Crowdsourcing Approach Research Articles

Combining environmental-socio-economic data with volunteer geographic information for mapping flood risk zones in Zhengzhou, Henan Province, China

Due to the occurrence of extreme weather phenomena, flooding caused by precipitation has become a frequent, widespread, and highly destructive natural disaster. For densely populated urban areas, efficient identification of people's emergency rescue needs and mapping of high flood risk areas are particularly important for decision makers to formulate disaster relief strategies. In this study, we employed a machine learning approach along with volunteer geographic information (VGI)1 data and environmental-socio-economic indicators to map the flood risk area in Zhengzhou. Firstly, the sentiment analysis tool based on artificial intelligence platform initially identified the public's emergency rescue needs. Secondly, the crowd-sourcing approach and geographical approach were used to evaluate the VGI data quality and the variable importance measures (VIMs)2 method to optimize the evaluation indicators. Lastly, the flood risk area was classified in four categories: flood environmental susceptibility, flood-induced risk, flood exposure risk, and flood mitigation capacity, subsequently resulting in a comprehensive risk map of Zhengzhou. The results showed that the accuracy of flood risk assessment increased from 85.7 % to 92.4 % after VGI quality evaluation. The most important indicators affecting flood risk assessment were population density, river system and nighttime light intensity. The comprehensive flood risk map better reflected the spatial distribution of high-risk areas in Zhengzhou. It allows emergency responders to quickly identify areas that require urgent attention.

Comparison of speech and music input in North American infants' home environment over the first 2 years of life.

Infants are immersed in a world of sounds from the moment their auditory system becomes functional, and experience with the auditory world shapes how their brain processes sounds in their environment. Across cultures, speech and music are two dominant auditory signals in infants' daily lives. Decades of research have repeatedly shown that both quantity and quality of speech input play critical roles in infant language development. Less is known about the music input infants receive in their environment. This study is the first to compare music input to speech input across infancy by analyzing a longitudinal dataset of daylong audio recordings collected in English-learning infants' home environments, at 6, 10, 14, 18, and 24 months of age. Using a crowdsourcing approach, 643 naïve listeners annotated 12,000 short snippets (10 s) randomly sampled from the recordings using Zooniverse, an online citizen-science platform. Results show that infants overall receive significantly more speech input than music input and the gap widens as the infants get older. At every age point, infants were exposed to more music from an electronic device than an in-person source; this pattern was reversed for speech. The percentage of input intended for infants remained the same over time for music while that percentage significantly increased for speech. We propose possible explanations for the limited music input compared to speech input observed in the present (North American) dataset and discuss future directions. We also discuss the opportunities and caveats in using a crowdsourcing approach to analyze large audio datasets. A video abstract of this article can be viewed at https://youtu.be/lFj_sEaBMN4 RESEARCH HIGHLIGHTS: This study is the first to compare music input to speech input in infants' natural home environment across infancy. We utilized a crowdsourcing approach to annotate a longitudinal dataset of daylong audio recordings collected in North American home environments. Our main results show that infants overall receive significantly more speech input than music input. This gap widens as the infants get older. Our results also showed that the music input was largely from electronic devices and not intended for the infants, a pattern opposite to speech input.

Designing Gestures for Data Exploration with Public Displays via Identification Studies

In-lab elicitation studies inform the design of gestures by having the participants suggest actions to activate the system functions. Conversely, crowd-sourced identification studies follow the opposite path, asking the users to associate the control actions with functions. Identification studies have been used to validate the gestures produced by elicitation studies, but not to design interactive systems. In this paper, we show that identification studies can be combined with in situ observations to design the gestures for data exploration with public displays. To illustrate this method, we developed two versions of a gesture-controlled system for data exploration with 368 users: one designed through an elicitation study, and one designed through in situ observations followed by an identification study. Our results show that the users discovered the majority of the gestures with similar accuracy across the two prototypes. Additionally, the in situ approach enabled the direct recruitment of target users, and the crowd-sourced approach typical of identification studies expedited the design process.

