Hybrid Methodology Research Articles

A hybrid methodology based battery power management and torque control of open-end winding induction motor drive for electric vehicles

This paper proposes a hybrid strategy for an isolated battery-powered induction motor drive with two stages fed by an inverter and open-end winding, designed for electric vehicle applications. The hybrid approach, termed EOO-RERNN, combines the Eurasian Oystercatcher Optimizer (EOO) and Recalling Enhanced Neural Network methods. RERNN predicts the control pulses generated by EOO, which are utilized to control the voltage source inverter (VSI) switches. The system comprises dual motors, two battery packs (BPs), and VSIs supplying power to both the rear motor (RM) and front motor (FM). The primary objective of the EOO-RERNN technique is to regulate each DC-link's power share to maintain equilibrium in the electric vehicle's charge. Direct Torque Control (DTC) is employed due to its quick and precise torque response and tolerance for parameter variations. Proper tuning is required to control the state of charge battery level. The EOO-RERNN method is implemented in the Matrix Laboratory (MATLAB) platform, with performance contrasted to other methods such as Wild Horse Optimizer (WHO), Grasshopper Optimization Algorithm (GOA), and Heap-Based Optimizer (HBO). Simulation results indicate a motor speed of 4850 rpm for the EOO-RERNN method.

A Residual Deep Learning Method for Accurate and Efficient Recognition of Gym Exercise Activities Using Electromyography and IMU Sensors

The accurate and efficient recognition of gym workout activities using wearable sensors holds significant implications for assessing fitness levels, tailoring personalized training regimens, and overseeing rehabilitation progress. This study introduces CNN-ResBiGRU, a novel deep learning architecture that amalgamates residual and hybrid methodologies, aiming to precisely categorize gym exercises based on multimodal sensor data. The primary goal of this model is to effectively identify various gym workouts by integrating convolutional neural networks, residual connections, and bidirectional gated recurrent units. Raw electromyography and inertial measurement unit data collected from wearable sensors worn by individuals during strength training and gym sessions serve as inputs for the CNN-ResBiGRU model. Initially, convolutional neural network layers are employed to extract unique features in both temporal and spatial dimensions, capturing localized patterns within the sensor outputs. Subsequently, the extracted features are fed into the ResBiGRU component, leveraging residual connections and bidirectional processing to capture the exercise activities’ long-term temporal dependencies and contextual information. The performance of the proposed model is evaluated using the Myogym dataset, comprising data from 10 participants engaged in 30 distinct gym activities. The model achieves a classification accuracy of 97.29% and an F1-score of 92.68%. Ablation studies confirm the effectiveness of the convolutional neural network and ResBiGRU components. The proposed hybrid model uses wearable multimodal sensor data to accurately and efficiently recognize gym exercise activity.

A Systematic Approach for Evaluating and Selecting Healthcare Waste Treatment Devices using OWCM-CODAS and Triangular Neutrosophic Sets

Healthcare is a fundamental aspect of human life, impacting individuals, communities, and societies. Investing in healthcare infrastructure, services, and education is essential for fostering a healthy, thriving population. Healthcare waste management is a critical aspect of public health, and it requires a concerted effort from healthcare facilities, governments, and communities to ensure that waste is managed in a way that minimizes risks to human health and the environment. This paper proposes a hybrid methodology combining the Opinion Weight Criteria Method (OWCM) and the Combinative Distance-Based Assessment (CODAS) within the framework of Triangular Neutrosophic Sets (TNS) to evaluate and select the optimal healthcare waste treatment devices. The proposed methodology balances various conflicting criteria and incorporates uncertainty in expert assessments to ensure a robust decision-making process. The paper also provides a comprehensive review of healthcare waste management devices and highlights the need for a comprehensive approach to healthcare waste management. The proposed methodology is applied to a case study involving evaluating healthcare waste treatment devices based on different factors such as economic, environmental, technological, and social aspects. The results show that the OWCM-CODAS methodology, integrated with TNS, effectively evaluates and ranks healthcare waste treatment devices based on multiple criteria. The sensitivity analysis demonstrates the robustness of the proposed model, and the results indicate that the model's performance and the relative ranking of the alternatives are not sensitive to changes in the threshold parameter τ within the tested range.

