Добірка наукової літератури з теми "Boosting window algorithm"
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся зі списками актуальних статей, книг, дисертацій, тез та інших наукових джерел на тему "Boosting window algorithm".
Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.
Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.
Статті в журналах з теми "Boosting window algorithm"
1
Deng, Shangkun, Chenguang Wang, Jie Li, Haoran Yu, Hongyu Tian, Yu Zhang, Yong Cui, Fangjie Ma, and Tianxiang Yang. "Identification of Insider Trading Using Extreme Gradient Boosting and Multi-Objective Optimization." Information 10, no. 12 (November 25, 2019): 367. http://dx.doi.org/10.3390/info10120367.
Повний текст джерелаАнотація:
Illegal insider trading identification presents a challenging task that attracts great interest from researchers due to the serious harm of insider trading activities to the investors’ confidence and the sustainable development of security markets. In this study, we proposed an identification approach which integrates XGboost (eXtreme Gradient Boosting) and NSGA-II (Non-dominated Sorting Genetic Algorithm II) for insider trading regulation. First, the insider trading cases that occurred in the Chinese security market were automatically derived, and their relevant indicators were calculated and obtained. Then, the proposed method trained the XGboost model and it employed the NSGA-II for optimizing the parameters of XGboost by using multiple objective functions. Finally, the testing samples were identified using the XGboost with optimized parameters. Its performances were empirically measured by both identification accuracy and efficiency over multiple time window lengths. Results of experiments showed that the proposed approach successfully achieved the best accuracy under the time window length of 90-days, demonstrating that relevant features calculated within the 90-days time window length could be extremely beneficial for insider trading regulation. Additionally, the proposed approach outperformed all benchmark methods in terms of both identification accuracy and efficiency, indicating that it could be used as an alternative approach for insider trading regulation in the Chinese security market. The proposed approach and results in this research is of great significance for market regulators to improve their supervision efficiency and accuracy on illegal insider trading identification.
2
Li, Yongfeng, Hang Shu, Jérôme Bindelle, Beibei Xu, Wenju Zhang, Zhongming Jin, Leifeng Guo, and Wensheng Wang. "Classification and Analysis of Multiple Cattle Unitary Behaviors and Movements Based on Machine Learning Methods." Animals 12, no. 9 (April 20, 2022): 1060. http://dx.doi.org/10.3390/ani12091060.
Повний текст джерелаАнотація:
The behavior of livestock on farms is the primary representation of animal welfare, health conditions, and social interactions to determine whether they are healthy or not. The objective of this study was to propose a framework based on inertial measurement unit (IMU) data from 10 dairy cows to classify unitary behaviors such as feeding, standing, lying, ruminating-standing, ruminating-lying, and walking, and identify movements during unitary behaviors. Classification performance was investigated for three machine learning algorithms (K-nearest neighbors (KNN), random forest (RF), and extreme boosting algorithm (XGBoost)) in four time windows (5, 10, 30, and 60 s). Furthermore, feed tossing, rolling biting, and chewing in the correctly classified feeding segments were analyzed by the magnitude of the acceleration. The results revealed that the XGBoost had the highest performance in the 60 s time window with an average F1 score of 94% for the six unitary behavior classes. The F1 score of movements is 78% (feed tossing), 87% (rolling biting), and 87% (chewing). This framework offers a possibility to explore more detailed movements based on the unitary behavior classification.
3
Song, Moon Kyou, and Md Mostafa Kamal Sarker. "Modeling and Implementing Two-Stage AdaBoost for Real-Time Vehicle License Plate Detection." Journal of Applied Mathematics 2014 (2014): 1–8. http://dx.doi.org/10.1155/2014/697658.
Повний текст джерелаАнотація:
License plate (LP) detection is the most imperative part of the automatic LP recognition system. In previous years, different methods, techniques, and algorithms have been developed for LP detection (LPD) systems. This paper proposes to automatical detection of car LPs via image processing techniques based on classifier or machine learning algorithms. In this paper, we propose a real-time and robust method for LPD systems using the two-stage adaptive boosting (AdaBoost) algorithm combined with different image preprocessing techniques. Haar-like features are used to compute and select features from LP images. The AdaBoost algorithm is used to classify parts of an image within a search window by a trained strong classifier as either LP or non-LP. Adaptive thresholding is used for the image preprocessing method applied to those images that are of insufficient quality for LPD. This method is of a faster speed and higher accuracy than most of the existing methods used in LPD. Experimental results demonstrate that the average LPD rate is 98.38% and the computational time is approximately 49 ms.