US-skepticism and transnational conspiracy in the 2024 Taiwanese presidential election

Taiwan has one of the highest freedom of speech indexes while it also encounters the largest amount of foreign interference due to its contentious history with China. Because of the large influx of misinformation, Taiwan has taken a public crowdsourcing approach to combatting misinformation, using both fact-checking ChatBots and public dataset called CoFacts. Combining CoFacts with large-language models (LLM), we investigated misinformation across three platforms (Line, PTT, and Facebook) during the 2024 Taiwanese presidential elections. We found that most misinformation appears within China-friendly political groups and attacks US-Taiwan relations through visual media like images and videos. A considerable proportion of misinformation does not question U.S. foreign policy directly. Rather, it exaggerates domestic issues in the United States to create a sense of declining U.S. state capacity. Curiously, we found misinformation rhetoric that references conspiracy groups in the West.

A Fair Crowd-Sourced Automotive Data Monetization Approach Using Substrate Hybrid Consensus Blockchain

This work presents a private consortium blockchain-based automotive data monetization architecture implementation using the Substrate blockchain framework. Architecture is decentralized where crowd-sourced data from vehicles are collectively auctioned ensuring data privacy and security. Smart Contracts and OffChain worker interactions built along with the blockchain make it interoperable with external systems to send or receive data. The work is deployed in a Kubernetes cloud platform and evaluated on different parameters like throughput, hybrid consensus algorithms AuRa and BABE, along with GRANDPA performance in terms of forks and scalability for increasing node participants. The hybrid consensus algorithms are studied in depth to understand the difference and performance in the separation of block creation by AuRa and BABE followed by chain finalization through the GRANDPA protocol.

Crowdsourcing to increase hepatitis B and C testing and reduce hepatitis stigma among medical students in Bangladesh.

This study addresses the pervasive challenges of low hepatitis B (HBV) and hepatitis C (HCV) testing rates coupled with the stigma associated with these diseases in low- and middle-income countries (LMICs) with a special focus on Bangladesh. This study aims to introduce an innovative crowdsourcing intervention that involves medical students, a crucial cohort with the potential to shape healthcare attitudes. Through a structured crowdsourcing approach, the study designs and implements a digital intervention to counter stigma and promote testing among medical students in Dhaka, Bangladesh. Participants submitted brief videos or texts aiming to encourage hepatitis testing and reduce stigma. The call, advertised through meetings, emails, and social media, welcomed entries in English or Bengali over 3 weeks. A panel of six judges evaluated each entry based on clarity, impact potential, innovation, feasibility, and sustainability, awarding prizes to students behind the highest-rated submissions. Seventeen videos and four text messages received an average score of 5.5 among 440 surveyed medical students, predominantly 22 years old (16%) and in their fourth year (21%). After viewing, 360 students underwent screening, identifying two previously undiagnosed HBV cases referred for care; no HCV infections were found. Notably, 41% expressed concerns about individuals with HBV working in hospitals or having a doctor living with HBV. In conclusion, this pilot showcases the power of medical students in spearheading campaigns to counter hepatitis stigma and encourage testing. By utilizing crowdsourcing, the study introduces an innovative approach to a persistent issue in LMICs specially in Bangladesh, offering a model that could potentially be adapted by other regions grappling with similar challenges.

Community Partnership to Co-Develop an Intervention to Promote Equitable Uptake of the COVID-19 Vaccine Among Pediatric Populations

Community Partnership to Co-Develop an Intervention to Promote Equitable Uptake of the COVID-19 Vaccine Among Pediatric Populations

Crowdsourcing approach in the model of digital transformation of a tourism enterprise

Increased economic uncertainty and public concern about the new degree of risks to safe living give rise to changes in the structure of supply and demand in the travel industry. The share of cultural and ecological recreation in domestic tourism is growing, with a focus on the consumption of goods from local producers. The universal digitalization of public life increases the importance of cultural self-identification and creative self-expression, which also affects consumer behavior. All this forces tourism enterprises to look for new solutions to adapt their production processes and increase digital maturity. However, the complex of internal and external factors that have a decisive influence on management decision-making makes it difficult to apply existing models of digital transformation of organizations engaged in the field of tourism services. The expert literature on these issues is limited to examples of large companies and entire resorts. The author conducted an approbation of the methodology for drawing up a digital transformation strategy, proposed by a team of authors in the work "Digital Transformation Strategy: write to execute". The study is presented in the form of a case study of an Internet service development project Biggeo.ru the Sochi travel company. The article presents the experience of developing and implementing a digital transformation strategy for a travel agency, which can be useful both to representatives of the scientific community and creative industries involved in the development of innovative products and services, as well as to the heads of companies of alternative types of tourism. The digital transformation model was based on a crowdsourcing approach in the field of cultural and creative tourism, thanks to which an innovative tourist information resource was developed. The work carried out made it possible to confirm the hypothesis about the possibility of using this model in small enterprises of the tourism sector, to carry out a detailed description of the process of drawing up a strategy and to fill a gap in the scientific and expert literature devoted to this area. New in-demand activities and an innovative digital product, which appeared due to the implementation of the strategy for increasing digital maturity, allow us to characterize the first results of the project as successful, and the developing project is able to meet the needs of stakeholders in tools for promoting cultural and creative tourism.

