Search

Fuzzy clustering algorithms are widely applied in the field of traffic driving, aiding in the classification of driving behaviors from massive traffic data and enhancing traffic safety levels. However, classical Fuzzy C-Means (FCM) algorithms are sensitive to noise during the clustering process, leading to suboptimal performance when dealing with traffic datasets with lower accuracy. Moreover, single-kernel clustering algorithms are greatly influenced by kernel function selection. To address these issues, this paper proposes a Possibility Weighted Multi-Kernel Fuzzy Clustering Algorithm (PMWFCM). By integrating possibility-based fuzzy clustering with FCM and introducing a multi-kernel weighting mechanism, PMWFCM effectively reduces FCM’s sensitivity to outliers while resolving issues of clustering consistency in Possibilistic C-Means (PCM) algorithms, overcoming the challenges associated with kernel function selection. Validation on three different types of datasets demonstrates that the PMWFCM algorithm performs exceptionally well in terms of average accuracy, normalized information, average time, robustness, and convergence. When applied to the evaluation of driving behaviors in traffic datasets. Therefore, the improved FCM algorithm proposed in this paper can accurately and comprehensively reflect changes in traffic data, providing a solid theoretical foundation for identifying and assessing major risk types among passenger drivers.

Abstract Remote Sensing Image Object Detection (RSIOD) faces the challenges of multi-scale objects, dense overlap of objects and uneven data distribution in practical applications. In order to solve these problems, this paper proposes a YOLO-ACPHD RSIOD algorithm. The algorithm adopts Adaptive Condition Awareness Technology (ACAT), which can dynamically adjust the parameters of the convolution kernel, so as to adapt to the objects of different scales and positions. Compared with the traditional fixed convolution kernel, this dynamic adjustment can better adapt to the diversity of scale, direction and shape of the object, thus improving the accuracy and robustness of Object Detection (OD). In addition, a High-Dimensional Decoupling Technology (HDDT) is used to reduce the amount of calculation to 1/N by performing deep convolution on the input data and then performing spatial convolution on each channel. When dealing with large-scale Remote Sensing Image (RSI) data, this reduction in computation can significantly improve the efficiency of the algorithm and accelerate the speed of OD, so as to better adapt to the needs of practical application scenarios. Through the experimental verification of the RSOD RSI data set, the YOLO-ACPHD model in this paper shows very satisfactory performance. The F1 value reaches 0.99, the Precision value reaches 1, the Precision-Recall value reaches 0.994, the Recall value reaches 1, and the mAP value reaches 99.36 $$\%$$ % , which indicates that the model shows the highest level in the accuracy and comprehensiveness of OD.

The environmentally responsible behavior of tourists has been one of the focal points in the field of sustainable tourism research in recent years. Taking Guangzhou City Park as an example, this study investigates the relationship between restorative perception, place attachment, and environmentally responsible behavior of urban park recreationists by constructing the theoretical framework of ''cognition-emotion-behavior'' of recreationalists via online questionnaire surveys and using the test method of structural equation mode. Studies have shown that: (1) When the restorative perception of the environment is compatible, malleable, and attractive, the recreationist will produce environmentally responsible behavior. Meanwhile, when the environment has a sense of distance and compatibility, it will promote the active environmentally responsible behavior of tourists; (2) the path of perceptual environmental compatibility in the restorative perception of recreationists being → place dependence→ place identity → environmentally responsible behavior has a positive impact on environmentally responsible behavior; (3) place attachment has a significant positive impact on environmentally responsible behavior. This paper suggests that urban park management governors should focus on improving the charm and attractiveness of parks, diversifying recreational activities, and creating emotional attachment places, so as to promote the development of urban parks and meet the diverse needs and experiences of park recreation.