Exact solutions for clamped spherical and cylindrical panels via a unified formulation and boundary discontinuous method

Numerous works in both recent and historical literature have concentrated on formulating theories to perform static analysis on simply-supported shell structures. However, it is worth noting that obtaining analytical solutions for clamped boundary conditions presents a strong challenge. In this paper, closed-form solutions for clamped cross-ply laminated and sandwich shells are achieved by employing a robust and hybrid methodology not previously reported in the literature. The high versatility of the Carrera Unified Formulation (CUF), based on the Equivalent-Single-Layer (ESL) description, is utilized to implement several refined shell theories. The Principle of Virtual Displacements (PVD) is utilized to derive the strong form of the governing equations in terms of displacement variables. As the main novelty, these equations are solved by the Boundary Discontinuous Fourier-based method (BDM) which provides highly accurate analytical solutions. The validity and robustness of the proposed methodology are assessed through a detailed comparison with references available in the open literature, as well as with FEM 3D results obtained with commercial software. Furthermore, the stress recovery technique is exploited to fulfill zero-stress and interlaminar continuity (IC) conditions. The findings might be useful in training artificial intelligence (AI) models, which, for instance, could facilitate the development of digital twin structures.

Impact of uncertainty in building operation patterns and electric energy demand on the design and techno-economic performance of solar photovoltaic systems in different climates

The optimal design of renewable energy systems for buildings requires accurately estimating building electric energy loads. While this energy demand highly depends on how occupants and facility managers use building systems, operation-related uncertainty is rarely accounted for in the renewable energy design workflow. This paper presents a comprehensive framework to quantify the impact of uncertainty in building operation patterns and electric demand on the techno-economic performance of grid-connected photovoltaic (PV) systems (with and without battery storage). A hybrid methodology is proposed, combining and comparing two approaches to studying building performance under uncertainty: (i) physics-based building performance simulations coupled with parametric variations of occupant behavioral profiles (e.g., austere vs. wasteful), and (ii) data-driven modeling using a large national building dataset. The approach is illustrated and validated on small, medium, and large-sized office buildings in different climate zones (hot dry, mixed marine, and cold humid). Results show that different building operational patterns could lead up to 60% increase in building electric demand, which translated to similar increases in PV energy capacity and the corresponding capital costs of the systems. The findings emphasize the urgent need to better account for uncertainty in building operational patterns in the design workflows of buildings with PV generation and energy storage capabilities.

Strategies for economic sustainability: An empirical study on Muri, Mura, and Muda in the readymade garment sector

Achieving economic sustainability in the garment manufacturing industry necessitates the implementation of several strategic measures. Basic strategies like adoption of automation, utilization of sustainable energy sources, diversification of markets and products, enhancement of supply chain resilience, etc. lead to the attainment of economic sustainability in the garment manufacturing industry. Additionally, the underlying component of these strategies for ensuring economic sustainability is the minimization of process waste, which can be effectively achieved through the application of lean manufacturing principles, specifically targeting the elimination of Muri, Mura, and Muda. This strategic commitment ensures business longevity amid evolving industrial landscapes, fostering innovation and competitiveness. In emerging economies like Bangladesh, pinpointing precise approaches to reduce waste is vital. This study explores into Muri, Mura, and Muda in the RMG sector, utilizing Pareto analysis, Fuzzy theory, Total Interpretative Structural Modeling (TISM), and Matriced’ Impacts Cruoses Multiplication Applique an un Classement (MICMAC) analysis. After the initial identification of 21 (twenty) factors, Pareto analysis pinpointed the primary 16 (sixteen) factors. Subsequently, these factors underwent analysis through fuzzy TISM and fuzzy MICMAC. The results highlighted “Demand variation”, “Supplier variation”, “Workforce variation”, and “Energy supply variation” as the most crucial factors. The novelty of this study lies in exploring Muri and Mura factors in correlation with Muda employing the existing hybrid and effective methodology that combines Pareto analysis, Fuzzy MICMAC, and Fuzzy TISM methodologies. It offers fresh perspectives on their significance for economic sustainability in the garment sector. Prior research has not explored this integrated approach to reduce process waste by addressing Muri and Mura factors in emerging economies’ garment industries. This research is poised to significantly impact waste reduction in the RMG sector, enhancing competitiveness, appealing to environmentally conscious consumers, and ensuring industry standards adherence essential for sustained success. The contribution of this research is grounded in helping the practitioners and entrepreneurs in developing nations make strategic choices that will lead to the RMG sector’s resilience and, ultimately, economic sustainability.

