Effective Marketing Analysis on Gender and Age Classification with Hyperparameter Tuning

DNN learning jobs are common in today's clusters due to the advances in AI driven services such as machine translation and image recognition. The most critical phase of these jobs for model performance and learning cost is the tuning of hyperparameters. Existing approaches make use of techniques such as early stopping criteria to reduce the tuning impact on learning cost. However, these strategies do not consider the impact that certain hyperparameters and systems parameters have on training time. This paper presents PipeTune, a framework for DNN learning jobs that addresses the trade-offs between these two types of parameters. PipeTune takes advantage of the high parallelism and recurring characteristics of such jobs to minimize the learning cost via a pipelined simultaneous tuning of both hyper and system parameters. Our experimental evaluation using three different types of workloads indicates that PipeTune achieves up to 22.6% reduction and 1.7× speed up on tuning and training time, respectively. PipeTune not only improves performance but also lowers energy consumption up to 29%.

Mental health is an essential component of human life and maintaining a healthy state is often overlooked in today's world. While playing games online is a fantastic method to reduce stress, it imposes a negative impact on people's mental health. For instance, anxiety disorders are a group of mental illnesses marked by intense emotions of fear and anxiety which are witnessed in online gamers to a greater extent. To aid the identification process of anxiety levels, machine learning algorithms have emerged as a handy tool. In this paper, the anxiety levels of online gamers are detected by utilizing a dataset from Kaggle by nine machine learning algorithms. The performances of the ML models have been observed through Python simulation, and comprehensive comparative analysis has been shown for both hyperparameter tuning and without hyperparameter tuning. Random search cross-validation has been brought into action for tuning the hyper parameters. In terms of several performance measures such as accuracy, precision, recall, F1-Score, and ROC-AUC, satisfactory results have been observed. It is observed that Multilayer perceptron (MLP) outperformed the other classifiers with an accuracy of 99.96%. However, Support Vector Machine (SVM) depicted promising accuracy of 99.43% whereas Gradient Boosting (GB) and XGBoost (XGB) depicted 98.54% and 98.04% accuracy respectively. Therefore, it can be concluded that with proper implementation of the ML-based diagnosis system, it is possible to detect the anxiety level of online gamers which can assist in having a deeper understanding of behaviors and impact of online gaming in daily life.

In this study, we aimed to find an optimized approach to improving facial and masked facial recognition using machine learning and deep learning techniques. Prior studies only used a single machine learning model for classification and did not report optimal parameter values. In contrast, we utilized a grid search with hyperparameter tuning and nested cross-validation to achieve better results during the verification phase. We performed experiments on a large dataset of facial images with and without masks. Our findings showed that the SVM model with hyperparameter tuning had the highest accuracy compared to other models, achieving a recognition accuracy of 0.99912. The precision values for recognition without masks and with masks were 0.99925 and 0.98417, respectively. We tested our approach in real-life scenarios and found that it accurately identified masked individuals through facial recognition. Furthermore, our study stands out from others as it incorporates hyperparameter tuning and nested cross-validation during the verification phase to enhance the model's performance, generalization, and robustness while optimizing data utilization. Our optimized approach has potential implications for improving security systems in various domains, including public safety and healthcare.

In the telecommunications industry, predicting customer churn is crucial for maintaining business sustainability. High churn rates can negatively impact profitability, necessitating effective retention strategies. This research aims to enhance the accuracy of telecommunications customer churn prediction by optimizing the C4.5 classification algorithm through feature selection and hyperparameter tuning. The methods used include Information Gain for feature selection and hyperparameter tuning with Random Search and Grid Search. This study utilizes the Telco Customer Churn dataset from Kaggle, split into an 80:20 ratio for training and testing data. Six approaches are applied: (1) the basic C4.5 algorithm, (2) C4.5 with Information Gain, (3) C4.5 with Random Search, (4) C4.5 with Grid Search, (5) C4.5 with a combination of Information Gain and Random Search, and (6) C4.5 with a combination of Information Gain and Grid Search. The results indicate that the C4.5 algorithm alone achieves an accuracy of 74.09%, while applying Information Gain increases accuracy to 78.42%. Hyperparameter tuning with Random Search achieves the highest accuracy of 80.05%, whereas Grid Search reaches 77.71%. Combining Information Gain with Random Search results in an accuracy of 78.99%, while combining Information Gain with Grid Search yields an accuracy of 78.85%. These findings suggest that hyperparameter tuning using Random Search significantly improves accuracy compared to other methods, while Information Gain feature selection does not have a significant impact on performance in this context.

