Improved K-nearest Neighbor Algorithm Research Articles

An efficient dynamic migration and consolidation method of VMs based on improved K-nearest neighbor algorithm and attribute weighting

Virtual machine (VM) consolidation and migration that only consider current workload can result in excessive unnecessary migrations. To address this issue, a VM consolidation algorithm based on resource utilization prediction is proposed. An improved K-nearest neighbor (KNN) classification algorithm weighted by attribute inconsistency is proposed to predict the workload of both the host and the VMs. Firstly, two distributions are partitioned according to the neighboring relationship for comparing consistency. Then, an inconsistency evaluation function based on earth mover’s distance (EMD) is designed to measure the inconsistency between the neighboring sample set of each sample under each attribute and the equivalent partition refined by the decision attribute. Finally, the inconsistency level of the neighboring samples is transformed into the importance of the corresponding attribute to implement the attribute weighting KNN classifier. When selecting the source host and target host for VM migration, both current and predicted overloads are considered to avoid unnecessary VM migrations. Simulation tests were performed with random and realistic workloads, and the results show that the proposed method can reduce the overall energy consumption of the host, while also reducing service level agreement (SLA) violations and VM migration.

An Improved k-Nearest Neighbor Algorithm for Recognition and Classification of Thyroid Nodules.

To complete the task of automatic recognition and classification of thyroid nodules and solve the problem of high classification error rates when the samples are imbalanced. An improved k-nearest neighbor (KNN) algorithm is proposed and a method for automatic thyroid nodule classification based on the improved KNN algorithm is established. In the improved KNN algorithm, we consider not only the number of class labels for various classes of data in KNNs, but also the corresponding weights. And we use the Minkowski distance measure instead of the Euclidean distance measure. A total of 508 ultrasound images of thyroid nodules, including 415 benign nodules and 93 malignant nodules, were used in the paper. Experimental results show the improved KNN has 0.872549 accuracy, 0.867347 precision, 1 recall, and 0.928962 F1-score. At the same time, we also considered the influence of different distance weights, the value of k, different distance measures on the classification results. A comparison result shows that our method has a better performance than the traditional KNN and other classical machine learning methods.

A bitcoin service community classification method based on Random Forest and improved KNN algorithm

AbstractThere are service communities with different functions in the Bitcoin transactions system. Identifying community categories helps to further understand the Bitcoin transactions system and facilitates targeted regulation of anonymized Bitcoin transactions. To this end, a Bitcoin service community classification method based on Random Forest and improved K‐Nearest Neighbor (KNN) algorithm is proposed. First, the transaction characteristics of different types of communities are analyzed and summarized, and the corresponding transaction features are extracted from the address and entity levels; then multiple classification algorithms are compared, the optimal model to filter the effective features is selected, and the feature vector of entity addresses is constructed. Finally, a classification model is constructed based on Random Forest and improved KNN algorithm to classify the entities. By constructing different classification models for experimental comparison, the accuracy and stability advantages of the proposed method for classification in service community classification research are verified.

Spatial correlation-based machine learning framework for evaluating shale gas production potential: A case study in southern Sichuan Basin, China

Assessment of production potential and prediction of sweet spots in unexploited shale gas wells are crucial technologies for achieving a high success rate in drilling. Most existing methods are only applicable for yield forecasting of shale gas wells with known geological and drilling/completion factors after production. In addition, the shale gas reservoir in the Longmaxi Formation in the southern Sichuan Basin of China is characterized by low porosity, low permeability, and diverse gas reservoir states. Thus, forecasting production from unexploited wells and predicting the exact location of the sweet spot under complex geological conditions have become challenging topic for both academia and industry. According to the first law of geography, shale gas wells that are closer in space have more similar geologic features. Based on this foundation, a machine-learning prediction model based on spatial correlation (SC-MLPM) is proposed for evaluating potential production of shale gas wells in the Changning play located in Longmaxi Formation in the southern Sichuan basin, China. Specifically, an improved K-nearest neighbor algorithm (SC-KNN) based on the spatial correlation characteristics of the exploited wells is designed to estimate the relevant geological factors of the unexploited wells in the same area. In addition, an extreme gradient lifting model based on Huber loss function (Hu-XGB) is developed to predict the potential production of unexploited shale gas wells, and then the shale gas sweet spot area in the research area is predicted quickly and accurately. The experimental results on 88 shale gas wells from Changning play show that the mean relative error of the prediction results of the proposed method is 9.8%. Furthermore, the results also determine that the sweet spots of shale gas wells in the research area are mainly developed in the northwest and northeast directions, and gradually become worse in the southeast direction. Eventually, experimental results for the Fox Creek play in Canada show that the proposed model obtains better predictive performance as the number of gas wells increases, and also verifies the generalizability. This work provides a basis for the efficient development of the research area.

