Accuracy Of Algorithm Research Articles

Time Delay Estimation for Acoustic Temperature Measurement of Loose Coal Based on Quadratic Correlation PHAT-β Algorithm

The acoustic temperature measurement method has a broad application prospect due to its advantages of high precision, non-contact, etc. It is expected to become a new method for hidden fire source detection in mines. The acoustic time of flight (TOF) can directly affect the accuracy of acoustic temperature measurement. We proposed a quadratic correlation-based phase transform weighting (PHAT-β) algorithm for estimating the time delay of the acoustic temperature measurement of a loose coal. Validation was performed using an independently built experimental system for acoustic temperature measurement of loose coals under multi-factor coupling. The results show that the PHAT-β algorithm estimated acoustic TOF values closest to the reference line as the sound travelling distance increased. The results of coal temperature inversion experiments show that the absolute error of the PHAT-β algorithm never exceeds 1 °C, with a maximum value of 0.862 °C. Using the ROTH weighted error maximum, when the particle of the coal samples is 3.0–5.0 cm, the absolute error maximum is 4.896 °C, which is a difference of 3.693 °C from the error minimum of 1.203 °C in this particle size interval. The accuracy of six algorithms was ranked as PHAT-β > GCC > PHAT > SCOT > HB > ROTH, further validating the accuracy and reliability of the PHAT-β algorithm.

GraphSlimmer: Preserving Read Mappability with the Minimum Number of Variants.

Modern genomic datasets, like those generated under the 1000 Genome Project, contain millions of variants belonging to known haplotypes. Although these datasets are more representative than a single reference sequence and can alleviate issues like reference bias, they are significantly more computationally burdensome to work with, often involving large-indexed genome graph data structures for tasks such as read mapping. The construction, preprocessing, and mapping algorithms can require substantial computational resources depending on the size of these variant sets. Moreover, the accuracy of mapping algorithms has been shown to decrease when working with complete variant sets. Therefore, a drastically reduced set of variants that preserves important properties of the original set is desirable. This work provides a technique for finding a minimal subset of variants such that for given parameters α and δ, all substrings up to length α in the haplotypes are guaranteed to be still alignable to the appropriate locations with either Hamming or edit distance at most δ, using only . Our contributions include showing the NP-hardness and inapproximability of these optimization problems and providing Integer Linear Programming (ILP) formulations. Our edit distance ILP formulation carefully decomposes the problem according to variant locations, which allows it to scale to support all of chromosome 22's variants from the 1000 Genome Project. Our experiments also demonstrate a significant reduction in the number of variants. For example, for moderately long reads, e.g., α = 1000, over 75% of the variants can be removed while preserving read mappability with edit distance at most one.

Research on RFI Mitigation Methods for Fast Radio Burst Observational Data

To quickly search for rare fast radio bursts (FRBs) from massive astronomical observational data, Radio Frequency interference (RFI) mitigation is one of the key and challenging task. RFI will cause search algorithm to output a large number of false positive candidates, and even submerges real astronomical events. Due to the complexity of the sources and types of RFI. there is currently no universal method to solve this problem. In order to reduce the impact of RFI on FRB search, the RFI in L band observational data of the Nanshan 26m radio telescope (NSRT-26m) was analyzed and studied. A three-layer RFI mitigation procedure was established for the main narrowband RFI and broadband RFI, which effectively alleviated the RFI pollution of observational data. Embedding this procedure into the FRB DDSS (Dispersion Dynamic Spectra Search) pipeline, experimental results show that the detection rate and accuracy of the search algorithm have been further improved. This method provides valuable reference for RFI mitigation of FRB observational data.

Prediction of delayed graft function by early salivary microbiota following kidney transplantation