A Hybrid Analysis of Brushless DC Motor

Brushless DC (BLDC) motors and derives have gained popularity because of numerous advantages. This motor application is achievable since permanent magnet (PM) technology has advanced. It has higher efficiency, reliability, and power with less maintenance due to the absence of brushes. A higher torque-to-mass ratio and long life are two of the most attractive characteristics making it appropriate for high-performance applications. This study describes the hybrid methodology for analyzing a three-phase, four-pole, 1500 W, brushless DC (BLDC) motor with an inner rotor. PI controllers and PWM in Matlab /Simulink, and the chopped current control in Maxwell 2d ae used. BLDC motor modeled by rotation machine export (RMxprt) analytical software and analyzed with a finite element method (FEM) Maxwell 2D software to calculate motor performance, such as torque, speed, and efficiency. The FEM results were verified by comparing them with the results taken from the Matlab/Simulink program and with the aid of the RMxprt software to supply some missing data. The motor torque and efficiency results from Maxwell 2D and Matlab show good agreement. A hybrid FEM-analytical approach is successfully applied to study a BLDC motor using three software packages RMxprt, Maxwell 2D, and Matlab/Simulink despite the lack of motor test data. The RMxprt program offers missing data like stator resistance, stator inductance, and torque constant. It is provided in the design sheet to help us with motor modeling. The successful adoption of the proposed hybrid FEM-analytical methodology will provide a good starting point for future BLDC motor research work

Innovation in Compensation Payments

The growing economic influence of cryptocurrency and the development of the associated infrastructure has brought about an interest in the new areas of its application. Payment of compensation in cryptocurrency is one such evolving application of cryptocurrency. Using a qualitative research design, we attempt to identify the factors and ecosystem constituents that play an important role in the diffusion, adoption and use of cryptocurrency as a compensation medium. A hybrid methodology involving both inductive and deductive methods of qualitative inquiry was used to develop the themes. The study identified nine main factors that influenced a participant’s decision to accept compensation in cryptocurrency. They are: (1) the prospects of high return; (2) ease of transaction; (3) faster international transactions; (4) price volatility of cryptocurrencies; (5) threat of hacking; (6) taxation policies of the country; (7) lack of recognition as legal tender; (8) influence of peer groups; and (9) influence of celebrities. The inductive part of the study enabled the mapping of the major stakeholders involved in the decision, namely, the government, the employer, the peer groups of the employee, celebrities and the cryptocurrency-issuing company.

