Exploring Federated Unlearning: Review, Comparison, and Insights

Do shareholders really matter for firm performance? Evidence from the ownership characteristics of Italian listed companies

Optimising predictive accuracy in sheet metal stamping with advanced machine learning: A LightGBM and neural network ensemble approach

As the world begins to move more and more towards Electric Vehicles (EVs), the imperative for innovative solutions to streamline energy management within charging infrastructure intensifies. This study delves into the realm of machine learning integration, focusing particularly on Random Forest (RF) techniques to revolutionize energy optimization in EV charging systems. While Gradient Boosting Machine (GBM) initially garners attention for its adeptness with intricate datasets, RF emerges as a potent complementary approach uniquely suited to handle the complexities of nonlinear relationships. By synergizing the strengths of RF and GBM algorithms, this research endeavors to dynamically refine charging schedules, curtail costs, and fortify grid stability. Through a fusion of historical data and real-time environmental factors, the envisioned "Adaptive Ensemble Learning Framework" (AELF)-driven smart charging infrastructure is primed to recalibrate charging strategies in response to energy demand fluctuations while judiciously balancing user preferences and grid constraints. Rigorous simulations and case studies serve as the litmus test, pitting the efficacy of the AELF approach against the conventional Decision Trees Model and Support Vector Machines Technique. The results tout enhancements of up to 15% across diverse performance metrics, underscoring its prowess in charting the course towards a sustainable and intelligent transportation ecosystem.

Generally, leukemia is one of the blood cancers that can lead to death. A huge amount of immature WBCs in the bone marrow affect the healthy cells and this has become the leading cause of leukemia disease. Moreover, “Acute Lymphoblastic Leukemia (ALL)” is a type of blood cancer that is generally categorized with a huge amount of immature lymphocytes that are given as blast cells. But, the analysis of this model is dependent, boring as well as time-consuming based on the skills of hematologists. So, there is a requirement for the most desirable techniques to tackle these restrictions. Additionally, the accurate and automated diagnosis of ALL is a crucial task. In this case, an automated detection model of ALL using ensemble segmentation and a heuristic-assisted layer-improved hybrid deep learning approach is implemented. In the initial stage, the raw images are collected from benchmark datasets. Further, the image pre-processing is undergone by contrast enhancement and filtering process. After pre-processing, the image segmentation is carried out by ensemble segmentation, which is acquired by the region growing, K-medoids, and Fuzzy C-Means (FCM). From the segmented images, based on the mutual information, the pixel is selected optimally, in which the optimal pixel is identified by Opposition-based Rain Optimization Algorithm (OROA). Subsequently, the optimal pixels are fed as input to the Layer Improved Hybrid DenseNet and ResNet (LIH-DRNet) model that is constructed with DenseNet and ResNet, where some hyperparameters are tuned optimally by the improved ROA. At last, the performance is evaluated with diverse performance metrics. Thus, the findings reveal that the developed hybrid deep learning method achieves a higher detection rate to ensure the effectiveness of the model.

This study evaluates the impact of physical literacy on basketball athletes' performance and injury prevention methods. A thorough evaluation was carried out on a group of basketball athletes to examine their physical literacy, encompassing several aspects such as behavior, positive impact, motivation, and motor skills. The research additionally examined the correlation between physical literacy and diverse performance metrics, encompassing skills, agility, endurance, and strength. Furthermore, it explored the connection between physical literacy and injury prevention strategies, encompassing strength and conditioning, warm-up and cool-down regimens, rest and recovery, and sports psychology methodologies. The study's findings revealed a statistically significant association between physical literacy and performance and injury prevention techniques. This underscores the need to incorporate physical literacy principles into basketball training regimens. The results emphasize the necessity of customized interventions and educational programs designed to improve physical literacy in basketball players to maximize performance and reduce the risk of injuries. This research study provides significant contributions to the understanding of the impact of physical literacy on basketball, hence informing future investigations and practical applications in the realms of athlete development and injury prevention within the sport.

Mental disorder is an illness that are more common in technical employees and are increasing among working professionals. It is an important and challenging issue in the world as the stress among the technical employees are high due to work culture. Mental health in the healthcare is necessary to recognize individual’s situation and continue to predict diverse situations accurately. Therefore, this study proposes the mental health disorder prediction using various feature selection algorithms for a specific dataset called Tech survey Datasets. We applied multiple machine learning classification algorithms on the best features of RFE, RFECV and LASSO to obtain the performance metrics of the model and to decide the best accuracy, precision and recall of the respective models. There are 61 features in the Tech survey Dataset consisting of the data in the technical workplace worldwide that provides mental health attribute and frequency. The results are discussed and an aggregated table is developed using the performance metrics to understand the percentage of technical employees undergoes mental disorder. The proposed research evaluates various classification algorithms along with feature selection algorithm to forecast the mental disorder in a particular workplace and found to be 79% accuracy.KeywordsMental disorderFeature selectionRFERFECVLASSOAssociative propertyDistributive property

