emerging new therapies for adult patients with FD.

scholarly journals Prediction of Fouling in Condenser Based on Fuzzy Stage Identification and Chebyshev Neural Network

2013 ◽  
Vol 13 (2) ◽  
pp. 94-99 ◽  
Author(s):  
Shaosheng Fan ◽  
Qingchang Zhong
Keyword(s):  
Neural Network ◽  
Prediction Model ◽  
Parameter Optimization ◽  
Adaptive Algorithm ◽  
External Disturbance ◽  
Operational Parameters ◽  
Chebyshev Neural Network ◽  
Adaptive Parameter ◽  
Novel Approach ◽  
Variation Trends

The prediction of fouling in condenser is heavily influenced by the periodic fouling process and dynamics change of the operational parameters, to deal with this problem, a novel approach based on fuzzy stage identification and Chebyshev neural network is proposed. In the approach, the overall fouling is separated into hard fouling and soft fouling, the variation trends of these two kinds of fouling are approximated by using Chebyshev neural network, respectively, in order to make the prediction model more accurate and robust, a fuzzy stage identification method and adaptive algorithm considering external disturbance are introduced, based on the approach, a prediction model is constructed and experiment on an actual condenser is carried out, the results show the proposed approach is more effective than asymptotic fouling model and adaptive parameter optimization prediction model.

scholarly journals SOSerbia: Android-Based Software Platform for Sending Emergency Messages

Complexity ◽  
2018 ◽  
Vol 2018 ◽  
pp. 1-9
Author(s):  
Mihailo Jovanovic ◽  
Ivan Babic ◽  
Milan Cabarkapa ◽  
Jelena Misic ◽  
Sasa Mijalkovic ◽  
...  
Keyword(s):  
Emergency Response ◽  
State Of The Art ◽  
Complete Solution ◽  
Real Life ◽  
Android Application ◽  
Unique Combination ◽  
Background Process ◽  
Life Problems ◽  
The Republic ◽  
National Police

This paper presents Android-based SOS platform named SOSerbia for sending emergency messages by citizens in Serbia. The heart of the platform is SOS client Android application which is an easy and simple solution for sending SOS messages with unique combination of volume buttons. The proposed platform solves a lot of safety, security, and emergency problems for people who can be in dangerous situations. After a person presses a correct combination of buttons, a message with his or her location is sent to the operating center of the Serbian Police. The platform merges several appropriately combined advanced Android technologies into one complete solution. The proposed solution also uses the Google location API for getting user’s location and Media Player broadcast receiver for reading pressed buttons for volume. This logic can be also customized for any other mobile operating system. In other words, the proposed architecture can be also implemented in iOS or Windows OS. It should be noted that the proposed architecture is optimized for different mobile devices. It is also implemented with simple widget and background process based on location. The proposed platform is experimentally demonstrated as a part of emergency response center at the Ministry of Interior of the Republic of Serbia. This platform overcomes real-life problems that other state-of-the-art solutions introduce and can be applied and integrated easily in any national police and e-government systems.

scholarly journals A Network Parameter Database False Data Injection Correction Physics-Based Model: A Machine Learning Synthetic Measurement-Based Approach

2021 ◽  
Vol 11 (17) ◽  
pp. 8074
Author(s):  
Tierui Zou ◽  
Nader Aljohani ◽  
Keerthiraj Nagaraj ◽  
Sheng Zou ◽  
Cody Ruben ◽  
...  
Keyword(s):  
Machine Learning ◽  
Power Systems ◽  
State Of The Art ◽  
Real Life ◽  
The State ◽  
Wide Area ◽  
Network Parameter ◽  
False Data Injection ◽  
Network Parameters ◽  
Injection Attacks

Concerning power systems, real-time monitoring of cyber–physical security, false data injection attacks on wide-area measurements are of major concern. However, the database of the network parameters is just as crucial to the state estimation process. Maintaining the accuracy of the system model is the other part of the equation, since almost all applications in power systems heavily depend on the state estimator outputs. While much effort has been given to measurements of false data injection attacks, seldom reported work is found on the broad theme of false data injection on the database of network parameters. State-of-the-art physics-based model solutions correct false data injection on network parameter database considering only available wide-area measurements. In addition, deterministic models are used for correction. In this paper, an overdetermined physics-based parameter false data injection correction model is presented. The overdetermined model uses a parameter database correction Jacobian matrix and a Taylor series expansion approximation. The method further applies the concept of synthetic measurements, which refers to measurements that do not exist in the real-life system. A machine learning linear regression-based model for measurement prediction is integrated in the framework through deriving weights for synthetic measurements creation. Validation of the presented model is performed on the IEEE 118-bus system. Numerical results show that the approximation error is lower than the state-of-the-art, while providing robustness to the correction process. Easy-to-implement model on the classical weighted-least-squares solution, highlights real-life implementation potential aspects.