How to detect fake online physician reviews: A deep learning approach.

The COVID-19 pandemic has spurred an increased interest in online healthcare and a surge in usage of online healthcare platforms, leading to a proliferation of user-generated online physician reviews. Yet, distinguishing between genuine and fake reviews poses a significant challenge. This study aims to address the challenges delineated above by developing a reliable and effective fake review detection model leveraging deep learning approaches based on a fake review dataset tailored to the context of Chinese online medical platforms. Inspired by prior research, this paper adopts a crowdsourcing approach to assemble the fake review dataset for Chinese online medical platforms. To develop the fake review detection models, classical machine learning models, along with deep learning models such as Convolutional Neural Network and Bidirectional Encoder Representations from Transformers, were applied. Our experimental deep learning model exhibited superior performance in identifying fake reviews on online medical platforms, achieving a precision of 98.36% and an F2-Score of 97.97%. Compared to the traditional machine learning models (i.e., logistic regression, support vector machine, random forest, ridge regression), this represents an 8.16% enhancement in precision and a 7.7% increase in F2-Score. Overall, this study provides a valuable contribution toward the development of an effective fake physician review detection model for online medical platforms.

Identification of Effective Factors on Public Oversight of Public Policies with a Crowdsourcing Approach Using Thematic Analysis and DEMATEL Techniques

Objective: The primary goal of this article is to identify the factors influencing public oversight of public policies using a crowdsourcing approach with thematic analysis and DEMATEL techniques. Methodology: The research methodology is mixed (qualitative-quantitative). In addition to documentary studies, thematic analysis technique has been utilized. The statistical population in this study comprised all experts in the field of public policy-making, managers, and public health professionals, with theoretical saturation achieved after 16 interviews. Eventually, basic, organizing, and global themes were extracted, and in the quantitative part, the DEMATEL technique was used to determine the impact and influence of factors on public oversight of public policies with a crowdsourcing approach. Findings: This study identified 15 dimensions (health service capacities, motivational factors, environmental factors, internal policies, domestic infrastructure, executive factors, development and education of public services in health, development of domestic services, globalization of public services, development of knowledge sharing policies and services, structural issues, laws and regulations, cultural factors, financial management) and 32 components and 159 indicators were extracted. Through the DEMATEL method in the quantitative section, 8 influential components and 7 influenced components were identified. Conclusion: The studies indicated that among the identified dimensions, the dimension of health service capacities has the highest importance in terms of impact and requires special attention, while the dimension of cultural factors is the most influenced dimension that is affected by other dimensions.

Strategi Melakukan Proses Rekrutmen Ditengah Buruknya Citra Perusahaan Pialang

This discussion aims to identify and address the challenges faced by brokerage firms in carrying out employee recruitment processes in the context of poor corporate image. Faced with these challenges, the study adopted a crowdsourcing approach by involving brokers and local communities. Methods included surveys, interviews and group discussions with stakeholders. The discussion identified various challenges faced by the Brokerage Company, such as low community trust, lack of interest of prospective employees to join the company, and communication issues. The review recommended various strategies, including efforts to improve the company's image, and more attractive training programs. It also makes an important contribution towards improving the image of brokerage firms and enhancing their recruitment processes. Integrating the brokerage firm into the local community is expected to strengthen the relationship between the firm and the community and create a better recruitment environment. The results of this study are expected to serve as a guide for Brokerage Firms and similar organizations to overcome similar challenges and build better relationships with the community.

