Kernel Density Estimation Algorithm Research Articles

Fruit Distribution Density Estimation in YOLO-Detected Strawberry Images: A Kernel Density and Nearest Neighbor Analysis Approach

Precise information on strawberry fruit distribution is of significant importance for optimizing planting density and formulating harvesting strategies. This study applied a combined analysis of kernel density estimation and nearest neighbor techniques to estimate fruit distribution density from YOLOdetected strawberry images. Initially, an improved yolov8n strawberry object detection model was employed to obtain the coordinates of the fruit centers in the images. The results indicated that the improved model achieved an accuracy of 94.7% with an mAP@0.5~0.95 of 87.3%. The relative error between the predicted and annotated coordinates ranged from 0.002 to 0.02, demonstrating high consistency between the model predictions and the annotated results. Subsequently, based on the strawberry center coordinates, the kernel density estimation algorithm was used to estimate the distribution density in the strawberry images. The results showed that with a bandwidth of 200, the kernel density estimation accurately reflected the actual strawberry density distribution, ensuring that all center points in high-density regions were consistently identified and delineated. Finally, to refine the strawberry distribution information, a comprehensive method based on nearest neighbor analysis was adopted, achieving target area segmentation and regional density estimation in the strawberry images. Experimental results demonstrated that when the distance threshold ϵ was set to 600 pixels, the correct grouping rate exceeded 94%, and the regional density estimation results indicated a significant positive correlation between the number of fruits and regional density. This study provides scientific evidence for optimizing strawberry planting density and formulating harvesting sequences, contributing to improved yield, harvesting efficiency, and reduced fruit damage. In future research, this study will further explore dynamic models that link fruit distribution density, planting density, and fruit growth status.

A Robot Ground Medium Classification Algorithm Based on Feature Fusion and Adaptive Spatio-Temporal Cascade Networks

With technological advancements and scientific progress, mobile robots have found widespread applications across various fields. To enable robots to perform tasks safely and effectively in diverse and unknown environments, this paper proposes a ground medium classification algorithm for robots based on feature fusion and an adaptive spatio-temporal cascade network. Specifically, the original directional features in the dataset are first transformed into quaternion form. Then, spatio-temporal forward and reverse neighbors are identified using KD trees, and their connection strengths are evaluated via a kernel density estimation algorithm to determine the final set of neighbors. Subsequently, based on the connection strengths determined in the previous step, we perform noise reduction on the features using discrete wavelet transform. The noise-reduced features are then weighted and fused to generate a new feature representation.After feature fusion, the Adaptive Dynamic Convolutional Neural Network (ADC) proposed in this paper is cascaded with the Long Short-Term Memory (LSTM) network to further extract hybrid spatio-temporal feature information from the dataset, culminating in the final terrain classification. Experiments on the terrain type classification dataset demonstrate that our method achieves an average accuracy of 97.46% and an AUC of 99.80%, significantly outperforming other commonly used algorithms in the field. Furthermore, the effectiveness of each module in the proposed method is further demonstrated through ablation experiments.

A Chua’s Chaotic Chirp Spread-Spectrum Power Spectral Homogenization Strategy Based on Distribution Transformation

When utilizing high-dimensional chaotic signals for frequency modulation, achieving a uniformly distributed power spectrum is a challenging task. This paper addresses this challenge by proposing a power spectrum homogenization strategy based on distribution transformation. The strategy transforms the task of achieving a uniformly distributed power spectrum in frequency modulation of high-dimensional chaotic signals to solve and equalize the probability density function of the chaotic signals, thereby further enhancing the ability of high-dimensional chaotic signals to suppress electromagnetic interference. Firstly, the difficulty of obtaining a smooth probability density function of chaotic modulation signals is solved using the kernel density estimation algorithm. Then, a distribution transformation algorithm is proposed to convert non-uniformly distributed chaotic modulation signals into uniformly distributed chaotic modulation signals. By using uniformly distributed chaotic modulation signals for frequency modulation, the objective of power spectrum equalization is achieved. Finally, taking the Chua’s chaotic signal as an example, the effectiveness of the proposed strategy is verified using an experimental platform based on a digital signal processor-controlled active clamping flyback converter.