4
WANG, CHI-CHEN RAXLE, JIN-YI WU, and JENN-JIER JAMES LIEN. "PEDESTRIAN DETECTION SYSTEM USING CASCADED BOOSTING WITH INVARIANCE OF ORIENTED GRADIENTS." International Journal of Pattern Recognition and Artificial Intelligence 23, no. 04 (June 2009): 801–23. http://dx.doi.org/10.1142/s0218001409007363.
Повний текст джерелаАнотація:
This study presents a novel learning-based pedestrian detection system capable of automatically detecting individuals of different sizes and orientations against a wide variety of backgrounds, including crowds, even when the individual is partially occluded. To render the detection performance robust toward the effects of geometric and rotational variations in the original image, the feature extraction process is performed using both rectangular- and circular-type blocks of various sizes and aspect ratios. The extracted blocks are rotated in accordance with their dominant orientation(s) such that all the blocks extracted from the input images are rotationally invariant. The pixels within the cells in each block are then voted into rectangular- and circular-type 9-bin histograms of oriented gradients (HOGs) in accordance with their gradient magnitudes and corresponding multivariate Gaussian-weighted windows. Finally, four cell-based histograms are concatenated using a tri-linear interpolation technique to form one 36-dimensional normalized HOG feature vector for each block. The experimental results show that the use of the Gaussian-weighted window approach and tri-linear interpolation technique in constructing the HOG feature vectors improves the detection performance from 91% to 94.5%. In the proposed scheme, the detection process is performed using a cascaded detector structure in which the weak classifiers and corresponding weights of each stage are established using the AdaBoost self-learning algorithm. The experimental results reveal that the cascaded structure not only provides a better detection performance than many of the schemes presented in the literature, but also achieves a significant reduction in the computational time required to classify each input image.
5
Chen, Zhiwei, Wei Zheng, Wenjie Yin, Xiaoping Li, Gangqiang Zhang, and Jing Zhang. "Improving the Spatial Resolution of GRACE-Derived Terrestrial Water Storage Changes in Small Areas Using the Machine Learning Spatial Downscaling Method." Remote Sensing 13, no. 23 (November 24, 2021): 4760. http://dx.doi.org/10.3390/rs13234760.
Повний текст джерелаАнотація:
Gravity Recovery and Climate Experiment (GRACE) satellites can effectively monitor terrestrial water storage (TWS) changes in large-scale areas. However, due to the coarse resolution of GRACE products, there is still a large number of deficiencies that need to be considered when investigating TWS changes in small-scale areas. Hence, it is necessary to downscale the GRACE products with a coarse resolution. First, in order to solve this problem, the present study employs modeling windows of different sizes (Window Size, WS) combined with multiple machine learning algorithms to develop a new machine learning spatial downscaling method (MLSDM) in the spatial dimension. Second, The MLSDM is used to improve the spatial resolution of GRACE observations from 0.5° to 0.25°, which is applied to Guantao County. The present study has verified the downscaling accuracy of the model developed through the combination of WS3, WS5, WS7, and WS9 and jointed with Random Forest (RF), Extra Tree Regressor (ETR), Adaptive Boosting Regressor (ABR), and Gradient Boosting Regressor (GBR) algorithms. The analysis shows that the accuracy of each combined model is improved after adding the residuals to the high-resolution downscaled results. In each modeling window, the accuracy of RF is better than that of ETR, ABR, and GBR. Additionally, compared to the changes in the TWS time series that are derived by the model before and after downscaling, the results indicate that the downscaling accuracy of WS5 is slightly more superior compared to that of WS3, WS7, and WS9. Third, the spatial resolution of the GRACE data was increased from 0.5° to 0.05° by integrating the WS5 and RF algorithm. The results are as follows: (1) The TWS (GWS) changes before and after downscaling are consistent, decreasing at −20.86 mm/yr and −21.79 mm/yr (−14.53 mm/yr and −15.46 mm/yr), respectively, and the Nash–Sutcliffe efficiency coefficient (NSE) and correlation coefficient (CC) values of both are above 0.99 (0.98). (2) The CC between the 80% deep groundwater well data and the downscaled GWS changes are above 0.70. Overall, the MLSDM can not only effectively improve the spatial resolution of GRACE products but also can preserve the spatial distribution of the original signal, which can provide a reference scheme for research focusing on the downscaling of GRACE products.