The smarty4covid dataset and knowledge base as a framework for interpretable physiological audio data analysis

Harnessing the power of Artificial Intelligence (AI) and m-health towards detecting new bio-markers indicative of the onset and progress of respiratory abnormalities/conditions has greatly attracted the scientific and research interest especially during COVID-19 pandemic. The smarty4covid dataset contains audio signals of cough (4,676), regular breathing (4,665), deep breathing (4,695) and voice (4,291) as recorded by means of mobile devices following a crowd-sourcing approach. Other self reported information is also included (e.g. COVID-19 virus tests), thus providing a comprehensive dataset for the development of COVID-19 risk detection models. The smarty4covid dataset is released in the form of a web-ontology language (OWL) knowledge base enabling data consolidation from other relevant datasets, complex queries and reasoning. It has been utilized towards the development of models able to: (i) extract clinically informative respiratory indicators from regular breathing records, and (ii) identify cough, breath and voice segments in crowd-sourced audio recordings. A new framework utilizing the smarty4covid OWL knowledge base towards generating counterfactual explanations in opaque AI-based COVID-19 risk detection models is proposed and validated.

Using crowdsourcing approach to obtain real-world insights to improve access to cancer medicine.

135 Background: Barriers of access to cancer medicines vary tremendously among practice settings. Our initiative is aimed at obtaining insights about the challenges and potential solutions to improve access to cancer medicine from a wide range of stakeholders and front-line practitioners across the world. Methods: We used a two-step approach. The first step is to convene a panel of distinguished international experts to identify key stakeholders and pertinent issues to cover during crowdsourcing process. The second step is to run a crowdsourcing (Hackathon) through a virtual platform (Within3, Lakewood, Ohio, USA). The platform was divided into four rooms, each moderated by one expert posing a series of questions related to the following themes: Access to affordable quality medicines; reliable, verifiable, and sustainable supply chain; guidelines and the rationale use of medicines; and measuring and validating quality standards. Results: Between June 8 and July 8, 2022, 78 participants from 33 countries joined the platform. Participants responded to questions by reporting local/ regional experiences and suggested solutions. Participants were able to comment on others’ posts or like a specific comment. The contributions revealed the disparities in access to medicines and highlighted the needs for cooperation across borders and among healthcare systems and stakeholder organizations and emphasized the needs to improve communications, education and accurate data generation and experience sharing. Questions that generated the most responses related to access to quality essential medicines (n=25) and the use of treatment guidelines based on essential cancer medicines (n=22). Solutions that generated the most “likes” related to actions that can be taken to make medicines more affordable and accessible and actions to engage diverse audiences in efforts to improve access to medicines. The importance of creating practical and relevant guidelines was clearly highlighted. Conclusions: Crowdsourcing is an innovative and practical approach to gain insights from stakeholders of different backgrounds professionally, geographically and practice settings. It creates an opportunity for interested individuals to participate in asynchronous ways in easily accessible platform at their convenience over extended period of time. A follow-up plan is underway to crystalize the most practical next steps to build on the complied information.

The pupil collaboration: A multi-lab, multi-method analysis of goal attribution in infants

The rise of pupillometry in infant research over the last decade is associated with a variety of methods for data preprocessing and analysis. Although pupil diameter is increasingly recognized as an alternative measure of the popular cumulative looking time approach used in many studies (Jackson & Sirois, 2022), an open question is whether the many approaches used to analyse this variable converge. To this end, we proposed a crowdsourced approach to pupillometry analysis. A dataset from 30 9-month-old infants (15 girls; Mage = 282.9 days, SD = 8.10) was provided to 7 distinct teams for analysis. The data were obtained from infants watching video sequences showing a hand, initially resting between two toys, grabbing one of them (after Woodward, 1998). After habituation, infants were shown (in random order) a sequence of four test events that varied target position and target toy. Results show that looking times reflect primarily the familiar path of the hand, regardless of target toy. Gaze data similarly show this familiarity effect of path. The pupil dilation analyses show that features of pupil baseline measures (duration and temporal location) as well as data retention variation (trial and/or participant) due to different inclusion criteria from the various analysis methods are linked to divergences in findings. Two of the seven teams found no significant findings, whereas the remaining five teams differ in the pattern of findings for main and interaction effects. The discussion proposes guidelines for best practice in the analysis of pupillometry data.