Mapping morphological cortical networks with joint probability distributions from multiple morphological features

Morphological features sourced from structural magnetic resonance imaging can be used to infer human brain connectivity. Although integrating different morphological features may theoretically be beneficial for obtaining more precise morphological connectivity networks (MCNs), the empirical evidence to support this supposition is scarce. Moreover, the incorporation of different morphological features remains an open question. In this study, we proposed a method to construct cortical MCNs based on multiple morphological features. Specifically, we adopted a multi-dimensional kernel density estimation algorithm to fit regional joint probability distributions (PDs) from different combinations of four morphological features, and estimated inter-regional similarity in the joint PDs via Jensen-Shannon divergence. We evaluated the method by comparing the resultant MCNs with those built based on different single morphological features in terms of topological organization, test-retest reliability, biological plausibility, and behavioral and cognitive relevance. We found that, compared to MCNs built based on different single morphological features, MCNs derived from multiple morphological features displayed less segregated, but more integrated network architecture and different hubs, had higher test-retest reliability, encompassed larger proportions of inter-hemispheric edges and edges between brain regions within the same cytoarchitectonic class, and explained more inter-individual variance in behavior and cognition. These findings were largely reproducible when different brain atlases were used for cortical parcellation. Further analysis of macaque MCNs revealed weak, but significant correlations with axonal connectivity from tract-tracing, independent of the number of morphological features. Altogether, this paper proposes a new method for integrating different morphological features, which will be beneficial for constructing MCNs.

Uncovering the progressive failure process of primary coal-rock mass specimens: Insights from energy evolution, acoustic emission crack patterns, and visual characterization

The failure and instability of deep coal-rock mass structures, which are influenced by mining disturbances, are major contributors to disasters like rock bursts. This study involved conducting indoor experiments using uniaxial loading test and acoustic emission (AE) experiments on indigenous primary coal-rock mass (PCRM). We utilize chaotic bifurcation based on strain energy to characterize the progressive damage stages of PCRM, demonstrating the chaotic characteristics of energy evolution during the gradual destruction process. The degree of damage resulting from PCRM failure was evaluated by jointly applying P-wave velocity tomography and AE event localization. Additionally, the classification of crack patterns in PCRM was conducted using the RA-AF correlation analysis method. The segmentation boundaries of crack classification patterns were then redefined using the Gaussian mixture model (GMM) algorithm. The research findings indicate that the chaotic bifurcation model of strain energy classifies stress into four stages: the stable region (Ⅰ), the metastable region (Ⅱ), the bifurcation region (Ⅲ), and the chaotic region (Ⅳ). The presence of a low-velocity zone in P-waves may indicate crack accumulation and damage within the system. Additionally, areas with abnormal P-wave velocities exhibit numerous AE events. The crack classification patterns of the four stages undergo an evolution from predominantly tensile cracks to a mixture of tensile and shear cracks, and the GMM algorithm successfully identifies the optimal separation path for crack classification boundaries. We propose an adaptive kernel density estimation (AKDE) algorithm to quantify the spatial distribution of AE events, thus offering a visual representation of the damage patterns at various stages.

Spatial Analysis Leveraging Geographic Information System and Kernel Density Estimation for Crime Prediction

This study explored the potential of spatial analysis techniques to predict crime hotspots and coldspots within the province of Antique, Philippines. The unique blend of geographical features (coastal and mountainous regions) and socio-economic characteristics in Antique presented a compelling opportunity for the research. Crime data from 2018 to 2023, encompassing direct assaults, homicides, murders, and parricides, was acquired from the Police Regional Office 6. Using Quantum Geographic Information System (QGIS) software and Kernel Density Estimation (KDE) algorithms, the researchers analyzed these crime records. The findings highlighted a positive trend – a decrease in direct assaults over the study period. However, homicide data presented a more concerning picture, with specific locations consistently reporting higher rates. While murder cases showed a decline, parricide incidents remained relatively low, with occasional fluctuations. In conclusion, this data-driven approach, utilizing advanced crime analysis tools, offers valuable insights for policymakers in Antique. By investing in such technology and adopting data-driven strategies, policymakers can work towards creating a safer and more secure future for their communities.

