REVIEW | doi:10.20944/preprints201811.0029.v1
Subject: Social Sciences, Psychology Keywords: food marketing; sex/gender; personalization; customization; nutrition
Online: 2 November 2018 (07:00:20 CET)
In recent years, food and drink marketers have become increasingly interested in the question of whether there are any meaningful sex/gender differences in the world of taste/flavour perception. However, it turns out that while there are a large number of individual differences in the experience of food/drink, few, if any, fall neatly along sex/gender lines. As such, the marketers of food and drink need to tread very carefully when it comes to marketing food or beverage products specifically at men, or more usually, women. All too often, the brands entering this space soon find their attempts branded crass and/or sexist. Adopting a stealthy or implicit gender-based product development strategy is therefore perhaps more likely to succeed than the explicit targeting of food/beverage-related products in what is undoubtedly a highly-politicized area. That said, the one area where the public appear willing to accept products that are explicitly targeted at men or women is in the case of nutritional foods/supplements.
ARTICLE | doi:10.20944/preprints202307.1044.v1
Subject: Social Sciences, Education Keywords: Artificial Intelligence; language learning, Multiple intelligences; personalization and engagement
Online: 17 July 2023 (03:44:07 CEST)
This paper explores the integration of multiple intelligences and artificial intelligence (AI) in language learning, focusing on its potential to enhance personalization and engagement. Drawing from existing research and studies conducted in various contexts, including the Philippines, this study aims to contribute to the understanding of the benefits, challenges, and effectiveness of this integration. The paper begins with an introduction that highlights the background and significance of integrating multiple intelligences and AI in language learning, identifying research gaps, objectives, research questions, and the theoretical framework. A literature review provides an overview of multiple intelligences theory by Howard Gardner, the role of AI in language learning, and identifies gaps in the existing literature. The methodology section outlines the research design and approach, participant selection, data collection methods, validity and reliability measures, and ethical considerations. Findings and results are presented through the analysis of qualitative data, exploring emergent themes and patterns. The discussion section critically examines the identified research gaps, discusses the validity and reliability of the study, addresses the scope and limitations, and explores the implications of the findings for theory, practice, and future research. The conclusion summarizes the key findings and contributions of the study, reflects on the achievement of research objectives, offers recommendations for further research, and provides final remarks tying together the main points of the study. This paper contributes to the existing body of knowledge by providing insights into the integration of multiple intelligences and AI in language learning and its impact on personalization, engagement, and language learning outcomes.
ARTICLE | doi:10.20944/preprints202109.0335.v1
Subject: Engineering, Other Keywords: human body; anthropometric dimensions; personalization; subject-specific model; biofidelity
Online: 20 September 2021 (14:15:24 CEST)
Virtual human body models contribute to designing safe and user-friendly products through virtual prototyping. Anthropometric biomechanical models address different physiques using average dimensions. In designing personal protective equipment, biomechanical models with the correct geometry and shape shall play a role. The presented study shows the variations of subject-specific anthropometric dimensions from the average for the different population groups in the Czech Republic and China as a background for the need for personalized human body models. The study measures a set of clothing industry dimensions of Czech children, Czech teens, Czech adults and Chinese adults and compares them to the corresponding age average, which is represented by a scaled anthropometric human body model. The cumulative variation of clothing industry dimensions increases the farer is the population group from the average. It is smallest for the Czech adults 7.54% ± 6.63%, Czech teens report 7.93% ± 6.25% and Czech children differ 9.52% ± 6.08%. Chinese adults report 10.86% ± 11.11%. As the variations of the particular clothing industry dimensions from the average prove the necessity of having personalized subject-specific models, the personalization of particular body segments using the measured clothing industry dimensions leading to a subject-specific virtual model is addressed. The developed personalization algorithm results in the continuous body surface desired for contact applications for assessing body behavior and injury risk under impact loading.