Distributed Representations of Wi-Fi Fingerprints from Non-Contextual Text-Embedding Techniques with Applications in Crowdsourcing Zone-Level Localization

Over the past decade, indoor localization systems have gained increasing attention and found widespread applications in commercial and research environments. Specifically, a Wi-Fi fingerprint-based system offers a low-cost solution over its counterparts such as Bluetooth, ultra-wideband (UWB), and radio frequency identification (RFID) technologies due to the ubiquity of Wi-Fi access points (WAPs) in most buildings. However, the main disadvantage of the fingerprint-based system is intensive survey effort required during system initialization and maintenance. This work explores a solution to alleviate this limitation by considering a crowdsourcing approach for zone-level localization. Instead of relying only on the labelled fingerprint data from trained surveyors, this approach uses the more-attainable unlabelled fingerprint data collected by participating volunteers. This unlabelled data is then used to augment the survey data in a process called pseudo labelling, forming a more comprehensive training dataset for subsequent localization tasks; this semi-supervised approach allows for minimal survey effort during system initialization and maintenance. To enable such solution, this work introduces a novel approach of employing non-contextual word embedding techniques to construct distributed vector representations of fingerprint data to overcome 3 challenges; (a) high memory requirement in the downstream tasks due to high-dimensional non-distributed vector representations from the “standard” vector transformation, (b) inclusion of an arbitrary value that represents missing WAPs which can affect the performance of the downstream localization tasks in a non-transparent manner, and most importantly, (c) poor pseudo-labelling and semi-supervised zone-prediction performances due to poor data separability in a feature space. The choice of the non-contextual text-embedding techniques, as opposed to the contextual counterparts, leads to less computational requirement in model training and distributed-representation generation due to simpler model architectures (no deep learning) and no requirement for pre-trained model during distributed-representation generation. To this end, we considered non-contextual word embedding techniques commonly used in natural language processing such as Word2Vec, GloVe, and Doc2Vec in the distributed-representation transformation, and compared the resulting downstream performances with those from well-recognized dimensionality reduction techniques such as PCA, Isomap, and UMAP. The results show that Word2Vec and GloVe transformations outperform other types of transformations in terms of separability in fingerprint representations, pseudo-labelling performance, and semi-supervised zone-prediction accuracy. Together with the promising robustness property against potential data inhomogeneity, Word2Vec and GloVe transformations are the recommended transformation processes for constructing vector representations of fingerprints in crowdsourcing zone-level localization. HIGHLIGHTS This work introduces a novel approach of employing non-contexual word-embedding techniques to construct distributed vector representations of Wi-Fi fingerprint data to facilitate pseudo-labelling and semi-supervised zone-prediction tasks in crowdsourcing zone-level localization The benefits of employing word-embedding techniques are (a) lower memory requirement in the downstream tasks due to distributed vector representations (b) no inclusion of an arbitrary value that represents missing WAPs which can affect the performance of the downstream localization tasks in a non-transparent manner (c) improved pseudo-labelling and semi-supervised zone-prediction performances due to improved data separability in a feature space The benefit of employing non-contextual techniques, as opposed to the contextual counterparts, is less computational requirement in model training and distributed-representation generation due to simpler model architectures (no deep learning) and no requirement for pre-trained model during distributed-representation generation The results show that Word2Vec and GloVe transformations outperform other types of transformations in terms of separability in fingerprint representations, pseudo-labelling performance, and semi-supervised zone-prediction accuracy GRAPHICAL ABSTRACT

CrowdFusion: Multisignal Fusion SLAM Positioning Leveraging Visible Light

With the fast development of location-based services, an ubiquitous indoor positioning approach with high accuracy and low calibration has become increasingly important. In this work, we target on a crowdsourcing approach with zero calibration effort based on visible light, magnetic field and WiFi to achieve sub-meter accuracy. We propose a CrowdFusion Simultaneous Localization and Mapping (SLAM) comprised of coarse-grained and fine-grained trace merging respectively based on the Iterative Closest Point (ICP) SLAM and GraphSLAM. ICP SLAM is proposed to correct the relative locations and directions of crowdsourcing traces and GraphSLAM is further adopted for fine-grained pose optimization. In CrowdFusion SLAM, visible light is used to accurately detect loop closures and magnetic field to extend the coverage. According to the merged traces, we construct a radio map with visible light and WiFi fingerprints. An enhanced particle filter fusing inertial sensors, visible light, WiFi and floor plan is designed, in which visible light fingerprinting is used to improve the accuracy and increase the resampling/rebooting efficiency. We evaluate CrowdFusion based on comprehensive experiments. The evaluation results show a mean accuracy of 0.67m for the merged traces and 0.77m for positioning, merely replying on crowdsourcing traces without professional calibration.