An experimental evaluation and guideline for path finding in weighted dynamic network

2021 ◽  
Vol 14 (11) ◽  
pp. 2127-2140
Author(s):  
Mengxuan Zhang ◽  
Lei Li ◽  
Xiaofang Zhou
Keyword(s):  
Shortest Path ◽  
State Of The Art ◽  
Dynamic Networks ◽  
Real Life ◽  
Dynamic Network ◽  
Problem Space ◽  
Network Applications ◽  
Complete Problem ◽  
Path Computation ◽  
Shortest Path Computation

Shortest path computation is a building block of various network applications. Since real-life networks evolve as time passes, the Dynamic Shortest Path (DSP) problem has drawn lots of attention in recent years. However, as DSP has many factors related to network topology, update patterns, and query characteristics, existing works only test their algorithms on limited situations without sufficient comparisons with other approaches. Thus, it is still hard to choose the most suitable method in practice. To this end, we first identify the determinant dimensions and constraint dimensions of the DSP problem and create a complete problem space to cover all possible situations. Then we evaluate the state-of-the-art DSP methods under the same implementation standard and test them systematically under a set of synthetic dynamic networks. Furthermore, we propose the concept of dynamic degree to classify the dynamic environments and use throughput to evaluate their performance. These results can serve as a guideline to find the best solution for each situation during system implementation and also identify research opportunities. Finally, we validate our findings on real-life dynamic networks.

A Study of the State of the Art in Synthetic Emotional Intelligence in Affective Computing

2020 ◽  
pp. 1199-1212
Author(s):  
Syeda Erfana Zohora ◽  
A. M. Khan ◽  
Arvind K. Srivastava ◽  
Nhu Gia Nguyen ◽  
Nilanjan Dey
Keyword(s):  
Emotional Intelligence ◽  
Affective Computing ◽  
Ethical Issues ◽  
State Of The Art ◽  
Real Life ◽  
Life Time ◽  
The State ◽  
Point Of View ◽  
General Idea ◽  
Tremendous Amount

In the last few decades there has been a tremendous amount of research on synthetic emotional intelligence related to affective computing that has significantly advanced from the technological point of view that refers to academic studies, systematic learning and developing knowledge and affective technology to a extensive area of real life time systems coupled with their applications. The objective of this paper is to present a general idea on the area of emotional intelligence in affective computing. The overview of the state of the art in emotional intelligence comprises of basic definitions and terminology, a study of current technological scenario. The paper also proposes research activities with a detailed study of ethical issues, challenges with importance on affective computing. Lastly, we present a broad area of applications such as interactive learning emotional systems, modeling emotional agents with an intention of employing these agents in human computer interactions as well as in education.

scholarly journals Augmented Intention Model for Next-Location Prediction from Graphical Trajectory Context

2019 ◽  
Vol 2019 ◽  
pp. 1-12
Author(s):  
Canghong Jin ◽  
Zhiwei Lin ◽  
Minghui Wu
Keyword(s):  
State Of The Art ◽  
Real Life ◽  
Traffic Planning ◽  
Trajectory Prediction ◽  
User Intention ◽  
Convolutional Networks ◽  
Proposed Model ◽  
Gated Recurrent Units ◽  
The Given ◽  
Travel Recommendation

Human trajectory prediction is an essential task for various applications such as travel recommendation, location-sensitive advertisement, and traffic planning. Most existing approaches are sequential-model based and produce a prediction by mining behavior patterns. However, the effectiveness of pattern-based methods is not as good as expected in real-life conditions, such as data sparse or data missing. Moreover, due to the technical limitations of sensors or the traffic situation at the given time, people going to the same place may produce different trajectories. Even for people traveling along the same route, the observed transit records are not exactly the same. Therefore trajectories are always diverse, and extracting user intention from trajectories is difficult. In this paper, we propose an augmented-intention recurrent neural network (AI-RNN) model to predict locations in diverse trajectories. We first propose three strategies to generate graph structures to demonstrate travel context and then leverage graph convolutional networks to augment user travel intentions under graph view. Finally, we use gated recurrent units with augmented node vectors to predict human trajectories. We experiment with two representative real-life datasets and evaluate the performance of the proposed model by comparing its results with those of other state-of-the-art models. The results demonstrate that the AI-RNN model outperforms other methods in terms of top-k accuracy, especially in scenarios with low similarity.

Sign in / Sign up

Export Citation Format

Share Document