Search Results (112)

Achieving optimal agricultural yields and promoting sustainable farming relies on accurate crop recommendations. However, the applicability of many current systems is limited by their considerable computational requirements and dependence on comprehensive datasets, especially in resource-limited contexts. This paper presents HOLISTIQ RS, a novel crop recommendation system explicitly designed for operation on low-specification hardware and in data-scarce regions. HOLISTIQ RS combines collaborative filtering with a Markov model to predict appropriate crop choices, drawing upon user profiles, regional agricultural data, and past crop performance. Results indicate that HOLISTIQ RS provides a significant increase in recommendation accuracy, achieving a MAP@5 of 0.31 and nDCG@5 of 0.41, outperforming standard collaborative filtering methods (the KNN achieved MAP@5 of 0.28 and nDCG@5 of 0.38, and the ANN achieved MAP@5 of 0.25 and nDCG@5 of 0.35). Significantly, the system also demonstrates enhanced recommendation diversity, achieving an Item Variety (IV@5) of 23%, which is absent in deterministic baselines. Significantly, the system is engineered for reduced energy consumption and can be deployed on low-cost hardware. This provides a feasible and adaptable method for encouraging informed decision-making and promoting sustainable agricultural practices in areas where resources are constrained, with an emphasis on lower energy usage. Full article

In the recommendation system (RS) literature, a distinction exists between studies dedicated to fully operational (known users/items) and cold-start (new users/items) RSs. The warm-up phase—the transition between the two—is not widely researched, despite evidence that attrition rates are the highest for users and content providers during such periods. RS formulations, particularly deep learning models, do not easily allow for a warm-up phase. Herein, we propose two independent and complementary models to increase RS performance during the warm-up phase. The models apply to any cold-start RS expressible as a function of all user features, item features, and existing users’ preferences for existing items. We demonstrate substantial improvements: Accuracy-oriented metrics improved by up to 14% compared with not handling warm-up explicitly. Non-accuracy-oriented metrics, including serendipity and fairness, improved by up to 12% compared with not handling warm-up explicitly. The improvements were independent of the cold-start RS algorithm. Additionally, this paper introduces a method of examining the performance metrics of an RS during the warm-up phase as a function of the number of user–item interactions. We discuss problems such as data leakage and temporal consistencies of training/testing—often neglected during the offline evaluation of RSs. Full article

The 4Rs of sports nutrition were proposed in recent years as an evidence-based framework to optimize post-exercise recovery within the context of allostasis. Under this paradigm, it is important to consider that each R represents a factor with a tremendous influence on the allostatic response and improves individual components of the allostatic load (AL), which will positively impact the exercise-induced adaptations and the athlete’s recovery. The 4Rs correspond to the following. (i) Rehydration—This is necessary to guarantee the post-exercise consumption of at least 150% of the body mass lost during the exercise accompanied by sodium (if faster replacement is required). (ii) Refuel—Carbohydrate intake (~1.2 g/kg body mass per hour for up to 4 h post-exercise) is essential not only in restoring glycogen reserves but also in supporting the energy needs of the immune system and facilitating tissue repair. Despite changes in substrate utilization, a ketogenic diet generally has neutral or negative effects on athletic performance compared to carbohydrate-rich diets. (iii) Repair—The ingestion of high-quality protein stimulates post-exercise net muscle protein anabolism and might contribute to faster tissue growth and repair. The use of certain supplements, such as creatine monohydrate, might help to enhance recovery, while tart cherry, omega-3 fatty acids, and dietary nitrate (e.g., Beta vulgaris, Amaranthus L.), as well as other herbal extracts containing flavonoid-rich polyphenols, deserve further clinical research. (iv) Recuperate—Pre-sleep nutrition (casein- or protein-rich meal with slow digestion rate) has a restorative effect, facilitating the recovery of the musculoskeletal, endocrine, immune, and nervous systems. In this article, we update the 4Rs framework, delve deeper into the allostasis paradigm, and offer theoretical foundations and practical recommendations (the 4Rs app) for the assessment of AL in athletes. We cautiously propose an AL index (AL_index) for physique competitors and elite athletes to evaluate the cumulative physiological stress induced by exercise and, thereby, to adjust exercise and nutrition interventions. Full article

