Influenced by the great success of deep learning in computer vision and language understanding, research recommendation has shifted to inventing new recommender models based on neural networks. In recent years, we have witnessed significant progress developing models, which generalize surpass traditional owing strong representation power this survey paper, conduct a systematic review aiming summarize field facilitate researchers practitioners working systems. Specifically, data usage during...

Currently, active-bending structures and their shape optimization techniques have become a hot topic in the design of spatial freeform buildings. However, form-finding process is usually time-consuming, application finite element methods (FEM) requires huge computational effort. In face these challenges, artificial intelligence great potential for bring many important advantages to this field. paper, we propose novel, data-driven, bidirectional prediction method based on neural networks. It...

Fault diagnosis is essentially a kind of pattern recognition. The measured signal samples usually distribute on nonlinear low-dimensional manifolds embedded in the high-dimensional space, so how to implement feature extraction, dimensionality reduction and improve recognition performance crucial task. In this paper novel machinery fault approach based statistical locally linear embedding (S-LLE) algorithm which an extension LLE by exploiting class label information proposed. first extracts...

We investigate the problem of processing a large amount continuous spatial-keyword queries over streaming data, which is essential in many applications such as location-based recommendation and advertising, thanks to proliferation geo-equipped devices ensuing social media applications. For example, e-coupon system may allow potentially millions users register their (e.g., interests nearby sales) by specifying set keywords spatial region; then delivers each incoming spatial-textual object...

In order to better predict the traffic states on freeways and make management decisions, a hybrid model of support vector machine (SVM) K-nearest neighbor (KNN) is proposed for short- term freeway exiting volume prediction. First, historical data set built by using toll data. The abnormal records, such as records that have same entry exit station, illogical time record travel speed, are excluded quality control. Based dataset, it found has periodical variation over which provides basis...

High-resolution micro traffic data are important to safety and efficiency analysis. In this study, a roadside LiDAR sensor is used collect 3D point clouds of surrounding objects. An automatic background construction object detection method proposed on the basis operation principle sensor. algorithm, discrete horizontal vertical angular values can be considered as coordinates pixels in digital images, farthest mean distance each azimuth construct dataset. Then, vehicle pedestrian points...

Automatic traffic sign detection and recognition (ATDR) plays a crucial role as submodule of the intelligent transportation system (ITS) has gained significant attention in recent years. However, ATDR faces challenges due to two main factors: small size signs images long-tailed distribution categories real world (i.e.,only few have sufficient samples, most insufficient samples). These result decline performance existing frameworks. In this article, we propose novel framework for detection,...

Recent advancements in flexible sensing and machine learning have positioned soft sensors as promising alternatives to traditional methods for human posture detection. However, most research has centered on calibration, with limited progress practical applications due the challenges posed by diverse users complex scenarios such human-robot interaction. To address these challenges, this study developed a system capable of accurately predicting joint angles moments, validated it through...

We report a statistical study of medium-scale traveling ionospheric disturbances (MSTIDs) during 2014–2017 in the low-latitude China region using Hong Kong Continuously Operating Reference Stations network with baseline length 10–15 km. Polynomial fitting and multichannel maximum entropy method are utilized to derive MSTID parameters from global positioning system total electron content data. find that MSTIDs can be sorted into three types this region. One type is daytime MSTIDs, which...

Evaporation ducts are a particular type of atmospheric stratification that frequently appears on the sea surface. The accurate and timely prediction evaporation duct height (EDH) is significant for practical application electromagnetic communication equipment. Due to typical time-series (TS) characteristics measured data, we construct an EDH model based long short-term memory network (LSTM-EDH model) first time. experimental results show LSTM-EDH model’s root-mean-square error (RMSE)...

As one of the most important elements in intelligent transportation system (ITS), road traffic monitoring (RTMS) needs to be functioned with a recognition mechanism. Current works on mainly target at field automatic driving and cannot directly used RTMS. In this paper, we propose decision tree-based algorithm using roadside fixed light detection ranging (LiDAR) sensors These LiDAR have low vertical resolution, which implies that get clear far boundary obvious features roads from point cloud...

Traffic information collection is an important foundation for intelligent transportation systems. In this paper, 3D Light Detection And Ranging (LiDAR) deployed in the roadside of urban environments to collect vehicle and pedestrian information. A background filtering algorithm, including a mean modeling build map difference method filter static noise points, proposed fixed LiDAR facilities. Background points are filtered through between data frames multi-level map, then there still small...

In the last few years, thanks to their computational power, progressively increasing programmability and wide adoption in both research community industry, GPUs have become part of HPC clusters (for example, US Titan Stampede Chinese Tianhe-1A supercomputers). As a result, widely used open-source cluster resource managers (e.g. SLURM TORQUE) recently been extended with GPU support capabilities. These systems, however, provide simple scheduling mechanisms that often result underutilization...

With the ubiquitous use of networking technologies in military domain, network-centric warfare, which aims at improving system systems (SoS) capability, is a no-way-back trend development. Recently, it has become increasingly important to construct an airborne backbone network (ABN) maintain coverage and provide reach-back units because terrestrial networks cannot be flexibly deployed have poor survivability. Given advantages software-defined (SDN), architecture (SD-ABN) proposed for ABN...

Traffic sign detection and recognition (TSDR) has attracted extensive studies recently due to its broad application prospect in Intelligent Transport Systems. TSDR is still challenging the small size of traffic signs image. Besides, real world exhibit a long-tailed distribution (i.e., data for most categories are scarce while others abundant.), which will lead significant performance drop framework. In this paper, we propose novel framework address these problems. order detect signs, an...