Threefold Approach Research Articles

AI enabled business decisions that enhance sustainability impact of an apparel and fashion supply chain

ABSTRACT This paper highlights the implications of leveraging artificial intelligence (AI) to enhance business decision making that has a simultaneous impact in strengthening sustainability initiatives in the apparel and fashion industry. This paper provides a detailed understanding of how AI implemented for procurement, designing, manufacturing and distribution decisions can impact the state of sustainability in organisations. A threefold approach is adopted to provide academic and industry insights. The first section summarises the existing state of technology and AI in the apparel and fashion industry. The existing literature is reviewed based on focused research issues of apparel supply chain and the AI-based methodologies. The second section focuses on gathering industry insights and summarises the findings from experts across procurement, design, manufacturing, distribution and retail. A qualitative research approach is applied with 11 semi-structured in-depth interviews from 5 high end fashion retailers who have implemented AI in designing, manufacturing and selling. The third section provides a foundation for achieving sustainability goals through AI enabled decision making. Research findings reveal that AI can be leveraged to create three main sustainability impacts in the apparel and fashion industry: (i) waste reduction due to process and material efficiency, (ii) reduced discards due to process improvements and (iii) recyclability.

A Threefold Approach for Enhancing Fuzzy Interpolative Reasoning: Case Study on Phishing Attack Detection Using Sparse Rule Bases

Fuzzy systems are powerful modeling systems for uncertainty applications. In contrast to traditional crisp systems, fuzzy systems offer the opportunity to extend the binary decision to continuous space, which could offer benefits for various application areas such as intrusion detection systems (IDSs), because of their ability to measure the degree of attacks instead of making a binary decision. Furthermore, fuzzy systems offer a suitable environment that is able to deal with uncertainty. However, fuzzy systems face a critical challenge represented by the sparse fuzzy rules. Typical fuzzy systems demand complete fuzzy rules in order to offer the required results. Additionally, generating complete fuzzy rules can be difficult due to many factors, such as a lack of knowledge base or limited data availability, such as in IDS applications. Fuzzy rule interpolation (FRI) was introduced to overcome this limitation by generating the required interpolation results in cases with sparse fuzzy rules. This work introduces a threefold approach designed to address the cases of missing fuzzy rules, which uses a few fuzzy rules to handle the limitations of missing fuzzy rules. This is achieved by finding the interpolation condition of neighboring fuzzy rules. This procedure was accomplished based on the concept of factors (which determine the degree to which each neighboring fuzzy rule contributes to the interpolated results, in cases of missing fuzzy rules). The evaluation procedure for the threefold approach was conducted using the following two steps: firstly, using the FRI benchmark numerical metrics, the results demonstrated the ability of the threefold approach to generate the required results for the various benchmark scenarios. Secondly, using a real-life dataset (phishing attacks dataset), the results demonstrated the effectiveness of the suggested approach to handle cases of missing fuzzy rules in the area of phishing attacks. Consequently, the suggested threefold approach offers an opportunity to reduce the number of fuzzy rules effectively and generate the required results using only a few fuzzy rules.

Exit with My Colleagues: Exploring Collaborative Career Change of Journalists to High-Tech Roles

ABSTRACT This empirical study contributes to the existing body of research on journalists leaving their profession due to challenging working conditions, inadequate compensation, and heightened levels of stress. By employing a three-fold research approach, encompassing in-depth interviews, the Walkthrough Method on messaging forums, and a descriptive survey, this paper presents novel findings on the exit process and sheds light on the collaborative aspect of journalists transitioning to high-tech alternative careers. Through interviews with current and former journalists who have successfully shifted to the high-tech industry, the study reveals the underlying motivations driving this career transition and uncovers the unexpected network of support facilitating journalists’ departure from journalism. Additionally, this research raises concerns about the potential implications of this significant exodus in the field of journalism, highlighting the need for further examination and attention to this issue.