Analysis of load plays an important role in the operation of modern power systems due to its highly intermittent nature. This manuscript proposes the best approach by comparing results of Hold out, Cross and Re-Substitution validation from hyperparameter tuned Short Term Load Forecasting (STLF). Tree, Neural Network and GPR (Gaussian Process Regression) are three stochastic regression methods used. Each validation procedure is compared with every considered regression method, leading to 9 such combinations. Each combination is analysed with statistical parameters like RMSE (Root Mean Square Error), R Squared, MSE(Mean Square Error), MAE (Mean Absolute Error) and training time. The best approach is further optimised by modifying hyper parameters using Bayesian, Grid Search, and Random Search and most suitable method is proposed. The simulations are performed in Python and MATLAB platforms. The best combination for computation of STLF is K-fold validation with Tree Regression The statistical parameters obtained from the combination are RMSE, R Squared, MSE, MAE and training time of 0.077, 0.88, 0.0059, 0.046, 1.2 respectively. The best method for hyper-parameter tuning is found out to be Grid search with a reduced MSE of 0.0023.

Background: A grid search, at the cost of training and testing a large number of models, is an effective way to optimize the prediction performance of deep learning models. A challenging task concerning grid search is time management. Without a good time management scheme, a grid search can easily be set off as a "mission" that will not finish in our lifetime. In this study, we introduce a heuristic three-stage mechanism for managing the running time of low-budget grid searches with deep learning, sweet-spot grid search (SSGS) and randomized grid search (RGS) strategies for improving model prediction performance, in an application of predicting the 5-year, 10-year, and 15-year risk of breast cancer metastasis. Methods: We develop deep feedforward neural network (DFNN) models and optimize the prediction performance of these models through grid searches. We conduct eight cycles of grid searches in three stages, focusing on learning a reasonable range of values for each of the adjustable hyperparameters in Stage 1, learning the sweet-spot values of the set of hyperparameters and estimating the unit grid search time in Stage 2, and conducting multiple cycles of timed grid searches to refine model prediction performance with SSGS and RGS in Stage 3. We conduct various SHAP analyses to explain the prediction, including a unique type of SHAP analyses to interpret the contributions of the DFNN-model hyperparameters. Results: The grid searches we conducted improved the risk prediction of 5-year, 10-year, and 15-year breast cancer metastasis by 18.6%, 16.3%, and 17.3%, respectively, over the average performance of all corresponding models we trained using the RGS strategy. Conclusions: Grid search can greatly improve model prediction. Our result analyses not only demonstrate best model performance but also characterize grid searches from various aspects such as their capabilities of discovering decent models and the unit grid search time. The three-stage mechanism worked effectively. It not only made our low-budget grid searches feasible and manageable but also helped improve the model prediction performance of the DFNN models. Our SHAP analyses not only identified clinical risk factors important for the prediction of future risk of breast cancer metastasis, but also DFNN-model hyperparameters important to the prediction of performance scores.

This paper explores the effectiveness of machine learning and deep learning approaches in detecting deepfake images. With the increasing sophistication and prevalence of deepfake technology, it is becoming increasingly important to develop reliable methods for detecting manipulated images. The paper outlines the steps involved in creating a deepfake image detection model, including data preprocessing, dataset splitting, hyperparameter tuning, and the use of deep learning and machine learning techniques. Comprehensive review of the literature on deepfake detection, highlighting the challenges and limitations of existing approaches. They then propose a novel deep learning-based approach that leverages the power of convolutional neural networks (CNNs) to detect deepfake images. The proposed approach involves training a CNN on a large dataset of real and manipulated images, and using transfer learning to fine-tune the model on a smaller dataset of deepfake images. Here we try to evaluate the performance of their approach on a benchmark dataset of deepfake images, and compare it to several state-of-the-art deepfake detection methods. The results show that the proposed approach outperforms existing methods in terms of accuracy, precision, and recall. This paper provides valuable insights into the use of machine learning and deep learning approaches for deepfake image detection, and presents a promising new approach that could help to mitigate the risks of digital disinformation.