12 Conversational Archetypes for Human-AI Interaction

Artificial Intelligence (AI), once exclusive to sophisticated technological spheres, now plays a transformative role across all aspects of society, driving significant progress and innovation. In this backdrop, basic conversational interface aka chat emerged as the easiest, and the simplest way to interact with AI systems. However, the current Human-AI conversations are fraught with a host of challenges necessitating a critical exploration into their design, approach, and implications. As AI technologies continue to permeate our lives, the need for seamless, intuitive, and human-like conversations is amplified. While our larger research embarks on a research study to suggest a conceptual framework to help design more effective and engaging Human-AI conversations, this paper focuses on a critical aspect that surfaced as a primary gap during our literature review. Conversations are effective and engaging only when their fundamental purpose is identified and understood by their participants. Hence, formulating a purpose driven conversational typology emerged as a key design imperative to inform an array of frameworks that could help create meaningful Human-AI conversations. This study evaluates a dataset of over hundred Human-AI and Human-to-Human conversations, proposing twelve conversational archetypes central to a conceptual framework intended to enhance Human-AI conversations. Employing a hybrid methodology that integrates content analysis with case study research, this paper examines the issue from a human perspective. It aims to provide a useful resource for designers, developers, researchers, and industry professionals who seek to foster deeper connections and trust in human-AI interactions.

Significance of concurrent evaluation of HER2 gene amplification and p53 and Ki67 expression in gastric cancer tissues.

The primary objective of this study is to explore the significance of concurrent evaluation of HER2 gene amplification and p53 and Ki67 expression in gastric cancer tissues. Fluorescence in situ hybridization (FISH) and immunohistochemistry (IHC) methodologies were used to detect HER2 gene amplification, as well as the expression levels of HER2, p53, and Ki67 proteins, across a group of 78 gastric cancer cases. The expression rate of the HER2 protein was determined to be 43.6% (34/78), with 17.9% (14/78) categorized as HER2 protein 3 + , 14.1% (11/78) as HER2 protein 2 + , and 11.5% (9/78) as HER2 protein 1 + . Using FISH technology, the HER2 gene amplification rate was identified as 19.2% (15/78), including 3 cases of HER2 gene cluster amplification, 5 cases of large granular amplification, 4 cases of punctate amplification, and 3 cases of high polysomy. The positive rate of p53 in gastric cancer cells was 52.6% (41/78), with 62.8% (49/78) of patients exhibiting a ki67 proliferation index ≤ 30, and 37.2% (29/78) accounting for a ki67 proliferation index > 30. The expression rates of the HER2 gene, p53, and ki67 in gastric cancer tissues were significantly associated with both gastric cancer staging and lymph node metastasis (P < 0.05). The HER2 gene amplification rate and gene copy number exhibit a positive correlation with the expression rates of p53 and ki67. Combining these assessments can provide crucial insights into the assessment of metastatic potential, disease progression, and prognosis of gastric tumor cells. This holds paramount importance in steering the formulation of individualized treatment strategies.

Forecasting deep learning-based risk assessment of vector-borne diseases using hybrid methodology.

Dengue fever is rapidly becoming Malaysia's most pressing health concern, as the reported cases have nearly doubled over the past decade. Without efficacious antiviral medications, vector control remains the primary strategy for battling dengue, while the recently introduced tetravalent immunization is being evaluated. The most significant and dangerous risk increasing recently is vector-borne illnesses. These illnesses induce significant human sickness and are transmitted by blood-feeding arthropods such as fleas, parasites, and mosquitos. A thorough grasp of various factors is necessary to improve prediction accuracy and typically generate inaccurate and unstable predictions, as well as machine learning (ML) models, weather-driven mechanisms, and numerical time series. In this research, we propose a novel method for forecasting vector-borne disease risk using Radial Basis Function Networks (RBFNs) and the Darts Game Optimizer (DGO) algorithm. The proposed approach entails training the RBFNs with historical disease data and enhancing their parameters with the DGO algorithm. To prepare the RBFNs, we used a massive dataset of vector-borne disease incidences, climate variables, and geographical data. The DGO algorithm proficiently searches the RBFN parameter space, fine-tuning the model's architecture to increase forecast accuracy. RBFN-DGO provides a potential method for predicting vector-borne disease risk. This study advances predictive demonstrating in public health by shedding light on effectively controlling vector-borne diseases to protect human populations. We conducted extensive testing to evaluate the performance of the proposed method to standard optimization methods and alternative forecasting methods. According to the findings, the RBFN-DGO model beats others in terms of accuracy and robustness in predicting the likelihood of vector-borne illness occurrences.