A Novel Query Method for Spatial Database Based on Improved K-Nearest Neighbor Algorithm

Spatial database is a spatial information database and is the core component of geographic information systems (GIS). Aiming at the problem that time complexity of k-nearest neighbor (kNN) querying algorithms are proportionate to scale of training samples, an efficient query method for spatial database based on the Spark framework and the reversed k-nearest neighbor (RkNN) is proposed. Firstly, based on the Spark framework, a two-layer indexing structure based on grid and Voronoi diagram is constructed, and an efficient filtering and a refining processing algorithm are proposed. Secondly, the filtering step of proposed algorithm is used to obtain the candidates, and the refining step is used to remove the candidates. Finally, the candidate sets from different regions are merged to get the final result. Results of experiments on real-world datasets validate that the proposed method has better query performance and better stability and significantly improves the processing speed.

Multi-wavelength HPLC fingerprint similarity metric for cold-hot nature identification of Chinese herbal medicines

Cold-hot nature theory is the core basic theory of the nature of Chinese herbal medicines (CHMs). It is found that the material basis of cold-hot nature is CHM ingredients. In view of this, our group proposed a scientific hypothesis that “CHMs with similar nature should have similar materialbasis”. To demonstrate this hypothesis, we developed a novel multi-wavelength high performance liquid chromatography (HPLC) fingerprint similarity metric scheme for cold-hot nature identification. We explored a multi-wavelength distance metric learning model to compute the similarity of CHM ingredients, and developed an improved k-nearest neighbor algorithm based on multi-wavelength HPLC fusion (KMHF) to predict cold-hot nature of CHMs. Firstly, multi-wavelength HPLC fingerprints were used to extract the characteristic information of CHM ingredients. Secondly, we defined the similarity of CHM ingredients as semantic relevance and fingerprint similarity. We studied a multi-wavelength distance metric to measure the similarity of CHM ingredients. The learned distance metric could discover complementary characteristics of different wavelength HPLC through an optimization algorithm. Finally, an improved multi-wavelength k-nearest neighbor algorithm KMHF was proposed to analyze the relationship between cold-hot nature and CHM ingredients. Numerous experiments were designed to test the feasibility of the proposed KMHF algorithm. Experimental results indicate that the performance of our KMHF algorithm outperforms that of the compared algorithms. Experimental results demonstrate that the hypothesis that CHMs with similar cold-hot nature have similar material basis. The KMHF model is evaluated to be feasible for nature identification.

Process parameters design of squeeze casting through an improved KNN algorithm and existing data

Process parameters are key to the production and cast quality of squeeze casting, and conventional methods to obtain the process parameters are based on experiments, which is costly and time-consuming. Based on big data, this paper proposes a data-driven method of designing squeeze-casting process parameters. Based on the potential impact features and differences in the process influential factors on squeeze-casting process parameters, an E-TKNN algorithm was developed by improving the k-nearest neighbor (KNN) algorithm for data clustering to obtain the process parameters of a new squeeze cast based on the similarity principle and existing data. To promote similarity accuracy, the impact difference of the process influential factors is first weighted by assembling the data of the process parameter and the factors using a matrix and calculating the entropy of their data matrix; second, a change trend measurement method is developed to consider the impacts of trace elements. Furthermore, an application framework (SR-E-TKNN) to design the process parameter of squeeze-casting through E-TKNN is established, in which a support vector machine–recursive feature elimination (SVM-RFE) algorithm is introduced to remove the redundant factors to optimize the data input of E-TKNN. Two experiments were conducted to verify the feasibility and superiority of the proposed method. The results demonstrated that the designed process parameter can aid in achieving practical production quality. Compared with the traditional design method, the accuracy of the design method based on E-TKNN outperforms conventional data modeling methods such as linear regression. This method utilizes the existing relevant squeeze-casting process data, eliminates the tedious research process, and provides a new concept for the design of other process parameters.