The Application of TiO2/ZrO2-Modified Nanocomposite PES Membrane for Improved Permeability of Textile Dye in Water.

This study investigates the modification of polyethersulfone (PES) membranes with 1 wt% titanium dioxide (TiO2), zirconium dioxide (ZrO2) and a nanocomposite of TiO2/ZrO2. The aim was to efficiently remove Rhodamine B (RhB) from water using a threefold approach of adsorption, filtration and photodegradation. Among the modified membranes (TiO2, ZrO2 and TiO2/ZrO2), the TiO2/ZrO2-PES nanocomposite membrane showed a better performance in rejection of RhB than other membranes with the rejection efficiency of 96.5%. The TiO2/ZrO2-PES membrane was found to possess a thicker selective layer and reduced mean pore radius, which contributed to its improved rejection. The TiO2/ZrO2 nanocomposite membrane also showed high bulk porosity and a slightly lower contact angle of 69.88° compared to pristine PES with a value of 73°, indicating an improvement in hydrophilicity. Additionally, the TiO2/ZrO2-PES nanocomposite membrane demonstrated a relatively lower surface roughness (Sa) of 8.53 nm, which offers the membrane antifouling properties. The TiO2/ZrO2-PES membrane showed flux recovery ratio (FRR), total fouling (Rt), reversible fouling (Rr) and irreversible fouling (Rir) of 48.0%, 88.7%, 36,8% and 52.9%, respectively. For the photocatalytic degradation performance, the removal efficiency of RhB followed this order TiO2 > TiO2/ZrO2 > ZrO2 (87.6%, 85.7%, 67.8%). The tensile strength and elongation were found to be compromised with the addition of nanoparticles and nanocomposites. This indicates the necessity to further modify and optimise membrane fabrication to achieve improved mechanical strength of the membranes. At low pressure, the overall findings suggest that the TiO2/ZrO2 nanocomposite has the potential to offer significant improvements in membrane performance (water flux) compared to other modifications.

Artificial intelligence model for enhancing the accuracy of transvaginal ultrasound in detecting endometrial cancer and endometrial atypical hyperplasia

ObjectivesTransvaginal ultrasound is typically the initial diagnostic approach in patients with postmenopausal bleeding for detecting endometrial atypical hyperplasia/cancer. Although transvaginal ultrasound demonstrates notable sensitivity, its specificity remains limited. The objective...

Deep learning approaches for assessing pediatric sleep apnea severity through SpO2 signals

Pediatric Sleep Apnea–Hypopnea (SAH) presents a significant health challenge, particularly in diagnostic contexts, where conventional Polysomnography (PSG) testing, although effective, can be distressing for children. Addressing this, our research proposes a less invasive method to assess pediatric SAH severity by analyzing blood oxygen saturation (SpO2) signals. We adopted two advanced deep learning architectures, namely ResNet-based and attention-augmented hybrid CNN-BiGRU models, to process SpO2 signals in a one-dimensional (1D) format for Apnea–Hypopnea Index (AHI) estimation in pediatric subjects. Employing the CHAT dataset, which includes 844 SpO2 signals, the data was partitioned into training (60%), testing (30%), and validation (10%) sets. A predefined validation subset was randomly selected to ensure the models' robustness via a threefold cross-validation approach. Comparative analysis revealed that while the ResNet model attained an average accuracy of 72.9% across four SAH severity categories with a kappa score of 0.57, the CNN-BiGRU-Attention model demonstrated superior performance, achieving an average accuracy of 75.95% and a kappa score of 0.63. This distinction underscores our method's efficacy in both estimating AHI and categorizing SAH severity levels with notable precision. Further, to evaluate diagnostic capabilities, the models were benchmarked against common AHI thresholds (1, 5, and 10 events/hour) in each test fold, affirming their effectiveness in identifying pediatric SAH. This study marks a significant advance in the field, offering a non-invasive, child-friendly alternative for pediatric SAH diagnosis. Although challenges persist in accurately estimating AHI, particularly in severe cases, our findings represent a critical stride towards improving diagnostic processes in pediatric SAH.