ARTICLE | doi:10.20944/preprints202008.0700.v1
Subject: Computer Science And Mathematics, Information Systems Keywords: hybrid educational recommender system; learning objects; matrix factorization; personalization
Online: 31 August 2020 (04:58:50 CEST)
One of the main challenges for autonomous learning in virtual environments is finding the right material that fits students’ needs and supports their learning process. Personalized recommender systems partially solve this problem by suggesting online educational resources to students based on their preferences. However, in educational environments (which need a proper characterization of both users and educational resources), most existing recommendation algorithms either fail to include all the available information or use hybrid processes that do not exploit possible relationships between users and item features. This article presents a personalized recommender system for educational resources aimed at combining user and item information into a single mathematical model based on matrix factorization. As a result, estimated latent factors can provide insight into possible interactions between users and item features, improving the quality of the information retrieval process. We validated the proposed model on a real dataset that contains the ratings assigned by students from Universidad Nacional de Colombia and Universidade Feevale to educational resources in the Colombian Federation of Learning Object Repositories (FROAC in Spanish). User characterization included learning style and educational level, whereas item characterization (obtained from the objects’ metadata), included interactivity level, aggregation level and type, and resource format. These results, compared to those obtained when not all the available information is included, show that our method can improve the recommendation process.
ARTICLE | doi:10.20944/preprints202306.0289.v2
Subject: Computer Science And Mathematics, Other Keywords: Discrete distribution estimation; Local differential privacy; Item-oriented personalization; Randomized response
Online: 8 June 2023 (03:16:47 CEST)
Discrete distribution estimation is a fundamental statistical tool, which is widely used to perform data analysis tasks in various applications involving sensitive personal information. Due to privacy concerns, individuals may not always provide their raw information, which leads to unpredictable biases in the final results of estimated distribution. Local Differential Privacy (LDP) is an advanced technique for privacy protection of discrete distribution estimation. Currently, typical LDP mechanisms provide same protection for all items in the domain, which imposes unnecessary perturbation on less sensitive items and thus degrades the utility of final results. Although, several recent works try to alleviate this problem, the utility can be further improved. In this paper, we propose a novel notion called Item-Oriented Personalized LDP (IPLDP), which independently perturbs different items with different privacy budgets to achieve personalized privacy protection. Furthermore, to satisfy IPLDP, we propose the Item-Oriented Personalized Randomized Response (IPRR) based on the observation that the sensitivity of data shows an inverse relationship with the population size of respective individuals. Theoretical analysis and experimental results demonstrate that our method can provide fine-grained privacy protection and improve data utility simultaneously.
ARTICLE | doi:10.20944/preprints202307.1393.v1
Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: large language models; recommender systems; GPT-4; context awareness; personalization; cultural heritage; museum
Online: 20 July 2023 (08:41:04 CEST)
This paper proposes the utilization of large language models as recommendations systems for museums. Since the aforementioned models lack the notion of context, they can’t work with temporal information that is often present in recommendations for cultural environments (e.g. special exhibitions or events). In this respect, the current work aims at enhancing the capabilities of large language models through a fine-tuning process that incorporates contextual information and user instructions. The resulting models are expected to be capable of providing personalized recommendations, aligned with user preferences and desires. More specifically, Generative Pre-trained Transformer 4, a knowledge-based large language model is fine-tuned and turned into a context-ware recommendation system, adapting its suggestions based on user input and specific contextual factors such as location, time of visit, and other relevant parameters. The effectiveness of the proposed approach is evaluated through certain user studies, which ensure an improved user experience and engagement within the museum environment.
TECHNICAL NOTE | doi:10.20944/preprints202307.1206.v1
Subject: Computer Science And Mathematics, Other Keywords: ACUX-R; graphical user interface; mobile application; cultural tourism; recommendation systems; visiting preferences; personalization
Online: 18 July 2023 (09:51:25 CEST)
This article presents the graphical user interface of the ACUX-R mobile recommendation system, tailored for the cultural tourism domain. ACUX-R offers personalized recommendations based on visiting preferences, augmenting the overall user experience. Building upon a comprehensive methodology and recommendation algorithms from previous work, this contribution focuses on the user interface aspects of the ACUX-R by highlighting key design considerations, user interface elements and functionalities that contribute to an effective and engaging user experience. In an effort to evaluate the proposed interface, an initial case study with a dataset consisting of points of interest from the City of Athens, Greece has been performed. In the framework of the aforementioned study, the proposed user interface attained high ratings with respect to inspiring, exciting, interesting, and enthusiastic user experiences.
