Fig 4 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Distribution of population in all the samples from the training, validation, and testing dataset by demographic composition groups. Scales on the y-axis are original and logarithm with base 10 for the left and right figure, respectively. The blue lines across ages indicate that the values were from the same sample in a mesh cell either in 2015 or 2020.
Source publication
Population aging is one of the most serious problems in certain countries. In order to implement its countermeasures, understanding its rapid progress is of urgency with a granular resolution. However, a detailed and rigorous survey with high frequency is not feasible due to the constraints of financial and human resources. Nowadays, Deep Learning...
Contexts in source publication
Context 1
... I describes the summary statistics of samples by the type of dataset and sample year. As seen on the left in Figure 4, the distribution of the population is heavily skewed. On the other hand, the logarithm with base 10 was applied for the original number of the population, which is shown on the right in Figure 4. Thus, for the labels of the CNN model, this paper employs the logarithm of the original population with base 10, However, some samples contain 0 for certain demographic composition groups, where the logarithm is not defined. ...
Context 2
... seen on the left in Figure 4, the distribution of the population is heavily skewed. On the other hand, the logarithm with base 10 was applied for the original number of the population, which is shown on the right in Figure 4. Thus, for the labels of the CNN model, this paper employs the logarithm of the original population with base 10, However, some samples contain 0 for certain demographic composition groups, where the logarithm is not defined. ...
Similar publications
In artificial intelligence (AI), computer vision consists of intelligent models to interpret and recognize the visual world, similar to human vision. This technology relies on a synergy of extensive data and human expertise, meticulously structured to yield accurate results. Tackling the intricate task of locating and resolving blockages within sew...
This paper presents a comprehensive survey of publicly available neural network models specifically designed for detecting wildfires using regular visible-range cameras positioned on hilltops or forest lookout towers. The surveyed models are first pre-trained on the ImageNet-1K dataset and then fine-tuned on a custom wildfire dataset to enhance the...
Citations
... For instance, China's approach to AI ethics is closely aligned with its state-centric model, where AI is used to support national interests and societal goals, such as through surveillance systems designed to maintain public order (Huw Roberts & Floridi, 2024). Japan, on the other hand, emphasizes AI development for societal benefit, particularly to support an aging population and promote overall well-being (Sato, 2023) ...
This chapter examines the ethical complexities of Artificial Intelligence (AI) and automated decision-making systems, now integral to fields like healthcare, finance, criminal justice, and education. While AI presents immense opportunities for innovation and efficiency, it also introduces significant ethical challenges. The chapter explores foundational ethical frameworks—Utilitarianism, Deontological Ethics, and Virtue Ethics—offering insight into the moral duties guiding AI development. It examines global and international perspectives, emphasizing the cultural and regulatory variations shaping AI governance. Key ethical issues such as bias, transparency, privacy, and global impacts are explored, supported by case studies across various sectors. Emerging concerns, including deepfakes, autonomous weapons, and AI's impact on employment and inequality, are also addressed. The chapter calls for continuous dialogue and proactive governance to ensure responsible AI development for societal benefit, providing a roadmap for ethical AI governance.