Standard correlation analysis is one of the frequently used methods in financial markets. However, this matrix can give erroneous results in the conditions of chaos, fractional systems, entropy, and complexity for the variables. In this study, we employed the time-dependent correlation matrix based on isospectral flow using the Lie group method to assess the price of Bitcoin and gold from 19 July 2010 to 31 December 2024. Firstly, we showed that the variables have a chaotic and fractional structure. Lo’s rescaled range (R/S) and the Mandelbrot–Wallis method were used to determine fractionality and long-term dependence. We estimated and tested the d parameter using GPH and Phillips’ estimators. Renyi, Shannon, Tsallis, and HCT tests determined entropy. The KSC determined the evidence of the complexity of the variables. Hurst exponents determined mean reversion, chaos, and Brownian motion. Largest Lyapunov and Hurst exponents and entropy methods and KSC found evidence of chaos, mean reversion, Brownian motion, entropy, and complexity. The BDS test determined nonlinearity, and later, the time-dependent correlation matrix was obtained by using the stochastic SO(2) Lie group. Finally, we obtained robustness check results. Our results showed that the time-dependent correlation matrix obtained by using the stochastic SO(2) Lie group method yielded more successful results than the ordinary correlation and covariance matrix and the Spearman correlation and covariance matrix. If policymakers, financial managers, risk managers, etc., use the standard correlation method for economy or financial policies, risk management, and financial decisions, the effects of nonlinearity, fractionality, entropy, and chaotic structures may not be fully evaluated or measured. In such cases, this can lead to erroneous investment decisions, bad portfolio decisions, and wrong policy recommendations. Full article

Background: 2-Phenoxyethanol (2-PE) has been safely included as a preservative and/or stabilizer in more than thirty vaccine formulations at amounts ranging from 0.5 to 5 mg per dose; however, the nonclinical safety data publicly available for intramuscular (IM) or subcutaneous (SC) administration are relatively limited. Here, in addition to the available clinical and nonclinical data for 2-PE, we summarize the nonclinical safety data of experimental 13vPnC (Prev(e)nar 13) formulations with or without 2-PE. Methods: Two repeat-dose toxicity studies in rabbits, one for a 2-PE-free formulation of 13vPnC and the other for an MDV formulation of 13vPnC with 5 mg/dose 2-PE, were conducted as part of an overall nonclinical safety package for vaccine development. The studies were designed and conducted in compliance with the relevant guidelines and regulations. Results: In repeat-dose toxicity studies in rabbits, five IM administrations of a preservative-free 13vPnC single-dose syringe formulation or a 13vPnC multi-dose vial (MDV) formulation containing 5 mg 2-PE/0.5 mL dose were well tolerated with no systemic toxicity. Robust serotype-specific IgG antibody responses to each of the 13 pneumococcal serotypes were also confirmed for both formulations. The observations for the 13vPnC MDV including local inflammatory reaction, increases in fibrinogen, and increased splenic germinal centers were nonadverse, reversible, and consistent with findings previously observed for the IM administration of vaccines, including the 2-PE-free 13vPnC single-dose syringe formulation. Conclusions: Together with the other available nonclinical and clinical data of 2-PE and vaccine formulations containing 2-PE and following the 3Rs principle, our risk-assessment-based recommendation is that no additional nonclinical safety studies are needed when evaluating a 2-PE-containing presentation of a previously well-characterized vaccine product if the amount of 2-PE is ≤10 mg/dose. Full article

Background: Behçet’s Disease (BD) is a complex vasculitis affecting multiple organ systems, with Neuro-Behçet’s Disease (NBD) representing a rare yet severe manifestation. Data on NBD are limited, particularly in Middle Eastern populations. Methods: This retrospective observational study, spanning from 2000 to 2021, involved 262 BD patients at a tertiary medical center in Lebanon. NBD was diagnosed based on International Consensus Recommendation diagnostic criteria. Clinical data, including demographics, manifestations, inflammatory blood markers, genetics, and treatments, were collected. The modified Rankin Scale (mRS) was used to assess disease severity. Results: Among the cohort, 27 (10.3%) had NBD, with headaches, weakness, and dizziness as the most common presenting symptoms. The prevalence of NBD was similar across genders, which differs from some regional studies. HLA-B51 positivity was found in 50 out of 60 (83.3%) tested BD patients. Parenchymal NBD cases exhibited greater disease severity than non-parenchymal cases, with female patients experiencing a more severe course compared to males. Elevated inflammatory markers (CRP and ESR) were more common in patients with severe NBD. Corticosteroids and colchicine were the most commonly used therapies overall, while patients with better disease severity were more frequently prescribed methotrexate, mycophenolate, cyclophosphamide, adalimumab, and rituximab. An analysis of disease progression showed that at presentation, 57.1% (n = 12) of NBD patients had mild to moderate disability, which increased to 76.2% (n = 16) at the last follow-up, including 10 patients who showed an improvement in their mRS score. Conclusions: This study provides valuable insights into the prevalence and clinical characteristics of NBD in a Middle Eastern population. These findings enhance our understanding of NBD in the Middle East, highlighting the need for further research to improve diagnosis and management. Full article