ARTICLE | doi:10.20944/preprints202007.0078.v1
Subject: Computer Science And Mathematics, Information Systems Keywords: personalization; decision making; medical data; artificial intelligence; Data-driving; Big Data; Data Mining; Machine Learning
Online: 5 July 2020 (15:04:17 CEST)
The study was conducted on applying machine learning and data mining methods to personalizing the treatment. This allows investigating individual patient characteristics. Personalization is built on the clustering method and associative rules. It was suggested to determine the average distance between instances for optimal performance metrics finding. The formalization of the medical data pre-processing stage for finding personalized solutions based on current standards and pharmaceutical protocols is proposed. The model of patient data is built. The paper presents the novel approach to clustering built on ensemble of cluster algorithm with better than k-means algorithm Hopkins metrics. The personalized treatment usually is based on decision tree. Such approach requires a lot of computation time and cannot be paralyzed. Therefore, it is proposed to classify persons by conditions, to determine deviations of parameters from the normative parameters of the group, as well as the average parameters. This made it possible to create a personalized approach to treatment for each patient based on long-term monitoring. According to the results of the analysis, it becomes possible to predict the optimal conditions for a particular patient and to find the medicaments treatment according to personal characteristics.
ARTICLE | doi:10.20944/preprints202304.0078.v1
Subject: Public Health And Healthcare, Public Health And Health Services Keywords: aging population; healthcare systems; healthcare system evaluation; chronic illness; digital healthcare; personalization; healthcare usability; healthcare satisfaction
Online: 6 April 2023 (08:48:56 CEST)
The ageing of the population is growing significantly and will challenge healthcare systems. Chronic diseases in the older population require a change in service delivery, and new technologies can be a key element in ensuring the viability and sustainability of these systems. However, the generation gap and the physical and cognitive decline commonly associated with the older generation are barriers to the transition to these models of care. Despite this, there has been a trend towards digital healthcare, which has many potential benefits for the older population. Numerous studies have assessed the acceptability of new technologies for older people in health care. These studies highlight the importance of perceived usefulness, compatibility, ease of use and personalisation of the technology. Personalisation is necessary to ensure that the system is useful for users, and different characteristics such as country of origin, gender, age or comfort with the technology should be taken into account. A person-centred approach in the development of new health technology systems is essential to ensure that applications can be better tailored to the needs of different ageing populations. Many organisations have dedicated time and resources to ensure a person-centred approach in the development of new health technology systems, and putting the individual first is the best way forward in digital health. This article presents the work carried out in this regard in the framework of the European TeNDER project together with an analysis of the results obtained in terms of satisfaction, usefulness and usability by end users.
ARTICLE | doi:10.20944/preprints202306.2253.v1
Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Epilepsy; Seizure Prediction; Preictal; Federated Learning (FL); Spiking Encoder; Graph Convolutional Neural Network (GCNN); Patient-specific Personalization
Online: 30 June 2023 (14:48:14 CEST)
Electroencephalography (EEG) signals are the primary source for discriminating the preictal from the interictal stage, enabling early warnings before the seizure onset. The epileptic seizure prediction models face significant challenges due to data scarcity, diversity, and privacy. This paper proposes a three-tier architecture for epileptic seizure prediction associated with the Federated Learning (FL) model that enhances the capability by utilizing the significant amount of seizure patterns from globally distributed patients with data privacy. The determination of the preictal state is influenced by global and local model-assisted decision-making by modeling the two-level edge layer. Integrating the Spiking Encoder (SE) with Graph Convolutional Neural Network (Spiking-GCNN) works as the local model trained using the bi-timescale approach. Each local model utilizes the aggregated seizure knowledge from the different medical centers through FL and determines the preictal probability in the coarse-grained personalization. The Adaptive Neuro-Fuzzy Inference System (ANFIS) is utilized in fine-grained personalization to recognize epileptic seizure patients by examining the outcomes of the FL model, heart rate variability features, and patient-specific clinical features. The proposed seizure prediction is evaluated using benchmark datasets by comparing them with the existing works to demonstrate the potential results.