Data-Driven-Based Intelligent Alarm Method of Ultra-Supercritical Thermal Power Units

In order to ensure the safe operation of the ultra-supercritical thermal power units (USCTPUs), this paper proposes an intelligent alarm method to enhance the performance of the alarm system. Firstly, addressing the issues of slow response and high missed alarm rate (MAR) in traditional alarm systems, a threshold optimization method is proposed by integrating kernel density estimation (KDE) and convolution optimization algorithm (COA). Based on the traditional approach, the expected detection delay (EDD) indicator is introduced to better evaluate the response speed of the alarm system. By considering the false alarm rate (FAR), and EDD, a threshold optimization objective function is constructed, and the COA is employed to obtain the optimal alarm threshold. Secondly, to address the problem of excessive nuisance alarms, this paper reduces the number of nuisance alarms by introducing an adaptive delay factor into the existing system. Finally, simulation results demonstrate that the proposed method significantly reduces the MAR and EDD, improves the response speed and performance of the alarm system, and effectively reduces the number of nuisance alarms, thereby enhancing the quality of the alarms.

Interval prediction of sinter screening index based on gate recurrent unit and kernel density estimation algorithm

Since there are many uncertain factors in the actual production process, reliable information cannot be obtained from point prediction results. Therefore, this paper proposes an interval prediction method to evaluate the screening index. Firstly, feature engineering algorithms are used to select the most suitable data and variables for modeling. Secondly, based on the sequential characteristics of the sintering process, the gated cycle unit (GRU) model is used to make point predictions on the indicators. then the kernel density estimation (KDE) algorithm is used to quantify the error of the index to obtain the interval prediction results, and the RandomizedSearchCV algorithm is used to optimize the parameters of the model. Finally, comparison shows that the GRU model has higher point prediction accuracy, and the KDE algorithm can better quantify the prediction error, and then obtain reliable interval prediction results. This method has guiding significance for the high-quality production of sinter.

Automatic location of multiple leakage points of hydropower station gate based on approximate kernel density estimation algorithm

Automatic location of multiple leakage points of hydropower station gate based on approximate kernel density estimation algorithm

COVERT: A classless approach to generating balanced datasets for process modelling

In this work, a classless oversampling technique, Covert, was developed to improve historical datasets from industrial processing plants to aid process modelling. Using kernel density estimation and nearest neighbour algorithms, sparse regions are identified and resampled, developing a more balanced dataset.When applied to a real dataset from a geothermal power plant, Covert outperforms current best practice (Smote) in uniformly populating the input feature space and generating credible data in the output variable. When used to develop a data-driven model Covert improved model accuracy by 20% when predicting outside the original data’s feature space. Smote, however, reduced model accuracy by 6% in the same feature space.Developing reliable models of industrial processes continues to be a significant hurdle in developing a digital twin. Using Covert, existing imbalanced historical data can be used to extend the range of applicability of any process model.

Exploring the Factors Influencing Traffic Accidents: An Analysis of Black Spots and Decision Tree for Injury Severity

This research aimed to examine the spatial distribution of road traffic accidents in Budapest, Hungary. The primary objective was to identify the factors associated with traffic accidents on the city's transportation network and to determine the locations of the most frequent accidents during peak and off-peak hours. A quantitative methodology was employed in this study, utilizing a dataset of recent accidents that occurred between 2019 and 2021, classified into peak and off-peak incidents. The data was analyzed using Python software and Quantum Geographic Information System (QGIS) tools for big data analytics. These programs enabled the creation of spatial maps of the study area and the identification of accident spots based on latitude and longitude information. A decision tree classification approach was used in the machine-learning method implemented with Python software. Additionally, the dataset file was uploaded to QGIS, which applied the heatmap (Kernel Density Estimation) algorithm to identify accident hotspots. The study findings revealed that the city center was the most common location for accidents overall, with peak and off-peak times, lanes, and days of the week investigated as potential contributing factors. The target variable was the number of accidents involving serious and minor injuries, which were found to be significantly associated with the identified accidents in this study.