6
Kim, Yeongmin, Minsu Chae, Namjun Cho, Hyowook Gil, and Hwamin Lee. "Machine Learning-Based Prediction Models of Acute Respiratory Failure in Patients with Acute Pesticide Poisoning." Mathematics 10, no. 24 (December 7, 2022): 4633. http://dx.doi.org/10.3390/math10244633.
Повний текст джерелаАнотація:
The prognosis of patients with acute pesticide poisoning depends on their acute respiratory condition. Here, we propose machine learning models to predict acute respiratory failure in patients with acute pesticide poisoning using a decision tree, logistic regression, and random forests, support vector machine, adaptive boosting, gradient boosting, multi-layer boosting, recurrent neural network, long short-term memory, and gated recurrent gate. We collected medical records of patients with acute pesticide poisoning at the Soonchunhyang University Cheonan Hospital from 1 January 2016 to 31 December 2020. We applied the k-Nearest Neighbor Imputer algorithm, MissForest Impuer and average imputation method to handle the problems of missing values and outliers in electronic medical records. In addition, we used the min–max scaling method for feature scaling. Using the most recent medical research, p-values, tree-based feature selection, and recursive feature reduction, we selected 17 out of 81 features. We applied a sliding window of 3 h to every patient’s medical record within 24 h. As the prevalence of acute respiratory failure in our dataset was 8%, we employed oversampling. We assessed the performance of our models in predicting acute respiratory failure. The proposed long short-term memory demonstrated a positive predictive value of 98.42%, a sensitivity of 97.91%, and an F1 score of 0.9816.
7
Wei, Guanhao, Li Zhou, Lynn L. Lu, and Robert G. Steen. "Advanced tumor progression detection by leveraging EHR based convolutional neural network boosting approaches." Journal of Clinical Oncology 39, no. 15_suppl (May 20, 2021): e13581-e13581. http://dx.doi.org/10.1200/jco.2021.39.15_suppl.e13581.
Повний текст джерелаАнотація:
e13581 Background: Medical research in the areas of immunotherapies and targeted therapies has been drawing heavy attention and investment as the number of approved therapies continue to rise. Advanced findings on cancer treatment based on rich healthcare records help doctors to understand patient’s characteristics. The more accurate one can make a mathematical model predicting the likelihood of disease appearance, progression or treatment initiation, the better a proactive and effective targeting solution can be provided. Methods: Create positive/negative labels for patients who start to receive treatment or not within a time-sensitive window. Based on EHR records as Procedures, Prescription, and Diagnosis (PPD), patient’s feature interrelationship can be determined by a conditional probability matrix. Map PPD data to a well-designed patient-image profiles based a modified genetic algorithm to optimize and measure closeness. A Convolutional Neural Networks (CNN) model is then used to extract characteristics from patients’ feature image and learn the local patterns. Training the CNN model together with other upgraded AIML models is used to enhance overall prediction precision. Results: 144 different aggregated PPD features for patients with Chronic Lymphocytic Leukemia (CLL) were selected from the databases. Overall, the number of positive patients, who received treatment due to disease progression, is around 3% among 60K cases in each cohort, which is an extremely unbalanced dataset that is a challenge task for model training. In practice, we care about the model precision at k, which is the percentage of truly identified patients with k highest prediction scores. Comparing to common machine models like Random Forest, XGBoost and CatBoost, our proposed CNN model boosts the ensemble of baseline model performance in terms of average prediction precision at 1000 from 14.9% to 17.1%, which is about 15% relative percentage increase. Using this approach, many more truly identified patients could potentially receive targeted treatment on time. Patients’ top features and key feature interactions can also be identified as important references. Conclusions: The novel CNN boosting algorithm considers both aggregated PPD feature pairs using the graphical structure, significantly improves prediction model performance, and increases the model interpretability. In summary, the proposed model can help identify more potential patient candidates and determine precise treatment options.