Delayed graft function (DGF) is a frequently observed complication following kidney transplantation (KT). Our prior research revealed dynamic shifts in salivary microbiota post-KT with immediate graft function (IGF), yet its behavior during DGF remains unexplored. Five recipients with DGF and 35 recipients with IGF were enrolled. Saliva samples were collected during the perioperative period, and 16S rRNA gene sequencing was performed. The salivary microbiota of IGFs changed significantly and gradually stabilized with the recovery of renal function. The salivary microbiota composition of DGFs was significantly different from that of IGFs, although the trend of variation appeared to be similar to that of IGFs. Salivary microbiota that differed significantly between patients with DGF and IGF at 1 day after transplantation were able to accurately distinguish the two groups in the randomForest algorithm (accuracy = 0.8333, sensitivity = 0.7778, specificity = 1, and area under curve = 0.85), with Selenomonas playing an important role. Bacteroidales (Spearman’s r = − 0.4872 and p = 0.0293) and Veillonella (Spearmen’s r = − 0.5474 and p = 0.0125) were significantly associated with the serum creatinine in DGF patients. Moreover, the significant differences in overall salivary microbiota structure between DGF and IGF patients disappeared upon long-term follow-up. This is the first study to investigate the dynamic changes in salivary microbiota in DGFs. Our findings suggested that salivary microbiota was able to predict DGF in the early stages after kidney transplantation, which might help the perioperative clinical management and early-stage intervention of kidney transplant recipients.Key points• Salivary microbiota on the first day after KT could predict DGF.• Alterations in salivary taxa after KT are related to recovery of renal function.

Klasifikasi Metode Data Mining untuk Prediksi Kelulusan Tepat Waktu Mahasiswa dengan Algoritma Naïve Bayes, Random Forest, Support Vector Machine (SVM) dan Artificial Neural Nerwork (ANN)

Timely graduation of students is essential for determining the quality of college. Universities must know the percentage of students' ability to complete their studies on time. So, to deal with this problem, data mining classification is carried out to predict student graduation on time to find patterns for student on-time graduation predictions. This research can yield new information to help colleges anticipate student graduations that are not on time. The method used is a classification data mining method with 4 algorithms: naïve Bayes, random forest, support vector machine (SVM), and artificial neural network (ANN). The attributes used are gender, parental income, length of guidance, working student status or not, semester 1 to semester 8 grades, and GPA. This study used Python 3 programming language on jupyter notebooks in Anaconda to process datasets. The distribution of datasets is divided by 70% for training data and 30% for testing data. The results of this study were obtained with the best algorithm accuracy in the support vector machine (SVM) algorithm is 0.94. Based on the results of this study, the accuracy is good for predicting student graduation on time.

Optimasi Algoritma Machine Learning Menggunakan Teknik Bagging Pada Klasifikasi Diagnosis Kanker Payudara

Classification algorithms have a very important role in Machine Learning, but not all algorithms have the same performance in every case. Algorithm performance can be affected by the type of data used, differences in problem characteristics, and the parameters used. Additionally, ensemble learning techniques such as Bagging can affect algorithm performance. Therefore, the problem arises of how to choose the most suitable algorithm for a particular classification task and how to optimize the performance of the algorithm. This research aims to carry out a comparative analysis and optimization of classification algorithms in Machine Learning. Classification algorithms that will be evaluated include Support Vector Machine (SVM), Neural Network, Logistic Regression, Decision Tree, and K-Nearest Neighbors (K-NN). Evaluation of the performance of these algorithms will be carried out using the confusion matrix, Receiver Operating Characteristic (ROC) Curve, and Area Under Curva (AUC). The result of this research is a comparative analysis of the optimization of classification algorithms using the bagging technique. After carrying out the evaluation process using the confusion matrix and ROC curve, it was found that the algorithm optimization using the bagging technique only had an effect on the Decision Tree (DT) and K-Nearest Neighbors (KNN) algorithms. . The accuracy of the DT algorithm increased by 0.6% while the accuracy of KNN increased by 1.3%. The AUC value for the DT algorithm increased by 1.4% and the KNN algorithm increased by 0.3%.

A COMPREHENSIVE EVALUATION OF FACE RECOGNITION SOFTWARE: BALANCING TOTAL COST OF OWNERSHIP, ACCURACY AND SPEED

As face recognition technology continues to play a pivotal role in various domains, selecting an optimal software solution becomes imperative. This paper thoroughly analyzes face recognition algorithms, emphasizing a holistic assessment of implementing them that includes the overall cost of ownership, accuracy, and speed. The research aims to guide decision-makers in choosing a solution that balances these three critical factors. The study employs a rigorous methodology and evaluates various intrusion detection solutions across multiple industries. It examines the cost of ownership comprehensively, including initial investment, maintenance expenses, and potential hidden costs. A cost-benefit analysis is conducted to unveil the true economic implications of each implementation. The accuracy of the face recognition algorithms which is the core of intrusion detection systems is assessed through the learnings from academia and real-world feedback from the security industry. Furthermore, the paper examines the critical aspect of speed, recognizing its important role in real-time applications. The evaluation considers the processing speed of each software solution, considering its responsiveness to various environments and working with large-scale datasets. This research provides a comprehensive overview of face recognition algorithms, offering small business decision-makers valuable insights to make informed choices for their intrusion detection solutions. By combining the total cost of ownership, accuracy, and speed, organizations can select a solution that aligns with their specific needs and maximizes the return on investment in intrusion detection technology.