Machine Learning-Based Intrusion Detection for Rare-Class Network Attacks

Due to the severe imbalance in the quantities of normal samples and attack samples, as well as among different types of attack samples, intrusion detection systems suffer from low detection rates for rare-class attack data. In this paper, we propose a geometric synthetic minority oversampling technique based on the optimized kernel density estimation algorithm. This method can generate diverse rare-class attack data by learning the distribution of rare-class attack data while maintaining similarity with the original sample features. Meanwhile, the balanced data is input to a feature extraction module built upon multiple denoising autoencoders, reducing information redundancy in high-dimensional data and improving the detection performance for unknown attacks. Subsequently, a soft-voting ensemble learning technique is utilized for multi-class anomaly detection on the balanced and dimensionally reduced data. Finally, an intrusion detection system is constructed based on data preprocessing, imbalance handling, feature extraction, and anomaly detection modules. The performance of the system was evaluated using two datasets, NSL-KDD and N-BaIoT, achieving 86.39% and 99.94% multiclassification accuracy, respectively. Through ablation experiments and comparison with the baseline model, it is found that the inherent limitations of a single machine-learning model directly affect the accuracy of the intrusion detection system, while the superiority of the proposed multi-module model in detecting unknown attacks and rare classes of attack traffic is demonstrated.

Using Kernel Density Estimation in Knowledge Distillation to Construct the Prediction Model for Bipolar Disorder Patients

Bipolar disorder is a severe mood disorder and is one of the top 20 causes of disability in the world. Although there have been numerous studies based on machine learning models for the detection of bipolar disorder patients, these works have limitations. This study used a kernel density estimation algorithm to generate distributions of the input data, which can make knowledge distillation work and can improve prediction performances of the machine learning models for bipolar disorder. To the best of our knowledge, this is the first attempt to apply kernel density estimation to knowledge distillation. Another main contribution is that we used medical history information that was readily available from the electronic health record system, trying to improve the limitation of previous studies that needed to use special instruments to collect input data. Furthermore, in view of the fact that most previous studies have sample sizes of less than 1000, we collected tens of thousands of data samples to improve the representativeness of the constructed prediction models. Finally, the generated data distributions helped the decision tree algorithm to select the appropriate branching attributes to construct the prediction models. These branching attributes can be mapped back to specific diseases that are all associated with bipolar disorder.

A 5500-year record of coastal dune evolution along the shores of Lake Michigan in the North American Great Lakes: The relationship of lake-level fluctuations and climate

Dune fields line much of the ∼1750-km long shore of Lake Michigan that extends from northwestern Indiana, north along the west coast of Lower Michigan, and west across southern Upper Michigan. Numerous geomorphic studies at specific sites or defined coastal reaches have demonstrated that dune formation began during the Nipissing maximum (∼5500–4500 calendar year Before Present (cal yr BP) and continued episodically to the present. Dune formation in these geographically confined areas is linked mostly to high lake stages and periods of increased storminess. Some recent research has also invoked drought as a potential causal mechanism on a site-specific basis. Although more than 250 collective absolute carbon-14 (14C) and optically stimulated luminescence (OSL) ages have been acquired in these many studies, a comprehensive statistical assessment of this robust dataset has yet to be conducted to reconstruct a full chronological reconstruction of dune evolution.This study statistically analyzes the dataset of all known OSL (118) and 14C ages (175) acquired directly from sand dunes. Application of a kernel density estimation (KDE) algorithm function to both datasets revealed the temporal patterns in the ages. Analysis of OSL ages indicates three major periods of dune growth, beginning between ∼5.0 and 3.8 ka during the Nipissing high stand and subsequent regression. The second phase occurred between ∼3.0 and 2.0 ka during the Algoma high stand and regression. Finally, the most recent interval of dune growth transpired between ∼1.3 and 0.8 ka in the aftermath of a high lake stage at ∼1.7 ka and another, shorter peak in lake level at ∼1.0 ka. These findings indicate that major pulses of dune building mostly occur during lake regressions. They also correspond to the relatively warmer and drier conditions of the Holocene Climate Optimum, Roman Climate Optimum, and Medieval Warm Period, respectively, as well as periods of relative drought in the region. These associations indicate that drier conditions may have contributed to dune activation.Plotting of 14C data reveals no single variable, such as stability or burial, explains the timing of the four peaks in the kernel distribution of ages derived from organic remains. Intervals of higher 14C age frequencies occurred between ∼4500 and 3800 cal yr BP, ∼3500 and 2600 cal yr BP, ∼2300 and 1600 cal yr BP, and ∼700 and 200 cal yr BP. The peak at ∼4200 cal yr BP corresponds with a similar OSL pattern, indicating that 14C ages derived from weakly developed Entisols during this interval reflects their burial by eolian sand. Peaks in 14C densities within the latter intervals at ∼3200, ∼1800, and ∼400 cal Yr BP align with distinct drops in the OSL distribution. This pattern indicates that 14C ages from these intervals reflect episodes of stability and soil formation subsequent to episodes of dune building. Although this study demonstrates the general patterns of dune growth and stability, local variations in behavior likely occurred.

