Search

Underwater acoustic (UWA) channel prediction technology, as an important topic in UWA communication, has played an important role in UWA adaptive communication network and underwater target perception. Although many significant advancements have been achieved in underwater acoustic channel prediction over the years, a comprehensive summary and introduction is still lacking. As the first comprehensive overview of UWA channel prediction, this paper introduces past works and algorithm implementation methods of channel prediction from the perspective of linear, kernel-based, and deep learning approaches. Importantly, based on available at-sea experiment datasets, this paper compares the performance of current primary UWA channel prediction algorithms under a unified system framework, providing researchers with a comprehensive and objective understanding of UWA channel prediction. Finally, it discusses the directions and challenges for future research. The survey finds that linear prediction algorithms are the most widely applied, and deep learning, as the most advanced type of algorithm, has moved this field into a new stage. The experimental results show that the linear algorithms have the lowest computational complexity, and when the training samples are sufficient, deep learning algorithms have the best prediction performance. [ABSTRACT FROM AUTHOR]

This paper proposes a method of beforehand prediction of electric equipment faults based on chain-linked recurrent neural network algorithm, which takes the operating parameters of power equipment and other relevant environmental factors as inputs, and takes the fault characteristics as output judgment marks, and constructs a machine learning training model to realize the prediction of power equipment faults. The neural network algorithm adopted in this paper adopts a tree structure. Each sub-node can transfer information with its multiple superior nodes, so that the correlation between the data of the front and back nodes can be obtained, which meets the needs of the equipment fault prediction model. Considering that the occurrence of power transformer faults is sudden and greatly affected by changes in the surrounding environment, the input of prediction algorithms should consider more environmental factors. This method takes the historical data of various parameters including meteorological phenomena, geography data, and temperature of adjacent equipment and facilities as the training sample set, improves the learning model, gives the trend curve of each index, and gives a prompt at its threshold to ensure the prediction accuracy and give the index prediction. [ABSTRACT FROM AUTHOR]

This paper introduces the Composite Rating Method (CRM), a novel approach for the integrated evaluation of basketball player and team performances across multiple leagues. Utilizing data from Euroleague, EuroCup, and Basketball Champions League, the presented method provides comprehensive and accurate rankings, including accounting for actions not included in personal statistics. Drawing inspiration from established methodologies such as ELO, PER, Offensive and Defensive ratings, CRM offers a balanced assessment of player and team capabilities. The paper delineates the data collection and preprocessing procedures, details the algorithmic framework of CRM, and showcases its predictive capacity. By presenting a well-rounded approach to ranking, this paper aims to contribute to the advancement of performance evaluation methods in basketball and sports in general. [ABSTRACT FROM AUTHOR]

In the era of e-commerce, accurately predicting user purchase intentions has become a crucial factor for enhancing sales efficiency and optimizing the customer experience. Addressing the limitations of traditional ensemble strategies, which often suffer from subjective biases during the model design phase, this paper introduced an adaptive evolutionary ensemble learning model to predict user purchase intentions. This model adaptively selected the optimal base learners and meta-learners, incorporating both the predictive information from the base learners and the differential information between features to expand the feature dimensions, enhancing prediction accuracy. Moreover, to further refine the predictive capabilities of the model, this paper designed a binary adaptive differential evolution algorithm for feature selection, aiming to identify features that significantly influence the prediction outcome. Research results show that the binary adaptive differential evolution algorithm outperforms traditional optimization algorithms in global searches and feature selection. Compared to six common ensemble models and the DeepForest model, the proposed evolutionary ensemble model achieves a 2.76% and 2.72% increase in AUC value, respectively, and effectively mitigates the impacts of data imbalance [ABSTRACT FROM AUTHOR]

This study aims to present a comparative analysis of the Bayesian regularization backpropagation and Levenberg–Marquardt training algorithms in neural networks for the metrics prediction of damaged archaeological artifacts, of which the state of conservation is often fragmented due to different reasons, such as ritual, use wear, or post-depositional processes. The archaeological artifacts, specifically laminar blanks (so-called blades), come from different sites located in the Southern Levant that belong to the Pre-Pottery B Neolithic (PPNB) (10,100/9500–400 cal B.P.). This paper shows the entire procedure of the analysis, from its normalization of the dataset to its comparative analysis and overfitting problem resolution. [ABSTRACT FROM AUTHOR]

• A novel combined interval prediction algorithm is proposed in this paper. • Hybrid feature selection strategy is designed in the proposed system. • Multi-objective optimization mechanism reflects strong search capabilities. • Four interval prediction models cover the inherent modes of sequence. Traditional point prediction approaches can not reflect the uncertainty, which brings greater risks to decision-makers. To fill this gap, this paper extends a feature selection strategy that relies solely on correlation and redundant feature judgment, proposes a novel combined interval prediction algorithm, 3-Mcip (Combined Interval Prediction Based on Maximize Relevancy, Minimize Redundancy and Maximize Synergy) system, and solves the tradeoff between prediction accuracy and interval width. This system first designs a hybrid feature selection strategy to optimally select candidate variables and reduce model input redundancy. Secondly, the structure of the four ANN models is improved to accommodate the results of feature selection, and an optimization mechanism is introduced to search for the Pareto optimal solution set. In order to measure the comprehensive performance of the 3-Mcip system, hourly power load data and related candidate variables from Pittsburgh and Washington, D.C are considered. The numerical results show that the 3-Mcip system has coverage rates of 53.3333, 90.1667, and 99.4479 for Site 1 at different levels of interval width coefficients, which not only achieves perfect prediction of power load but also analyzes uncertainty. It is also helpful for power system managers to better capture the fluctuation range of future load and improve the flexibility of smart grid dispatching. [ABSTRACT FROM AUTHOR]

For discrete time nonlinear networked control systems, a novel self-triggered adaptive model predictive control (MPC) strategy is developed. Different from the existing self-triggered MPC methods that determine the triggering instants based on the difference between the optimal and real states at one single instant, the proposed approach updates the MPC system according to the differential form of the state error of two consecutive sampling moments to effectively reduce the computation and communication burden while maintaining the ideal control performance. In addition, this paper introduces a new adaptive prediction horizon mechanism to the self-triggered MPC, so that the amplitude of prediction horizon contraction is sufficiently large to further reduce the computational burden of the MPC method. Finally, the recursive feasibility and robust stability of this proposed strategy are proved strictly by theoretical analysis, and the simulation comparison results are shown to verify the proposed framework. [ABSTRACT FROM AUTHOR]