ARTICLE | doi:10.20944/preprints201904.0093.v1
Subject: Medicine And Pharmacology, Pediatrics, Perinatology And Child Health Keywords: Patients involvement; research interests; ART treatments; treatment personalization; psychological effects; healthy habits; fertility protection; infertility prevention; lifestyle; diet
Online: 8 April 2019 (12:46:17 CEST)
STUDY QUESTION: Which are the main research interests among patients of assisted reproductive technologies (ART)? SUMMARY ANSWER: Patients identified as research priorities that deserve further investigation: success rates and risks of ART, side-effects of treatments, resources to cope with infertility, effectiveness of alternative therapies, lifestyle habits to protect fertility, oocyte quality and ovarian reserve, and causes of genetic or hereditary infertility. WHAT IS KNOWN ALREADY: The involvement of patients and caregivers in setting research agendas in medicine has gathered significant momentum in the last decade. Patients’ involvement in setting research priorities offers several benefits: improved patient knowledge and awareness of their condition; greater understanding of the medical professionals of the impact of the condition on patients’ quality of life; reduced costs associated with redundant research activities. This is may be also applicable to research in infertility and ART, where patients’ interests have never been explored before. STUDY DESIGN, SIZE, DURATION: This is a cross-sectional study that consists of an anonymous online survey, which was sent up to three times to 2112 patients from 11 fertility centers in 5 countries between January-December 2018. The study design was based on the James Lind Alliance priority setting partnership model, which comprises the identification of patients groups, the exploration of the research agenda, the analysis of collected data and identification of priorities. PARTICIPANTS/MATERIALS, SETTING, METHODS: Overall, 2112 patients were contacted, and 945 surveys were answered (RR: 44.7%). Patients were asked to identify research questions relevant to them in the areas of infertility causes and prevention, fertility treatments (medication and ART), and the emotional aspects of infertility. Answers were categorized in topics and ranked by frequency. A long list of the top-30 research topics was extracted from the aggregate results, from which, a short list of the top-10 research topics was created. At the end, 10 research questions related to each of the 10 research topics were constructed, based on the answers given by patients. MAIN RESULTS AND THE ROLE OF CHANCE: Female (845, 89.4%) and male (100, 10.6%) patients were included. The mean age of patients was 37.8 (SD 1.74). Most of the patients did not have children at the time of the survey (523, 59%), while 51 (5.7%) were pregnant. Sixty (6.3%) patients did not start treatment, 579 (61.3%) were performing a treatment with their own gametes and 304 (32.2%) were treated through gamete donation. Patients were mainly interested in the effectiveness of ART -especially per clinical profile-, side effects of drugs, protection of fertility and prevention of infertility –especially through diet and exercise-, and psychological aspects of the infertility journey. The top-10 research questions (and weight) obtained were: 1) What are the side-effects of ART treatments? (41.6%); 2) What are the most effective methods to cope with infertility from the psychological point of view? (37.2%); 3) What effects could diet have on fertility? (25.9%); 4) What are ART success rates per clinical profile? (25.9%); 5) Are there habits and lifestyle factors that could prevent infertility? (20.0%); 6) What are the long-term risks associated to ART? (18.5%); 7) Are alternative therapies such as acupuncture, yoga, and meditation effective to treat/prevent infertility? (18.5%); 8) What is the impact of exercise on fertility? (15.4%); 9) How does oocytes quantity and quality affect fertility? (9.5%); 10) What are the genetic patterns or hereditary conditions causing/related to infertility? (9.5%). LIMITATIONS, REASONS FOR CAUTION: Although all respondents had attended a fertility center, not all of them were diagnosed as infertile (i.e. single women) and had started treatment at the time of response, while a few were pregnant; their priorities for research might have been influenced by their infertility journey. Also, all participants attended private fertility centers: areas of interest may be different in public settings. WIDER IMPLICATIONS FOR THE FINDINGS: Researchers and clinicians should keep in mind that, in addition to improvement of treatments’ success rates and side-effects, patients greatly value research on causes, prevention and emotional aspects of infertility. As their views might differ from those of medical professionals, patients’ voices should be incorporated in setting infertility research priorities.
REVIEW | doi:10.20944/preprints201809.0434.v1
Subject: Medicine And Pharmacology, Oncology And Oncogenics Keywords: colorectal cancer, cancer stem cells, mesenchymal stromal cells, stem cell markers, chemoresistance, treatment personalization, biomarkers, cancer stem cell markers
Online: 21 September 2018 (10:07:54 CEST)
BACKGROUND: Treatment failure in primary as well as metastatic cancer patients, caused by chemo and radio resistance, has truncated the research for the applicability of personalized medicine. The use of stem cells and cancer stem cells in such a treatment approach will be reviewed in this study. RESULTS: CRC stem cells prove to be a promising asset for CRC treatment optimization both by serving as biomarkers for the current therapy modalities by means of treatment personalization and patient/tumor stratification, as well as in the development of targeted therapies, selective for the stem cell population. Similar conclusions are drawn, regarding mesenchymal stromal cells and their effect in CRC therapy; while resident stromal cells of tumor microenvironment seem to promote the tumorigenic and metastatic processes in addition to conferring to the chemo- and radio resistance, under certain conditions they are able to improve the treatment outcome of CRC chemotherapy, e.g. by targeted enzyme/prodrug treatment of CRC cells. CONCLUSION: This review, truncates the dynamic potential of cancer stem cells and other stem cell types in CRC treatment personalization as well as, in the improvement of current treatment approaches opting to a higher therapeutic rate, improved prognosis, survival and quality of life for CRC patients.