Prevalence and Help Seeking Behavior for Non-Suicidal Self-Injury on College Students

The high prevalence of NSSI has become a widespread health issue in various countries. Unfortunately, NSSI studies in Eastern countries are not as many as in Western countries. This study aims to explore the self-injury behavior of students in Indonesia. Crowdsourcing approach is used by distributing questionnaires through Google Form. A total of 909 students aged 18-25 years (mean age = 20.3, SD = 1,329, 75.4% female) participants completed the Inventory of Statements About Self-injury (ISAS) self-report scale to comprehensively assess non suicidal self-injury (NSSI). Participants were recruited during June 2022–July 2022. The results shows 30% of students were involved in NSSI behavior. The mean age of onset was 15.5 years. As many as 55% of subjects reported having committed more than 50 acts of self-injury. The reported NSSI methods included slashing (78% hair pulling, hitting 74%, biting 57.1%, interfering wound healing 46.9%, carving 26.7%, pinching 66%, scratching 63.3%, stabbing 25.2%, and ingesting a hazardous substance 7.3%. It was reported that 88.3% used more than one method, 17.2% did not feel pain while doing self-injury. In conclusion, the prevalence of NSSI among students in Indonesia is not different from other countries. Prevention and management actions need to be developed to help people who self-injure to have strategies in dealing with problems adaptively and avoiding risky behavior.

An algorithmic crowdsourcing approach for atrial fibrillation detection on Apple Watch ECG data

In the present study, we investigated the test-retest stability of resting state alpha asymmetry in 18 children (9 male and 9 female) in a longitudinal design. Children’s resting state brain activation asymmetries were assessed by means of EEG first after 14 months of age, and again a second time at 83 months of age, and frontal (AsymF), temporal (AsymT), and parietal (AsymP) alpha activation asymmetries were calculated. Analyses demonstrate positive relations between frontal asymmetry scores at 14 and 83 months of age. Temporal and parietal asymmetries did not show this stability over time. This finding provides further support for the use of frontal alpha asymmetry measures to investigate processes underlying emotion and motivation in childhood, and its stability over time.

Creating large, high-quality geospatial datasets from historical maps using novice volunteers

Unlocking data from historical maps for landscape analysis is costly. Automatic extraction using Machine Learning (ML) requires extensive preparation and expertise. Crowdsourcing scales better than direct digitisation by experts, but requires an appropriate platform and the technical skills to adapt it. Existing research provides little guidance as to when investments in these approaches become worthwhile. Here we present a customisation of the Field Acquired Information Management Systems (FAIMS) Mobile platform tailored to offer a streamlined, collaborative system for crowdsourcing map digitisation by volunteers with no prior GIS experience. Deployed in Bulgaria as an ancillary activity during 2017–2018 archaeological fieldwork, FAIMS Mobile was used to digitise 10,827 mound features from Soviet military topographic maps. This digitisation required 241 person-hours (57 from staff; 184 from novice volunteers), with an error rate under 6%. The resulting dataset was consistent, well-documented, and ready for analysis with a few hours of processing. A conservative estimate based on our work suggests our crowdsourcing approach is most efficient for digitisation projects of 10,000–60,000 features, but may offer advantages for datasets as small as a few hundred records. Furthermore, it indicates that systems designed for field data collection, running on mobile devices, can be profitably customised to serve as participatory geospatial data systems accessible to novice volunteers.

Complementing Solutions for Facility Location Optimization via Video Game Crowdsourcing and Machine Learning Approach

The facility location problem (FLP) is a complex optimization problem that has been widely researched and applied in industry. In this research, we proposed two innovative approaches to complement the limitations of traditional methods, such as heuristics, metaheuristics, and genetic algorithms. The first approach involves utilizing crowdsourcing through video game players to obtain improved solutions, filling the gap in existing research on crowdsourcing for FLP. The second approach leverages machine learning techniques, specifically prediction methods, to provide an efficient exploration of the solution space. Our findings indicate that machine learning techniques can complement existing solutions by providing a more comprehensive approach to solving FLP and filling gaps in the solution space. Furthermore, machine learning predictive models are efficient for decision making and provide quick insights into the system’s behavior. In conclusion, this research contributes to the advancement of problem-solving techniques and has potential implications for solving a wide range of complex, NP-hard problems in various domains.