Mechanical properties are important indicators for evaluating the quality of strips. This paper proposes a mechanical performance prediction model based on the Gray Wolf Optimization (GWO) algorithm and the Extreme Learning Machine (ELM) algorithm. In the modeling process, GWO is used to determine the optimal weights and deviations of ELM and experiments are used to determine the model's key parameters. The model effectively avoids manual intervention and significantly improves aluminum alloy strips' mechanical property prediction accuracy. This paper uses processed data from the aluminum alloy production plant of Shandong Nanshan Aluminum Co., Ltd. as experimental data. When the prediction deviation is controlled within ±10%, the GWO-ELM model can achieve a correct rate of 100% for tensile strength, 97.5% for yield strength, and 77.5% for elongation on the test set. The RMSE of the tensile strength, yield strength, and elongation of the GWO-ELM model was 5.365, 11.881, and 1.268, respectively. The experimental results show that the GWO-ELM model has higher accuracy and stability in predicting aluminum alloy strips' tensile strength, yield strength, and elongation. The GWO-ELM model effectively avoids the defects of the traditional model. It has a special guiding significance for producing aluminum alloy strips. [ABSTRACT FROM AUTHOR]

Purpose: The use of aviation incident data to carry out aviation risk prediction is of great significance for improving the initiative of accident prevention and reducing the occurrence of accidents. Because of the nonlinearity and periodicity of incident data, it is challenging to achieve accurate predictions. Therefore, this paper aims to provide a new method for aviation risk prediction with high accuracy. Design/methodology/approach: This paper proposes a hybrid prediction model incorporating Prophet and long short-term memory (LSTM) network. The flight incident data are decomposed using Prophet to extract the feature components. Taking the decomposed time series as input, LSTM is employed for prediction and its output is used as the final prediction result. Findings: The data of Chinese civil aviation incidents from 2002 to 2021 are used for validation, and Prophet, LSTM and two other typical prediction models are selected for comparison. The experimental results demonstrate that the Prophet–LSTM model is more stable, with higher prediction accuracy and better applicability. Practical implications: This study can provide a new idea for aviation risk prediction and a scientific basis for aviation safety management. Originality/value: The innovation of this work comes from combining Prophet and LSTM to capture the periodic features and temporal dependencies of incidents, effectively improving prediction accuracy. [ABSTRACT FROM AUTHOR]

With the widespread use of unmanned aerial vehicles (UAVs), spectrum resources are becoming less and less available. Better utilization of the spectrum can be achieved by spectrum prediction. In this paper, four algorithms, hidden Markov model (HMM), support vector machine (SVM), multi-layer perceptron (MLP), and long short-term memory neural network (LSTM-NN) algorithms, were introduced for the prediction of channel states in the radio-frequency spectrum. Experiments are conducted on a dataset. It was found from results that when the number of output sequence was fixed as 1 and the number of input channel state information (CSI) sequence was 1-20, the more input sequences were, the lower the error rate of the algorithm was; when the number of input CSI sequences was 20, the error rate of the LSTM algorithm was the lowest among several algorithms, which was 4.82%; when the number of input CSI sequenced was fixed as 1 and the future 1-15 CSI sequences were predicted, the more sequences need to be predicted was, the higher the error rate of the algorithm was; when 15 CSI sequences were predicted, the error rate of the LSTM algorithm was the lowest, 42.33%. The experimental results demonstrate that the LSTM algorithm is reliable in radiofrequency spectrum prediction and can be applied in practical UAV communication. [ABSTRACT FROM AUTHOR]

Many studies have shown that long-chain noncoding RNAs (lncRNAs) are involved in a variety of biological processes such as post-transcriptional gene regulation, splicing, and translation by combining with corresponding proteins. Predicting lncRNA-protein interactions is an effective approach to infer the functions of lncRNAs. The paper proposes a new computational model named LPI-IBWA. At first, LPI-IBWA uses similarity kernel fusion (SKF) to integrate various types of biological information to construct lncRNA and protein similarity networks. Then, a bounded matrix completion model and a weighted k -nearest known neighbors algorithm are utilized to update the initial sparse lncRNA-protein interaction matrix. Based on the updated lncRNA-protein interaction matrix, the lncRNA similarity network and the protein similarity network are integrated into a heterogeneous network. Finally, an improved Bi-Random walk algorithm is used to predict novel latent lncRNA-protein interactions. 5-fold cross-validation experiments on a benchmark dataset showed that the AUC and AUPR of LPI-IBWA reach 0.920 and 0.736, respectively, which are higher than those of other state-of-the-art methods. Furthermore, the experimental results of case studies on a novel dataset also illustrated that LPI-IBWA could efficiently predict potential lncRNA-protein interactions. • LPI-IBWA is an effective computational model to predict lncRNA-protein interactions. • Similarity kernel fusion is used to integrate heterogenous biological similarities. • Bounded matrix completion updates lncRNA-protein interaction matrix. • Bi-Random walk on lncRNA-protein interactions network predicts novel interactions. [ABSTRACT FROM AUTHOR]

The objective of this paper is to assess whether existing pavement temperature prediction algorithms can be used to reliably determine Performance Grade (PG) design temperatures for Australian asphalt pavements. The results show good agreement between internationally and locally developed pavement temperature algorithms for the prediction of high pavement design temperature. There is more variability between models in the prediction of low pavement design temperature. The paper also provides a set of PG grading results for a range of Australian asphalt binders. The findings indicate that for a given design situation harder bitumen, ormore highly modified binder would be specified in Australia than in jurisdictions using the PG system. [ABSTRACT FROM AUTHOR]

