The task of automatic minuting, i.e., capturing all the points from transcripts of multi-party meetings, presents considerable challenges owing to the spontaneous and complex nature of discussions. As organisations increasingly depend on meetings for decision-making, the need for efficient and optimised minuting has intensified, underscoring the shortcomings of manual note-taking due to cognitive overload and diverted participant engagement. This study systematically analyses the impact of scaling Large Language Models (LLMs) on automatic minuting , emphasising key factors including pretrained dataset size, model size, context length, and prompt length. The benchmark evaluation includes both quantitative and qualitative with 19 open-source models (from 77M to 70B parameters) and 4 closed-source models (over 1T parameters) across 4 meeting corpora and prompts. Our findings indicate that (1) models with less than 8B parameters offer a favorable trade-off between performance and efficiency, achieving comparable results to their larger counterparts. (2) scaling pretrained data size improves performance up to a threshold, beyond which gains diminish. (3) context length exhibits a non-linear effect, with optimal performance around 8K-16K tokens. (4) longer prompts consistently degrade output quality, highlighting the need for concise and well-structured prompting. To the best of our knowledge this is the first work, exploring scaling LLMS on automatic minuting. Code is available at https://anonymous.4open.science/r/MeetMultiX-9A36

Falls are one of the most costly population health issues. Screening of older adults for fall risks can allow for earlier interventions and ultimately lead to better outcomes and reduced public health spending. This work proposes a solution to limitations in existing fall screening techniques by utilizing a hip-based accelerometer worn in free-living conditions. The work proposes techniques to extract fall risk features from periods of free-living ambulatory activity. Analysis of the proposed techniques is conducted and compared with existing screening methods using Functional Tests and Lab-based Gait Analysis. 1705 Older Adults from Umea (Sweden) were assessed. Data consisted of 1 Week of hip worn accelerometer data, gait measurements and performance metrics for 3 functional tests. Retrospective and Prospective fall data were also recorded based on the incidence of falls occurring 12 months before and after the study commencing respectively. Machine learning based experiments show accelerometer based measures perform best when predicting falls. Prospective falls had a sensitivity and specificity of 0.61 and 0.66 respectively while retrospective falls had a sensitivity and specificity of 0.61 and 0.68 respectively.

In the last decade the total global number of displaced refugees has increased significantly and consistently. This has been further inflated by 5 million Syrians who were externally displaced in 2017. Often these individuals flee their home countries without identification documentation and thus find it extremely difficult to verify their true identities when they attempt to reconstruct their lives in their new homelands. The requirement for identification documentation is a constant element of daily life within modern societies. This functions to both protect the rights of individuals and also the entities and organisations they interact with. The need to provide identification documentation can present significant challenges for displaced people trying to reconstruct their lives. In the digital age where individuals are creating large digital footprints, online accounts and activities can prove to be a valuable source of information that may contribute to `proof' that an asserted identity is genuine. Online social contextual data - or `Digital identities' - pertaining to real people are built over time and bolstered by associated accounts, relationships and attributes. This data is difficult to fake and therefore may have the capacity to provide proof of a `real' identity. This paper outlines the design and initial development of a solution that could potentially allow refugees who are resettling to build a digital identity document over time as they settle in a new land, without the need for multiple sources of traditional identity documentation. This solution utilizes data sourced from an individual's digital footprint to assess the likelihood that it pertains to a `real' identity. This is achieved through application of machine learning and Bayesian probabilistic modelling techniques. Where identity sources are considered reliable, a secure and intelligent digital identification artefact will be created. This artefact will emulate a blockchain-inspired ledger and may subsequently be used to prove identity in place of traditional paper documentation.

As human-kind becomes increasingly dependent on online services to conduct the fundamental aspects of daily life, digital footprints and the associated online service digital identities have the capacity to provide verification that an individual is a `real person' and possesses a true identity. A recognized challenge in utlising this data in this manner is that different types of online services possess different levels of reliability. This paper explores the application of naïve Bayes theorem to subsets of attributes contained within various types of online accounts that are presented as `identity sources'. This seeks to demonstrate that less reliable sources such as social media accounts will produce lower trust scores than more reliable sources following application of Bayes theorem. The results for which will be used to determine if digital identity sources can be relied upon in place of traditional paper identification documentation. This research and testing has been conducted as an element of a larger intelligent identity authentication system that seeks to create a solution that proves an identity is genuine via an individual's digital footprint.

Gait-based person identification suffers from the problem of different covariate factors such as clothing and carrying objects, which drastically reduce the recognition rate. Most existing methods capture dynamic and static information and remove the covariate factors without any systematic study. However, it has been reported in the literature that the head is one of the important features and the removal of the head from static information decreases the recognition rate. In our preliminary study, we developed a novel random walk (RW)-based gait extraction method that retains the head portion and removes certain static body parts to reduce the effect of covariate factors. The RW-based method is a novel gait feature extraction method and should be exploited more for its discriminative power to separate different body parts efficiently. However, the dynamic part is also significant in gait information, which is not very effectively represented in the RW-based gait extraction method. Therefore, a discrete Fourier transform (DFT)-based frequency component of the gait is considered to represent the dynamic part of gait information. Furthermore, we propose a novel gait recognition algorithm that fuses dynamic and static information from DFTand RW-based representations. The proposed method systematically retains the discriminative static gait information along with the frequency attribute embedded as the dynamic gait information. Extensive experiments on the Chinese Academy of Sciences, Institute of Automation and the HumanID datasets have been carried out to demonstrate that the proposed fused gait features-based approach outperforms the existing methods, particularly when there are substantial appearance changes.