ARTICLE | doi:10.20944/preprints201807.0629.v1
Subject: Engineering, Automotive Engineering Keywords: user experience, UX, user interface, user interaction, automotive cockpit design, intuitive driving, driving automation, digitalization, personalization, Valeo Mobius, Valeo MyMobius.
Online: 31 July 2018 (16:18:10 CEST)
As we approach the 135th anniversary of the automobile, two industry trends, automation and digitalization, are rapidly revolutionizing the thus far, relatively unchanged automotive user experience. This paper describes the development of the Valeo MyMobius user interface concept. The goal of this project was to explore how to achieve an intuitive driving experience as the automotive industry undergoes transition from primarily analog to primarily digital interfaces and from physical buttons to multimodal interactions. To achieve the perception of intuitiveness, designers must understand their users, find and reduce physical and cognitive friction points, and bridge knowledge gaps with interface designs that facilitate discovery and learnability. The Valeo MyMobius concept featured steering wheel touch displays that supported quick, frequent menu selections using swiping gestures (common in smartphone interactions) and reinforcing icons (to facilitate learnability). Learning algorithms personalized the experience by tailoring suggestions, while more complex interactions were handled with a conversational voice assistant, which also served as a driving copilot, capable of contextually suggesting when Advanced Driving Assistance System (ADAS) features such as ACC could be utilized. The visual design aesthetic embodied Kenya Hara’s design philosophy of “Emptiness,” reducing visual clutter and creating spaces that are ready to receive inspiration and information. Altogether, the Valeo MyMobius concept demonstrated an attainable future where the perception of intuitiveness can be achieved with today’s technologies.
ARTICLE | doi:10.20944/preprints201901.0294.v2
Subject: Computer Science And Mathematics, Analysis Keywords: Data preprocessing; data validation; recommendation engine; E-commerce; Click-through rate; Buy-through rate; online customer behavior; non-parametric outlier removal; personalization
Online: 1 February 2019 (10:22:37 CET)
E-commerce businesses employ recommender models to assist in identifying a personalized set of products for each visitor. To accurately assess the recommendations’ influence on customer clicks and buys, three target areas—customer behavior, data collection, user-interface —will be explored for possible sources of erroneous data. Varied customer behavior misrepresents the recommendations’ true influence on a customer due to the presence of B2B interactions and outlier customers. Non-parametric statistical procedures for outlier removal are delineated and other strategies are investigated to account for the effect of a large percentage of new customers or high bounce rates. Subsequently, in data collection we identify probable misleading interactions in the raw data, propose a robust method of tracking unique visitors, and accurately attributing the buy influence for combo products. Lastly, user-interface issues discuss the possible problems caused due to the recommendation widget’s positioning on the e-commerce website and the stringent conditions that should be imposed when utilizing data from the product listing page. This collective methodology results in an exact and valid estimation of the customer’s interactions influenced by the recommendation model in the context of standard industry metrics such as Click-through rates, Buy-through rates, and Conversion revenue.
REVIEW | doi:10.20944/preprints202306.0672.v1
Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Review; Human action recognition; Smart living; Services; Applications; Context Awareness; Data Availability; Personalization; Privacy; Sensing technology; Machine learning; Deep learning; Signal processing; Smart home; Smart environment; Smart city; Smart Community; Ambient Assisted Living
Online: 9 June 2023 (05:34:18 CEST)
Smart Living, an increasingly prominent concept, entails incorporating sophisticated technologies in homes and urban environments to elevate the quality of life for citizens. A critical success factor for Smart Living services and applications, from energy management to healthcare and transportation, is the efficacy of human action recognition (HAR). HAR, rooted in computer vision, seeks to identify human actions and activities using visual data and various sensor modalities. This paper extensively reviews the literature on HAR in Smart Living services and applications, amalgamating key contributions and challenges while providing insights into future research directions. The review delves into the essential aspects of Smart Living, the state of the art in HAR, and the potential societal implications of this technology. Moreover, the paper meticulously examines the primary application sectors in Smart Living that stand to gain from HAR, such as smart homes, smart healthcare, and smart cities. By underscoring the significance of the four dimensions of Context Awareness, Data Availability, Personalization, and Privacy in HAR, this paper serves as a valuable resource for researchers and practitioners striving to advance Smart Living services and applications.