This paper focuses on millimeter wave (mmWave) channel prediction by machine learning (ML) methods. Previous ML-based mmWave channel predictors have limitations on requirements of the amount of training data, model ge...
详细信息
This paper focuses on millimeter wave (mmWave) channel prediction by machine learning (ML) methods. Previous ML-based mmWave channel predictors have limitations on requirements of the amount of training data, model generalization ability, robustness to noise, etc. In this paper, we propose a CNN model with a novel feature selection strategy for mmWave channel prediction. automatic hyperparameter tuning (AHT) algorithms are embedded in the training process to iteratively optimize the predictive performance of the proposed CNN. The diversification strategy is leveraged to enhance the robustness of the AHT procedure against different communication scenarios. To improve the generalization ability of the prediction model, the input features are designed to capture the correlation between the physical environment and the channel characteristics. In parallel, the Cartesian coordinates of the transmitter (Tx) and receiver (Rx) are transformed into polar ones to reduce the model's sensitivity to coordinate noise. Numerical results demonstrate the effectiveness of the proposed CNN model in predicting mmWave channel characteristics in various communication scenarios.
Given the high number of hyperparameters in deep learning models, there is a need to tune automatically deep learning models in specific research cases. Deep learning models require hyperparameters because they substa...
详细信息
ISBN:
(纸本)9781665481021
Given the high number of hyperparameters in deep learning models, there is a need to tune automatically deep learning models in specific research cases. Deep learning models require hyperparameters because they substantially influence the model's behavior. As a result, optimizing any given model with a hyperparameter optimization technique will improve model efficiency significantly. This paper discusses the hyperparameter-optimized Speech Emotion Recognition (SER) research case using Transformer-CNN deep learning model. Each speech samples are transformed into spectrogram data using the RAVDESS dataset, which contains 1,536 speech samples (192 samples per eight emotion classes). We use the Gaussian Noise augmentation technique to reduce the overfitting problem in training data. After augmentation, the RAVDESS dataset yields a total of 2,400 emotional speech samples (300 samples per eight emotion classes). For SER model, we combine the Transformer and CNN for temporal and spatial speech feature processing. However, our Transformer-CNN must be thoroughly tested, as different hyperparameter settings result in varying accuracy performance. We experiment with Naive Bayes to optimize many hyperparameters of Transformer-CNN (it could be categorical or numerical), such as learning rate, dropouts, activation function, weight initialization, epoch, even the best split data scale of training and testing. Consequently, our automatically tuned Transformer-CNN achieves 97.3% of accuracy.
Recently, more and more real life problems are solved using artificial intelligence (AI) algorithms. One of the biggest challenges when working with AI is the selection and tuning of the best algorithm for solving the...
详细信息
Recently, more and more real life problems are solved using artificial intelligence (AI) algorithms. One of the biggest challenges when working with AI is the selection and tuning of the best algorithm for solving the problem. The results generated by a given AI algorithm heavily depend on the way in which its hyperparameters are set. In most cases the process of algorithm selection and tuning is a manual, time consuming process in which the developer, based on experience and intuition tries to find the best solution from quality and execution time perspective. In this paper we present a method for solving the problem of AI algorithm selection and tuning, without human intervention, in a fully automated way. The method is a hybrid approach, a combination between particle swarm optimization and simulated annealing. We compare our approach with other similar tools like Auto-sklearn or Hyperopt-sklearn. We demonstrate the time efficiency and high accuracy of this method with some experiments on some known datasets. The paper also presents a platform for AI processing that include a set of procedures and services necessary in case of automatic processing of big datasets as well as the method for AI algorithm selection and tuning. This platform is useful for researchers and developers in an incipient phase of application development, when the best solution must be decided;it is also useful for specialists in different domains (physics, industry, economy) with less experience in using AI algorithms, but which has to process huge amount of data in an automated way.
In this paper,we introduce a novel Multi-scale and Auto-tuned Semi-supervised Deep Subspace Clustering(MAS-DSC)algorithm,aimed at addressing the challenges of deep subspace clustering in high-dimensional real-world da...
详细信息
In this paper,we introduce a novel Multi-scale and Auto-tuned Semi-supervised Deep Subspace Clustering(MAS-DSC)algorithm,aimed at addressing the challenges of deep subspace clustering in high-dimensional real-world data,particularly in the field of medical *** deep subspace clustering algorithms,which are mostly unsupervised,are limited in their ability to effectively utilize the inherent prior knowledge in medical *** MAS-DSC algorithm incorporates a semi-supervised learning framework that uses a small amount of labeled data to guide the clustering process,thereby enhancing the discriminative power of the feature ***,the multi-scale feature extraction mechanism is designed to adapt to the complexity of medical imaging data,resulting in more accurate clustering *** address the difficulty of hyperparameter selection in deep subspace clustering,this paper employs a Bayesian optimization algorithm for adaptive tuning of hyperparameters related to subspace clustering,prior knowledge constraints,and model loss *** experiments on standard clustering datasets,including ORL,Coil20,and Coil100,validate the effectiveness of the MAS-DSC *** results show that with its multi-scale network structure and Bayesian hyperparameter optimization,MAS-DSC achieves excellent clustering results on these ***,tests on a brain tumor dataset demonstrate the robustness of the algorithm and its ability to leverage prior knowledge for efficient feature extraction and enhanced clustering performance within a semi-supervised learning framework.
Cement-based grouting material, distinguished by excellent fluidity and high strength, is widely used in the field of construction reinforcement, and anchoring of restraints. Owing to the high-performance requirements...
详细信息
Cement-based grouting material, distinguished by excellent fluidity and high strength, is widely used in the field of construction reinforcement, and anchoring of restraints. Owing to the high-performance requirements and complicated influencing factors of grouting material, the design of the mixing proportion has been challenging. This study proposes a machine learning (ML) based algorithmic framework integrating prediction, interpretation, and automatic hyperparameter tuning to identify the complex potential relationships between the mixing pro-portion parameters on the compressive strength and fluidity of cement-based grouting materials. The 442 compressive strength data and 217 fluidity data derived from both published literatures and laboratory exper-iments were collected to build a dataset for demonstrating the predictive performance of the ML models. The results indicated that the hyperparametertuning technique via Bayesian Optimisation (BO) can significantly improve the time efficiency compared to grid search, reducing time consumption from 8000 s to 197 s with comparable accuracy. The optimal prediction results were obtained based on the XGBoost model with R2 = 0.93, RMSE = 7.37 for compressive strength, and R2 = 0.92, RMSE = 16.33 for fluidity. The SHapley Additive exPlainations (SHAP) is introduced to interpret the evaluation results and the influence of the various mix factors on grouting material from both global(model) and local(instance) perspectives. The suggested model can be seen as a function of influential input variables that help engineers conduct a rapid assessment and then in turn to optimize the design of the mixture proportion.
暂无评论