A new approach, SRR, for small infrared target detection in single image is described herein. SRR based on local self-similarity descriptor, according to the characteristics of targets. Using certainty targets can be easily measured. Compared some conventional cutter removal methods, extensive experimental results show that proposed approach outperforms these methods. Additionally, has a simple structure, which convenient implementation. Plans future research include incorporating...

The analysis on the measurement uncertainty of output power in field test tidal energy converters is an important process to evaluate characteristics performance tested converter. Based data assessment a converter, calculation results analyzed. research show that: (1) curve with information converter that drawn this paper, can reflect discreteness and during period; (2) sensitivity coefficient current velocity component has significant impact combined converters; (3) change slope velocity....

Flight delay prediction is a major topic in intelligent airport management systems, which emphasizes the use of historical data and potential features to estimate whether future flight will delay. However, many factors affect delays, these can be categorized into weather (e.g., temperature, humidity, wind speed) non-weather (day-of-month, day-of-week, scheduled departure arrival time). Moreover, impacts on delays are different. Weather play more important role adverse conditions main reason...

Abstract This paper presents models for flight delay prediction by considering both the local effects and network individual airport. Following a complex approach, authors analyse separately. Results indicate that long‐term delays are mainly caused effects, while short‐term strongly associated with delays. Therefore, existing factors such as temporal variables, weather condition seasonal replaced specific novel (e.g. crowdedness degree of airport air traffic system, demand‐capacity...

This study aims to achieve intelligent decision making in HVDC systems the framework of knowledge graphs (KGs). First, whole life cycle KG an system was established by combining making. Then, fault diagnosis studied as a typical case study, and decision-making method for based on XGBoost that significantly improved speed, accuracy, robustness designed. It is noteworthy dataset used this extracted KGs, accordingly combined. Four kinds data from KGs were firstly preprocessed, their features...

To enhance the precision of fault diagnosis for high-voltage direct-current (HVDC) systems by effectively extracting various types characteristics, a method based on long short-term memory network (LSTM) is proposed in this paper. The relies knowledge graph platform and developed using measured data from four an HVDC substation located southwest China. Firstly, constructed, then waveform preprocessed divided into training set test set. Various optimizers are employed to train LSTM....

Handling incomplete data in multi-view classification is challenging, especially when traditional imputation methods introduce biases that compromise uncertainty estimation. Existing Evidential Deep Learning (EDL) based approaches attempt to address these issues, but they often struggle with conflicting evidence due the limitations of Dempster-Shafer combination rule, leading unreliable decisions. To challenges, we propose Alternating Progressive Network (APLN), specifically designed enhance...

This paper proposes a novel technique to detect the main moving trajectory of indoor pedestrians. Based on Long Short- Term Memory(LSTM) Network, this deep learning network is capable human beings using Wi-Fi positioning data. The data collected by detectors densely installed in public building urban area, which can ensure detection any portable devices as long module turned on. Then model works form sequence modeling learn stream extracted from massive pedestrian In compare with methods...

In order to analyze the temperature fields, grads, thermal stress and strain of large caliber machine gun barrel during firing, an analysis model was established for gun. The finite element are founded boundary condition loaded. results indicated temperature, tube continuous shots. effect pulse loading on stress, is very obviously. So, primary origin barrel. At same time, one important factors affecting life tube.

Steer by wire (SBW) systems have many merits over traditional power steering in fuel efficiency, space security and comfort virtue of eliminating the mechanical link between wheel front wheel. This paper aims at modeling parts, motor, motor electronic control unit (ECU) SBW System bond graph approach simulating complete system dynamic behavior regarding vehicle maneuverability stability driver's feel. With model built Matlab/Simulink, simulation results demonstrated that enables to generate...

A novel method for fusion detection of infrared small target based on fisher linear discriminant analysis in wavelet domain is presented this paper. The proposed consists two processes. In the first process: a vector firstly obtained through model and background samples. And then converted to filter. second First, every frame image sequence decomposed by discrete frame. Second, approximation with level 2 filtered filter process. Third, images three consecutive frames are fused accumulate...

Study of traditional assist characteristic cure does not take into account the difference steering resistance torque caused by different road adhesion coefficient. Vehicle dynamics analysis model is established based on ADAMS/CAR. Simulation wheel realized under conditions. Departure from ideal boost characteristics requirements and combined with speed lateral acceleration., article built curve a certain The system can real-time select through identifying vehicle traveling conditions way BP...

In this paper, a robust single data set-STAP (SDS-STAP) algorithm is proposed to against steering vector mismatch. Traditional STAP methods require training set which usually absent in heterogeneous environment. addition, the surrounding range cells do not possess discrete jamming information of test (if existed) degrades suppression performance. The SDS-STAP methods, on other hand, overcome these problems by operating solely data. A novel based amplitude and phase estimation (APES)...

Distributed Multiple-input Multiple-output radar has been intensively studied recently and an important issue is to design orthogonal phase coded waveforms. In this paper, we firstly waveforms with expanded mainlobe width, the criterion minimize autocorrelation peak sidelobe levels (APSL) cross correlation (PCCL) of waveforms, match a desirable mainlobe. Then, further suppress APSL PCCL, method mismatched filters raised, which can be solved by convex optimization algorithm. Numerical results...

In this work, we proposed a CNN-LSTM deep learning framework to predict flight delays. The model consists of three main components: A Convolution neural network (CNN) followed by Long short-term memory (LSTM) network, and then Random Forest classifier is applied for delay prediction. First, convolution employed extract the spatial corrections among different regions. Then, results CNN algorithm are inputted into LSTM temporal dynamics modeling. Finally, use spatial-temporal correlations...