Humans and twinned linear ANNs (collectively, ‘learners’) learned two successive tasks (task A followed by task B) and were then retested on task A (Fig. 1). Each task required learners to map six discrete inputs (plants) onto positions on a…
Category: 7. Maths
- 
		
		

Minutes matter for life safety and risk exposure in Milford Sound, New Zealand
Wi-Fi proxy data
Wi-Fi capable devices periodically send a probe request to allow continuous connectivity through a Wi-Fi network. Counting these requests can be used as a proxy for the number of devices within a range and by inference, the number…
Continue Reading
 - 
		
		

An integrated approach for rare disease detection and classification in Spanish pediatric medical reports
Rare disease detection
This section is dedicated to describing the pipeline followed for building a dataset composed of texts mentioning rare diseases. First, we depict the original source of information from which the textual data is extracted…
Continue Reading
 - 
		
		

Research on the impact of explosive martial arts training on emotion regulation and attention based on questionnaire data
Overview
This section introduces a novel framework designed to address key challenges in sports-related vision and perception tasks. The increasingly data-rich environments of competitive and recreational sports have heightened the demand for…
Continue Reading
 - 
		
		

Prompt-dependent performance of multimodal AI model in oral diagnosis: a comprehensive analysis of accuracy, narrative quality, calibration, and latency versus human experts
Study design
The study was conducted in compliance with the Declaration of Helsinki (2013 revision) and reported in accordance with STARD 2015 and its STARD-AI extension7. This is a prospective, paired diagnostic-accuracy study comparing a…
Continue Reading
 - 
		
		

A lightweight large language model for regulatory affairs translation in pharmaceutical industry
The study constructs a new corpus for regulatory affairs in pharmaceutical industry. It comprises 1,506 documents officially published in China, both in English and Chinese. After web crawling, cleaning, and verifying the bilingual documents from…
Continue Reading
 - 
		
		

Behavioral TOPSIS technique based on probabilistic picture hesitant fuzzy probability splitting algorithm and novel interactive operations
Some defects of operations for PPHFEs
In this section, we will focus on analyzing the shortcomings of the basic operations proposed in reference23 using several examples, especially the defects that do not satisfy closeness.
Continue Reading
 - 
		
		

DRCNN-Lesion Proxy: a hybrid CNN with lesion-inspired feature simulation for diabetic retinopathy severity classification
The experimental pipeline was implemented and executed on Google Collaboratory, utilizing GPU acceleration for training. The environment provided a reproducible, cloud-based setup with integrated visualization and logging. Training, validation,…
Continue Reading
 - 
		
		

A chaotic parallel hash engine with dynamic stochastic diffusion for blockchain and cloud security
As stated previously, a secure hash function must possess strong collision resistance and produce an output that exhibits uniform distribution and sensitivity to slight changes. This chapter delves into the performance of the CPHDSD algorithm in…
Continue Reading
 - 
		
		

Impact of talent cultivation model for industry education integration in vocational education by artificial intelligence and BPNN
AI-driven talent development model for industry-education integration
Within the context of industry-education integration, multimodal data is extensively present across various phases of both theoretical and practical instruction. In theoretical…
Continue Reading
 