The jet stream is a primary factor contributing to turbulence, especially for upper-level aircraft. This study utilized pilot reports and ERA5 data from 2023 to investigate the relationship between upper-level turbulence and the East Asian westerly jet (EAJ). The results indicate that approximately 45.9% of upper-level aircraft turbulence occurs within the jet stream, with the lowest proportion in August and the highest in January. Additionally, the strongest vertical wind shear (VMS) is found concentrated in the lower part of the jet stream core, particularly in the South–Down part of the jet stream, where upper-level aircraft turbulence occurs most frequently (27.1%). The most turbulent area is located between 30–40° N and 110–120° E, with the main air routes experiencing turbulence being the Henan sections of G212 and B208. From a seasonal perspective, there is less frequent occurrence of upper-level aircraft turbulence in summer and autumn but more in winter and spring. The EAJ volume increases with the strengthening of the jet core wind speed, with the jet core regions being most distinct at altitudes of 200~300 hPa. Meanwhile, the jet stream intensity index peaks at 70.6 m/s in January and reaches its lowest value of 7.1 m/s in August. The jet stream axis shifts southward in winter and northward in summer, reaching the southernmost position in December at 32.2° N and the northernmost position in August at 43.5° N. Furthermore, the VMS at turbulence points within the jet stream is higher than that at the turbulence points outside the jet stream, and the Richardson number (RI) is lower. Moreover, the temporal distribution of upper-level aircraft turbulence is primarily determined by the location and intensity of the jet stream, of which the jet stream intensity index provides guidance and thus serves as a reliable indicator.

In order to achieve fast and accurate detection of Gannan navel orange fruits with different ripeness levels in a natural environment under all-weather scenarios and then to realise automated harvesting of Gannan navel oranges, this paper proposes a YOLOv5-NMM (YOLOv5 with Navel orange Measure Model) object detection model based on the improvement in the original YOLOv5 model. Based on the changes in the phenotypic characteristics of navel oranges and the Chinese national standard GB/T 21488-2008, the maturity of Gannan navel oranges is tested. And it addresses and improves the problems of occlusion, dense distribution, small target size, rainy days, and light changes in the detection of navel orange fruits. Firstly, a new detection head of 160 × 160 feature maps is constructed in the detection layer to improve the multi-scale target detection layer of YOLOv5 and to increase the detection accuracy of the different maturity levels of Gannan navel oranges of small sizes. Secondly, a convolutional block attention module is incorporated in its backbone layer to capture the correlations between features in different dimensions to improve the perceptual ability of the model. Then, the weighted bidirectional feature pyramid network structure is integrated into the Neck layer to improve the fusion efficiency of the network on the feature maps and reduce the amount of computation. Lastly, in order to reduce the loss of the target of the Gannan Navel Orange due to occlusion and overlapping, the detection frame is used to remove redundancy using the Soft-NMS algorithm to remove redundant candidate frames. The results show that the accuracy rate, recall rate, and average accuracy of the improved YOLOv5-NMM model are 93.2%, 89.6%, and 94.2%, respectively, and the number of parameters is only 7.2 M. Compared with the mainstream network models, such as Faster R-CNN, YOLOv3, the original model of YOLOv5, and YOLOv7-tiny, it is superior in terms of the accuracy rate, recall rate, and average accuracy mean, and also performs well in terms of the detection rate and memory occupation. This study shows that the YOLOv5-NMM model can effectively identify and detect the ripeness of Gannan navel oranges in natural environments, which provides an effective exploration of the automated harvesting of Gannan navel orange fruits.

Abstract In the development of anti-breast cancer drugs, the quantitative structure-activity relationship model of compounds is usually used to select potential active compounds. However, the existing methods often have problems such as low model prediction performance, lack of overall consideration of the biological activity and related properties of compounds, and difficulty in directly selection candidate drugs. Therefore, this paper constructs a complete set of compound selection framework from three aspects: feature selection, relationship mapping and multi-objective optimization problem solving. In feature selection part, a feature selection method based on unsupervised spectral clustering is proposed. The selected features have more comprehensive information expression ability. In the relationship mapping part, a variety of machine learning algorithms are used for comparative experiments. Finally, the CatBoost algorithm is selected to perform the relationship mapping between each other, and better prediction performance is achieved. In the multi-objective optimization part, based on the analysis of the conflict relationship between the objectives, the AGE-MOEA algorithm is improved and used to solve this problem. Compared with various algorithms, the improved algorithm has better search performance.