Recommender systems (RSs) are widely used in various domains, such as e-commerce, social media, and online content platforms, to guide users’ decision-making by suggesting items that match their preferences and interests. However, these systems are highly vulnerable to shilling attacks, where malicious users create fake profiles to manipulate the recommendation results, thereby influencing users’ decisions. Such attacks can severely degrade the quality and reliability of recommendations, undermining the trust in RSs. A comprehensive understanding of shilling attacks is critical not only for improving the robustness of RSs but also for designing effective countermeasures to mitigate their impact. Existing shilling attack methods often face significant challenges in achieving both invisibility (i.e., making fake profiles indistinguishable from legitimate ones) and transferability (i.e., the ability to work across different RSs). Many current approaches either fail to capture the natural distribution of real user data or are highly tailored to specific RS algorithms, limiting their general applicability and effectiveness. To overcome these limitations, we propose DIFshilling, a novel diffusion-based model for shilling attacks. DIFshilling leverages forward noising and reverse denoising techniques to better model the distribution of real user data, allowing it to generate fake users that are statistically similar to legitimate users, thus enhancing the invisibility of the attack. Unlike traditional methods, DIFshilling is independent of the specific recommendation algorithm, making it highly transferable across various RSs. We evaluate DIFshilling through extensive experiments on seven different victim RS models, demonstrating its superior transferability. The experimental results show that DIFshilling not only achieves outstanding effectiveness in terms of attack success but also exhibits strong adversarial defense capabilities, effectively evading detection mechanisms. Specifically, in experiments conducted on the ML100K dataset with the DGCF victim model, DIFshilling was able to increase the frequency of the targeted item by a factor of 15 while maintaining the lowest detection precision and recall, illustrating its ability to remain undetected by common defense techniques. These results underscore the potential of DIFshilling as a powerful tool for both evaluating the vulnerabilities of RS and designing more robust countermeasures. Full article

Bitter taste receptors (TAS2Rs) are expressed in extraoral tissues, exerting several functions and generating a whole-body chemosensory and protective system. TAS2Rs expression has been observed in the gastrointestinal tract, although their role is poorly understood. This study aims to investigate the role of TAS2R38 and 46 in human intestinal smooth muscle cells (HISMCs) after activation with the specific bitter ligands phenylthiocarbamide and absinthin, respectively. We found that TAS2R38 and 46 activation by phenylthiocarbamide (PTC) and absinthin, respectively, induces a rapid membrane depolarization and increase of cytosolic calcium levels due to internal storage in the IP₃ pathway, resulting in an accelerated cell contraction. Overall, this study unravels, for the first time, the contractile impact of these TAS2R subtypes on intestinal smooth muscle cells, suggesting their involvement in gut peristalsis and recommending these receptors as possible targets for new therapies. Full article

Unexpected yet advantageous findings, often referred to as serendipitous discoveries, are becoming increasingly significant in the field of computer science. This research aims to examine the impact of factors that could potentially trigger such serendipity within a recommender system (RS) and consequently proposes a novel, serendipity-incorporated recommender system (SRS). The SRS is developed by integrating elements that could stimulate the occurrence of serendipity into an RS algorithm. These elements include interestingness, diversity, and unexpectedness. As a result, the SRS is equipped to provide users with recommendations that are surprising, intriguing, and atypical. The algorithm within the SRS recommends three items predicated on a user’s preferred item. To facilitate the selection of items to be recommended, we have designed a computation method called the ’serendipity measure’, which is tasked with calculating the weights of all items. Our innovative algorithm and its efficient execution are expounded upon extensively in this study. The performance of the SRS was assessed using a quantitative serendipity evaluation model (QSEM). This model is a quantitative tool designed to measure the probability of users encountering serendipitous events within a specific information space. We conducted a user study to compare the SRS with the traditional cold-start recommender system (CRS), and the feedback for the SRS was positively received. The experiments confirm the viability of cultivating a serendipitous environment from a system’s perspective. The test results also underline the exciting potential that serendipity brings to recommender systems. Full article