DIRECTION OF ARRIVAL ESTIMATION BASED ON SMOOTH MUSIC ALGORITHM COMBINED SPECTRUM SELECTION TECHNIQUES OF NOISE CHARACTERISTICS OF MARINE TARGETS EQUIPPED PROPELLER

This article demonstrates a proposal for a direction of arrival (DOA) estimation algorithm for passive sonar systems based on the combination of the smooth multiple signal classification (Smooth MUSIC) algorithm and frequency bin selection (BS) of the sound of marine propeller-equipped targets, so-called BS-SMUSIC. The harmonics of propeller shaft and blade frequencies are considered useful information for detecting targets and estimating their parameters, including DOA. Low frequency analysis recording (LOFAR) is utilized to implement BS. By analyzing MUSIC-based algorithm together BS, passive DOA estimation algorithms have been significantly improved. Simulation results have been given in both cases: uncorrelated and correlated sources. Outcomes demonstrate that the BS-SMUSIC algorithm has the best performance in comparison to three MUSIC-based algorithms (MUSSIC, Modified MUSIC and Root MUSIC) in all investigation cases: narrow band signals at 5 dB of signal to noise (SNR); wideband signals at -5 dB of SNR. Besides, BS-SMUSIC algorithm also archives the lowest root mean square error (RMSE) in SNR range -5 dB to 20 dB. In the SNR range, the RMSE of BS-SMUSIC algorithm remains stable and is about 0.3 ◦ at -5 dB of SNR. This performance reflects its ability to ensure stable operation, super resolution and high accuracy of BS-SMUSIC algorithm for the passive sonar systems.

Evaluation of different methods for reference evapotranspiration assessment: A case study for Ukraine

The paper presents the results of the study devoted to the examination of the accuracy and reliability of the temperature-based approach of the ‘Evapotranspiration Calculator (Ukraine)’ application for the reference evapotranspiration assessment in Ukraine. The objective of the study was to determine the level of reliability and accuracy of modern alternative temperature-based algorithms for the reference evapotranspiration assessment in Ukraine compared to internationally recognized methods. The study was carried out for the territories of Ukraine, based on the meteorological data for the period 2021–2023. The basic methodology was compared to the standard Penman-Monteith method and the method of Hargreaves. The comparison was performed using the values of MAPE, RMSE, and correlation coefficient. Statistical analysis testified that there is a strong correlation and subtle difference between the Hargreaves method and the ‘Evapotranspiration Calculator (Ukraine)’ application, with an average MAPE of 30.3%, the correlation coefficient of 0.92, and RMSE of 1.46 mm. The difference between the Penman-Monteith method and the studied methodology was greater, as the MAPE averaged 41.0%, the correlation coefficient was 0.87, and the RMSE value was 2.05 mm. However, the high variation of the results by the regions of the country and the years of the study did not allow us to draw solid conclusions on whether the methodology embedded in the ‘Evapotranspiration Calculator (Ukraine)’ application is inferior to the method of Penman-Monteith. Further studies are required to clarify this issue through the improvement in the dataset, involvement of in-field reference evapotranspiration measurements, and application of adjustment guidelines for the ‘Evapotranspiration Calculator (Ukraine)’ application.

Integrating PointNet-Based Model and Machine Learning Algorithms for Classification of Rupture Status of IAs.