Existing methods for restoring color-distorted images in specific environments typically focus on a singular type of distortion, making it challenging to generalize their application across various types of color-distorted images. If it were possible to leverage the intrinsic connections between different types of color-distorted images and coordinate their interactions during model training, it would simultaneously enhance generalization, address potential overfitting and underfitting issues during data fitting, and consequently lead to a positive performance boost. In this paper, our approach primarily addresses three distinct types of color-distorted images, namely dust-laden images, hazy images, and underwater images. By thoroughly exploiting the unique characteristics and interrelationships of these types, we achieve the objective of multitask processing. Within this endeavor, identifying appropriate correlations is pivotal. To this end, we propose a knowledge selection and allocation strategy that optimally distributes the features and correlations acquired by the network from the images to different tasks, enabling a more refined task differentiation. Moreover, given the challenge of difficult dataset pairing, we employ unsupervised learning techniques and introduce novel Transformer blocks, feedforward networks, and hybrid modules to enhance context relevance. Through extensive experimentation, we demonstrate that our proposed method significantly enhances the performance of color-distorted image restoration.

Abstract In smart cities, the Internet-of-Thing (IoT) provides an enabling communication infrastructure to support tremendous amount of data exchange. Most IoT applications, e.g., wireless local area network, Bluetooth and so forth, utilize the channel-hopping scheme to suppress the transmission security threats. In this paper, to reduce the mutual interference and external jamming attacks, multiple novel channel-hopping patterns, i.e., traditional no-hit-zone (NHZ) hopping pattern and generalized NHZ hopping pattern, are introduced to suit to IoT networks. Particularly the design of probabilistic hopping pattern is first proposed, which has the various usage probabilities with regard to various channels. The properties of these hopping patterns are investigated by the step-to-step examples. Then, the error-rate performance of the multi-node IoT systems adopting these hopping patterns in the presence of jamming attacks is comprehensively analyzed. The extensive simulations show that the traditional/generalized NHZ hopping patterns are in favor of combating the mutual interference but with the limited capability of reducing jamming attacks, while the probabilistic hopping pattern possesses the opposite feature, that is, it has the predominant merit in suppressing jamming attacks. Thus, the novel channel-hopping pattern-based IoT could provide the secure transmission for communication applications in smart cities. Note that, as the physical-layer security technique, the channel-hopping patterns investigated in this paper are convenient to integrate with the security policies implemented in upper layers (e.g., encryption, authentication and so forth).

The interdecadal change of the summer (July–August) rainfall over North China (SRNC) is of great concern to the climate research community. Based on the sliding correlation and interdecadal difference analysis, the interdecadal change of SRNC was studied. Results show a significantly wetter period of SRNC since the mid-2000s, which was associated with strengthening negative relationship between SRNC and PDO. PDO affected the SRNC through the jet stream in the upper-level and the East Asia–Pacific (EAP) teleconnection pattern. In the negative phase of the PDO since the mid-2000s, the contractive upper-level jet stream in the west of North China resulted in the abnormal updraft over the southern region of North China. Meanwhile, the positive phase of the EAP teleconnection pattern brought warm and wet southeast flow entering North China from its eastern boundary, both bringing more rainfall in North China. The abnormal water vapor transport from the western Pacific was very different from that accompanying the East Asian summer monsoon.

Due to the low detection accuracy of YOLOv3 target detection method, this paper proposes an improved target detection method of YOLOv3 remote sensing image. Firstly, the feature extraction network DarkNet53 is strengthened to improve the ability of feature extraction; Secondly, the original Leaky ReLU activation function is replaced by the Mish activation function, thus improving the generalization of the method in this paper; Finally, the Learning rate and BatchSize parameters are modified to prevent overfitting. The remote sensing image datasets of RSOD and TGRS-HRRSD are used in this paper. The Average Precision (AP) results of the method on the RSOD datasets in this paper show that the mAP value is 5.33 percent higher than that of the previous YOLOV3 method. The log average miss-rate (LAMR) results show that the LAMR value is 0.1100 lower than that of the previous YOLOV3 method. The mAP results of the method on the TGRS-HRRSD datasets show that the MAP value is 1.29 percent higher than that of the previous YOLOV3 method, and the LAMR results show that the LAMR value is 0.0338 lower than that of the previous YOLOv3 method.