Towards a QBLM-Based Qualification-Management Methodology Supporting Human-Resource Management and Development

This position paper presents a novel perspective on addressing the challenges of digital transformation in higher education through the development of a qualification-based learning model (QBLM) qualification management methodology. It argues that the rapid pace of technological advancement and the resulting need for continuous upskilling and reskilling necessitate a more dynamic and adaptive approach to human-resource management and development. The paper posits that by extending QBLM through the integration of artificial intelligence (AI) and machine learning (ML), a more effective system for analyzing competence requirements and designing personalized learning pathways can be created. The paper proposes a three-fold approach: (1) developing the FPHR ontology to support semantic annotation of HR qualifications in higher-education institutions (HEIs), (2) integrating this ontology into QBLM to ensure the machine-readability of qualifications, and (3) modeling a knowledge-based production process for HRs in skills-based learning. This paper outlines the current state of the art, presents conceptual models, and describes planned proof-of-concept implementations and evaluations. It contends that this approach will significantly enhance the effectiveness of human-resource development in the rapidly evolving digital knowledge society. By presenting this position, the paper aims to stimulate discussion and collaboration within the academic community on innovative approaches to qualification management in higher education. The work addresses critical issues arising from technological development and offers a forward-thinking solution to bridge the gap between current and future skill requirements in industry and academia.

Physical and Spiritual Nourishment in the Catechetical Homilies of John Chrysostom

This article explores the previously underexamined dimension of physical and spiritual nourishment in John Chrysostom’s catechetical homilies, addressing two central inquiries: 1) Chrysostom’s expectations for new church members’ approach to eating and drinking, and 2) the connection between nourishment and their life as members of the liturgical community. Through a systematic analysis, the study reveals a threefold approach to Question 1. Firstly, Chrysostom cautions against the abuse of sustenance, emphasizing its corruptive impact on both body and soul. Secondly, the author expounds upon the functions of nutritional moderation, using the concept of fasting as an image of salutary abstinence from sin. Thirdly, Chrysostom discusses spiritual nourishment, distributed through homiletical discourse and the Eucharist. Addressing Question 2, the study finds connections between hymnody and nutritional moderation, promoting an “angelic” lifestyle that prepares individuals for deeper spiritual nourishment. The article concludes by highlighting the universal applicability of Chrysostom’s teachings on nourishment, intended for all members of the Church, regardless of their level of spiritual maturity, guiding them from moderate consumption of physical sustenance to participation in spiritual nourishment and the pursuit of eternal life.

Religion and Justice – from Leviticus to Lily

Abstract This article was a memorial lecture to the author's father, Rabbi Harry Jacobi, and begins with a tribute to his commitment to justice. It traces the concept of justice and its application from Leviticus to the Talmud to Lily Montagu. It suggests three models of approaching justice. In Leviticus, the principle of justice is clear and its application radical, especially in the concept of the Jubilee year. In the Talmud, the complexity of justice is addressed. Examples are given of debates about disputed possession, compensation and taxation. Finally, a biography of Lily Montagu and examples of her work are presented to show how she put the theory of justice into practice. It is suggested that a threefold approach to building justice is needed: a strong sense of justice, an acknowledgement of the complexities and a commitment to actively working for justice.