8
Xiang, Tao, Tao Li, Mao Ye, and Zijian Liu. "Random Forest with Adaptive Local Template for Pedestrian Detection." Mathematical Problems in Engineering 2015 (2015): 1–11. http://dx.doi.org/10.1155/2015/767423.
Повний текст джерелаАнотація:
Pedestrian detection with large intraclass variations is still a challenging task in computer vision. In this paper, we propose a novel pedestrian detection method based on Random Forest. Firstly, we generate a few local templates with different sizes and different locations in positive exemplars. Then, the Random Forest is built whose splitting functions are optimized by maximizing class purity of matching the local templates to the training samples, respectively. To improve the classification accuracy, we adopt a boosting-like algorithm to update the weights of the training samples in a layer-wise fashion. During detection, the trained Random Forest will vote the category when a sliding window is input. Our contributions are the splitting functions based on local template matching with adaptive size and location and iteratively weight updating method. We evaluate the proposed method on 2 well-known challenging datasets: TUD pedestrians and INRIA pedestrians. The experimental results demonstrate that our method achieves state-of-the-art or competitive performance.
9
Li, Lihua, Mengzui Di, Hao Xue, Zixuan Zhou, and Ziqi Wang. "Feature Selection Model Based on IWOA for Behavior Identification of Chicken." Sensors 22, no. 16 (August 17, 2022): 6147. http://dx.doi.org/10.3390/s22166147.
Повний текст джерелаАнотація:
In order to reduce the influence of redundant features on the performance of the model in the process of accelerometer behavior recognition, and to improve the recognition accuracy of the model, this paper proposes an improved Whale Optimization algorithm with mixed strategy (IWOA) combined with the extreme gradient boosting algorithm (XGBoost) as a preferred method for chicken behavior identification features. A nine-axis inertial sensor was used to obtain the chicken behavior data. After noise reduction, the sliding window was used to extract 44 dimensional features in the time domain and frequency domain. To improve the search ability of the Whale Optimization algorithm for optimal solutions, the introduction of the good point set improves population diversity and expands the search range; the introduction of adaptive weight balances the search ability of the optimal solution in the early and late stages; the introduction of dimension-by-dimension lens imaging learning based on the adaptive weight factor perturbs the optimal solution and enhances the ability to jump out of the local optimal solution. This method’s effectiveness was verified by recognizing cage breeders’ feeding and drinking behaviors. The results show that the number of feature dimensions is reduced by 72.73%. At the same time, the behavior recognition accuracy is increased by 2.41% compared with the original behavior feature dataset, which is 95.58%. Compared with other dimensionality reduction methods, the IWOA–XGBoost model proposed in this paper has the highest recognition accuracy. The dimension reduction results have a certain degree of universality for different classification algorithms. This provides a method for behavior recognition based on acceleration sensor data.
10
Dave, Pritul, Arjun Chandarana, Parth Goel, and Amit Ganatra. "An amalgamation of YOLOv4 and XGBoost for next-gen smart traffic management system." PeerJ Computer Science 7 (June 18, 2021): e586. http://dx.doi.org/10.7717/peerj-cs.586.
Повний текст джерелаАнотація:
The traffic congestion and the rise in the number of vehicles have become a grievous issue, and it is focused worldwide. One of the issues with traffic management is that the traffic light’s timer is not dynamic. As a result, one has to remain longer even if there are no or fewer vehicles, on a roadway, causing unnecessary waiting time, fuel consumption and leads to pollution. Prior work on smart traffic management systems repurposes the use of Internet of things, Time Series Forecasting, and Digital Image Processing. Computer Vision-based smart traffic management is an emerging area of research. Therefore a real-time traffic light optimization algorithm that uses Machine Learning and Deep Learning Techniques to predict the optimal time required by the vehicles to clear the lane is presented. This article concentrates on a two-step approach. The first step is to obtain the count of the independent category of the class of vehicles. For this, the You Only Look Once version 4 (YOLOv4) object detection technique is employed. In the second step, an ensemble technique named eXtreme Gradient Boosting (XGBoost) for predicting the optimal time of the green light window is implemented. Furthermore, the different implemented versions of YOLO and different prediction algorithms are compared with the proposed approach. The experimental analysis signifies that YOLOv4 with the XGBoost algorithm produces the most precise outcomes with a balance of accuracy and inference time. The proposed approach elegantly reduces an average of 32.3% of waiting time with usual traffic on the road.