The southwest vortex (SWV), a low-pressure system bringing severe rainfall in southwest China, is one of the most important synoptic systems in China. Using both the National Centers for Environmental Prediction Final (NCEP-FNL) operational global analysis dataset and the Weather Research and Forecasting (WRF) model simulation, a sophisticated SWV with dual-core structure (DCSWV) over the Sichuan Basin in 2010 was studied. The DCSWV system consisted of two cores, one near Leshan City (named “C1”) and another near Langzhong City (named “C2”). The high-resolution WRF model reproduced the life cycle of the DCSWV well. The diagnostic analysis of the vorticity budget indicated that the stretching and tilting terms played important roles in the development stage of “C1”, while the stretching and vertical advection of vorticity were the major contributors to the formation and development stage of “C2”, which implied the importance of moisture convergence and ascending motion. Sensitivity experiments showed that the DCSWV was closely associated with the release in latent heat as well as the effect of topography. The great release in latent heat provided significantly positive feedback to the DCSWV system, which was decisive to the formation and development stages of “C2”. The topography of the Tibetan Plateau and the Yun-Gui Plateau affected the location and duration of the DCSWV.

Noise exists widely in the nervous system, and plays a crucial role in the nervous system information processing. Noise can not only enhance but also weaken the ability of the nervous system to process information. Neurons are in a complex and variable electromagnetic field. Electromagnetic induction plays an important role in regulating the changes of neuronal membrane potential. Therefore, this paper simulates the electromagnetic field environment of the nervous system with a memristor and analyses the rich coherence resonance behavior of FitzHugh-Nagumo (FHN) neuron system under the drive of phase noise. By taking the amplitude, period and noise intensity of phase noise as the main parameters and the parameters of memristor as auxiliary parameters, the two-parameter changes are made from the angle of the amplitude and period of phase noise, the amplitude and intensity of phase noise, and the noise intensity and period of phase noise, respectively. The dynamic behaviors of coherent resonance of FHN neuron system are analyzed from the amplitude and period, amplitude and intensity as well as intensity and period of phase noise, respectively. When the amplitude and period of the phase noise and the intensity and period of the phase noise are used as independent variables for the two-parameter analysis, the FHN neuron system shows rich dynamic behaviors such as coherence mono-resonance, coherence bi-resonance and coherence multi-resonance. Especially when the amplitude and period of phase noise change as two-parameter, the system presents a coherence resonance of discharge pattern with period-adding cluster discharge at the valley. When the amplitude and intensity of phase noise are taken as independent variables for two-parameter analysis, FHN neuronal system presents single or dual coherence resonance at any value of noise intensity with the change of phase noise amplitude. The simulated results show that the FHN neuron system demonstrates rich coherence resonance behaviors under the drive of phase noise when the effect of electromagnetic induction in the nervous system is simulated by memristor.

Knowledge graphs are a popular research field in artificial intelligence, and store large amounts of real-world data. Since data are enriched over time, the knowledge graph is often incomplete. Therefore, knowledge graph completion is particularly important as it predicts missing links based on existing facts. Currently, the family of translation models delivers a better performance in knowledge graph completion. However, most of these models randomly generate negative triplets during the training process, resulting in the low quality of negative triplets. In addition, such models ignore the important characteristics of triplet-mapping properties during model learning. Therefore, we propose an optimization framework based on the translation models (Op-Trans). It enhances the knowledge-graph completion effect from both negative sampling and triplet-mapping properties. First, we propose a clustering cache to generate negative triplets, which generate negative triplets based on entity similarity. This sampling method can directly use the cache to track the negative triplets with large scores. In addition, we focus on the different contributions of the triplets to the optimization goal. We calculate the distinct weight for each triplet according to its mapping properties. In this way, the scoring function deals with each triplet depending on its own weight. The experimental results show that Op-Trans can help the state-of-the-art baselines to obtain a better performance in a link prediction task.