Rheumatoid Arthritis (RA) is a disease which attacks the synovial tissue lubricating skeletal joints. This systemic condition affects the musculoskeletal system, including bones, joints, muscles and tendons that contribute to loss of function and Range of Motion (ROM). Traditional measurement of arthritis requires labour intensive personal examination by medical staff which through their objective measures may hinder the enactment and analysis of arthritis rehabilitation. This paper presents the development of a smart glove to facilitate this rehabilitative process through the integration of sensors, processors and wireless technology to empirically measure ROM. The Tyndall/University of Ulster glove uses a combination of 20 bend sensors, 16 tri-axial accelerometers and 11 force sensors to detect joint movement. All sensors are placed on a flexible PCB to provide high levels of flexibility and sensor stability. The system operation means that the glove does not require calibration for each glove wearer.

Rheumatoid Arthritis (RA) is a disease which attacks the synovial tissue lubricating skeletal joints. This systemic condition affects the musculoskeletal system, including bones, joints, muscles and tendons that contribute to loss of function and Range of Motion (ROM). Traditional measurement of arthritis requires labour intensive personal examination by medical staff which through their objective measures may hinder the enactment and analysis of arthritis rehabilitation. This paper presents the development of a smart glove to facilitate this rehabilitative process through the integration of sensors, processors and wireless technology to empirically measure ROM. The Tyndall/University of Ulster glove uses a combination of 20 bend sensors, 16 tri-axial accelerometers and 11 force sensors to detect joint movement. All sensors are placed on a flexible PCB to provide high levels of flexibility and sensor stability. The system operation means that the glove does not require calibration for each glove wearer.

A reliable human skin detection method that is adaptable to different human skin colors and illumination conditions is essential for better human skin segmentation. Even though different human skin-color detection solutions have been successfully applied, they are prone to false skin detection and are not able to cope with the variety of human skin colors across different ethnic. Moreover, existing methods require high computational cost. In this paper, we propose a novel human skin detection approach that combines a smoothed 2-D histogram and Gaussian model, for automatic human skin detection in color image(s). In our approach, an eye detector is used to refine the skin model for a specific person. The proposed approach reduces computational costs as no training is required, and it improves the accuracy of skin detection despite wide variation in ethnicity and illumination. To the best of our knowledge, this is the first method to employ fusion strategy for this purpose. Qualitative and quantitative results on three standard public datasets and a comparison with state-of-the-art methods have shown the effectiveness and robustness of the proposed approach.

In this paper, the concept of object-oriented embedding (OOE) is introduced into information hiding in general and particularly to steganography which is the science that involves undetectable communication of secret data in an appropriate multimedia carrier. The proposal takes advantage of computer vision to orient the embedding process. Although, any existing algorithm can benefit from this technique to enhance its performance against steganalysis attacks, however this work also considers a new embedding algorithm in the wavelet domain using the Binary Reflected Gray Code (BRGC). In the realm of information hiding, one wing focuses on robustness, i.e., watermarking, and another wing focuses on imperceptibility, i.e., steganography. This work advocates for a new steganographic model that meets both robustness as well as imperceptibility. Resilience against common steganalysis attacks including the 274-D merged Markov and DCT features while surviving various image processing manipulations are reported. A neural network classifier was trained with features derived from 400 images. Comparisons with existing systems will also be highlighted.

This paper presents a novel dynamic threshold approach to discriminate skin pixels and non-skin pixels in color images. Fixed decision boundaries (or fixed threshold) classification approaches are successfully applied to segment human skin. These fixed thresholds mostly failed in two situations as they only search for a certain skin color range: 1) any non-skin object may be classified as skin if non-skin objects's color values belong to fixed threshold range. 2) any true skin may be mistakenly classified as non-skin if that skin color values do not belong to fixed threshold range. Therefore in this paper, instead of predefined fixed thresholds, novel online learned dynamic thresholds are used to overcome the above drawbacks. The experimental results show that our method is robust in overcoming these drawbacks.

The majority of existing methods have one thing in common which is the de-correlation of luminance from the considered colour channels. It is believed that the luminance is underestimated here since it is seen as the least contributing colour component to skin colour detection. This work questions this claim by showing that luminance can be useful in separating skin and non-skin clusters. To this end, this work uses a new colour space which contains error signals derived from differentiating the grayscale map and the non-encoded-red grayscale version. The advantages of this approach are the reduction of space dimensionality from 3D to 1D space and the construction of a rapid classifier necessary for real time applications. This method is meant to assist digital image steganography to orient the embedding process since skin information is deemed to be psycho-visually redundant.

Previous studies have shown that Steganography tools such as the S-Tools application outperforms counterpart tools in hiding data in the spatial domain. Another tool called F5 is identified as a robust tool in implementing Steganography in the frequency domain. This paper presents a Steganographic system which exploits the YCbCr colour space. YCbCr is intended to take advantage of human colour-response characteristics. Results show that our algorithm outperforms both F5 and S-Tools. Moreover, our system demonstrates improved performance in retrieving the hidden data after applying image processing attacks in the form of additive artificial noise. As a performance measurement for image distortion Peak-Signal-to-Noise Ratio (PSNR), which is classified under the difference distortion metrics, can be applied to the Stego images. This study also shows that by adopting an object oriented Steganography mechanism, in the sense that we track skin tone objects in video frames, we get a higher PSNR value.

We present a method for recognizing individuals from their ldquostyle of actionrdquo. Two forms of human recognition can be useful: the determination that an object is from the class of humans (which is called human detection), and the determination that an object is a particular individual from this class (this is called individual recognition). This paper focuses on the latter problem. A periodicity is detected in from a sequence of motion detected binary image frames by finding the maximum similarity measure between them. Based on the periodicity information the Motion History Image (MHI) is applied for each individual sequence to find out entire motion information of periodic action. The individual is then recognized using a partial Hausdorff Distance similarity measure and the SVM classification approach.