Time-fractional lorenz type chaotic systems with asymmetric gaussian uncertainty: series solutions via extended He-Mohand algorithm in fuzzy-caputo sense

In this paper, modeling and analysis of 3D fuzzy-fractional Lorenz type systems is presented. System under-consideration includes classical Lorenz, Chen and Burke-Shaw chaotic systems. Asymmetrical Gaussian fuzzy logic with fractional calculus is applied to model complex systems with intricate patterns. The focus of this study is fuzzy-fractional modeling and simulations. For solution purpose, a hybrid perturbation method is introduced where standard homotopy perturbation method (HPM) is enhanced by incorporating Mohand transform in fuzzy-Caputo sense. This hybrid mechanism provides an efficient way to find solutions in fuzzy-fractional environment. Validity of obtained solutions is checked by computing residual errors, which ultimately confirms the convergence of applied methodology. The dynamical behavior of fuzzy-fractional chaotic models is analyzed through various 2-3D plots to represent the chaotic regions as well unpredictable trajectories at both upper and lower bounds. Fuzzy membership functions of 3D models at different values of fractional derivative are also demonstrated through 2D plots. Analysis reveals that extended hybrid methodology proves to be a valuable tool for researchers dealing with nonlinear chaotic fractional systems with fuzzy characteristics.

An Efficient Numerical Solution of a Multi-Dimensional Two-Term Fractional Order PDE via a Hybrid Methodology: The Caputo–Lucas–Fibonacci Approach with Strang Splitting

An Efficient Numerical Solution of a Multi-Dimensional Two-Term Fractional Order PDE via a Hybrid Methodology: The Caputo–Lucas–Fibonacci Approach with Strang Splitting

TransLevelSet: Integrating vision transformers with level-sets for medical image segmentation

Recently, Vision Transformers (ViTs) have emerged as a breakthrough in computer vision and image analysis. Still, their exceptional performance depends on the availability of large amounts of annotated training data and the availability of considerable computational resources. This naturally raises the risk of overfitting and limited generalization capability in settings with limited training data. Aiming to cope with this issue, we propose the Level-Set Transformer (TransLevelSet), a hybrid methodology that encompasses an additional term in the loss function used in the ViT learning process, which has been originally defined in the context of Level-Set (LS) deformable models. This loss term avails the spatial information obtained by the level-set energy terms for image segmentation and mitigates the dependency of ViTs on the amount of available data. Moreover, this level-set loss promotes smooth and topologically consistent demarcation of structures, taking advantage of the capacity of ViTs to capture complex spatial relationships and contextual information. The main contributions of this work include: a) a pioneering approach to the integration of ViTs with level-sets; and, b) the application of the proposed methodology on two case studies related to cancer, namely the malignant melanoma, and colon cancer. We evaluate TransLevelSet on three different publicly available benchmark datasets for medical image segmentation, that include dermoscopic and histopathological images. The results of the experiments demonstrate consistent gains in terms of generalization capability introduced by the LS terms.

Political Economy of STI in China: Analyzing Official Discourse on Science, Technology and Innovation-Driven Development in the Contemporary China