In this paper, we analysed the effect of trench-hill soil surface on ground-penetrating radar (GPR) full-wave inversion for soil moisture measurement. We conducted numerical experiments by modelling the trench-hill surface using finite-difference time–domain (FDTD) simulations. The FDTD simulations were carried out with the open-source software gprMax, using different centre frequencies, namely, 150 MHz, 250 MHz and 450 MHz. The gprMax source/receiver for each centre frequency was calibrated, respectively, to transform the FDTD radar signal to normalized Green’s functions for wave propagation in multilayered media. The radar signals and inversion results of the three different frequency ranges are compared. The FDTD Green’s functions of the trench-hill surface with a flat surface are also compared. The results show that the trench-hill surface only slightly affects the inversion when frequency is lower than 190 MHz, which agrees with Rayleigh’s criterion. Field measurements were performed as well, using a prototype radar mounted on an irrigation robot. The low-frequency antenna was calibrated over a large water plane. The optimal operating frequency range was set to 130–190 MHz. TDR measurements were performed as well for comparison. The results demonstrated promising perspectives for automated and real-time determination of the root–zone soil moisture in potato fields, and thereby for precise and automatic irrigation.

The coal pillar stress distribution at the 311102 working face in the Bayangaole Mine is analyzed and revealed. In addition, borehole stressmeter, PASSAT monitoring system, and numerical modelling are fully utilized. Based on the patterns of acoustic wave velocity distribution, it is discovered that the impact created by mining activity can expand into the working face around 40 m, where the peak stress concentration is found about 15 m ahead. According to borehole stressmeter readings, mildly impacted, ordinarily impacted, and severely impacted zones are distinguished. The equilibrium theory and corresponding calculation indicated that the coal body in front of the working face has a plastic zone width of 4.96 m. The stress-displacement analysis based on numerical simulation showed that the relationship between peak vertical stress and pillar width is unimodal and bimodal. Specifically, both 5 and 10 m wide pillars showed a unimodal stress-width correlation and the peak vertical stresses are all located at the pillar center, whereas 15 m wide pillar has a bimodal stress-width relationship. In comparison, 10 m wide pillar holds the maximum in-situ stress. In consideration of site conditions and economic influences, 6 m wide coal strip coal pillar is designed at the working face 311102. As a result, stopping was successfully completed, and remarkable economic benefits were achieved.

Previous studies indicate that the summer (July-August) rainfall over North China has decreased since the mid-1970s due to the weakening of East Asian summer monsoon (EASM). However, this study firstly discovers the new evidences that the summer rainfall over North China had a significant increasing tendency during 1979–1996; since 1997, this increasing tendency has halted while more summer droughts occurred over North China. One important cause for the halted increasing tendency over North China is the interdecadal decrease of the westerly water vapor transport during 1997–2016 in addition to the weakened EASM. The decrease of the westerly water vapor transport during 1997–2016 was due to the interdecadal warming over Lake Baikal. The interdecadal warming in the upper troposphere at 200 hPa forced the weakening of the upper-level zonal winds since 1997, which resulted in the anomalous descending flow over the north side of North China and the halted precipitation trend in North China.

In this paper, a Lyapunov stability theorem is used to design a model system with adaptive control synchronization. The system uses the pseudo-randomness of chaotic signals to hide the signals that need to be transmitted in seemingly messy chaotic signals. The small input signals are superimposed on the chaotic signals, and the receiving end demodulates the useful information with a synchronized chaotic signal. The system can dynamically adjust the value of the controller according to the initial value of the neuron model so that the two coupling Hindmarsh-Rose neural system can be in a better synchronous state, with good stability and self-adaptability. In this paper, the controller is applied to chaotic secure communication. The simulation results verify the feasibility and effectiveness of the designed controller, and the capability of realizing the transmission of confidential information.

