首页|National Institute of Technology Karnataka Researchers Advance Knowledge in Mach ine Learning (Hybrid Bio-Optimized Algorithms for Hyperparameter Tuning in Machi ne Learning Models: A Software Defect Prediction Case Study)
National Institute of Technology Karnataka Researchers Advance Knowledge in Mach ine Learning (Hybrid Bio-Optimized Algorithms for Hyperparameter Tuning in Machi ne Learning Models: A Software Defect Prediction Case Study)
扫码查看
点击上方二维码区域,可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-New research on artificial intelligence is the su bject of a new report. According to news reporting out of Mangalore, India, by N ewsRx editors, research stated, "Addressing real-time optimization problems beco mes increasingly challenging as their complexity continues to escalate over time . So bio-optimization algorithms (BoAs) come into the picture to solve such prob lems due to their global search capability, adaptability, versatility, paralleli sm, and robustness." Our news editors obtained a quote from the research from National Institute of T echnology Karnataka: "This article aims to perform hyperparameter tuning of mach ine learning (ML) models by integrating them with BoAs. Aiming to maximize the a ccuracy of the hybrid bio-optimized defect prediction (HBoDP) model, this resear ch paper develops four novel hybrid BoAs named the gravitational force Levy flig ht grasshopper optimization algorithm (GFLFGOA), the gravitational force Levy fl ight grasshopper optimization algorithm-sparrow search algorithm (GFLFGOA-SSA), the gravitational force grasshopper optimization algorithm-sparrow search algori thm (GFGOA-SSA), and the Levy flight grasshopper optimization algorithm-sparrow search algorithm (LFGOA-SSA). These aforementioned algorithms are proposed by in tegrating the good exploration capacity of the SSA with the faster convergence o f the LFGOA and GFGOA. The performances of the GFLFGOA, GFLFGOA-SSA, GFGOA-SSA, and LFGOA-SSA are verified by conducting two different experiments. Firstly, the experimentation was conducted on nine benchmark functions (BFs) to assess the m ean, standard deviation (SD), and convergence rate. The second experiment focuse s on boosting the accuracy of the HBoDP model through the fine-tuning of the hyp erparameters in the artificial neural network (ANN) and XGBOOST (XGB) models. To justify the effectiveness and performance of these hybrid novel algorithms, we compared them with four base algorithms, namely the grasshopper optimization alg orithm (GOA), the sparrow search algorithm (SSA), the gravitational force grassh opper optimization algorithm (GFGOA), and the Levy flight grasshopper optimizati on algorithm (LFGOA)."
National Institute of Technology Karnata kaMangaloreIndiaAsiaAlgorithmsCyborgsEmerging TechnologiesGravitat ional ForcesMachine LearningPhysicsSearch AlgorithmsSoftware