Mobility predictions are becoming more valuable in various applications with the rise of mobile devices. Given that existing prediction techniques are composed of two key procedures: 1) profiling past mobility trajectories as sequences of discrete atomic states (e.g., grid locations, semantic locations) and capturing them with an appropriate statistical model, 2) making a prediction on the next state using the statistical model, TravelMiner tackles the former with paths utilized as the atomic states for the first time, where the paths are defined as sub-trajectories with no branches. Comparing to available location-based predictors, TravelMiner makes a fundamental difference in that it is able to predict the sequence of paths rather than locations, which is far more detailed in the perspective of knowing the exact route to follow. TravelMiner enables this benefit by extracting disjoint paths from GPS trajectories via a similarity metric for curves, called Frechet distance and keeping the sequences of such paths in a statistical model, called probabilistic radix tree. Our extensive simulations over the GPS trajectories of 124 users reveal that TravelMiner outperforms other predictors in diverse popular performance metrics including predictability, prediction accuracy and prediction resolution.

The use of machine learning models in consequential decision making often exacerbates societal inequity, in particular yielding disparate impact on members of marginalized groups defined by race and gender. The area under the ROC curve (AUC) is widely used to evaluate the performance of a scoring function in machine learning, but is studied in algorithmic fairness less than other performance metrics. Due to the pairwise nature of the AUC, defining an AUC-based group fairness metric is pairwise-dependent and may involve both intra-group and inter-group AUCs. Importantly, considering only one category of AUCs is not sufficient to mitigate unfairness in AUC optimization. In this paper, we propose a minimax learning and bias mitigation framework that incorporates both intra-group and inter-group AUCs while maintaining utility. Based on this Rawlsian framework, we design an efficient stochastic optimization algorithm and prove its convergence to the minimum group-level AUC. We conduct numerical experiments on both synthetic and real-world datasets to validate the effectiveness of the minimax framework and the proposed optimization algorithm.

Visualization of population in a high-dimensional objective space throughout the evolution process presents an attractive feature that could be well exploited in designing many-objective evolutionary algorithms (MaOEAs). In this paper, a new visualization method is proposed. It maps individuals from a high-dimensional objective space into a 2-D polar coordinate plot while preserving Pareto dominance relationship, retaining shape and location of the Pareto front, and maintaining distribution of individuals. From it, a decision-maker can observe the evolution process, estimate location, range, and distribution of Pareto front, assess quality of the approximated front and tradeoff between objectives, and easily select preferred solutions. Furthermore, its applications can be scalable to any dimensions, handle a large number of individuals on front, and simultaneously visualize multiple fronts for comparison. Based on this visualization tool, a performance metric, named polar-metric, is designed. The convergence of the approximate front is measured by radial values of all population members on that front. Meanwhile, the diversity performance is mainly determined by niche count of each subregion in a high-dimensional objective space. Experimental results show that it can provide a comprehensive and reliable comparison among MaOEAs.

Network-on-Chip (NoC) has been developed as an interconnect patterns in state-of-the-art multiprocessors. Core mapping and identifying suitable NoC platforms have a substantial effect on NoC system performance and corresponding costs. In this research work, investigated core mapping and optimization of NoC platforms by using an efficient algorithm. Consider two performance metrics (reliability and delay) and two cost metrics (area and power). The proposed mapping algorithm was assessed by applying it to different NoC benchmarks. The simulation results expose that the suggested mapping technique outperformed the other mapping techniques in terms of performance and cost metrics.