Hyperparameter tuning is crucial for optimising deep learning models. Traditional methods like grid search and random search can be time consuming and computationally expensive. This study explores space filling methodology for hyperparameter tuning, aiming to explore the hyperparameter space for optimal configurations. Hyperparameters are tuned for ResNet models using CIFAR-10 dataset and compared MaxPro space filling methodology with randomised search and grid search in terms of accuracy and computational costs. A greater accuracy was observed for the hyperparameters selected based on space filling methodology as compared to the randomised search while the runtime is similar for both. By systematically exploring the hyperparameter space, space filling offers an efficient approach to hyperparameter tuning, enabling faster model development. The findings underscore space filling methodology's potential for effective hyperparameter tuning, especially in resource constrained scenarios.

Due to the Covid-19 virus millions of people lost their lives and livelihood all the over the world, so quick and accurate diagnosis ofcovid-19 patients is the emergent need of today. Deep learning (DL) techniques, nowadays widely gained much popularity as compared to machine learning methods. Furthermore, DL is well-known in the field of image processing, whereas X-ray pictures are frequently used to diagnose Covid-19 patients. In this article, HyperCNN approach introduced through which higher accuracy can be achieved as compared to other traditional Convolutional Neural Network (CNN). Normally, the tuning of hyper parameters is done manually, which are both costly and time consuming in order to identify the optimum model with the highest accuracy. As per the experiment done, the traditional CNN model provides the accuracy 96.6% whereas the proposed model which is tuned using Bayesian optimization achieves accuracy 98.33%. Hence, it is observed that there is an improvement of 2% in the performance of the proposed model as compared to the traditional CNN model. With this experiment, we claim that automatic hyper parameter optimization is a powerful method for improving the accuracy in transfer learning.KeywordsHyper parameterOptimizationConvolutional neural networkDeep learningCovid-19 diagnosis

Objectives: To propose a new hybrid deep learning model to boost lung nodule detection and classification in combination with a bioinspired method for efficient hyper-parameter optimization to maximize true positive and nodule discrimination rates. Methods: In order to extract the intrinsic and complex features from different lung nodules, deep learning-based enhanced CNN (ECNN) is used. Segmentation masks are generated using Mask-RCNN to isolate and capture the ROIs, which serve as input to CNN. Prior to segmentation and extraction, data cleaning, transformation, and augmentation is done. Hyper-parameter optimization is done using a bio-inspired differential evolution method, which helps to identify the learning rate and number of layers to achieve optimal performance. We utilize BCE to quantify the performance of classification tasks. A large-scale CT-DICOM image dataset with 25,1135 images is used for this research work, collected from the cancer imaging archive, which has a clinically proven record of 355 instances with detailed image analysis, tumor location, and bounding boxes with a resolution of 512x512 pixels. 175794 images are used for training, and 75341 images are used for testing and validation. The performance of the new system is assessed using MATLAB, where results are compared with existing models such as SVM-WSS, GCPSO-PNN, and 3D-DLCNN models. Findings: The newly suggested ECNN with DE Bio-inspired model boosts the performance of lung nodule detection and classification with 94.7% accuracy, 93.8% sensitivity, 94.5% specificity, 93.4% F1 score, 92.4% dice coefficient, 0.1 Log Loss and AUC-ROC with 0.93 TPR and 0.07 FPR. Novelty: The novel method presents an advanced computational model using deep learning and bio-inspired algorithms for robust classification of lung nodules, which significantly improves the early diagnosis. This CAD model overcomes the limitations of the existing approaches SVM-WSS, GCPSO-PNN, and 3D-DLCNN in terms of segmentation, classification, error detection, and hyper-parameter tuning. Keywords: Lung Nodules, Deep Learning, Disease Classification, Image Processing, ECNN- DE Classifier, CT-DICOM Dataset

Recently, deep learning has been exploited in the field of medical image analysis. However, the training of deep learning models with medical images is time-consuming since most medical image data are three-dimensional volumes or high-resolution two-dimensional images. Moreover, the optimization of numerous hyperparameters strongly affects the performance of deep learning. If a framework for training deep learning with hyperparameter optimization on a supercomputer system can be realized, it is expected to accelerate the training of deep learning with medical images. In this study, we described our novel environment for training deep learning with medical images on the supercomputer system in our institute (Reedbush-H supercomputer system) based on asynchronous parallel Bayesian optimization. We trained two types of automated lesion detection application in a constructed environment. The constructed environment enabled us to train deep learning with hyperparameter tuning in a short time.