Recommendation systems (RS) have become integral to numerous digital platforms and applications, ranging from e-commerce to content streaming field. A critical problem in RS is that the ratings are missing not at random (MNAR), which is due to the users always giving feedback on items with self-selection. The biased selection of rating data results in inaccurate rating prediction for all user-item pairs. Doubly robust (DR) learning has been studied in many tasks in RS, which is unbiased when either a single imputation or a single propensity model is accurate. In addition, multiple robust (MR) has been proposed with multiple imputation models and propensity models, and is unbiased when there exists a linear combination of these imputation models and propensity models is correct. However, we claim that the imputed errors and propensity scores are miscalibrated in the MR method. In this paper, we propose a gradient-based calibrated multiple robust learning method to enhance the debiasing performance and reliability of the rating prediction model. Specifically, we propose to use bi-level optimization to solve the weights and model coefficients of each propensity and imputation model in MR framework. Moreover, we adopt the differentiable expected calibration error as part of the objective to optimize the model calibration quality directly. Experiments on three real-world datasets show that our method outperforms the state-of-the-art baselines. Full article

Background: Despite the high progress that has been made in the field of cardiology, the left ventricular assist device (LVAD) can still cause complications (thrombosis/bleeding) in heart failure (HF) patients after implantation. Complications develop due to the incorrect dose of antithrombotic therapy, due to the influence of the non-physiological shear stress of the device, and also due to inherited genetic polymorphisms. Therefore, the aim of our study is to identify the influence of the genetic polymorphisms on complication development in HF patients with implanted LVADs with prescribed antiplatelet therapy. Methods: Our study investigated 98 HF patients with/without complications who were genotyped for 21 single-nucleotide polymorphisms (SNPs) associated with cardiovascular events, the coagulation system, and the metabolism of warfarin and aspirin drugs. This study performed a more detailed analysis on genetic polymorphism in the UGT1A6 gene and its influence on aspirin dose. Results: SNP rs2070959 in the UGT1A6 gene showed a significant association with the group of HF patients with complications [(OR (95% CI): 4.40 (1.06–18.20), p = 0.044]. The genetic polymorphism of rs2070959 in the UGT1A6 gene showed a significant association in HF patients who received aspirin treatment on the 12th month after LVAD implantation [OR (95% CI): 5.10 (1.31–19.87), p = 0.018]. Moreover, our genotype distribution analysis showed that the GG genotype of rs2070959 in the UGT1A6 gene was significantly higher in the group with aspirin treatment than without treatment after the 12th month of treatment (50.0% vs. 0%, p = 0.008), especially in the group of patients with complications. A higher frequency of the GG genotype with long-lasting aspirin therapy up to the 12th month showed that 100 mg of aspirin was not an effective dose in the group of patients with complications. Conclusions: Our study identified that genotyping for genetic polymorphism rs2070959 in the UGT1A6 gene could predict the recommended dose of aspirin in HF patients, which could help to prevent and predict complication development after LVAD implantation. Full article

In the era of vast information, individuals are immersed in choices when purchasing goods and services. Recommender systems (RS) have emerged as vital tools to navigate these excess options. However, these systems encounter challenges like data sparsity, impairing their effectiveness. This paper proposes a novel approach to address this issue and enhance RS performance. By integrating user demographic data, singular value decomposition (SVD) clustering, and semantic similarity in collaborative filtering (CF), we introduce the UDIS method. This method amalgamates four prediction types—user-based CF (U), demographic-similarity-based (D), item-based CF (I), and semantic-similarity-based (S). UDIS generates separate predictions for each category and evaluates four different merging techniques—the average, max, weighted sum, and Shambour methods—to integrate these predictions. Among these, the average method proved most effective, offering a balanced approach that significantly improved precision and accuracy on the MovieLens dataset compared to alternative methods. Full article

