Federated Learning (FL) is an emerging distributed machine learning (ML) technique distinguished by non-independent and identically distributed (Non-IID) data, statistical heterogeneity, and an expected large number of participating clients to collaboratively train a shared model without fusing the training data into one centralized server. State-of-the-art FL research focuses on gradient-based models, which is not suitable for ML-based intrusion detection systems that utilize tree-based learning methods such as Random Forest. Adapting a typical gradient-based FL method to a tree-based training technique is non-trivial, as ensembling trees and aggregating decision trees from different random forests across clients can be computationally, spatially, and temporally intensive. To overcome these challenges, this paper proposes FedRand, a novel adaptive Federated Random Forest Aggregation Learning Technique for Anomaly Detection in Internet of Things (IoT) networks. This paper thoroughly examines a suite of novel tree selection and aggregation strategies within a federated learning framework, ensuring robust model accuracy, accelerated aggregation, and global model convergence. We believe that this work opens up a promising solution for federated tree-based learning techniques.

The increasing elderly population necessitates increased geriatric care. However, a shortage of caregivers leads to a risk of falls and bedsores in the elderly, both of which result in severe injuries. Whilst wearable devices, and vision sensors have been adopted for monitoring. However, these sensors come with limitations, impacting comfort and privacy for the elderly. To address these challenges, non-intrusive sensing devices integrated into the environment offer promising value for continuous elderly activity monitoring. This study uses a panel sensor embedded with four sensors, consisting of two piezoelectric sensors and two pressure sensors. It is placed beneath the mattress. The position classification encompasses five distinct positions: off-bed, sitting, lying in the center, lying on the left side, and lying on the right side. To find the best position for placing the panel, the positions of the panel and the combination of panel sensors positions are evaluated for five-bed positions classification. As a result, the best position for a sensor panel was in the middle of the bed (position No. 3), with an accuracy of 97.12%. This suggests the panel sensor should be placed at 123.5 cm, measured from the top of the bed. Moreover, in the case of placing two-panel sensors, the most effective arrangement comprises placing one-panel sensor placed at the the bed-top (position No. 1) and the other in the middle of the bed (position No. 3), yielding accuracy 99.93%.

The Thammasat AI City distributed platform is a proposed AI platform designed to enhance city intelligent management. It addresses the limitations of current smart city architecture by incorporating cross-domain data connectivity and machine learning to support comprehensive data collection. In this study, we delve into two main areas, that is, monitoring and visualization of city ambient lighting, and indoor human physical distance tracking. The smart street light monitoring system provides real-time visualization of street lighting status, energy consumption, and maintenance requirement, which helps to optimize energy consumption and maintenance reduction. The indoor camera-based system for human physical distance tracking can be used in public spaces to monitor social distancing and ensure public safety. The overall goal of the platform is to improve the quality of life in urban areas and align with sustainable urban development concepts.

This research proposes an AI platform for data sharing across multiple domains. Since the data in the smart city concept are domain-specific processed, the existing smart city architecture is suffered from cross-domain data interpretation. To go beyond the digital transformation efforts in smart city development, the AI city is created on the architecture of cross-domain data connectivity and transform learning in the machine learning paradigm. In this research, the health and human behavioral data are targeted on human traceability and contactless technologies. To measure the inhabitants quality of life (QoL), the primary emotion expression study is conducted to interpret the emotional states and the mental health of people in the urbanized city. The results of information augmentation draw attention to the immersive visualization of the Thammasat model.

MOTIVATION: Probabilistic latent semantic analysis (pLSA) is commonly applied to describe mass spectra (MS) images. However, the method does not provide certain outputs necessary for the quantitative scientific interpretation of data. In particular, it lacks assessment of statistical uncertainty and the ability to perform hypothesis testing. We show how linear Poisson modelling advances pLSA, giving covariances on model parameters and supporting χ2 testing for the presence/absence of MS signal components. As an example, this is useful for the identification of pathology in MALDI biological samples. We also show potential wider applicability, beyond MS, using magnetic resonance imaging (MRI) data from colorectal xenograft models. RESULTS: Simulations and MALDI spectra of a stroke-damaged rat brain show MS signals from pathological tissue can be quantified. MRI diffusion data of control and radiotherapy-treated tumours further show high sensitivity hypothesis testing for treatment effects. Successful χ2 and degrees-of-freedom are computed, allowing null-hypothesis thresholding at high levels of confidence. AVAILABILITY AND IMPLEMENTATION: Open-source image analysis software available from TINA Vision, www.tina-vision.net. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Motivation: Matrix-assisted laser desorption/ionisation time-of-flight mass spectrometry (MALDI) facilitates the analysis of large organic molecules. However, the complexity of biological samples and MALDI data acquisition leads to high levels of variation, making reliable quantification of samples difficult. We present a new analysis approach that we believe is well-suited to the properties of MALDI mass spectra, based upon an Independent Component Analysis derived for Poisson sampled data. Simple analyses have been limited to studying small numbers of mass peaks, via peak ratios, which is known to be inefficient. Conventional PCA and ICA methods have also been applied, which extract correlations between any number of peaks, but we argue makes inappropriate assumptions regarding data noise, i.e. uniform and Gaussian. Results: We provide evidence that the Gaussian assumption is incorrect, motivating the need for our Poisson approach. The method is demonstrated by making proportion measurements from lipid-rich binary mixtures of lamb brain and liver, and also goat and cow milk. These allow our measurements and error predictions to be compared to ground truth. Availability and implementation: Software is available via the open source image analysis system TINA Vision, www.tina-vision.net. Contact: [email protected]. Supplementary information: Supplementary data are available at Bioinformatics online.