The classification of clinical notes into specific diagnostic categories is critical in healthcare, especially for mental health conditions like anxiety and adjustment disorder. In this study, we compare the performance of various artificial intelligence models, including both traditional machine learning approaches (random forest, support vector machine, K-nearest neighbors, decision tree, and eXtreme Gradient Boost) and deep learning models (DistilBERT and SciBERT), to classify clinical notes into these two diagnoses. Additionally, we implemented three oversampling strategies: No Oversampling, Random Oversampling, and Synthetic Minority Over-sampling Technique (SMOTE), to assess their impact on model performance. Hyperparameter tuning was also applied to optimize model accuracy. Our results indicate that oversampling techniques had minimal impact on model performance overall. The only exception was SMOTE, which showed a positive effect specifically with Bidirectional Encoder Representations from Transformers (BERT)-based models. However, hyperparameter optimization significantly improved accuracy across the models, enhancing their ability to generalize and perform on the dataset. The decision tree and eXtreme Gradient Boost models achieved the highest accuracy among machine learning approaches, both reaching 96%, while the DistilBERT and SciBERT models also attained 96% accuracy in the deep learning category. These findings underscore the importance of hyperparameter tuning in maximizing model performance. This study contributes to the ongoing research on AI-assisted diagnostic tools in mental health by providing insights into the efficacy of different model architectures and data balancing methods.

Optimizing hyperparameters is crucial for enhancing the performance of deep learning (DL) models. The process of configuring optimal hyperparameters, known as hyperparameter tuning, can be performed using various methods. Traditional approaches like grid search and random search have significant limitations. In contrast, Bayesian optimization (BO) utilizes a surrogate model and an acquisition function to intelligently navigate the hyperparameter space, aiming to provide deeper insights into performance disparities between naïve and advanced methods. This study evaluates BO's efficacy compared to baseline methods such as random search, manual search, and grid search across multiple DL architectures, including multi-layer perceptron (MLP), convolutional neural network (CNN), and LeNet, applied to the Modified National Institute of Standards and Technology (MNIST) and CIFAR-10 datasets. The findings indicate that BO, employing the tree-structured parzen estimator (TPE) search method and expected improvement (EI) acquisition function, surpasses alternative methods in intricate DL architectures such as LeNet and CNN. However, grid search shows superior performance in smaller DL architectures like MLP. This study also adopts a multi-objective (MO) perspective, balancing conflicting performance objectives such as accuracy, F1 score, and model size (parameter count). This MO assessment offers a comprehensive understanding of how these performance metrics interact and influence each other, leading to more informed hyperparameter tuning decisions.

This paper presents a comprehensive analysis and predictive modeling approach for rental prices in India. Utilizing a dataset of house rents from Kaggle, this study employs a range of machine learning algorithms to analyze and forecast rental prices. The methodology begins with establishing baselines using simple regression techniques. It then advances to more sophisticated models, including Gradient Boosting (GB) and Extreme GB (XGBoost), to enhance prediction accuracy. Hyperparameter tuning is conducted using the OPTUNA framework to identify the most effective algorithm. In cases of potential overfitting, the study shifts to ensemble methods, such as voting and bagging models, to improve robustness and generalizability. The paper aims to cover exploratory data analysis, data preprocessing, model training, and performance evaluation. By systematically comparing different algorithms and optimizing their parameters, this research provides a detailed framework for predicting rental prices with greater accuracy. The findings offer valuable insights for making informed decisions in real estate investments and rental management in India.

Coronary artery disease (CAD) is a category of cardiovascular disease that causes the highest mortality rate in the world. CAD occurs due to plaque build-up on the walls of the arteries that supply blood to the heart and other organs of the body. To control the mortality rate, a practical model that is capable of predicting CAD is needed. Machine learning approaches have been used in solving various problems in various domains, including biomedicine. However, real-world data often has an unbalanced class distribution that can interfere with classifier performance. In addition, data has many features to process. This study focuses on effective modeling capable of predicting CAD using feature selection to handle high dimensional data and feature resampling to handle unbalanced data. Feature selection is very effective by eliminating irrelevant features from the training data. Hyperparameter tuning is also done to find the best combination of parameters in support vector machines (SVM). Our results show that the SVM cross-validated ten times has a more accurate training result. Furthermore, the grid search on SVM cross-validated ten times had more accurate training model results and achieved 88% accuracy on the test data.