Science, technology, and Innovation (STI) have been the cornerstone of China’s Reform and Opening-up processes. Employing a hybrid methodology, including textual analysis, this paper asserts that four decades of reform and opening-up have witnessed STI’s pivotal role across sectors despite numerous challengesб such as economic slowdown, growing disparities, environmental issues, and a huge burden on the state-owned enterprises. China’s substantial investments in the Fourth Industrial Revolution technologies, including Artificial Intelligence and New Energy Vehicles, exemplify its commitment to innovation, reflected in over 2.5% of GDP allocated for research and development in 2022. This robust investment has bolstered China’s innovative capabilities and brought about its high ranking on the Global Innovation Index. In Chinese STI politics and policy-making, the programs like MLP-2006, SEI-2010 and Made in China 2025 have created a watershed moment. Three central research questions guide our exploration: the trajectory of policy framing on STI-Driven development, the theoretical underpinnings of Innovation-Driven Development and Green Development in Chinese STI politics, and the significance of these paradigms in China’s context. This paper also hypothesizes the emergence of two distinct trajectories within China’s STI politics through the adoption of Innovation-Driven Development and Green Development, positioning STI at the core of China’s development paradigm. The study thoroughly dissects China’s official discourse, framing these paradigms within the Sustainable Development context and highlighting their crucial roles in China’s journey toward technological advancement and sustainability. The analysis of the evolution of China’s STI policy as portrayed in official discourse offers insights into the strategic role played by science, technology, and Innovation in moulding China’s socio-economic trajectory alongside global implications stemming from its transformative development agenda.

Tridimensional porosity modeling through fuzzy logic and geostatistics

The three-dimensional porosity simulation plays a pivotal role in the exploration and prospecting of oil fields. In this study, we introduce a hybrid methodology for subsismic resolution porosity estimation, combining algorithms based on fuzzy logic and geostatistics. We demonstrate how it is possible to use simulated facies association surfaces and structural surfaces as input parameters for the fuzzy logic algorithm to derive porosity trends, subsequently refined using simple kriging with magnetic resonance log obtained from wells. The selected simulation area is the Sapinhoá field, located in the Santos Basin, Brazil, covering the age interval from 123 Ma to 113 Ma. To statistically validate the results, we employed the Pearson correlation coefficient, along with graphs comparing the measured and simulated porosity in the wells. The obtained results showed satisfactory levels of accuracy in the evaluated wells. Moreover, in areas lacking well data, the simulated porosity volumes aligned with the trends modeled using fuzzy logic.

Feature Selection for Data Classification in the Semiconductor Industry by a Hybrid of Simplified Swarm Optimization

In the semiconductor manufacturing industry, achieving high yields constitutes one of the pivotal factors for sustaining market competitiveness. When confronting the substantial volume of high-dimensional, non-linear, and imbalanced data generated during semiconductor manufacturing processes, it becomes imperative to transcend traditional approaches and incorporate machine learning methodologies. By employing non-linear classification models, one can achieve more real-time anomaly detection, subsequently facilitating a deeper analysis of the fundamental causes behind anomalies. Given the considerable dimensionality of production line data in semiconductor manufacturing, there arises a necessity for dimensionality reduction to mitigate noise and reduce computational costs within the data. Feature selection stands out as one of the primary methodologies for achieving data dimensionality reduction. Utilizing wrapper-based heuristics algorithms, although characterized by high time complexity, often yields favorable performance in specific cases. If further combined into hybrid methodologies, they can concurrently satisfy data quality and computational cost considerations. Accordingly, this study proposes a two-stage feature selection model. Initially, redundant features are eliminated using mutual information to reduce the feature space. Subsequently, a Simplified Swarm Optimization algorithm is employed to design a unique fitness function aimed at selecting the optimal feature subset from candidate features. Finally, support vector machines are utilized as the classification model for validation purposes. For practical cases, it is evident that the feature selection method proposed in this study achieves superior classification accuracy with fewer features in the context of wafer anomaly classification problems. Furthermore, its performance on public datasets further substantiates the effectiveness and generalization capability of the proposed approach.