Factors of Authenticity: Exploring Santorini’s Heritage Hotels

The purpose of this article is to investigate the factors that influence the authenticity of heritage hotels in popular tourist destinations. Using the Greek island of Santorini as a case study, the following three (3) factors, which have not been systematically studied so far, are examined and appear to have a significant impact on authenticity in the conversion of a heritage architectural building into a heritage hotel: (a) its structural characteristics, (b) the influence of the star classification system and (c) the extent to which each business promotes authenticity elements and heritage identity. For the purposes of this study, a threefold methodological approach was conducted, which includes archival research in the registry of the Hellenic Chamber of Hotels for all the heritage hotels in Santorini (69 units), research in the accounting data of the island’s heritage hotels certified with the national star ranking system for their services and amenities and research analysis of the information regarding the promotion of the heritage hotels through their official websites. Additionally, a cartographic representation of the locations of these hotels was created and their positioning was compared to the boundaries of traditional or non-traditional settlements. The results validated the basic finding of the literature review, that the authenticity of a heritage hotel is a construction under constant negotiation, influenced by a multitude of factors. The conversion of a historic building into a heritage hotel is a multidimensional process that requires a delicate balance between preserving cultural value and adapting to the needs of modern tourism, as well as a continuous evaluation and review of the policies in place.

Exploring Child Standpoint Theory in Early Childhood Education

This empirical study in Bangladesh explores the potential of Child Standpoint Theory in constructing and reconstructing the child in early childhood education (ECE) and its role in facilitating cross-cultural comparisons in and of ECE systems. The comparative gaze is considered for ways of scholarly investigation in the context of ECE system messiness. The paper suggests viewing children as relational ethnographic units of comparisons for comparing the conditionality, contextual elements, and temporality of each child's education across cultures through a three-fold approach. Spanning method and theory, the approach combines the notion of the entangled researcher and the comparative case study tool of tracing with Child standpoint theory. Findings are presented through a comprehensive visualization of a ‘child’ going through the ECE system during a day as a pathway to deeper analysis of facets underpinning ECE from a bottom-up rather than top-down approach.

Modelling the water supply-demand relationship under climate change in the Buffalo River catchment, South Africa

Climate change strains the global water supplies’ capability to meet demands, especially in regions like South Africa, where resources are already scarce. The interconnectedness of water, energy, and food (WEF) exacerbates this challenge, amplifying the impact of climate change on water resource management across these sectors. Thus, in strengthening the long-term resilience and reliability of water resources, a necessity in South Africa, research on climate change and the WEF nexus is needed for water resource planning and development. Employing the WEF nexus approach, we applied the Climate Land-Use Energy and Water Strategies (CLEWS) modelling framework to assess climate change impacts on the water supply-demand relationship, considering the domestic, agriculture (irrigation) and energy generation sectors, and adopting the Buffalo River catchment, KwaZulu-Natal, South Africa, as a case study. A threefold approach was utilized: (1) water supplies and demands and the total unmet demands were quantified; (2) the percentages of water demands covered per sector were derived; and (3) the reliability of the water system to meet each sector’s water demands was computed. The findings projected slight decreases (2%) in the Buffalo River catchment’s total water demands towards the end of the 21st century, mainly due to changes in land suitability for agriculture. While the water system is projected to be reliable for highly populated municipalities (demand coverage index > 70%; reliability index ≥ 20%), it is unreliable for sparsely populated and agriculturally intensive municipalities (demand coverage index ≤ 12%; reliability index = 0%). Such unreliability will strain agricultural production as more than 70% of irrigation water demands come from these municipalities. Nexus-smart water allocation and capacity development plans are recommended to manage these challenges and ensure a just and sustainable water supply-demand relationship in light of climate change.

Wanghong e-commerce in/as China’s economic transformation: A case study of beauty wanghong

This article examines the crucial encounter between wanghong and e-commerce in the specific process of China’s platformization. We develop a threefold (macro-meso-micro) approach that combines perspectives from political economy, critical industry studies, and ethnographic research to identify and unpack the heterogeneous actors and actions in the evolution of wanghong e-commerce, using beauty wanghong as a case study. Drawing upon document studies (146 documents between 2001 and 2022) and 21 semi-structured interviews (supplemented by ethnographic field observations over seven months in 2018), we argue that: first, the contrast between strong consumer demand (activated by beauty wanghong) and poorly developed retail and distribution channels in the Chinese beauty industry provides a precondition for the emergence of beauty wanghong e-commerce; second, e-commerce platform Alibaba has boosted and institutionalized the convergence of wanghong and e-commerce, developing a new “social commerce model” that integrates social networking with entertainment in the context of e-commerce transactions; finally, China’s ongoing economic transformation has created possibilities and challenges for wanghong e-commerce and energized this new “social commerce” business model. The articulation of the wanghong and e-commerce is a result—and also a stage—of the integration of the manufacturing industry and platform economy in China. It is a consequence, yet an embodiment of China’s economic transformation.