Mobile applications have been shown to be an effective and feasible intervention medium for improving healthy food intake in different target groups. As part of the PeRsOnalized nutriTion for hEalthy livINg (PROTEIN) European Union H2020 project, the PROTEIN mobile application was developed as an end-user environment, aiming to facilitate healthier lifestyles through artificial intelligence (AI)-based personalised dietary and physical activity recommendations. Recommendations were generated by an AI advisor for different user groups, combining users’ personal information and preferences with a custom knowledge-based system developed by experts to create personalised, evidence-based nutrition and activity plans. The PROTEIN app was piloted across different user groups in five European countries (Belgium, Germany, Greece, Portugal, and the United Kingdom). Data from the PROTEIN app’s user database (n = 579) and the PROTEIN end-user questionnaire (n = 446) were analysed using the chi-square test of independence to identify associations between personal goals, meal recommendations, and meal adherence among different gender, age, and user groups. The results indicate that weight loss-related goals are more prevalent, as well as more engaging, across all users. Health- and physical activity-related goals are key for increased meal adherence, with further differentiation evident between age and user groups. Congruency between user groups and their respective goals is also important for increased meal adherence. Our study outcomes, and the overall research framework created by the PROTEIN project, can be used to inform the future development of nutrition mobile applications and enable researchers and application designers/developers to better address personalisation for specific user groups, with a focus on user intent, as well as in-app features. Full article

The recommender system (RS) has been widely adopted in many applications, including online advertisements. Predicting the conversion rate (CVR) can help in evaluating the effects of advertisements on users and capturing users’ features, playing an important role in RS. In real-world scenarios, implicit rather than explicit feedback data are more abundant. Thus, directly training the RS with collected data may lead to suboptimal performance due to selection bias inherited from the nature of implicit feedback. Methods such as reweighting have been proposed to tackle selection bias; however, these methods omit delayed feedback, which often occurs due to limited observation times. We propose a novel likelihood approach combining the assumed parametric model for delayed feedback and the reweighting method to address selection bias. Specifically, the proposed methods minimize the likelihood-based loss using the multi-task learning method. The proposed methods are evaluated on the real-world Coat and Yahoo datasets. The proposed methods improve the AUC by 5.7% on Coat and 3.7% on Yahoo compared with the best baseline models. The proposed methods successfully debias the CVR prediction model in the presence of delayed implicit feedback. Full article

Mulching is one of the most recommended practices in agriculture due to its positive effects on the plant/soil system. Very few experiments have been conducted to date to investigate the effect of mulching, with both organic and inorganic materials, on tobacco. The main aim of this study was to test the synergic effect of a soil-biodegradable (according to standard EN17033) mulching film (the commercial Mater-Bi^®, Novamont SpA, Novara, Italy) and drip irrigation (M-D) compared with that of bare soil and sprinkler/drip irrigation (first/second part of the growing season; BS-SD) on a tobacco crop (Nicotiana tabacum L., flue-cured Virginia) grown in the Tiber Valley (the tobacco cultivation district of Central Italy). BS-SD represents the standard practice applied by tobacco growers in the study area. The plants grown under the M-D management system grew more and developed faster than the plants grown under BS-SD conditions. Under the M-D system, yields increased in comparison with the BS-SD conditions (+29%, on average). The gross revenue obtained via the M-D-cured products also increased (+63%, on average) thanks to higher prices assigned by expert evaluators on the basis of the extrinsic quality traits (color, structure and texture, degree of ripeness, elasticity, lamina integrity, handling defects, and vein incidence). The economic value of the cured products increased with the leaf crowns; it was the lowest in the basal (B) leaves and the highest in the middle-upper (MU) leaves. The intrinsic quality traits of the cured leaves (total N and nitrate contents, alkaloids, and reducing sugars) also confirmed that the best quality was found in the M-D-cured products, as determined by expert evaluation. Interestingly, the reducing sugar (RS) contents of tobacco obtained using the M-D management system were 2.5-, 1.1-, and 0.9-fold greater than those under the BS-SD conditions (B, M, and MU products, respectively). An additional commercial value of the cured products was thus obtained with the M-D crop management system due to RS, an intrinsic quality trait considered by manufacturing industries. Full article