The rupture of intracranial aneurysms (IAs) would result in subarachnoid hemorrhage with high mortality and disability. Predicting the risk of IAs rupture remains a challenge. This paper proposed an effective method for classifying IAs rupture status by integrating a PointNet-based model and machine learning algorithms. First, medical image segmentation and reconstruction algorithms were applied to 3D Digital Subtraction Angiography (DSA) imaging data to construct three-dimensional IAs geometric models. Geometrical parameters of IAs were then acquired using Geomagic, followed by the computation of hemodynamic clouds and hemodynamic parameters using Computational Fluid Dynamics (CFD). A PointNet-based model was developed to extract different dimensional hemodynamic cloud features. Finally, five types of machine learning algorithms were applied on geometrical parameters, hemodynamic parameters, and hemodynamic cloud features to classify and recognize IAs rupture status. The classification performance of different dimensional hemodynamic cloud features was also compared. The 16-, 32-, 64-, and 1024-dimensional hemodynamic cloud features were extracted with the PointNet-based model, respectively, and the four types of cloud features in combination with the geometrical parameters and hemodynamic parameters were respectively applied to classify the rupture status of IAs. The best classification outcomes were achieved in the case of 16-dimensional hemodynamic cloud features, the accuracy of XGBoost, CatBoost, SVM, LightGBM, and LR algorithms was 0.887, 0.857, 0.854, 0.857, and 0.908, respectively, and the AUCs were 0.917, 0.934, 0.946, 0.920, and 0.944. In contrast, when only utilizing geometrical parameters and hemodynamic parameters, the accuracies were 0.836, 0.816, 0.826, 0.832, and 0.885, respectively, with AUC values of 0.908, 0.922, 0.930, 0.884, and 0.921. In this paper, classification models for IAs rupture status were constructed by integrating a PointNet-based model and machine learning algorithms. Experiments demonstrated that hemodynamic cloud features had a certain contribution weight to the classification of IAs rupture status. When 16-dimensional hemodynamic cloud features were added to the morphological and hemodynamic features, the models achieved the highest classification accuracies and AUCs. Our models and algorithms would provide valuable insights for the clinical diagnosis and treatment of IAs.

Judicial leadership matters (yet again): the association between judge and public trust for artificial intelligence in courts

Artificial intelligence (AI) is rapidly expanding in myriad industries and systems. This study sought to investigate public trust in using AI in the criminal court process. While previous research has identified factors that influence trust in AI, such as perceived accuracy and transparency of algorithms, less is known about the role of influential leaders—such as judges—in shaping public trust in new technology. This study examined the relationship between locus of control, anthropomorphism, cultural values, and perceived trust in AI. Participants completed a survey assessing their perceptions of trust in AI in determining bail eligibility, bail fines and fees, sentencing length, sentencing fines and fees, and writing legal documents (e.g., findings and disposition). Participants were more likely to trust AI performing financial calculations rather than determining bail eligibility, sentence length, or drafting legal documents. Participants’ comfort with AI in decision-making also depended on their perceptions of judges’ trust in AI, and they expressed concerns about AI perpetuating bias and the need for extensive testing to ensure accuracy. Interestingly, no significant association was found with other participant characteristics (e.g., locus of control, anthropomorphism, or cultural values). This study contributes to the literature by highlighting the role of judges as influential leaders in shaping public trust in AI and examining the influence of individual differences on trust in AI. The findings also help inform the development of recommended practices and ethical guidelines for the responsible use of AI in the courts.

Enhancing Map Matching Accuracy Using Backtracking Technique

Map matching integrates positioning data with road network information to accurately identify a vehicle exact location on a specific road. Modern location-based services heavily rely on accurate map matching techniques to match observed trajectories with road networks. This paper presents a novel map matching approach that leverages topological information and integrates the backtracking technique to enhance the accuracy and robustness of map matching. By considering the logical relationships between road segments, our method achieves excellent results in scenarios with complex road geometries and challenging urban environments. We integrate the backtracking technique to address noise and ambiguity in trajectory data, resulting in improved precision and a reduced likelihood of false matches. Extensive experimentation using real-world trajectory datasets in Beijing validates the effectiveness of our approach, highlighting its superiority over traditional methods. The algorithm accuracy achieved as high as 99.92%. The results of the evaluation demonstrate that the proposed approach exhibits superior performance compared to earlier map-matching algorithms in both simple and complex road networks. Additionally, it can be effectively implemented on GPS datasets with different time intervals. In addition to the obvious map matching applications of our technology, it has the potential to be adapted across domains, with implications in transportation, urban planning, and location-based services. This paper not only presents a substantial advancement in map matching but also opens new avenues for location-based analyses enhancing and services across various domains.