With the rapid development of globalization economy, countries in the world are more and more closely connected in business, and international import and export trade has also achieved rapid development. Based on the analysis of the status quo of the country's import and export trade, this article combines the main national economic indicators to analyze and study the algorithm of import and export trade forecasting. RVM is a sparse probability model and a new supervised learning method. Firstly, this paper introduces the protection system of block chain technology for import and export trade data information. Then, a hybrid RVM model is constructed, which is optimized by PSO algorithm, and the import and export volume is predicted based on this model. Based on the analysis of the data, it is tested that the security protection coefficient of the blockchain security technology for import and export trade data can reach up to 99.9%, and the accuracy of the import and export trade forecast based on the PSO optimized hybrid RVM model can reach up to 85.79%. A series of experiments show that the import and export trade forecast model studied in this paper can accurately predict the volume of import and export trade, thus providing a new method for the country's import and export trade, with high practical significance. [ABSTRACT FROM AUTHOR]

To solve the problem of feature selection and error correction after mode decomposition and improve the ability of power load forecasting models to capture complex time series information, a two-stage short-term power load forecasting method based on recursive feature elimination with a cross validation (RFECV) algorithm and time convolution network–efficient channel attention mechanism–long short-term memory network (TCN–ECA–LSTM) is presented. First, the load sequence is decomposed into a relatively stable set of modal components using variational mode decomposition. Then, the RFECV-based method filters the feature set of each modal component to construct the best feature set. Finally, a two-stage prediction model based on TCN–ECA–LSTM is established. The first stage predicts each modal component and the second stage reconstructs the load forecast based on the predicted value of the previous stage. This paper takes actual data from New South Wales, Australia, as an example, and the results show that the method proposed in this paper can build the feature set reliably and efficiently and has a higher accuracy than the conventional prediction model. [ABSTRACT FROM AUTHOR]

Chronic disease identification and management is a significant issue in Australia, with general practice being the primary contact point for those at risk of, or living with, chronic disease. However, there is a well-described gap between guideline recommendations for chronic disease management and translation in the general practice setting. In 2018, a group of researchers, clinicians and software developers collaborated to develop a tool to support the identification and management of chronic disease in general practice, with the aim to create a platform that met the needs of general practice. The co-design process drew together core principles and expectations for the establishment of a technological platform, called Future Health Today (FHT), which would sit alongside the electronic medical record (EMR) management system within general practice. FHT used algorithms applied to EMR data to identify patients with, or at risk of, chronic disease and requiring review. Using chronic kidney disease as a clinical focus, the FHT prototype was piloted in a large, metropolitan general practice, and a large regional general practice. Based on user feedback, the prototype was further developed and improved. This paper provides a report on the key features and functionalities that participants identified and implemented in practice. Future Health Today is a new platform, co-designed by general practice for general practice, which aims to streamline the identification and management of chronic disease to improve health outcomes. This paper describes the development of the technology platform and how it was optimised through an implementation study in general practice. [ABSTRACT FROM AUTHOR]

Accurate prediction of re-entry time and location of an uncontrolled re-entering space object is crucial but challenging. This paper presents in-house re-entry prediction algorithms: RSMGA, STKOptim, STKLTOptim, and ABPro. Case studies on re-entry prediction of Starlink-26 (COSPAR ID 2019-029F or NORAD ID 44240) and CZ-5B (COSPAR ID 2021-035B or NORAD ID 48275) during the IADC re-entry test campaigns 2021/1 and 2021/2, respectively are presented. Simultaneous application of these re-entry prediction algorithms facilitates decision-making on automation of switching between these algorithms during various phases (short term or long-term) of the re-entry campaign. The effectiveness and applicability of these algorithms are studied based on percentage error. The study focuses on the overall and time-based performance of the four methods. Six more re-entered objects are selected (three Geosynchronous transfer orbit (GTO) objects and 3 Low-Earth orbit (LEO) objects), and their re-entry time prediction has been carried out using the four methods for different time instances before re-entry. Prediction estimates are compared among the methods for all the time instances in terms of percentage error. Also, the study helps in fixing the suitability of the re-entry time prediction algorithm for objects from GTO and LEO. [ABSTRACT FROM AUTHOR]

A depth map fusion algorithm fuses depth maps from different perspectives into a unified coordinate framework and performs surface calculations to generate dense point clouds of the entire scene. The existing algorithms ensure the quality of these dense point clouds by eliminating inconsistencies between depth maps, but the problem of many redundant calculations often arises. In this paper, a depth map fusion algorithm based on pixel region prediction is proposed. First, the image combination is calculated to select a set of candidate neighbor images for each reference image in the scene. Second, voxels and measure estimates are constructed on a coarse scale, and an inference strategy and a corrector are proposed to merge pixel regions at a fine scale guided by the coarse scale. Finally, the deduced pixel regions at the fine scale are used as the image-space constraints for depth fusion. Public and actual oblique images datasets are used for experimental verification. Compared with the famous COLMAP, OPENMVS, Gipuma and ACMP methods, the number of redundant calculations is significantly reduced; according to Data1 ∼ Data9 in the experiment, as the number of images increases, the fusion efficiency is increased by 47.5% to 156.6%; at the same time, the point cloud accuracy is comparable to other methods. [ABSTRACT FROM AUTHOR]

Accurate and reliable prediction of PM2.5 concentrations is the basis for appropriate warning measures, and a single prediction model is often ineffective. In this paper, we propose a novel decomposition-and-ensemble model to predict the concentration of PM2.5. The model utilizes Ensemble Empirical Mode Decomposition (EEMD) to decompose PM2.5 series, Support Vector Regression (SVR) to predict each Intrinsic Mode Function (IMF), and a hybrid algorithm based on Differential Evolution (DE) and Grey Wolf Optimizer (GWO) to optimize SVR parameters. The proposed prediction model EEMD-SVR-DEGWO is employed to forecast the concentration of PM2.5 in Guangzhou, Wuhan, and Chongqing of China. Compared with six prediction models, the proposed EEMD-SVR-DEGWO is a reliable predictor and has achieved competitive results. [ABSTRACT FROM AUTHOR]