Дисертації з теми "Boosting window algorithm"
1
Elahi, Haroon. "A Boosted-Window Ensemble." Thesis, Blekinge Tekniska Högskola, Institutionen för datalogi och datorsystemteknik, 2014. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-5658.
Повний текст джерелаАнотація:
Context. The problem of obtaining predictions from stream data involves training on the labeled instances and suggesting the class values for the unseen stream instances. The nature of the data-stream environments makes this task complicated. The large number of instances, the possibility of changes in the data distribution, presence of noise and drifting concepts are just some of the factors that add complexity to the problem. Various supervised-learning algorithms have been designed by putting together efficient data-sampling, ensemble-learning, and incremental-learning methods. The performance of the algorithm is dependent on the chosen methods. This leaves an opportunity to design new supervised-learning algorithms by using different combinations of constructing methods. Objectives. This thesis work proposes a fast and accurate supervised-learning algorithm for performing predictions on the data-streams. This algorithm is called as Boosted-Window Ensemble (BWE), which is invented using the mixture-of-experts technique. BWE uses Sliding Window, Online Boosting and incremental-learning for data-sampling, ensemble-learning, and maintaining a consistent state with the current stream data, respectively. In this regard, a sliding window method is introduced. This method uses partial-updates for sliding the window on the data-stream and is called Partially-Updating Sliding Window (PUSW). The investigation is carried out to compare two variants of sliding window and three different ensemble-learning methods for choosing the superior methods. Methods. The thesis uses experimentation approach for evaluating the Boosted-Window Ensemble (BWE). CPU-time and the Prediction accuracy are used as performance indicators, where CPU-time is the execution time in seconds. The benchmark algorithms include: Accuracy-Updated Ensemble1 (AUE1), Accuracy-Updated Ensemble2 (AUE2), and Accuracy-Weighted Ensemble (AWE). The experiments use nine synthetic and five real-world datasets for generating performance estimates. The Asymptotic Friedman test and the Wilcoxon Signed-Rank test are used for hypothesis testing. The Wilcoxon-Nemenyi-McDonald-Thompson test is used for performing post-hoc analysis. Results. The hypothesis testing suggests that: 1) both for the synthetic and real-wrold datasets, the Boosted Window Ensemble (BWE) has significantly lower CPU-time values than two benchmark algorithms (Accuracy-updated Ensemble1 (AUE1) and Accuracy-weighted Ensemble (AWE). 2) BWE returns similar prediction accuracy as AUE1 and AWE for synthetic datasets. 3) BWE returns similar prediction accuracy as the three benchmark algorithms for the real-world datasets. Conclusions. Experimental results demonstrate that the proposed algorithm can be as accurate as the state-of-the-art benchmark algorithms, while obtaining predictions from the stream data. The results further show that the use of Partially-Updating Sliding Window has resulted in lower CPU-time for BWE as compared with the chunk-based sliding window method used in AUE1, AUE2, and AWE.
2
You, Mingshan. "An Adaptive Machine Learning Framework for Access Control Decision Making." Thesis, 2022. https://vuir.vu.edu.au/43688/.
Повний текст джерелаАнотація:
With the increasing popularity of information systems and digital devices, data
leakage has become a serious threat on a global scale. Access control is recognised
as the first defence to guarantee that only authorised users can access sensitive
data and thus prevent data leakage. However, currently widely used attributebased
access control (ABAC) is costly to configure and manage for large-scale
information systems. Furthermore, misconfiguration and policy explosion are
two significant challenges for ABAC strategies.
In recent years, machine learning technologies have been more applied in access
control decision-making to improve the automation and performance of access
control decisions. Nevertheless, existing studies usually fail to consider the
dynamic class imbalance problem in access control and thus achieve poor performance
on minority classes. In addition, the concept drift problem caused by the
evolving user and resource attributes, user behaviours, and access environments
is also challenging to tackle.