Handling Data Imbalance Problem in Hybrid Resampling Approach to Improve Accuracy of K-Nearest Neighbors Algorithm

Handling Data Imbalance Problem in Hybrid Resampling Approach to Improve Accuracy of K-Nearest Neighbors Algorithm

Distance correction range-free localization algorithm for WSNs

Accurate location information is essential for the effective deployment of Wireless Sensor Networks (WSNs) applications. Recently, researchers have developed numerous localization algorithms, with multi-hop methods being particularly attractive due to their cost-effectiveness and robustness, but their accuracy is still unsatisfactory. For better localization accuracy, this paper presented a distance correction range-free localization algorithm (DCRA). Firstly, the proposed algorithm estimates the distance between neighboring nodes based on neighbor connectivity to improve the accuracy of single-hop distance estimation. Secondly, during the multi-hop distance estimation phase, path similarity metrics are employed to ascertain the optimal path correction coefficients, thereby minimizing multi-hop distance estimation errors. Finally, based on the estimated distances, the node localization is converted into an optimization problem, which is then solved using an enhanced particle swarm algorithm to obtain the node coordinates. Simulation results show that the distance estimation accuracy of the DCRA algorithm in different node density scenarios is improved by more than 31 % and 12 % compared to the DV-Hop and DV-RND algorithms, respectively; and in terms of localization accuracy the DCRA algorithm is improved by more than 58 % and 35 % compared to the DV-Hop and DV-RND algorithms, respectively.

An Improved MonoDepth2 Algorithm for Vehicle Monocular Depth Estimation

Depth estimation algorithms are of great significance for autonomous vehicle ranging. In order to solve the problems of large errors, fuzzy image generation and detail loss in depth estimation algorithms, this paper proposes an improved algorithm of the MonoDepth2 algorithm. First, the feature extraction network of the original algorithm is changed to the ResNeXt block to improve the running speed and enrich feature information. Secondly, the Convolutional Block Attention Module attention mechanism is added to the depth estimation network to improve the algorithm accuracy and promote detail detection effect. Finally, the Atrous Spatial Pyramid Pooling network structure is added between the encoder and decoder of the depth estimation network to optimize feature fusion at different scales and extract more detailed features. Compared with the original MonoDepth2 algorithm, the improved algorithm reduces the Absolute Relative Error by 0.4 %, the Squared Relative Error by 6.1 %, the Root Mean Square Error by 15 %, and the accuracy(thr=1.25), increased by 0.4 %, The generated depth map recovers deeper image details and a more detailed target contour.

Using Runs of Homozygosity and Machine Learning to Disentangle Sources of Inbreeding and Infer Self-Fertilization Rates.

Runs of homozygosity (ROHs) are indicative of elevated homozygosity and inbreeding due to mating of closely related individuals. Self-fertilization can be a major source of inbreeding which elevates genome-wide homozygosity and thus should also create long ROHs. While ROHs are frequently used to understand inbreeding in the context of conservation and selective breeding, as well as for consanguinity of populations and their demographic history, it remains unclear how ROH characteristics are altered by selfing and if this confounds expected signatures of inbreeding due to demographic change. Using simulations, we study the impact of the mode of reproduction and demographic history on ROHs. We apply random forests to identify unique characteristics of ROHs, indicative of different sources of inbreeding. We pinpoint distinct features of ROHs that can be used to better characterize the type of inbreeding the population was subjected to and to predict outcrossing rates and complex demographic histories. Using additional simulations and four empirical datasets, two from highly selfing species and two from mixed-maters, we predict the selfing rate and validate our estimations. We find that self-fertilization rates are successfully identified even with complex demography. Population genetic summary statistics improve algorithm accuracy particularly in the presence of additional inbreeding, e.g. from population bottlenecks. Our findings highlight the importance of ROHs in disentangling confounding factors related to various sources of inbreeding and demonstrate situations where such sources cannot be differentiated. Additionally, our random forest models provide a novel tool to the community for inferring selfing rates using genomic data.