Predicting the long-term lifetime of power MOSFET devices plays a central role in the prevention of unprecedented failures for power MOSFETs used in safety-critical applications. The various traditional model-based approaches and statistical and filtering algorithms for prognostics have limitations in terms of handling the dynamic nature of failure precursor degradation data for these devices. In this paper, a prognostic model based on LSTM and GRU is developed that aims at estimating the long-term lifetime of discrete power MOSFETs using dominant failure precursor degradation data. An accelerated power cycling test has been designed and executed to collect failure precursor data. For this purpose, commercially available power MOSFETs passed through power cycling tests at different temperature swing conditions and potential failure precursor data were collected using an automated curve tracer after certain intervals. The on-state resistance degradation data identified as one of the dominant failure precursors and potential aging precursors has been analyzed using RNN, LSTM, and GRU-based algorithms. The LSTM and GRU models have been found to be superior compared to RNN, with MAPE of 0.9%, 0.78%, and 1.72% for MOSFET 1; 0.90%, 0.66%, and 0.6% for MOSFET 5; and 1.05%, 0.9%, and 0.78%, for MOSFET 9, respectively, predicted at 40,000 cycles. In addition, the robustness of these methods is examined using training data at 24,000 and 54,000 cycles of starting points and is able to predict the long-term lifetime accurately, as evaluated by MAPE, MSE, and RMSE metrics. In general, the prediction results showed that the prognostics algorithms developed were trained to provide effective, accurate, and useful lifetime predictions and were found to address the reliability concerns of power MOSFET devices for practical applications. [ABSTRACT FROM AUTHOR]

Link prediction has been widely studied as an important research direction. Higher-order link prediction has gained, in particular, significant attention since higher-order networks provide a more accurate description of real-world complex systems. However, higher-order networks contain more complex information than traditional pairwise networks, making the prediction of higher-order links a formidable challenging task. Recently, researchers have discovered that local features have advantages over long-range features in higher-order link prediction. Therefore, it is necessary to develop more efficient and concise higher-order link prediction algorithms based on local features. In this paper, we proposed two similarity metrics via local information, simplicial decomposition weight and closed ratio weight, to predict possible future higher-order interactions (simplices) in simplicial networks. These two algorithms capture local higher-order information at two aspects: simplex decomposition and cliques' state (closed or open). We tested their performance in eight empirical simplicial networks, and the results show that our proposed metrics outperform other benchmarks in predicting third-order and fourth-order interactions (simplices) in most cases. In addition, we explore the robustness of the proposed algorithms, and the results suggest that the performance of these novel algorithms is advanced under different sizes of training sets. [ABSTRACT FROM AUTHOR]

Current link prediction strategies are about finding new probable strong relations to establish or weak ones to remove. An interesting strategy is utilizing link prediction to prioritize the edges in the network and finding newly probable established relations. In this paper we will introduce and explain RLP, reverse link prediction, as a new paradigm, and use popular basic scoring methods including CN, JC, AA, RA, and PA, as its core to examine. The test cases are nine datasets. Half of them are contact networks in different levels from personal contact to aviation, and another half is for covering different test situations. After reviewing the edge removal based epidemic mitigation methods, we show that RLP can be used to decrease the epidemics spreading speed as a general method with various link prediction algorithms, and here in this paper, preferential attachment (PA) has the best results overall. But the results heavily depend on the nature of the examined networks: regular, scale-free or small-world. We also propose an easy to understand criteria, path count, for comparing the efficacy of epidemics mitigation methods. RLP can be extended to use other link prediction scoring methods in various types of graphs as well. [ABSTRACT FROM AUTHOR]

Most of the existing image tampering detection methods are only for a certain tampering method, and there is a problem that the detection accuracy of the tampered area boundary is not high. In this regard, this paper proposed a U-shaped network based on dual-stream encoder-decoder architecture for image tampering. Firstly, the method used the skip connection between the encoder and the decoder to fuse the low-level and high-level features in the tampered image, and used the atrous convolution and CBAM attention mechanism to fuse the features output by the encoder, so that the network had better localization performance for tampered regions of different scales; Secondly, in order to improve the network’s detection accuracy of the boundary of the tampered area, this algorithm used the image morphological method to make a tampered boundary dataset; Finally, it used multiple loss functions to optimize the performance of the network simultaneously, namely it used cross-entropy and root-mean-square loss functions to measure the tampered region loss and tampered boundary loss of the prediction graph respectively. The experimental results on 4 public datasets: CASIA, Columbia, NIST16, Coverage show that the method proposed in this paper can effectively detect the tampering area of the fake image with splicing and copy-paste tampering methods, and output pixel-level tampering region location map. Compared with other mainstream tampering detection methods, the proposed method achieves the highest AUC values on the CASIA and Columbia dataset and the highest F1 values on the Columbia dataset. [ABSTRACT FROM AUTHOR]

For traditional predictor-corrector guidance algorithm for reentry glide vehicle, it cost a lot of time to obtain predicted flight range with a slow speed to iterate. In this paper, according to residual network (ResNet)'s block and dynamic model of vehicle, through analyzing the characteristics of predicted flight range with constraints, the flight range prediction block and flight range prediction neural network are designed, which can obtain the predicted range accurately and quickly; then aiming at the separation between guidance logic and no-fly zone avoidance logic, which may lead to guidance failure and increasing of the sign variation number of the bank angle, the no-fly zone crossrange and the no-fly zone mapping crossrange are proposed in this paper. According the repulsion force of artificial potential field, an adaptive crossrange corridor combining guidance logic and no-fly zone avoidance logic is proposed, and the convergence of the corridor is analyzed theoretically. Through simulation, the block number of flight range prediction network is determined firstly. By this method, the efficiency of lateral guidance can be improved. Then, through the simulation with the different no-fly zones under different disturbed conditions, the stability and validity of the guidance method are verified. Finally, compared with other predictor-corrector algorithms, the proposed method can realize guidance with less sign variation number of bank angle and better avoidance for no-fly zones. [ABSTRACT FROM AUTHOR]

Machine learning and deep learning algorithms have shown positive outcomes in a variety of industries. The number of defects in machinery equipment is predicted to rise as the usage of smart machinery grows. The use of diverse algorithms to detect and diagnose machine faults is becoming more common. Using both open-source and closed-source data sets and machine learning methods, a variety of studies have been conducted and published. This paper reviews current work that uses the bearing data set to detect and diagnose equipment faults using machine learning and deep learning methods. In this paper, the working algorithm, result, and other relevant details are described, as well as the recently published studies. [ABSTRACT FROM AUTHOR]