Social Processes of Public Sector Collaborations in Kenya: Unpacking Challenges of Realising Joint Actions in Public Administration

AbstractSocial processes behind the success or failure of collaborative implementation frameworks in African public administration contexts are under-researched. This paper addresses this gap by paying particular attention to trust attributes in collaborative implementation arrangements in Kenya. It shows how implementation challenges of policy programs and interventions may be linked to these interventions’ social characteristics in the public sector. The paper draws on a threefold approach of mutual trust and administrative data on public sector collaborative implementation arrangements for Kenyan anti-corruption policy like the Kenya Leadership Integrity Forum. Findings show that despite increased efforts to realise joint actions in public sector collaborative arrangements, they remain primarily symbolic and hierarchical and feature loose social cohesion among actors, producing challenges bordering on deficiencies in social processes of implementation. These include politicised aloofness or lack of commitment, unclear governance structures, coordination deficiencies, inter-agency conflicts, layered fragmentations, and overlapping competencies among different agencies. The paper recommends identifying and nurturing socially sensitive strategies embedded in mutual trust, like informal knowledge-sharing channels, to address primarily mandated public sector collaboration challenges in Kenya. Such efforts should consider systematic training and incentivising public managers to think outside inward-looking organisational cultures, allowing them to devise sustainable collaborative implementation approaches (promote open innovation) for policy programs, particularly anti-corruption policy.

Synthesis and Properties of a Strained Triple Nanohoop.

A strained triple nanohoop with a shared central benzene unit is synthesized using a threefold intramolecular ring-closing approach. Among the five possible constitutional isomers, the isomer with the highest D3h symmetry is isolated, the structure of which contains three nanohoop blades and a central hexaphenylbenzene unit. The structure is elucidated using NMR spectroscopy and mass spectrometry. The optical and electrochemical properties are investigated, revealing a moderate fluorescence quantum yield of 40 %. A water-soluble nanomaterial is prepared using a nanoparticle encapsulation method, and a fluorescence quantum yield of 10 % is retained, which demonstrates the potential of the nanomaterial in biological systems.

Feasibility, acceptability and preliminary effect of a community-led HIV self-testing model among adolescent girls and young women in Rural Northern Uganda: a quasi-experimental study protocol

BackgroundAdolescent girls and young women (AGYW) in sub-Saharan Africa face a disproportionately higher HIV/AIDS burden despite the global decline in incidence. Existing interventions often fail to adequately address their unique social, economic, and cultural challenges, limiting access to essential HIV/AIDS services, including HIV testing. Emerging evidence indicates that HIV self-testing, a user-friendly and confidential method, enhances HIV diagnosis and linkage to care by targeting these barriers. This study aims to assess the feasibility, acceptability, and preliminary impact of a peer-delivered, community-health worker (CHW)-facilitated HIV self-testing intervention for AGYW in Northern Uganda.MethodsThis mixed-methods quasi-experimental implementation science study will employ a three-fold approach. Firstly, we will conduct baseline formative qualitative research with 50 AGYW, 50 parents/partners to AGYW, 30 CHWs, 15 community leaders, and the district health office to inform the design of a peer-delivered CHW-facilitated HIV self-testing intervention tailored to AGYW’s needs in Northern Uganda. Secondly, we will implement a mixed-methods pilot study to assess the intervention’s feasibility and acceptability, involving 415 AGYW, 30 AGYW peer leaders, and 10 CHWs in selected parishes and villages in Omoro district, Northern Uganda. Lastly, we will evaluate the implementation outcomes and preliminary impact of the intervention on HIV self-testing rates and linkage to care by collecting and analyzing quantitative data pre- and post-intervention, laying the groundwork for a future robust randomized controlled trial.DiscussionOur intervention combines CHWs and peer-led strategies to address the unique challenges of AGYW in Northern Uganda, leveraging community resilience and peer influence. Successful completion of this project will provide a scalable model to be evaluated in a randomized trial and replicated in similar contexts.Trial registration numberPACTR202404851907736. Registered with the Pan-African Clinical Trials Registry on April 22, 2024.