Multi-GPU-Parallel and Tile-Based Kernel Density Estimation for Large-Scale Spatial Point Pattern Analysis

Kernel density estimation (KDE) is a commonly used method for spatial point pattern analysis, but it is computationally demanding when analyzing large datasets. GPU-based parallel computing has been adopted to address such computational challenges. The existing GPU-parallel KDE method, however, utilizes only one GPU for parallel computing. Additionally, it assumes that the input data can be held in GPU memory all at once for computation, which is unrealistic when conducting KDE analysis over large geographic areas at high resolution. This study develops a multi-GPU-parallel and tile-based KDE algorithm to overcome these limitations. It exploits multiple GPUs to speedup complex KDE computation by distributing computation across GPUs, and approaches density estimation with a tile-based strategy to bypass the memory bottleneck. Experiment results show that the parallel KDE algorithm running on multiple GPUs achieves significant speedups over running on a single GPU, and higher speedups are achieved on KDE tasks of a larger problem size. The tile-based strategy renders it feasible to estimate high-resolution density surfaces over large areas even on GPUs with only limited memory. Multi-GPU parallel computing and tile-based density estimation, while incurring very little computational overhead, effectively enable conducting KDE for large-scale spatial point pattern analysis on geospatial big data.

Multi-leakage source localization of safety valve based on improved KDE algorithm

The safety valve is the core component of the safety pressure relief protection device of the pressure-bearing special equipment. When the safety valve leaks, the medium of the pressure vessel will be lost and wasted, which may lead to safety accidents. Aiming at the problem that it is difficult to accurately locate multiple tiny leak holes in safety valves, multi-leakage source localization of safety valve combining the acoustic emission (AE) test with improved approximate kernel density estimation (KDE) algorithm is proposed. The algorithm first introduces the improved wavelet threshold function denoising method to extract the time-frequency support domain which is less affected by environmental noise and the energy of the leaked sound source is dominant, which makes the premise of the application of the KDE algorithm established. In the aspect of improving the wavelet threshold function, an improved adaptive wavelet threshold noise reduction method is proposed by using the decay characteristics of the exponential function. On this basis, the high-frequency aliasing is suppressed by frequency division fusion processing, the approximate kernel density function is calculated, and the three-dimensional spectral base of the approximate kernel density function is reduced. Through numerical calculation, the location coordinates of the leakage source of the safety valve are obtained according to the peak value of the improved KDE spectrum. The results show that the relative errors of the leakage location results of safety valves with working pressures of 0.72 MPa, 0.75 MPa and 0.77 MPa are all within 10%. The method of combining the acoustic emission test with the improved KDE algorithm can accurately locate the leakage source of the safety valve, and with the increase of the working pressure of the safety valve, the positioning accuracy is also improved accordingly.