Research on the state of charge (SOC) prediction of lead–acid batteries is of great importance to the use and management of batteries. Due to this reason, this paper proposes a method for predicting the SOC of lead–acid batteries based on the improved AdaBoost model. By using the online sequence extreme learning machine (OSELM) as its weak learning machine, this model can achieve incremental learning of the model, which has a high computational efficiency, and does not require repeated training of old samples. Through improvement of the AdaBoost algorithm, the local prediction accuracy of the algorithm for the sample is enhanced, the scores of the proposed model in the maximum absolute error (AEmax) and maximum absolute percent error (APEmax) indicators are 6.8% and 8.8% lower, and the accuracy of the model is further improved. According to the verification with experimental data, when there are a large number of prediction samples, the improved AdaBoost model can reduce the prediction accuracy indicators of mean absolute percent error (MAPE), mean absolute error (MAE), and mean square error (MSE) to 75.4%, 58.3, and 84.2%, respectively. Compared with various other prediction methods in the prediction accuracy of battery SOC, the prediction accuracy indicators MAE, MSE, MAPE, AEmax, and APEmax of the model proposed in this paper are all optimal, which proves the validity and adaptive ability of the model. [ABSTRACT FROM AUTHOR]

Existing session-based recommendation algorithms mainly recommend by mining the item conversion relationship of a single target session, and take less account of the complex conversion information between items from other different sessions. This paper proposed a session-based recommendation algorithm fusing global and neighbor collaboration information（SFGN-GNN）, which simultaneously considered the collaboration information from neighbor and global sessions to fully exploit user preference. The algorithm expressed user preference by learning session representation. Firstly, it built the neighbor graph according to the pairwise item transfer relationship between the target session and neighbor session, and built the global graph according to the pairwise item transfer relationship in all sessions. Then, it used the graph neural network to obtain the neighbor-level and global-level item representations of the target session node. Next, it used the fusion gate to obtain the session-level item representation, and embedded the position information and time information of the item in the target session. Afterward, it obtained the final session representation by using the soft attention mechanism. Finally, it predicted the next possible interaction item by softmax function. Experiments on two datasets demonstrate the effectiveness of SFGN-GNN algorithm. [ABSTRACT FROM AUTHOR]

In order to fully mine nodes' features and better integrate these features simultaneously in the heterogeneous information network, this paper proposed a AMF L& GRec Firstly, AMFL & GRec used the Leader Rank algorithm to extract the target node' global sequence, and used a meta-path-bas ed heterogeneous information network embedding model to extract the node' local sequence,and used the skip-gram model to learn the node' global and local features. And then it used the self-attention mechanism to learn the preference of the target nodes' local and global features to obtain the feature representation of the target node in a single meta-path. Secondly, it used the self-attention mechanism to fuse the representation of the same node under different meta-paths to obtain the final feature representation. Finally, it utilized a multi-layer perceptron to achieve the task of rating prediction. This paper conducted a large number of experiments on two real datasets. The experimental results verify that the AMFL & GRec algorithm can not only capture the micro(local) structure of densely connected nodes, but also capture the global structure of the node in the network, and finally obtain nodes' overall (local +global) characteristics. At the same time, the experimental results also prove that the AMFL & GRec's rating prediction performance is better than the baselines. It proves that in the heterogeneous information network utilizing the self-attention mechanism to consider the nodes' preferences for local and global features and meta-paths can improve the accuracy of rating prediction. [ABSTRACT FROM AUTHOR]

Disease risk prediction is a rising challenge in the medical domain. Researchers have widely used machine learning algorithms to solve this challenge. The k-nearest neighbour (KNN) algorithm is the most frequently used among the wide range of machine learning algorithms. This paper presents a study on different KNN variants (Classic one, Adaptive, Locally adaptive, k-means clustering, Fuzzy, Mutual, Ensemble, Hassanat and Generalised mean distance) and their performance comparison for disease prediction. This study analysed these variants in-depth through implementations and experimentations using eight machine learning benchmark datasets obtained from Kaggle, UCI Machine learning repository and OpenML. The datasets were related to different disease contexts. We considered the performance measures of accuracy, precision and recall for comparative analysis. The average accuracy values of these variants ranged from 64.22% to 83.62%. The Hassanaat KNN showed the highest average accuracy (83.62%), followed by the ensemble approach KNN (82.34%). A relative performance index is also proposed based on each performance measure to assess each variant and compare the results. This study identified Hassanat KNN as the best performing variant based on the accuracy-based version of this index, followed by the ensemble approach KNN. This study also provided a relative comparison among KNN variants based on precision and recall measures. Finally, this paper summarises which KNN variant is the most promising candidate to follow under the consideration of three performance measures (accuracy, precision and recall) for disease prediction. Healthcare researchers and stakeholders could use the findings of this study to select the appropriate KNN variant for predictive disease risk analytics. [ABSTRACT FROM AUTHOR]

Background: MiRNA is a class of non-coding single-stranded RNA molecules with a length of approximately 22 nucleotides encoded by endogenous genes, which can regulate the expression of other genes. Therefore, it is very important to predict the associations between miRNA and disease. Predecessors developed a new prediction method of drug-disease association, and it achieved good results.Methods: In this paper, we introduced the method of LAGCN to identify potential miRNA-disease associations. First, we integrate three associations into a heterogeneous network, such as the known miRNA-disease association, miRNA-miRNA similarities and disease-disease similarities, next we apply graph convolution network to learn the embedding of miRNA and disease. We use an attention mechanism to combine embedding from multiple convolution layers. Unobserved miRNA-disease associations are scored based on integrated embedding.Results: After fivefold cross-validations, the value of AUC is reached 0.9091, which is higher than other prediction methods and baseline methods.Conclusions: In this paper, we introduced the method of LAGCN to identify potential miRNA-disease associations. LAGCN has achieved good performance in predicting miRNA-disease associations, and it is superior to other association prediction methods and baseline methods. [ABSTRACT FROM AUTHOR]

