Sound source localization is a critical problem in various fields, including communication, security, and entertainment. Binaural cues are natural technique used by mammalian ears for efficient sound localization. Spiking neural networks (SNNs) have emerged as promising tool implementing binaural approaches. However, optimizing the topology size of SNNs crucial to reduce computational costs while maintaining accuracy. This paper proposes real-time structure reservoir SNN (rSNN) called...

Abstract Background Skin cancer shows geographic and ethnic variation. New Zealand—with a predominantly fair-skinned populations, high UV indices outdoor lifestyles—has rates of skin cancer. However, population prevalence data is lacking. This study aimed to determine the demographics socioeconomic disease trends non-melanoma in Zealand from large targeted-screening study. Methods A targeted screening programme was conducted among 32,839 individuals, Fitzpatrick Types I IV Auckland, during...

Secure and energy-efficient network architectures are required due to the quick spread of 1 Internet Things (IoT) devices in vital industries including healthcare, smart cities, indus- 2 trial automation. In this paper, we propose a secure cross-layer architecture for 3 Things. The proposed incorporates security features energy-saving tech- 4 niques across various open system interconnections protocol layers. better energy 5 efficiency achieved using lightweight cryptographic protocols...

The widespread use of Internet Things (IoT) raises security and energy efficiency 1 concerns, particularly for low-resource devices. In this paper, we analyse a cross-layer IoT architecture 2 using machine learning models lightweight cryptography. We focus on analysing vulnerabilities 3 suggest energy-efficient solutions. Our proposed solution is based role-based access 4 control ensuring secure authentication in large-scale deployments blocks undesired 5 attempts. By combining convolutional...

Purpose This study aims to determine the effects of sexism and unfavourable job conditions on women's mental physical wellbeing in construction operations. In addition, this will establish mediating role work morale association between workplace challenges wellbeing. Design/methodology/approach Data for were obtained from women working office environments, onsite professionals those trades. A total 65 participants responded survey. The partial least square structural equation modelling...

This survey delves into cross layer energy-efficient solutions and cutting-edge security measures for Internet of Things (IoT) networks. The conventional techniques are considered inadequate, leading to the suggestion AI-powered intrusion detection systems novel strategies such as blockchain integration. In this paper, we provide a comprehensive review analysis secure energy efficient cross-layer framework IoT.We highlight significance developing IoT robust sustainable connected systems. We...

This survey delves into cross-layer energy-efficient solutions and cutting-edge security measures for Internet of Things (IoT) networks. The conventional techniques are considered inadequate, leading to the suggestion AI-powered intrusion detection systems novel strategies such as blockchain integration. research aims promote development smart cities by enhancing sustainability, security, efficiency in industrial agricultural sectors through use IoT, blockchain, AI, new communication...

Parkinson's disease is a progressive neurological resulting in motor impairments that decrease patients' quality of life. It condition currently without cure. This study proposes an approach to detection using multimodal analysis, combining handwriting and voice data. We introduce the use image transformer architectures classify patients from healthy subjects, as early diagnosis contributes management symptoms. Data-efficient with self-supervised learning on DINO obtained accuracy above 90%...

Abstract Attention mechanisms have been incorporated into many neural network-based natural language processing (NLP) models. They enhance the ability of these models to learn and reason with long input texts. A critical part such is computation attention similarity scores between two elements texts using a score function. Given that different architectures, it difficult comparatively evaluate effectiveness functions. In this paper, we proposed baseline model captures common components...

In many countries including New Zealand, tobacco use has been considered as the leading cause of preventable diseases and death. Among adult smokers, more than one fourth makes quit attempts every year. Therefore, selecting most suitable smoking cessation program support system is crucial to help smokers achieve desirable outcomes. A total 14,443 enrolments were analyzed in this study using machine learning techniques based on tree ensemble gradient boosted trees. The CatBoost model was...

Introduction: The challenge of navigating a Mobile robot in dynamic environments has grasped significant attention recent years. Despite the available techniques, there is still need for efficient and reliable approaches that can address challenges real-time near optimal navigation collision avoidance. Methods: This paper proposes novel Log-concave Model Predictive Controller (MPC) algorithm addresses these by utilizing unique formulation cost functions constraints, as well convergence...

This report introduces an Artificial Intelligence (AI) literacy framework developed by a research team from The University of Canterbury, academyEX, and AUT. Scaffolded AI Literacy (SAIL) was Delphi Study 17 experts in Aotearoa New Zealand overseas, with representatives both education industry, cultural experts.The has four levels capability. Three define literacy, additional level that indicates what further capabilities come beyond literacy. Know Understand Use Apply Evaluate Create +...

Abstract The identification of perpetrators, present in Child Sexual Abuse Imagery (CSAI), is a significant challenge due to the use anonymisation techniques that mask their identities. Consequently, researchers have investigated uncommon biometric identifiers such as knuckle patterns, palmprints and dorsal side hand. This research proposes Convolutional Neural Network (CNN) based, fully automated approach using hand images. performance three different CNN architectures, AlexNet, ResNet50...

Digital contact tracing application is a digital measure implemented by many countries across the globe in response to Covid-19 outbreak. Use of applications like these present certain concerns regarding user privacy and security. In this paper, four were tested using MobSF drozer check for risks code (static analysis) determine potential attack surfaces. The observations findings compiled tabular form, including OWASP mobile top 10 issues, as well CWE that detected MobSF. surfaces also listed.

Wireless sensor networks need to deliver real-time services such as video, audio and traditional data therefore providing efficient quality of (QoS) support is essential. In this paper we aim address the time-delay parameter QoS implemented using a new cross-layer framework design. The concept design based on architecture where different layers can exchange information in order improve overall network performance. Promising results achieved by optimization initiated significant research...

To estimate the direct cost of coronary heart disease [CHD] to Iranian oil industry, we calculated essential services for 1253 CHD patients admitted National Oil Corporation [NIOC] Central Hospital. The at Hospital was 10940 million rials [US$ 1 = 8000 rials], or 8.7 per patient. industry estimated 22 770 rials. Working days lost workers hospitalized amounted 62 832. heavy burden on necessitates introduction an industry-wide prevention programme