Multinomial random forest

Sun

Journal of Environmental and Public Health

et al. 2022

Environmental problem is an international problem that transcends national boundaries and develops into regional and global environmental pollution and ecological problems. Facing the increasing environmental pollution, the international community has successively formulated many relevant environmental pollution prevention laws, but the world situation is complicated after all, environmental problems still emerge endlessly, and the protection of environmental rights has become the consensus of the international community. Environmental right is an integral part of human rights, and protecting environmental right is the concrete expression and proper meaning of protecting human rights. Using international criminal law to protect environmental rights will play a positive role in global environmental protection. As with the development of computer technology, the research of machine learning has gradually transferred to the field of social science, especially the judicial field. While sentencing is a crucial part of environmental crime, this paper studies the sentencing of environmental rights cases from the perspective of international criminal law and uses Convolutional Neural Networks (CNN) to determine the sentencing of environmental rights cases. Through the experiment on the Integrated Database (IDB) dataset, the results show that the introduction of CNN improves the effect of the sentencing term prediction model and the fine prediction model significantly. The CNN-based model scored 91.6542 in the sentencing term prediction model and 90.8890 in the fine prediction model.

Section: Experiments and Results Analysismentioning

confidence: 99%

International Criminal Law Protection of Environmental Rights and Sentencing Based on Artificial Intelligence

Sun

Journal of Environmental and Public Health

et al. 2022

“…One example is the Tox21 project for toxicity assays, which is a database comprised of compounds with various activities in each of the 12 different pathway assays. To this end, Capuzzi et al [ 83 ] built quantitative structure-activity relationship (QSAR) [ 84 ] models by using the random forest method [ 85 ], DNNs, and various combinations of molecular descriptors and dataset-balancing protocols. However, the large experimental dataset has a higher chance of containing mislabeling either the chemical structures or their toxicity classes.…”

Section: Case Studies In Ooc Applicationsmentioning

confidence: 99%

The Synergy between Deep Learning and Organs-on-Chips for High-Throughput Drug Screening: A Review

et al. 2023

Organs-on-chips (OoCs) are miniature microfluidic systems that have arguably become a class of advanced in vitro models. Deep learning, as an emerging topic in machine learning, has the ability to extract a hidden statistical relationship from the input data. Recently, these two areas have become integrated to achieve synergy for accelerating drug screening. This review provides a brief description of the basic concepts of deep learning used in OoCs and exemplifies the successful use cases for different types of OoCs. These microfluidic chips are of potential to be assembled as highly potent human-on-chips with complex physiological or pathological functions. Finally, we discuss the future supply with perspectives and potential challenges in terms of combining OoCs and deep learning for image processing and automation designs.

“…The choice of which will be based on some optimization at the node. Another type of RF is the multinominal RF (MRF) [50] which is concerned about increasing the consistency and the differential privacy in RF with performance comparable to the standard RF.…”

Section: Tuning the Hyperparameters Of The Random Forest Modelmentioning

confidence: 99%

Simple Deterministic Selection-Based Genetic Algorithm for Hyperparameter Tuning of Machine Learning Models

et al. 2022

Hyperparameter tuning is a critical function necessary for the effective deployment of most machine learning (ML) algorithms. It is used to find the optimal hyperparameter settings of an ML algorithm in order to improve its overall output performance. To this effect, several optimization strategies have been studied for fine-tuning the hyperparameters of many ML algorithms, especially in the absence of model-specific information. However, because most ML training procedures need a significant amount of computational time and memory, it is frequently necessary to build an optimization technique that converges within a small number of fitness evaluations. As a result, a simple deterministic selection genetic algorithm (SDSGA) is proposed in this article. The SDSGA was realized by ensuring that both chromosomes and their accompanying fitness values in the original genetic algorithm are selected in an elitist-like way. We assessed the SDSGA over a variety of mathematical test functions. It was then used to optimize the hyperparameters of two well-known machine learning models, namely, the convolutional neural network (CNN) and the random forest (RF) algorithm, with application on the MNIST and UCI classification datasets. The SDSGA’s efficiency was compared to that of the Bayesian Optimization (BO) and three other popular metaheuristic optimization algorithms (MOAs), namely, the genetic algorithm (GA), particle swarm optimization (PSO) and biogeography-based optimization (BBO) algorithms. The results obtained reveal that the SDSGA performed better than the other MOAs in solving 11 of the 17 known benchmark functions considered in our study. While optimizing the hyperparameters of the two ML models, it performed marginally better in terms of accuracy than the other methods while taking less time to compute.