Analysis and prediction of the Horizon 2020 R&D&I collaboration network

This study presents a novel link prediction model for the analysis and prediction of collaboration networks in the context of H2020 projects. This model incorporates various databases and expands the list of variables used in the analysis. In this study, the accuracy and interpretability of both generic and nongeneric link prediction algorithms are examined through a comprehensive analysis. Additionally, collaborative groups that exhibit stronger linkages than initially anticipated are examined, and their prevalence across different regions is evaluated. In this study, it was found that the collaboration network within H2020 has significant concentration and fragmentation levels. Moreover, several key factors that strongly influence collaboration, including prior and concurrent project involvement, earned contribution, and the economic and technological characteristics of participating businesses, were identified. This study additionally demonstrated that cooperative communities exhibit geographical concentration in western Europe, whereas nongeneric models offer improved predictive accuracy for identifying relationships. This research contributes to the field of cooperation network analysis and offers guidance to decision-makers on strategies to promote future collaborations in the context of FP.

Automated generation of consistent annual maximum NDVI on coal bases with a new algorithm

Coal is one of the most important fossil energy sources and is ensuring global energy security. Annual maximum NDVI (Normalized Difference Vegetation Index) data is an important indicator for the research in balancing coal mining and vegetation conservation. However, the existing annual maximum NDVI data displayed lower values with temporally inconsistent and a noticeable mosaic line. Here we propose an algorithm for automatically generating the annual maximum NDVI of China’s coal bases in Google Earth Engine called: Auto-NDVIcb. The accuracy of the Auto-NDVIcb algorithm has been verified with an average RMSE of 0.087 for the 14 coal bases from 2013 to 2022. Based on the proposed Auto-NDVIcb algorithm, an annual maximum NDVI dataset for all 14 coal bases in China from 2013 to 2022 was publicly released. This dataset can be fast and automatically updated online. Hence, the public dataset will continuously serve to monitor the vegetation change induced by coal mining, exploring the mechanism of vegetation degradation, and providing scientific data for developing vegetation protection policies in coal mines.

Exploring the Accuracy and Limits of Algorithms for Localizing Recombination Breakpoints.

Phylogenetic methods are widely used to reconstruct the evolutionary relationships among species and individuals. However, recombination can obscure ancestral relationships as individuals may inherit different regions of their genome from different ancestors. It is, therefore, often necessary to detect recombination events, locate recombination breakpoints, and select recombination-free alignments prior to reconstructing phylogenetic trees. While many earlier studies have examined the power of different methods to detect recombination, very few have examined the ability of these methods to accurately locate recombination breakpoints. In this study, we simulated genome sequences based on ancestral recombination graphs and explored the accuracy of three popular recombination detection methods: MaxChi, 3SEQ, and Genetic Algorithm Recombination Detection. The accuracy of inferred breakpoint locations was evaluated along with the key factors contributing to variation in accuracy across datasets. While many different genomic features contribute to the variation in performance across methods, the number of informative sites consistent with the pattern of inheritance between parent and recombinant child sequences always has the greatest contribution to accuracy. While partitioning sequence alignments based on identified recombination breakpoints can greatly decrease phylogenetic error, the quality of phylogenetic reconstructions depends very little on how breakpoints are chosen to partition the alignment. Our work sheds light on how different features of recombinant genomes affect the performance of recombination detection methods and suggests best practices for reconstructing phylogenies based on recombination-free alignments.

Projected fuzzy [formula omitted]-means clustering algorithm with instance penalty

At present, high-dimensional data clustering has become a vital research field in machine learning. Traditional clustering algorithms cannot perform well on high-dimensional data, where the clustering task is usually divided into two stages: dimensionality reduction first and clustering later. In general, the existing high-dimensional clustering methods usually have the following shortcomings: (1) the two-stage strategy splits the connection between clustering and dimensionality reduction; (2) these algorithms do not consider the impact of anomalous instances in high-dimensional data on clustering performance. Therefore, to address these problems, a projected fuzzy c-means clustering algorithm with instance penalty (PCIP) is proposed. Firstly, we construct an instance penalty matrix and assign an instance penalty coefficient to each sample. Secondly, a model for clustering high-dimensional data is constructed by integrating fuzzy c-means clustering (FCM) and principal component analysis (PCA). The proposed model can perform dimensionality reduction and clustering simultaneously. In addition, the time complexity of the proposed algorithm is linearly related to the number of samples n, which can efficiently deal with large data sets. The proposed PCIP algorithm is verified by experiments using clustering accuracy and normalized mutual information (NMI) as evaluation metrics. The experimental results on 10 image datasets show that the average accuracy and average NMI of the PCIP algorithm are improved by 0.0375 and 0.0275, respectively, compared to the second-ranked algorithm.