This thesis focuses on leveraging machine learning algorithms to make more
accurate and adaptive access control decisions. Specifically, a minority class
boosted framework is proposed to address the possible concept drifts caused by
evolving users’ behaviours and system environments. Its basic idea is to adopt an
incremental batch learning strategy to update the classifier continuously. Within
this framework, a boosting window (BW) algorithm is specially designed to boost
the performance of the minority class since the minority class is fatal for data
protection in access control problems. Furthermore, to improve the overall performance
of access control, this study adopts a knowledge graph to mine the
interlinked relationships between users and resources. A knowledge graph construction algorithm is designed to build a domain-specific knowledge graph. The
constructed knowledge graph is also adopted into an online learning framework
for access control decision-making.
The proposed frameworks and algorithms are evaluated and verified through
two open-source real-world Amazon datasets. Experimental results show that the
proposed BW algorithm effectively boosts the performance of the minority class.
Furthermore, using topological features extracted from our constructed access
control knowledge graph can improve access control performance in both offline
and online learning scenarios.
Тези доповідей конференцій з теми "Boosting window algorithm"
1
Sousa, Daniel Alves de, Elaine Ribeiro de Faria, and Rodrigo Sanches Miani. "Evaluating the Performance of Twitter-based Exploit Detectors." In Simpósio Brasileiro de Segurança da Informação e de Sistemas Computacionais. Sociedade Brasileira de Computação - SBC, 2020. http://dx.doi.org/10.5753/sbseg.2020.19257.
Повний текст джерелаАнотація:
Patch prioritization is a crucial aspect of information systems security, and knowledge of which vulnerabilities were exploited in the wild is a powerful tool to help systems administrators accomplish this task. The analysis of social media for this specific application can enhance the results and bring more agility by collecting data from online discussions and applying machine learning techniques to detect real-world exploits. In this paper, we use a technique that combines Twitter data with public database information to classify vulnerabilities as exploited or not-exploited. We analyze the behavior of different classifying algorithms, investigate the influence of different antivirus data as ground truth, and experiment with various time window sizes. Our findings suggest that using a Light Gradient Boosting Machine (LightGBM) can benefit the results, and for most cases, the statistics related to a tweet and the users who tweeted are more meaningful than the text tweeted. We also demonstrate the importance of using ground-truth data from security companies not mentioned in previous works.
2
Chen, Neyu, and Yaojun Ge. "Aerodynamic Parameter Identification and Flutter Performance Prediction of Closed Box Girder Based on Machine Learning." In IABSE Congress, Nanjing 2022: Bridges and Structures: Connection, Integration and Harmonisation. Zurich, Switzerland: International Association for Bridge and Structural Engineering (IABSE), 2022. http://dx.doi.org/10.2749/nanjing.2022.1161.
Повний текст джерелаАнотація:
<p>A bridge wind resistance database has been built based on the wind tunnel testing results of 20 long-span bridges. The artificial intelligence models for identifying aerostatic coefficients and flutter derivatives of close box girders are trained and developed via machine learning methods, including error back propagation neural network based on Levenberg-Marquardt algorithm and gradient boosting decision tree. The identification of the aerostatic coefficients can be achieved with high accuracy. For flutter derivatives, the model can also explore the underlying distribution of dataset. In this way, the present research work can make the identification of aerodynamic parameters separated from tedious wind tunnel test and complex numerical simulation to some extent. It can also provide a convenient and feasible option for expanding data sets of aerodynamic parameters. In addition, it can help determine the appropriate shape of the box girder cross-section in preliminary design stage of long-span bridge and provide the necessary reference for the aerodynamic shape optimization by modifying local geometric features of the cross-section to evaluate the influence of the aerodynamic shape on flutter performance.</p>
3
Kumar, Devesh, Rishabh Abhinav, and Naran Pindoriya. "An Ensemble Model for Short-Term Wind Power Forecasting using Deep Learning and Gradient Boosting Algorithms." In 2020 21st National Power Systems Conference (NPSC). IEEE, 2020. http://dx.doi.org/10.1109/npsc49263.2020.9331902.
Повний текст джерела