A Healthcare Quality Assessment Model Based on Outlier Detection Algorithm

With the extremely rapid growth of data in various industries, big data is gradually recognized and valued by people. Medical big data, which can best reflect the significance of big data value, has also received attention from various parties. In Saudi Arabia, healthcare quality assessment is mostly based on human experience and basic statistical methods. In this paper, we proposed a healthcare quality assessment model based on medical big data in a region of Saudi Arabia, which integrated traditional evaluation methods and machine learning based techniques. Healthcare data has been accurate and effective after noise processing, and the outliers could reflect certain medical quality information. An improved k-nearest neighbors (KNN) algorithm has been proposed and its time complexity have been reduced to be more suitable for big data processing. An outlier indicator has been established based on statistical methods and the improved KNN algorithm. Experimental results showed that the proposed approach has good potential for detecting hospitals with financial fraud and poor-quality medical care.

Hotspot Prediction Of e-Commerce Network Users Based On Improved K-Nearest Neighbor Algorithm

Hotspot Prediction Of e-Commerce Network Users Based On Improved K-Nearest Neighbor Algorithm

An Improved K-Nearest Neighbor Algorithm for Pattern Classification

This paper proposed a “Locally Adaptive K-Nearest Neighbor (LAKNN) algorithm” for pattern exploration problem to enhance the obscenity of dimensionality. To compute neighborhood local linear discriminant analysis is an effective metric which determines the local decision boundaries from centroid information. KNN is a novel approach which uses in many classifications problem of data mining and machine learning. KNN uses class conditional probabilities for unfamiliar pattern. For limited training data in high dimensional feature space this hypothesis is unacceptable due to disfigurement of high dimensionality. To normalize the feature value of dissimilar metrics, Standard Euclidean Distance is used in KNN which s misguide to find a proper subset of nearest points of the pattern to be predicted. To overcome the effect of high dimensionality LANN uses a new variant of Standard Euclidian Distance Metric. A flexible metric is estimated for computing neighborhoods based on Chi-squared distance analysis. Chi-squared metric is used to ascertains most significant features in finding k-closet points of the training patterns. This paper also shows that LANN outperformed other four different models of KNN and other machine-learning algorithm in both training and accuracy.

Improved KNN Algorithm for Fine-Grained Classification of Encrypted Network Flow

The fine-grained classification of encrypted traffic is important for network security analysis. Malicious attacks are usually encrypted and simulated as normal application or content traffic. Supervised machine learning methods are widely used for traffic classification and show good performances. However, they need a large amount of labeled data to train a model, while labeled data is hard to obtain. Aiming at solving this problem, this paper proposes a method to train a model based on the K-nearest neighbor (KNN) algorithm, which only needs a small amount of data. Due to the fact that the importance of different traffic features varies, and traditional KNN does not highlight the importance of different features, this study introduces the concept of feature weight and proposes the weighted feature KNN (WKNN) algorithm. Furthermore, to obtain the optimal feature set and the corresponding feature weight set, a feature selection and feature weight self-adaptive algorithm for WKNN is proposed. In addition, a three-layer classification framework for encrypted network flows is established. Based on the improved KNN and the framework, this study finally presents a method for fine-grained classification of encrypted network flows, which can identify the encryption status, application type and content type of encrypted network flows with high accuracies of 99.3%, 92.4%, and 97.0%, respectively.

Medical Health Big Data Classification Based on KNN Classification Algorithm

The rapid development of information technology has led to the development of medical informatization in the direction of intelligence. Medical health big data provides a basic data resource guarantee for medical service intelligence and smart healthcare. The classification of medical health big data is of great significance for the intelligentization of medical information. Due to the simplicity of KNN (K-Nearest Neighbor) classification algorithm, it has been widely used in many fields. However, when the sample size is large and the feature attributes are large, the efficiency of the KNN algorithm classification will be greatly reduced. This paper proposes an improved KNN algorithm and compares it with the traditional KNN algorithm. The classification is performed in the query instance neighborhood of the conventional KNN classifier, and weights are assigned to each class. The algorithm considers the class distribution around the query instance to ensure that the assigned weight does not adversely affect the outliers. Aiming at the shortcomings of traditional KNN algorithm in processing large data sets, this paper proposes an improved KNN algorithm based on cluster denoising and density cropping. The algorithm performs denoising processing by clustering, and improves the classification efficiency of KNN algorithm by speeding up the search speed of K-nearest neighbors, while maintaining the classification accuracy of KNN algorithm. The experimental results show that the proposed algorithm can effectively improve the classification efficiency of KNN algorithm in processing large data sets, and maintain the classification accuracy of KNN algorithm well, and has good classification performance.