The nondestructive characterization of cylindrical objects is needed in many fields, such as medical diagnostics, tree trunk inspection, or concrete column testing. In this study, the radar equation of Lambot et al. is combined with cylindrical Green’s functions to fully model and invert ultra-wideband (UWB) ground-penetrating radar (GPR) data and retrieve the properties of cylindrical objects. Inversion is carried out using a lookup table (LUT) approach followed by local optimization to ensure retrieval of the global minimum of the objective function. Numerical experiments were conducted to analyze the capabilities of the developed inversion procedure to estimate the radius, permittivity, and conductivity of the cylinders. The full-wave model was validated in laboratory conditions on metallic and plastic pipes of different sizes. The adopted radar system consists of a lightweight vector network analyzer (VNA) connected to a single transmitting and receiving horn antenna. The numerical experiments highlighted the complexity of the inverse problem, mainly originating from the multiple propagation modes within cylindrical objects. The laboratory measurements demonstrated the accuracy of the forward modeling and reconstructions in far-field conditions.

Tibetan Plateau (TP) mesoscale vortex (TPMV) was regarded as one of the most important rain bearing systems in China. Previous studies focused on the mechanisms of the TPMV in the viewpoint of deterministic forecast; however, few studies investigate the predictability of the TPMV using the Observing System Research and Predictability Experiment (THORPEX) Interactive Grand Global Ensemble (TIGGE) from the European Center for Medium Range Weather Forecasts (ECWMF). This paper investigates the location and the intensity of the larger-scale synoptic systems that influenced the development of the TPMV and its associated heavy rainfall by correlation and composite analysis. The case study on 18 July 2013 shows that stronger Balkhash Lake ridge, weaker Baikal Lake trough, and weaker western Pacific subtropical high (WPSH) are favorable to formation of TPMV over the Sichuan basin (SCB); otherwise, weaker Balkhash Lake ridge, stronger Baikal Lake trough, and stronger WPSH result in formation of TPMV to west of the SCB slightly. After the initial time, forecast for next 48 h of the geopotential height over the SCB can be viewed as a precursor of the subsequent time-averaged 90–108 h forecast of TPMV. TPMV had critical contributions to the heavy rainfall over the SCB on 18 July 2013.

To overcome the problems of slow convergence speed, premature convergence leading to local optimization and parameter constraints when solving high-dimensional multi-modal optimization problems, an adaptive dynamic disturbance strategy for differential evolution algorithm (ADDSDE) is proposed. Firstly, this entails using the chaos mapping strategy to initialize the population to increase population diversity, and secondly, a new weighted mutation operator is designed to weigh and combinemutation strategies of the standard differential evolution (DE). The scaling factor and crossover probability are adaptively adjusted to dynamically balance the global search ability and local exploration ability. Finally, a Gauss perturbation operator is introduced to generate a random disturbance variation, and to accelerate premature individuals to jump out of local optimization. The algorithm runs independently on five benchmark functions 20 times, and the results show that the ADDSDE algorithm has better global optimization search ability, faster convergence speed and higher accuracy and stability compared with other optimization algorithms, which provide assistance insolving high-dimensionaland complex problems in engineering and information science.

The Arctic sea ice has undergone a substantial long-term decline with superimposed interannual sea ice minimum (SIM) events over the last decades. This study focuses on the relationship between atmospheric circulation and the SIM events in the Arctic region. Four reanalysis products and simulations of one climate model are first analysed to confirm the existence of the Arctic cell, a meridional circulation cell to the north of 80°N, by visualising through the mean streamline and mean mass stream function in the Northern Hemisphere. Dynamical analyses of zonally averaged stationary eddy heat and momentum fluxes as well as the global precipitation rate data further confirm its existence. Finally, we found that the change in the Arctic sea ice concentration lags the variations of the descending air flow intensity associated with the Polar and Arctic cells, by about 2 months for the climatic annual cycle and about 10 months for the interannual anomaly. Five Arctic SIM events during the last three decades support this relationship. These results have implications for understanding the relationship between atmospheric circulation and sea-ice variations, and for predicting the Arctic sea ice changes.

This paper studies the chemical synaptic coupling of Chay neurons and the effect of adding time delay on their synchronization behavior. The results indicate that coupling strength stimuli can affect the discharge activity and the synchronization behavior. In the absence of coupling strength, the Chay neurons have chaotic discharge behavior and the system is in a nonsynchronous state. When a certain coupling strength is added, the neurons change from chaotic discharge to ordered periodic discharge, and the system state changes from asynchronous to synchronous. On the other hand, a time lag can alter the coupled system from synchronous to asynchronous.