Refine
Has Fulltext
- yes (23) (remove)
Document Type
- Article (23) (remove)
Institute
Keywords
- Maschinelles Lernen (14)
- Machine learning (11)
- OA-Publikationsfonds2020 (8)
- Deep learning (5)
- OA-Publikationsfonds2018 (4)
- big data (4)
- machine learning (4)
- Biodiesel (2)
- Internet of things (2)
- OA-Publikationsfonds2019 (2)
- artificial intelligence (2)
- artificial neural networks (2)
- data science (2)
- extreme learning machine (2)
- mathematical modeling (2)
- random forest (2)
- wireless sensor networks (2)
- ANN modeling (1)
- Algorithmus (1)
- Artificial Intelligence (1)
- Bildanalyse (1)
- Bodentemperatur (1)
- Bubble column reactor (1)
- ContikiMAC (1)
- ELM (1)
- Energieeffizienz (1)
- Erneuerbare Energien (1)
- Fotovoltaik (1)
- Funktechnik (1)
- Gaussian process regression (1)
- Gebäude (1)
- Geometrie (1)
- Größenverhältnis (1)
- Hydrological drought (1)
- IOT (1)
- Infrastructures (1)
- Internet der Dinge (1)
- Internet der dinge (1)
- Internet of Things (1)
- K-nearest neighbors (1)
- KNN (1)
- Körper (1)
- Künstliche Intelligenz (1)
- M5 model tree (1)
- Mensch (1)
- Neuronales Netz (1)
- Optimierung (1)
- RSSI (1)
- Renewable energy (1)
- Risikomanagement (1)
- Sensor (1)
- Solar (1)
- Sustainability (1)
- Sustainable production (1)
- Vernetzung (1)
- action recognition (1)
- adaptive neuro-fuzzy inference system (ANFIS) (1)
- ant colony optimization algorithm (ACO) (1)
- back-pressure (1)
- biodiesel (1)
- classification (1)
- classifier (1)
- clear channel assessments (1)
- cluster density (1)
- cluster shape (1)
- clustering (1)
- computation (1)
- computational fluid dynamics (CFD) (1)
- congestion control (1)
- coronary artery disease (1)
- demand response programs (1)
- diesel engines (1)
- dimensionality reduction (1)
- duty-cycles (1)
- energy efficiency (1)
- energy, exergy (1)
- ensemble model (1)
- estimation (1)
- extreme pressure (1)
- firefly optimization algorithm (1)
- flow pattern (1)
- fog computing (1)
- food informatics (1)
- forward contracts (1)
- fuzzy decision making (1)
- growth mode (1)
- health informatics (1)
- heart disease diagnosis (1)
- human blob (1)
- human body proportions (1)
- hybrid machine learning (1)
- hybrid machine learning model (1)
- hydraulic jump (1)
- hydrology (1)
- image processing (1)
- industry 4.0 (1)
- least square support vector machine (LSSVM) (1)
- longitudinal dispersion coefficient (1)
- neural networks (NNs) (1)
- photovoltaic-thermal (PV/T) (1)
- precipitation (1)
- prediction (1)
- predictive model (1)
- principal component analysis (1)
- received signal strength indicator (1)
- reinforcement learning (1)
- response surface methodology (1)
- retailer (1)
- rice (1)
- risk management (1)
- rivers (1)
- rule based classification (1)
- seasonal precipitation (1)
- signal processing (1)
- smart sensors (1)
- soil temperature (1)
- spatial analysis (1)
- spatiotemporal database (1)
- spearman correlation coefficient (1)
- standard deviation of pressure fluctuations (1)
- statistical coeffcient of the probability distribution (1)
- stilling basin (1)
- stochastic programming (1)
- sugarcane (1)
- support vector machine (1)
- support vector regression (1)
- water quality (1)
- wavelet transform (1)
- wireless sensor network (1)
The K-nearest neighbors (KNN) machine learning algorithm is a well-known non-parametric classification method. However, like other traditional data mining methods, applying it on big data comes with computational challenges. Indeed, KNN determines the class of a new sample based on the class of its nearest neighbors; however, identifying the neighbors in a large amount of data imposes a large computational cost so that it is no longer applicable by a single computing machine. One of the proposed techniques to make classification methods applicable on large datasets is pruning. LC-KNN is an improved KNN method which first clusters the data into some smaller partitions using the K-means clustering method; and then applies the KNN for each new sample on the partition which its center is the nearest one. However, because the clusters have different shapes and densities, selection of the appropriate cluster is a challenge. In this paper, an approach has been proposed to improve the pruning phase of the LC-KNN method by taking into account these factors. The proposed approach helps to choose a more appropriate cluster of data for looking for the neighbors, thus, increasing the classification accuracy. The performance of the proposed approach is evaluated on different real datasets. The experimental results show the effectiveness of the proposed approach and its higher classification accuracy and lower time cost in comparison to other recent relevant methods.