Combination of DNN and Improved KNN for Indoor Location Fingerprinting

Fingerprinting based on Wi-Fi Received Signal Strength Indicator (RSSI) has been widely studied in recent years for indoor localization. While current algorithms related to RSSI Fingerprinting show a much lower accuracy than multilateration based on time of arrival or the angle of arrival techniques, they highly depend on the number of access points (APs) and fingerprinting training phase. In this paper, we present an integrated method by combining the deep neural network (DNN) with improved K-Nearest Neighbor (KNN) algorithm for indoor location fingerprinting. The improved KNN is realized by boosting the weights on K-nearest neighbors according to the number of matching access points. This will overcome the limitation of the original KNN algorithm on ignoring the influence of the neighboring points, which directly affect localization accuracy. The DNN algorithm is first used to classify the Wi-Fi RSSI Fingerprinting dataset. Then these possible locations in a certain class are also classified by the improved KNN algorithm to determine the final position. The proposed method is validated inside a room within about 13⁎9 m2. To examine its performance, the presented method has been compared with some classical algorithms, i.e., the random forest (RF) based algorithm, the KNN based algorithm, the support vector machine (SVM) based algorithm, the decision tree (DT) based algorithm, etc. Our real-world experiment results indicate that the proposed method is less dependent on the dense of access points and indoor radio propagation interference. Furthermore, our method can provide some preliminary guidelines for the design of indoor Wi-Fi test bed.

Classification Method of Teaching Resources Based on Improved KNN Algorithm

In order to effectively utilize the network teaching resources, a teaching resource classification method based on the improved KNN (K-Nearest Neighbor) algorithm was proposed. Taking the text class primary and secondary school teaching resources as the research object, combined with the domain characteristics, the KNN algorithm was improved. By measuring the sample space density, the text of the high-density area was found. Different clipping methods were proposed for both intra-class and inter-class regions. The problem of cropping in the space of multiple class boundaries was considered. Results showed that the method ensured uniform distribution of samples and reduced the time of classification. Therefore, under the Weka platform, the improved KNN algorithm is effective.

Analysis of Factors Influencing Rockfall Runout Distance and Prediction Model Based on an Improved KNN Algorithm

The prediction method plays crucial roles in the accurate prediction of rockfall runout range which could improve the protection of endangered residential areas and infrastructure. Recently, the Knearest neighbor (KNN) algorithm, one of many machine learning techniques, showed good performance in pattern classification. Therefore, the aim of this study was to use the K-nearest neighbor (KNN) algorithm to predict the rockfall runout range which is classified into different subintervals according to the distance from the slope toe. First, we proposed the prediction model of the rockfall runout range based on our improved KNN algorithm which could better offer robustness against different choices of the neighborhood size k, and it is the first work of applying our improved KNN algorithm to rockfall runout range prediction. Second, the shaking table tests of rockfall runout models were conducted for simulating the rockfall process, and the influence laws of factors-including types of an earthquake, peak ground acceleration, vibration frequency, slope angle, slope height, and block mass and block shape-on rockfall distance are investigated. Finally, there is a discussion of the performance of our proposed prediction model based on our improved KNN algorithm in the prediction of rockfall runout range. The extensive experimental results for rockfall runout range prediction demonstrate the effectiveness of our proposed prediction model.

An Improved k-nearest Neighbor Algorithm using Tree Structure and Pruning Technology

An Improved k-nearest Neighbor Algorithm using Tree Structure and Pruning Technology

A novel approach for precipitation forecast via improved K-nearest neighbor algorithm

The prediction method plays crucial roles in accurate precipitation forecasts. Recently, machine learning has been widely used for forecasting precipitation, and the K-nearest neighbor (KNN) algorithm, one of machine learning techniques, showed good performance. In this paper, we propose an improved KNN algorithm, which offers robustness against different choices of the neighborhood size k, particularly in the case of the irregular class distribution of the precipitation dataset. Then, based our improved KNN algorithm, a new precipitation forecast approach is put forward. Extensive experimental results demonstrate that the effectiveness of our proposed precipitation forecast approach based on improved KNN algorithm.