Deep learning techniques have recently demonstrated remarkable success in numerous domains. Typically, the success of these deep learning models is measured in terms of performance metrics such as accuracy and mean average precision (mAP). Generally, a model's high performance is highly valued, but it frequently comes at the expense of substantial energy costs and carbon footprint emissions during the model building step. Massive emission of CO2 has a deleterious impact on life on earth in general and is a serious ethical concern that is largely ignored in deep learning research. In this article, we mainly focus on environmental costs and the means of mitigating carbon footprints in deep learning models, with a particular focus on models created using knowledge distillation (KD). Deep learning models typically contain a large number of parameters, resulting in a 'heavy' model. A heavy model scores high on performance metrics but is incompatible with mobile and edge computing devices. Model compression techniques such as knowledge distillation enable the creation of lightweight, deployable models for these low-resource devices. KD generates lighter models and typically performs with slightly less accuracy than the heavier teacher model (model accuracy by the teacher model on CIFAR 10, CIFAR 100, and TinyImageNet is 95.04%, 76.03%, and 63.39%; model accuracy by KD is 91.78%, 69.7%, and 60.49%). Although the distillation process makes models deployable on low-resource devices, they were found to consume an exorbitant amount of energy and have a substantial carbon footprint (15.8, 17.9, and 13.5 times more carbon compared to the corresponding teacher model). The enormous environmental cost is primarily attributable to the tuning of the hyperparameter, Temperature (τ). In this article, we propose measuring the environmental costs of deep learning work (in terms of GFLOPS in millions, energy consumption in kWh, and CO2 equivalent in grams). In order to create lightweight models with low environmental costs, we propose a straightforward yet effective method for selecting a hyperparameter (τ) using a stochastic approach for each training batch fed into the models. We applied knowledge distillation (including its data-free variant) to problems involving image classification and object detection. To evaluate the robustness of our method, we ran experiments on various datasets (CIFAR 10, CIFAR 100, Tiny ImageNet, and PASCAL VOC) and models (ResNet18, MobileNetV2, Wrn-40-2). Our novel approach reduces the environmental costs by a large margin by eliminating the requirement of expensive hyperparameter tuning without sacrificing performance. Empirical results on the CIFAR 10 dataset show that the stochastic technique achieves an accuracy of 91.67%, whereas tuning achieves an accuracy of 91.78%-however, the stochastic approach reduces the energy consumption and CO2 equivalent each by a factor of 19. Similar results have been obtained with CIFAR 100 and TinyImageNet dataset. This pattern is also observed in object detection classification on the PASCAL VOC dataset, where the tuning technique performs similarly to the stochastic technique, with a difference of 0.03% mAP favoring the stochastic technique while reducing the energy consumptions and CO2 emission each by a factor of 18.5.

Medical images exchanged over vulnerable networks are sensitive to modifications or tampering which could lead to misdiagnosis, risking the lives of the patients. Therefore, to provide safe and secure transmission of medical images, key security requirements such as authenticity, integrity, and confidentiality must be addressed. In this paper, a novel and efficient algorithm is proposed which provides security services for transmitted medical images in tele-medicine applications. The proposed algorithm employs joint encryption/watermarking procedures to provide the required security services, as well as to provide control access privileges at the receiving side. The algorithm is based on reversible data hiding principles that guarantee the extraction of the hidden data while restoring the original image unaffected. The embedded data is basically two watermarks; a spatial domain watermark and an encrypted domain watermark. The dual watermarks allow the authenticity and integrity of the transmitted medical images to be verified in the spatial and encrypted domains. The proposed algorithm has been extensively evaluated using three performance metrics; embedding capacity, visual image quality, and entropy. The ability of the algorithm to fulfill the security, reversibility, and separability requirements has been validated.

ABSTRACTWe described in this paper the development of a high fidelity vehicle aerodynamic model to fit wind tunnel test data over a wide range of vehicle orientations. We also present a comparison between the effects of this proposed model and a conventional quasi steady-state aerodynamic model on race vehicle simulation results. This is done by implementing both of these models independently in multi-body quasi steady-state simulations to determine the effects of the high fidelity aerodynamic model on race vehicle performance metrics. The quasi steady state vehicle simulation is developed with a multi-body NASCAR Truck vehicle model, and simulations are conducted for three different types of NASCAR race tracks, a short track, a one and a half mile intermediate track, and a higher speed, two mile intermediate race track. For each track simulation, the effects of the aerodynamic model on handling, maximum corner speed, and drive force metrics are analysed. The accuracy of the high-fidelity model is shown to reduce the aerodynamic model error relative to the conventional aerodynamic model, and the increased accuracy of the high fidelity aerodynamic model is found to have realisable effects on the performance metric predictions on the intermediate tracks resulting from the quasi steady-state simulation.

Database systems allow quick creation of performance problems. The goal of database systems is to allow the computer-illiterate to write complex and complete applications. It is the job of the syst...

SummaryAccurate prediction of the solubility of chemical substances in solvents remains a challenge. The sparsity of high-quality solubility data is recognized as the biggest hurdle in the development of robust data-driven methods for practical use. Nonetheless, the effects of the quality and quantity of data on aqueous solubility predictions have not yet been scrutinized. In this study, the roles of the size and the quality of data sets on the performances of the solubility prediction models are unraveled, and the concepts of actual and observed performances are introduced. In an effort to curtail the gap between actual and observed performances, a quality-oriented data selection method, which evaluates the quality of data and extracts the most accurate part of it through statistical validation, is designed. Applying this method on the largest publicly available solubility database and using a consensus machine learning approach, a top-performing solubility prediction model is achieved.