Abstract Background Adverse drug reactions (ADRs) are an important concern in the medication process and can pose a substantial economic burden for patients hospitals. Because of limitations clinical trials, it is difficult to identify all possible ADRs before marketed. We developed new model based on data mining technology predict potential available data. Method Based Word2Vec Nature Language Processing, we propose knowledge graph embedding method that embeds drugs into their respective...

This manuscript describes a series of mesogen-jacketed liquid crystalline polymers (MJLCPs) and elastomers (MJLCEs) bearing novel polynorbornene backbone, onto which the mesogen is laterally attached by single covalent bond without spacers. The side-on mesogenic monomers are synthesized via palladium-catalyzed exo-hydroarylation norbornadiene, then polymerized using Grubbs' catalyst initiated ring opening metathesis polymerization (ROMP) method. MJLCEs prepared mixing MJLCPs with...

Support vector machine (SVM) is an algorithm based on structure risk minimizing principle and has high generalization ability, but sometimes we prefer to incremental learning algorithms handle very vast data for training SVM costly in time memory consumption or because the available are obtained at different intervals. works well model with impressive performance its outstanding power summarize space a concise way. This paper proposes intercross iterative approach taking possible impact of...

The direction of arrival (DOA) monostatic multiple input output (MIMO) radar wave for uniform linear array is studied, and a real valued root MUSIC method based on unitary transformation proposed. Based the traditional method, this constructs covariance matrix by transformation, then decomposes eigenvalues to obtain noise subspace. By constructing polynomial, used replace spectral peak search in method. obtained polynomial DOA estimation target. This does not need peak, computation greatly...

The advancements in intelligent action recognition can be instrumental developing autonomous robotic systems capable of analyzing complex human activities real-time, contributing to the growing field robotics that operates dynamic environments. precise basketball players' actions using artificial intelligence technology provide valuable assistance and guidance athletes, coaches, analysts, help referees make fairer decisions during games. However, unlike simpler scenarios, background is...

A novel generalized nested multiple-input multiple-output (MIMO) radar for direction of arrival (DOA) estimation is proposed in this paper. The structure utilizes the extended two-level array (ENA) as transmitter and receiver adjusts interelement spacing with an expanding factor. By optimizing element configuration, we can obtain best number elements attainable degrees freedom (DOF). Compared existing MIMO radar, configuration not only has closed-form expressions sensors’ positions maximum...

Weakly Supervised Semantic Segmentation (WSSS) with image-level labels has long been suffering from fragmentary object regions led by Class Activation Map (CAM), which is incapable of generating fine-grained masks for semantic segmentation. To guide CAM to find more non-discriminating patterns, this paper turns an interesting working mechanism in agent learning named Complementary Learning System (CLS). CLS holds that the neocortex builds a sensation general knowledge, while hippocampus...

Mathematical morphology techniques, such as white top-hat (WTH) and new (NWTH) transformation have been researched for small target detection application in the infrared (IR) images. However, its enhancement performance still depends on SE size set by users. To solve this problem, we propose a recursive multi-structuring elements (multi-SEs) NWTH method with an automatic decision mechanism of size. The proposed based updates multi-SEs calculating candidate target-to-clutter ratio gain...

Aiming at the problem that low signal-to-noise ratio in complex indoor environment will lead to data association and accuracy of simultaneous localization mapping (SLAM) method, a PHD-SLAM method based on memory attenuation (MA) filter mixed newborn maps information (MBMA-PHD-SLAM) is proposed this paper. First all, probability hypothesis density (PHD) filter. Therefore, avoids solves high computational complexity. Besides, general tends cause diverge when low. MA combined into PHD-SLAM....

Aiming at the scarcity of Low Earth Orbit (LEO) satellite spectrum resources, this paper proposes an algorithm interference signal feature extraction and pattern classification based on deep learning to further improve stability satellite–ground communication links. The can successfully predict pattern, start–stop time, frequency change range other parameters, has advantages excellent detection performance, high accuracy small parameter prediction error, etc. It be applied in field channel...

Vision-based mobile positioning technology has a broad application prospect. Still, it is easy to be disturbed by external environmental factors, and the accuracy robustness in complex environment are poor. Therefore, this paper designs high-precision visual strategy for via fusing stereo odometry Inertial Measurement Unit (IMU) data. A multi-sensor calibration method utilized compensate measurement error of IMU parameter camera. data synchronization alignment based on timestamp also...

In this paper, a downlink cell-free Massive MIMO system (CF-M-MIMO-S) is considered. The CF-M-MIMO-S distributed M-MIMO-S, where access points (APs) with very great quantity of antennas, and much smaller number independent users are randomly. Firstly, an approximate expression for the capacity perfect channel state information conjugate beamforming scheme derived. Secondly, energy-efficient (EE) resource allocation strategy advanced, which aim to maximize EE. Specifically, power consumption...

In order to realize the high-precision direction of arrival (DOA) estimation coherent source two-dimensional multiple-input and multiple-output (MIMO) radar, a solution is given by combining Toeplitz matrix set reconstruction. MIMO radar obtains larger aperture with fewer arrays. Traditional reconstruction Toeplitz-like algorithms use part information in construction two correlation matrices or covariance construct when performing DOA estimation, which makes utilization incomplete requires...

Abstract In order to improve the simultaneous localization and mapping (SLAM) accuracy of mobile robots in complex indoor environments, multi-robot cardinality-balanced multi-Bernoulli filter SLAM (MR-CBMber-SLAM) method is proposed. First all, this introduces a based on random finite set (RFS) theory solve data association problem. This aims overcome problem that will overestimate aspect map feature estimation, combines strategy balancing cardinality with filter. What more, further...

Abstract The problem of WordNet-based ontology construction was widely investigated and many effective methods have been proposed in China. utilizations the hierarchy structure WordNet, digraph WordNet auxiliary resources are main measures methods. Usually, facing three fundamental difficulties, computation semantic similarity, core development resources. Through our reviews previous researches, we find several inadequacies such as low utilization ratio lack standardized evaluation give some...

In this paper, aiming at the problem of poor path planning and obstacle avoidance effect autonomous underwater vehicle (AUV) in a dynamic environment, feasible rolling speed method is proposed. This combines window with method, designs suitable three-dimensional model predictive controller based on under hybrid structure, achieves stable tracking reference by optimizing objective function. A collision cone constructed while rolling. If condition met, critical point calculated, AUV guided to...