Solving vehicle routing problem by using improved K-nearest neighbor algorithm for best solution

ContextVehicle routing problem (VRP) is one of the many difficult issues that have no perfect solutions yet. Many researchers over the last few decades have established numerous researches and used many methods with different techniques to handle it. But, for all research, finding the lowest cost is very complex. However, they have managed to come up with approximate solutions that differ in efficiencies depending on the search space. ProblemIn this study the problem is as follows: have a number of vehicles which are used for transporting applications to instance place. Each vehicle starts from a main location at different times every day. The vehicle picks up applications from start locations to the instance place in many different routes and return back to the start location in at specific times every day, starting from early morning until the end of official working hours, on the following conditions: (1) Every location will be visited once in each route, and (2) The capacity of each vehicle is enough for all applications included in each route. ObjectivesOur paper attempt to find an optimal route result for VRP by using K-Nearest Neighbor Algorithm (KNNA). To achieve an optimal solution for VRP with the accompanying targets: (1) To reduce the distance and the time for all paths this leads to speedy the transportation of customers to their locations, (2) To implement the capacitated vehicle routing problem (CVRP) model for optimizing the solutions. ApproachThe approach has been presented based on two phases: firstly, the algorithms have been adapted to solve the research problem, where its procedure is different than the common algorithm. The structure of the algorithm is designed so that the program does not require a large database to store the population, which speeds up the implementation of the program execution to obtain the solution; secondly, the algorithm has proven its success in solving the problem and finds a shortest route. For the purpose of testing the algorithm’s capability and reliability, it was applied to solve the same problem online validated and it achieved success in finding a shorter route. FindingThe findings outcome from this study have shown that: (1) A universal listed of dynamic KNNACVRP; (2) Identified and built up an assessment measure for KNNACVRP; (3) Highlight the strategies, based KNNA operations, for choosing the most ideal way (4) KNNA finds a shorter route for VRP paths. The extent of lessening the distance for each route is generally short, but the savings in the distance becomes more noteworthy while figuring the aggregate distances traveled by all transports day by day or month to month. This applies likewise to the time calculate that has been decreased marginally in view of the rate of reduction in the distances of the paths.

Human performance modeling for manufacturing based on an improved KNN algorithm

Human performance is a key factor in a manufacturing system. Behavior modeling is a very important but difficult problem when describing human activities. Performance modeling based on data mining is an effective way to help managers predict personnel’s capabilities and to recruit appropriate new staff with relevant skills, which can be significant to ensure an enterprise’s competitiveness. The K-nearest neighbor (KNN) algorithm is the most common classification algorithm in cases of no prior knowledge of data distribution. In the paper, an improved KNN algorithm was proposed to cope with the human performance prediction problem with the improvements in three aspects, which are the neighboring distance calculation based on entropy, the classification determination strategy, and the quantitative description method of human performance. The improved KNN algorithm was proved to have better classification ability in comparison with other seven typical KNN algorithms and five classic classification algorithms using data sets from the University of California, Irvine (UCI) machine learning repository. The improved KNN algorithm was further tested with a real-world case of performance prediction, and the effectiveness of the algorithm was confirmed.

Predicting Trust Relationships in Social Networks Based on WKNN

Trust relationships between user pairs play a vital role in making decisions for social network users. In reality, available explicit trust relations are often extremely sparse, therefore, inferring unknown trust relations attracts increasing attention in recent years. In this paper, a new approach originating from machine learning is proposed to predict trust relationships in social networks by exploring an improved k-nearest neighbor algorithm based on distance weight (WKNN). Firstly, we extract three critical attributes from users' personal profiles and interactive information; then, an improved KNN algorithm named WKNN is proposed; finally, comparative analysis between them is performed by using real-world dataset from Epinions to evaluate their performance in trust prediction. Empirical evaluation demonstrates that the proposed framework (WKNN model) is feasible and effective in predicting trust relationships.