This paper presents a new algorithm to navigate robots in dynamically cluttered environments. The proposed algorithm uses basic concepts of space attraction (hence the term Agoraphilic) to navigate robots through dynamic obstacles. The new algorithm in this paper is an advanced development of the original Agoraphilic navigation algorithm that was only able to navigate robots in static environments. The Agoraphilic algorithm does not look for obstacles (problems) to avoid but rather for a free space (solutions) to follow. Therefore, it is also described as an optimistic navigation algorithm. This algorithm uses only one attractive force created by the available free space. The free-space concept allows the Agoraphilic algorithm to overcome inherited challenges of general navigation algorithms. However, the original Agoraphilic algorithm has the limitation in navigating robots only in static, not in dynamic environments. The presented algorithm was developed to address this limitation of the original Agoraphilic algorithm. The new algorithm uses a developed object tracking module to identify the time-varying free spaces by tracking moving obstacles. The capacity of the algorithm was further strengthened by the new prediction module. Future space prediction allowed the algorithm to make decisions considering future growing/diminishing free spaces. This paper also includes a bench-marking study of the new algorithm compared with a recently published APF-based algorithm under a similar operating environment. Furthermore, the algorithm was validated based on experimental tests and simulation tests. [ABSTRACT FROM AUTHOR]

In order to improve the accuracy of power load forecasting, this paper proposes a neural network-based short-term monitoring method. First, the original energy load signal is decomposed by the CEEMDAN algorithm to obtain several eigenmode function components and residual components; several eigenmode function components and residual functions are fed into the NARX neural network for computational purposes. The partial hypothesis is superimposed in the following part to obtain the final short-term forecast. According to the test results, the MAPE of the CEEMDAN-NARX model is 4.753%, 3.540%, and 0.343% lower than the SVM, RNN, and NARX models, respectively, and 3.741% and 2.682% lower than CEEMDAN-SVM and CEEMDAN-RNN, respectively. The MAPE and RMSE of the CEEMDAN-NARX model are 0.765% and 101.7 MW, respectively, which are 0.468% and 45.2 MW lower than NARX models, respectively. Compared to CEEMDAN-SVM, the MAPE of CEEMDAN-NARX and CEEMDAN-RNN decreased by 0.986% and 0.692%, respectively, and the RMSE of CEEMDAN-NARX decreased by 111.5 and 65.7 MW, respectively, compared to CEEMDAN-SVM. Conclusion is that the load forecasting model based on the combination of CEEMDAN algorithm and NARX neural network can effectively connect, reduce the negative impact of noise on forecasting results, and improve forecasting accuracy. [ABSTRACT FROM AUTHOR]

As an important energy storage device, lithium-ion batteries (LIBs) have been widely used in various fields due to their remarkable advantages. The high level of precision in estimating the battery's state of health greatly enhances the safety and dependability of the application process. In contrast to traditional model-based prediction methods that are complex and have limited accuracy, data-driven prediction methods, which are considered mainstream, rely on direct data analysis and offer higher accuracy. Therefore, this paper reviews how to use the latest data-driven algorithms to predict the SOH of LIBs, and proposes a general prediction process, including the acquisition of datasets for the charging and discharging process of LIBs, the processing of data and features, and the selection of algorithms. The advantages and limitations of various processing methods and cutting-edge data-driven algorithms are summarized and compared, and methods with potential applications are proposed. Effort was also made to point out their application methods and application scenarios, providing guidance for researchers in this area. [ABSTRACT FROM AUTHOR]

Partial label learning is a weakly supervised learning framework. In partial label learning, each instance is associa-ted with a set of candidate labels, and its ground-truth label is unknown to us during the training process. In order to eliminate the ambiguous of candidate labels, this paper put forward a novel partial label learning by semantic difference and manifold learning (PL-SDML) method, which combined the semantic difference maximization criterion of instances and manifold lear-ning for partial label learning. The PL-SDML method was a two-stage method that used semantic difference maximization criterion of instances and manifold learning to generate the labeling confidence for training instances in the training phase. Then, PL-SDML made predicts for unseen instances via a nearest neighbor voting-based approach in the predict phase. On the UCI datasets, PL-SDML is superior to other comparison algorithms in 70% cases. On the four real-world datasets, the classification performance of PL-SDML improves by 0.3%~13.8% compared with other baselines. [ABSTRACT FROM AUTHOR]

In the last years, the number of machine learning algorithms and their parameters has increased significantly. On the one hand, this increases the chances of finding better models. On the other hand, it increases the complexity of the task of training a model, as the search space expands significantly. As the size of datasets also grows, traditional approaches based on extensive search start to become prohibitively expensive in terms of computational resources and time, especially in data streaming scenarios. This paper describes an approach based on meta-learning that tackles two main challenges. The first is to predict key performance indicators of machine learning models. The second is to recommend the best algorithm/configuration for training a model for a given machine learning problem. When compared to a state-of-the-art method (AutoML), the proposed approach is up to 130x faster and only 4% worse in terms of average model quality. Hence, it is especially suited for scenarios in which models need to be updated regularly, such as in streaming scenarios with big data, in which some accuracy can be traded for a much shorter model training time. [ABSTRACT FROM AUTHOR]

As high-resolution global coverage cannot easily be achieved by direct bathymetry, the use of gravity data is an alternative method to predict seafloor topography. Currently, the commonly used algorithms for predicting seafloor topography are mainly based on the approximate linear relationship between topography and gravity anomaly. In actual application, it is also necessary to process the corresponding data according to some empirical methods, which can cause uncertainty in predicting topography. In this paper, we established analytical observation equations between the gravity anomaly and topography, and obtained the corresponding iterative solving method based on the least square method after linearizing the equations. Furthermore, the regularization method and piecewise bilinear interpolation function are introduced into the observation equations to effectively suppress the high-frequency effect of the boundary sea region and the low-frequency effect of the far sea region. Finally, the seafloor topography beneath a sea region (117.25°–118.25°E, 13.85°–14.85°N) in the South China Sea is predicted as an actual application, where gravity anomaly data of the study area with a resolution of 1′ × 1′ are from the DTU17 model. Comparing the prediction results with the data of ship soundings from the National Geophysical Data Center (NGDC), the root-mean-square (RMS) error and relative error can be up to 127.4 m and approximately 3.4%, respectively. [ABSTRACT FROM AUTHOR]