Characterization of Co–Ni–TiO2 coatings prepared by combined sol-enhanced and pulse current electrodeposition methods

Abstract This research comprehensively explores the synthesis of Co–Ni–TiO2 coatings employing a hybrid methodology that integrates sol-enhanced and pulse current electrodeposition techniques. The investigation examined the surface morphology and intrinsic properties of Co–Ni–TiO2 coatings, revealing the significant influence of pulse duty cycle variations on the characteristics of coatings. A detailed analysis indicates that a pulse duty cycle of 0.4 optimized the coating’s performance, offering superior attributes compared to other duty cycle settings. The study elucidates that lower duty cycles foster hydrogen evolution reactions on the cathode surface, culminating in the formation of a porous, needle-like coating structure. Conversely, higher duty cycles are found to mitigate the effects of material replenishment, thereby affecting the coating’s quality and performance. The findings of this investigation not only shed light on the critical relationship between the pulse duty cycle and the properties of Co–Ni–TiO2 coatings but also lay a foundational framework for the further refinement and optimization of these coatings for advanced applications.

NSGA-II based short-term building energy management using optimal LSTM-MLP forecasts

To conduct analysis on the field of electricity management in buildings is crucial to contribute to the clean energy promotion, energy efficiency, and resilience against climate change. This manuscript proposes a methodology for modeling a predictive and calibrated energy management system (EMS) using a hybrid methodology that combines long short-term memory and multilayer perceptron models (LSTM-MLP) optimized by non-dominated sorting genetic algorithm II (NSGA-II). The proposed approach utilizes global forecast system (GFS) data to anticipate energy consumption fluctuations and optimize the use of distributed energy sources, such as photovoltaic (PV) production, based on knowledge of the electricity prices in the free market one day ahead. This energy trade-off in the building is conducted with NSGA-II, guaranteeing the exploration and the exploitation of energy in the building while minimizing energy costs and energy wastes. The research carried out demonstrates the effectiveness of the hybrid LSTM-MLP model and the advantages of NSGA-II in hyperparameter tuning and in energy balance for sustainable building practices. The methodology conducted is tested in an existing building, the Industrial Engineering School located on the Campus Lagoas-Marcosende of the Universidade de Vigo, Spain.

Supporting healthy lifestyles for First Nations women and communities through co-design: lessons and early findings from remote Northern Australia.

The period before, during, and after pregnancy presents an opportunity to reduce diabetes-related risks, which in Australia disproportionately impact Aboriginal and Torres Strait Islander women. Collaboration with Aboriginal and Torres Strait Islander women/communities is essential to ensure acceptability and sustainability of lifestyle modifications. Using a novel co-design approach, we aimed to identify shared priorities and potential lifestyle strategies. We also reflected on learnings from this approach. We conducted 11 workshops and 8 interviews at two sites in Australia's Northern Territory (Central Australia and Top End), using experience-based co-design (EBCD) and incorporating principles of First Nations participatory research. Workshops/interviews explored participant' experiences and understanding of diabetes in pregnancy, contextual issues, and potential lifestyle strategies. Participants included three groups: 1) Aboriginal and Torres Strait Islander women of reproductive age (defined as aged 16-45 years); 2) Aboriginal and Torres Strait Islander community members; and 3) health/community services professionals. The study methodology sought to amplify the voices of Aboriginal women. Participants included 23 women between ages 16-45 years (9 with known lived experience of diabetes in pregnancy), 5 community members and 23 health professionals. Key findings related to identified priority issues, strategies to address priorities, and reflections on use of EBCD methodology. Priorities were largely consistent across study regions: access to healthy foods and physical activity; connection to traditional practices and culture; communication regarding diabetes and related risks; and the difficulty for women of prioritising their health among competing priorities. Strategies included implementation of a holistic women's program in Central Australia, while Top End participants expressed the desire to improve nutrition, peer support and community awareness of diabetes. EBCD provided a useful structure to explore participants' experiences and collectively determine priorities, while allowing for modifications to ensure co-design methods were contextually appropriate. Challenges included the resource-intensive nature of stakeholder engagement, and collaborating effectively with services and communities when researchers were "outsiders". A hybrid methodology using EBCD and First Nations participatory research principles enabled collaboration between Aboriginal women, communities and health services to identify shared priorities and solutions to reduce diabetes-related health risks. Genuine co-design processes support self-determination and enhance acceptability and sustainability of health strategies.