New three red-edge vegetation index (VI3RE) for crop seasonal LAI prediction using Sentinel-2 data

Leaf area index (LAI) serves as a pivotal parameter in crop monitoring, significantly impacting agricultural applications. Empirical models are one of the commonly used methods for estimating LAI, they are often dependent on vegetation indices (VIs), predominantly derived from low-to-moderate spatial resolution satellite sensors. A critical limitation of these VIs is their tendency to saturate at elevated LAI values. Additionally, the interplay between chlorophyll content (Cab), LAI, as well as average leaf inclination angle (ALA), particularly in reflectance spectra from red to red-edge regions, has been underexplored in past research. Based on Sentinel-2 satellite, with three red-edge bands and enhanced spatio-temporal resolution, this study introduced a new three red-edge vegetation index (VI3RE), comprising NDVI3RE and CI3RE, which leverages the unique spectral characteristics of these bands and related differential response to LAI and Cab variations. We investigated VI3RE’s efficacy through a threefold approach: firstly, by conducting sensitivity analyses using noise equivalent (NE)ΔLAI ((NE) ΔLAI=1.37 and 1.59 for NDVI3RE and CI3RE; (NE)ΔLAI = 1.75 – 3.25 for other VIs) and extended Fourier amplitude sensitivity test (EFAST) (the contribution of LAI: FOI > 30 % and TOI > 40 % for VI3RE; FOI ∼ 17 % − 28 % and TOI ∼ 25 % − 34 % for other VIs, except for NDVI with TOI ∼ 50 %), we demonstrated VI3RE’s heightened sensitivity to LAI and its improved capability for seasonal LAI estimation compared to other VIs. Secondly, by comprehensively considering the simplicity, interpretability, AIC and R2 values of various models, the linear regression model was selected for analyzing the relationships between LAI and various VIs. We established that VI3RE, particularly NDVI3RE, exhibits a robust correlation with LAI, thereby enhancing LAI estimation accuracy (R2 = 0.72, RMSE = 1.39). Lastly, we applied the LAI-VI regression models to generate crop LAI imageries throughout the growing season, subsequently validating by field measured LAI data. The results affirmed VI3RE’s superior performance in seasonal LAI estimation of crops, notably during peak growth and sowing phases. We conclude that the newly formulated VI3RE offers a universal, highly precise, and reliable model for LAI prediction across various crop types and phenological stages. However, the broader application of VI3RE may be limited, due to the three red-edge bands are not commonly found in most satellite platforms. In addition, some other aspects are not considered in this study, such as phenological information, meteorological factors, sampling strategies, etc., which should be meticulously considered in the future studies.

An Innovative Methodological Approach to Analysing Social Media Movements

Social media movements take place in an increasingly volatile technological landscape. Researchers who want to analyse their spread must navigate methodological challenges relating to data accessibility, combining qualitative and quantitative data, and remaining attentive to the shifting technological affordances of social media platforms. In response to key challenges, the paper outlines an innovative, three-fold methodological approach to the analysis of social media movements integrating three strands: the Linguistic, Material, and Processual (LMP). Using the hashtag #JeSuisCharlie as a case study, the paper demonstrates how an LMP approach can provide richer insights into social media movements which would be missed by most current methods. Its low-cost design, flexible approach, and technical accessibility equips the researcher in anticipation of further change in the technical landscape. The framework outlined in the paper can be applied to other social media platforms.