Understanding and forecasting air quality index (AQI) plays a vital role in guiding the reduction of air pollution and helping social sustainable development. By combining fuzzy logic with decomposition techniques, ANFIS has become an important means to analyze the data resources, uncertainty and fuzziness. However, few studies have paid attention to the noise of decomposed subseries. Therefore, this paper presents a novel decomposition-denoising ANFIS model named SSADD-DE-ANFIS (Singular Spectrum Analysis Decomposition and Denoising-Differential Evolution-Adaptive Neuro-Fuzzy Inference System). This method uses twice SSA to decompose and denoise the AQI series, respectively, then fed the subseries obtained after the decomposition and denoising into the constructed ANFIS for training and predicting, and the parameters of ANFIS are optimized using DE. To investigate the prediction performance of the proposed model, twelve models are included in the comparisons. The experimental results of four seasons show that: the RMSE of the proposed SSADD-DE-ANFIS model is 1.400628, 0.63844, 0.901987 and 0.634114, respectively, which is 19.38%, 21.27%, 20.43%, 21.27% and 87.36%, 88.12%, 88.97%, 88.71% lower than that of the single SSA decomposition and SSA denoising. Diebold-Mariano test is performed on all the prediction results, and the test results show that the proposed model has the best prediction performance. [ABSTRACT FROM AUTHOR]

Although collaborative filtering algorithms become widely applicable, they also suffer from the difficulties of scalability and extensibility. To address this problem, this paper proposed a collaborative filtering model for recommendation systems based on the classification of user complex network features（UCNFC）. Firstly, the method selects feature users based on degree values in the user set and establishes similarity thresholds to implement groups of non-feature users. Then, user-user similarity constructs the network and completes the community labeling in the network by K-core decomposition. Finally, the target users choose their neighbors within themselves group to accomplish movie rating prediction. Based on the experimental results of Movie Lens and Netflix datasets, the algorithm shows improved both temporal and spatial performance compared with the classical collaborative filtering algorithm, demonstrating more excellent scalability and extensibility. [ABSTRACT FROM AUTHOR]

Accurate gene-disease association prediction results are the basis for effective diagnosis and treatment of complex genetic diseases. However, existing studies related to this topic generally face problems in two aspects: large volume of original data and diverse data type, and data fusion difficulty. Therefore, this paper studied a gene-disease association prediction algorithm based on multi-source data fusion. At first, it processed the multidimensional gene phenotype data, analyzed the gene-disease associations of different phenotypes, and completed the selection of disease gene loci under multi-dimensional phenotypes. Then, this paper fused the multi-source data containing the gene expression data, gene sequence data, gene interaction data, and transcriptome sequencing data, and established the corresponding gene-disease association prediction model. At last, the effectiveness of the constructed prediction model was verified by experimental results. The research results obtained in this paper can improve the low utilization of gene datasets, restored the main features of the datasets to the greatest extent, reasonably processed the data noise, effectively enhanced the robustness of the model, and further improved the classification accuracy of the prediction of disease-causing genes. [ABSTRACT FROM AUTHOR]

In the process of multi-target motion trajectory prediction, due to insufficient detection accuracy and real-time performance, some target position information is lost and prediction accuracy is not high. This paper proposed a multi-target trajectory prediction ( MMTP) algorithm based on improved Kalman filter. MMTP algorithm used the YOLOv4 detector in the target detection stage to improve the accuracy and speed of target detection. In the target matching stage, MMTP algorithm used the KM matching algorithm to associate the detection target of the current detection frame with the target of the prediction frame predicted at the previous moment, thereby enhancing the accuracy of target association and avoiding target loss caused by target occlusion, target interleaving and drift. In the target coordinate prediction stage, this paper proposed an improved Kalman filter algorithm to predict the position coordinates of the next frame for each moving target and draw a prediction frame, so as to improve the prediction accuracy of target coordinates in non-linear scenes and reduce the error of predicted coordinates. Then it used the video sequence data set taken by MOT16 and the actual traffic system to verify the overall performance of the algorithm. The simulation results show that MMTP algorithm has better detection accuracy and speed in the target detection stage, which effectively improves the overall operating speed of the algorithm. In the target matching stage, MMTP algorithm can enhance the accuracy of target association and reduce target loss, which is better than RMOT, POI, SORT, Deep-SORT and YVTP. [ABSTRACT FROM AUTHOR]

Delay of flights is a core problem in civil aviation industry. It is significant to predict flight delay situation in advance so as to take reasonable measures to negative effects of flight delay. In order to improve the prediction performance, a flight delay multi-classification prediction model based on light gradient boosting machine(LightGBM)is put forward in this paper. This model can screen features by using variance filtering and recursive feature elimination according to flight information and weather information. It uses synthetic minority oversampling technique (SMOTE) and Tomek Link to deal with unbalanced data. Finally, LightGBM is used to build models, and multi-classification prediction of flight delay lengths can be realized. In order to verify the rationality of the model, this paper compares the proposed model with models constructed by other advanced algorithms. The experimental results show that the proposed model performs better in terms of various prediction performance indexes and can improve the prediction accuracy to 90% or higher. The model can also greatly reduce the training time and cost. [ABSTRACT FROM AUTHOR]

The state of health (SOH) of power battery reflects the difference between the current performance of the battery and the time it left the factory. Accurate prediction of it is the key to improving battery cycle efficiency. This paper studies the application of data-driven algorithms in power battery health estimation. Firstly, Using the data of actual operating vehicles which are monitoring in the data platform as the research objects. The charging event segmentation algorithm is designed for the full amount of data, and the K-means clustering model is used to extract slow charging events. Secondly, feature engineering is performed on the data, including the use of Pearson and Spearman coefficients analysis for numerical features, the use of one-hot encoding for category features to determine the final input features of SOH model. Eventually, using the Ridge linear regression model to predict the health status of the power battery. The research shows that the MAE is less than 5%, which meets the needs of practical use. In addition, this paper comparing Ridge with three other models named Linear Regression, Lasso, and Elastic Net. The result showed that the linear regression model with L2 regularization is more applicable in low-dimensional feature application scenarios without cell data in prediction of SOH. [ABSTRACT FROM AUTHOR]