A GIS Approach for Revealing Urban Mobility Hotspots: A Case Study of Amman City in Jordan

Transportation management is an essential aspect of sustainable city development, as transportation networks serve humans in their daily activities. Traffic demand is an important input for transportation planning considering the population growth and travel activities increase, which have produced more traffic congestion throughout the years. Normally, traffic congestions are not uniformly distributed across the city, but rather are concentrated in particular locations. These locations are known as hotspots. We developed a framework for studying urban spatiotemporal characteristics of human mobility behavior within Amman city, where a large amount of trajectory data were processed to extract their pick-up and drop-off points. The available data, which was recorded between May and September 2021, is sorted out in an accumulative way to represent the working days of the week. Travel demand was illustrated through a temporal data representation per day interval as the day was divided into three intervals to further understand mobility behavior throughout the day. Then, the Kernel Density Estimation algorithm (KDE) was applied to derive and categorize different significant hotspots that were visually represented using GIS Software as appropriate spatial clustering tools to produce heatmaps. Finally, the correlation between hotspots and their drop-off points was analyzed to understand the factors influencing the mobility pattern such as day intervals and community structure in terms of residential or commercial. The results enable us to build several strategies and recommendations for transportation planners as well as taxi operators.

MCIBox: a toolkit for single-molecule multi-way chromatin interaction visualization and micro-domains identification.

The emerging ligation-free three-dimensional (3D) genome mapping technologies can identify multiplex chromatin interactions with single-molecule precision. These technologies not only offer new insight into high-dimensional chromatin organization and gene regulation, but also introduce new challenges in data visualization and analysis. To overcome these challenges, we developed MCIBox, a toolkit for multi-way chromatin interaction (MCI) analysis, including a visualization tool and a platform for identifying micro-domains with clustered single-molecule chromatin complexes. MCIBox is based on various clustering algorithms integrated with dimensionality reduction methods that can display multiplex chromatin interactions at single-molecule level, allowing users to explore chromatin extrusion patterns and super-enhancers regulation modes in transcription, and to identify single-molecule chromatin complexes that are clustered into micro-domains. Furthermore, MCIBox incorporates a two-dimensional kernel density estimation algorithm to identify micro-domains boundaries automatically. These micro-domains were stratified with distinctive signatures of transcription activity and contained different cell-cycle-associated genes. Taken together, MCIBox represents an invaluable tool for the study of multiple chromatin interactions and inaugurates a previously unappreciated view of 3D genome structure.

Damage Location Monitoring of Graphene/Conducting Polymer Composites Film Based on Self-Sensing.

Conductive graphene polymer composites are considered promising functional materials in gas detection, strain detection, metal corrosion prevention, and electromagnetic wave absorption, owing to their good flexibility, lightweight, and adjustable conductivity. The internal defects or external damages of composite films will seriously affect the electrical and functional properties of the materials. Based on the conductive network inside the conductive polymer film and the self-inductance to ultrasonic wave, the defect self-monitoring system of the conductive polymer film is designed and optimized in this work. The self-damage detection system is composed of an electrode array, excitation source, resistance signal acquisition and processing circuit, and damage display. Aiming at different scenarios, the improved interdigital structure transducer for sensors and damage detection device for coating film with a large area are presented and optimized respectively. Meanwhile, the damage location algorithm based on time difference measurement and kernel density estimation algorithm is also optimized. The multiple damage detection is realized by a device with a 4 × 8 electrode array, and the relative error of damage area with 1 mm × 1 mm is less than 5%, and the lower detection limits of damage size are 0.3 mm × 0.3 mm.

An Underdetermined Convolutional Blind Separation Algorithm for Time–Frequency Overlapped Wireless Communication Signals with Unknown Source Number

It has been challenging to separate the time–frequency (TF) overlapped wireless communication signals with unknown source numbers in underdetermined cases. In order to address this issue, a novel blind separation strategy based on a TF soft mask is proposed in this paper. Based on the clustering property of the signals in the sparse domain, the angular probability density distribution is obtained by the kernel density estimation (KDE) algorithm, and then the number of source signals is identified by detecting the peak points of the distribution. Afterward, the contribution degree function is designed according to the cosine distance to calculate the contribution degrees of the source signals in the mixed signals. The separation of the TF overlapped signals is achieved by constructing a soft mask matrix based on the contribution degrees. The simulations are performed with digital signals of the same modulation and different modulation, respectively. The results show that the proposed algorithm has better anti-aliasing and anti-noise performance than the comparison algorithms.