Mandibular and dental measurements for sex determination using machine learning

The present study tested the combination of mandibular and dental dimensions for sex determination using machine learning. Lateral cephalograms and dental casts were used to obtain mandibular and mesio-distal permanent teeth dimensions, respectively. Univariate statistics was used for variables selection for the supervised machine learning model (alpha = 0.05). The following algorithms were trained: logistic regression, gradient boosting classifier, k-nearest neighbors, support vector machine, multilayer perceptron classifier, decision tree, and random forest classifier. A threefold cross-validation approach was adopted to validate each model. The areas under the curve (AUC) were computed, and ROC curves were constructed. Three mandibular-related measurements and eight dental size-related dimensions were used to train the machine learning models using data from 108 individuals. The mandibular ramus height and the lower first molar mesio-distal size exhibited the greatest predictive capability in most of the evaluated models. The accuracy of the models varied from 0.64 to 0.74 in the cross-validation stage, and from 0.58 to 0.79 when testing the data. The logistic regression model exhibited the highest performance (AUC = 0.84). Despite the limitations of this study, the results seem to show that the integration of mandibular and dental dimensions for sex prediction would be a promising approach, emphasizing the potential of machine learning techniques as valuable tools for this purpose.

A Human-Centered Power Conservation Framework based on Reverse Auction Theory and Machine Learning

Extreme outside temperatures resulting from heat waves, winter storms, and similar weather-related events trigger the Heating Ventilation and Air Conditioning (HVAC) systems, resulting in challenging, and potentially catastrophic, peak loads. As a consequence, such extreme outside temperatures put a strain on power grids and may thus lead to blackouts. In order to avoid the financial and personal repercussions of peak loads, demand response and power conservation represent promising solutions. Despite numerous efforts, it has been shown that the current state-of-the-art fails to consider: i) the complexity of human behavior when interacting with power conservation systems; and ii) realistic home-level power dynamics. As a consequence, this leads to approaches that are i) ineffective due to poor long-term user engagement; and ii) too abstract to be used in real-world settings. In this paper, we propose an auction-theory-based power conservation framework for HVAC designed to address such individual human component through a three-fold approach: personalized preferences of power conservation, models of realistic user behavior , and realistic home-level power dynamics . In our framework, the System Operator (SO) sends Load Serving Entities (LSEs) the required power saving to tackle peak loads at the residential distribution feeder. Each LSE then prompts its users to provide bids , i.e., personalized preferences of thermostat temperature adjustments, along with corresponding financial compensations. We employ models of realistic user behavior by means of online surveys to gather user bids and evaluate user interaction with such system. Realistic home-level power dynamics are implemented by our machine-learning-based Power Saving Predictions (PSP) algorithm, calculating the individual power savings in each user’s home resulting from such bids. A machine-learning-based Power Saving Predictions (PSP) algorithm is executed by the users’ Smart Energy Management System (SEMS). PSP translates temperature adjustments into the corresponding power savings. Then, the SEMS sends bids back to the LSE, which selects the auction winners through an optimization problem called POwer Conservation Optimization (POCO). We prove that POCO is NP-hard, and thus provide two approaches to solve this problem. One approach is an optimal pseudo-polynomial algorithm called DYnamic programming Power Saving (DYPS), while the second is a heuristic polynomial-time algorithm called Greedy Ranking Allocation (GRAN). EnergyPlus, the high-fidelity and gold-standard energy simulator funded by the U.S. Department of Energy, was used to validate our experiments, as well as to collect data to train PSP. We further evaluate the results of the auctions across several scenarios, showing that, as expected, DYPS finds the optimal solution, while GRAN outperforms recent state-of-the-art approaches.