Based on the BP neural network and the ARIMA model, this paper predicts the nonlinear residual of GDP and adds the predicted values of the two models to obtain the final predicted value of the model. First, the focus is on the ARMA model in the univariate time series. However, in real life, forecasts are often affected by many factors, so the following introduces the ARIMAX model in the multivariate time series. In the prediction process, the network structure and various parameters of the neural network are not given in a systematic way, so the operation of the neural network is affected by many factors. Each forecasting method has its scope of application and also has its own weaknesses caused by the characteristics of its own model. Secondly, this paper proposes an effective combination method according to the GDP characteristics and builds an improved algorithm BP neural network price prediction model, the research on the combination of GDP prediction model is currently mostly focused on the weighted form, and this article proposes another combination, namely, error correction. According to the price characteristics, we determine the appropriate number of hidden layer nodes and build a BP neural network price prediction model based on the improved algorithm. Validation of examples shows that the error-corrected GDP forecast model is also better than the weighted GDP forecast model, which shows that error correction is also a better combination of forecasting methods. The forecast results of BP neural network have lower errors and monthly prices. The relative error of prediction is about 2.5%. Through comparison with the prediction results of the ARIMA model, in the daily price prediction, the relative error of the BP neural network prediction is 1.5%, which is lower than the relative error of the ARIMA model of 2%. [ABSTRACT FROM AUTHOR]

The structural similarity based link prediction algorithms mainly exploit the information of network topology, such as links and nodes, to predict the potential links in complex networks. Among these algorithms, the local information similarity based algorithms have attracted the extensive attentions from the majority of researchers due to their low complexity and general applicability. The algorithms mainly exploit the attributes of common neighbors on the second-order transmission paths to predict the connection probability between the unconnected nodes, but ignore the structure attributes of endpoints. The structure attributes of an endpoint can be quantified as its influence resources, which make an important contribution to link prediction. To heighten the performances of local information based algorithms, this paper exploits the different structure attributes of endpoints to express the influence resources, and explores the contributions of the different endpoint attributes to local information algorithms. Extensive simulations on 12 real benchmark datasets show that, in most cases, the node degree expressing the influence resource makes the greatest contribution to improve the performances of the local information algorithms. Specifically, DCN, DAA and DRA algorithm possess the best prediction performances in 9, 5 and 7 datasets, respectively. Furthermore, compared with 6 mainstream algorithms, DRA as the best improved algorithm shows the optimal prediction performances in 8 datasets. [ABSTRACT FROM AUTHOR]

This paper presents a lossless image compression method with a fast decoding time and flexible adjustment of coder parameters affecting its implementation complexity. A comparison of several approaches for computing non-MMSE prediction coefficients with different levels of complexity was made. The data modeling stage of the proposed codec was based on linear (calculated by the non-MMSE method) and non-linear (complemented by a context-dependent constant component removal block) predictions. Prediction error coding uses a two-stage compression: an adaptive Golomb code and a binary arithmetic code. The proposed solution results in 30% shorter decoding times and a lower bit average than competing solutions (by 7.9% relative to the popular JPEG-LS codec). [ABSTRACT FROM AUTHOR]

In recommender systems, extracting higher order information about the graph using methods such as graph convolutional network alleviates the cold start problem. In order to fuse the deep feature extraction capability of neural network collaborative filtering on this basis, this paper proposed a two-channel collaborative filtering recommendation algorithm (GCNCF-2C) based on graph convolution. Firstly, it divided the recommendation problem into an upstream task and a downstream task. Secondly, to form a feature representation of nodes, in the upstream task, a pre-trained encoder extracted node features and higher-order features of the graph using a one-dimensional convolutional layer containing residuals and multiple graph convolutional layers in two independent channels. Finally, the decoder performed end-to-end training by node features for rating prediction. Experiments on the datasets MovieLens-100k and MovieLens-1M show that compared to the baseline models, the algorithm improves RMSE metrics by 1.72% and 1.76% on average and MAE metrics by 2.7% and 1.98% on average on the two datasets. Meanwhile, it improves RMSE metrics by 5.9% on average in the cold-start experiments based on users and projects, which shows overall performance. [ABSTRACT FROM AUTHOR]

Building electricity load forecasting plays an important role in building energy management, peak demand and power grid security. In the past two decades, a large number of data-driven models have been applied to building and larger-scale energy consumption predictions. Although these models have been successful in specific cases, their performances would be greatly affected by the quantity and quality of the building data. Moreover, for older buildings with sparse data, or new buildings with no historical data, accurate predictions are difficult to achieve. Aiming at such a data silos problem caused by the insufficient data collection in the building energy consumption prediction, this study proposes a building electricity load forecasting method based on a similarity judgement and an improved TrAdaBoost algorithm (iTrAdaBoost). The Maximum Mean Discrepancy (MMD) is used to search similar building samples related to the target building from public datasets. Different from general Boosting algorithms, the proposed iTrAdaBoost algorithm iteratively updates the weights of the similar building samples and combines them together with the target building samples for a prediction accuracy improvement. An educational building's case study is carried out in this paper. The results show that even when the target and source samples belong to different domains, i.e., the geographical location and meteorological condition of the buildings are different, the proposed MMD-iTradaBoost method has a better prediction accuracy in the transfer learning process than the BP or traditional AdaBoost models. In addition, compared with other advanced deep learning models, the proposed method has a simple structure and is easy for engineering implementation. [ABSTRACT FROM AUTHOR]

The survival prediction of children undergoing hematopoietic stem-cell transplantation is essential for successful transplantation. However, the performance of current algorithms for predicting mortality in this patient group has not improved over recent decades. This paper proposes a new feature selection technique for survival prediction problems using the Mud Ring Algorithm (MRA). Experiments and tests were initially performed on 13 real datasets with varying occurrences to compare the suggested algorithm with other algorithms. After that, the constructed model classification performance was compared to other techniques using the bone marrow transplant children's dataset. Modern techniques were used to acquire their classification results, which were then compared to the suggested outcomes using a variety of well-known metrics, graphical tools, and diagnostic analysis. This investigation has demonstrated that our suggested approach is comparable and outperformed other methods in terms of results. In addition, the results showed that the constructed model enhanced prediction accuracy by up to 82.6% for test cases. [ABSTRACT FROM AUTHOR]