Browse Articles

Dynamic pricing modeling and inventory management in omnichannel retail using Quantum Decision Theory and reinforcement learning

In the world of omnichannel retail, where customers seamlessly switch between online and offline channels, pricing and inventory management decisions have become more complex than ever. Customer purchasing behavior is influenced by uncertainty, market fluctuations, and competitive interactions, which traditional models fail to accurately predict. In such conditions, the need for intelligent and adaptive decision-making frameworks is more critical than ever. For the first time, this study presents a novel approach combining Quantum Decision Theory, Quantum Markov Chains (QMC), Quantum Dynamic Games, and Reinforcement Learning to optimize dynamic pricing and inventory management. By leveraging concepts such as superposition, observer effect, and quantum interference, the proposed model overcomes the limitations of classical models and provides a deeper understanding of customer behavior in uncertain environments. Additionally, a Quantum Multi-Level Markov Process (QMLMP) is employed to model market variations and enhance predictions. The results of this study demonstrate that the innovative model improves the accuracy of purchase behavior predictions, optimizes pricing and inventory management strategies, and helps retailers make more competitive and profitable decisions. This research introduces a transformative approach to tackling retail challenges in the digital age and paves the way for future studies in this domain.

Telomere length as a genomic biomarker for assessing microplastic-induced damage in farmed gilthead sea bream

Investigating the evolutionary dynamics and mutational pattern of SARS-CoV-2 spike gene on selected SARS-CoV-2 variants

The continuous evolution of SARS-CoV-2 has led to the emergence of several variants representing significant challenges for public health. Many studies highlight the relevance of phylogenetic inference or mutational pattern analysis to understand the evolutionary relatedness of viral variants and to estimate the potential effect of new mutations on viral transmission, virulence and antigenicity. Here we describe an evolutionary investigation approach combined with mutational analyses of SARS-CoV-2 Spike gene to annotate and potentially track important amino acid site variation of specific functional domain relevant for viral survival. This approach was applied on XBB*, EG* and BA* and their sub-lineages (see materials and methods) available from GISAID. In addition, we considered the major variants of concern (Alpha, Delta, Omicron) and Wuhan-Hu-1 strain as references. Maximum likelihood phylogenetic tree was constructed from the complete dataset while selection pressure and mutational analyses were conducted on single variants separately. The obtained phylogenetic tree of Spike amino acid gene sequence showed a clear separation of viral variants as well as their expected appearance order. This result supported the significance of selection pressure analyses outcomes combined with amino acid mutational frequencies where in many cases they showed a linear and parallel trend. This allowed also to hypothesize the potential importance of low-frequency mutations in new potential virus variants. This study constitutes an asset of important insights to be considered in regular monitoring programs. In addition, the analysis framework described here introduces a starting point for further standardization, optimization and application on different data types and in large-scale studies.

Thermal power plant proximity alters Olive composition and induces cytotoxicity in human cells

Correction: Is Benin on track to reach universal household coverage of basic water, sanitation and hygiene services by 2030?

Vulnerability assessment model integrating outcome and characteristic-based metrics for electric motorcycle battery swapping and charging stations

Abstract Battery swapping and charging stations are essential for increasing the adoption of electric motorcycles. The stations address the range anxiety issue and quickly obtain a fully recharged battery. However, operational issues with swapping and charging activities drive operational vulnerability. Therefore, this study proposes a vulnerability assessment model utilizing the IoT Platform data of electric motorcycle battery swapping and charging stations. The model computes a vulnerability score by integrating vulnerability indicator metrics of the system outcome and characteristic. The system outcome uses performance data representing vulnerability impact. The system characteristic uses data from the vulnerability driver and exposure factors. The driver factor represents mitigation ability, and the exposure factor represents conditions that may affect both the mitigation ability and performance. The model also classifies the vulnerability of stations in four categories: not vulnerable, potentially vulnerable, moderately vulnerable, and vulnerable. The model was implemented in a case in Jakarta. The result reveals significant differences in vulnerability among stations, although most stations fall into the not vulnerable to moderately vulnerable categories. The findings facilitate identifying station characteristics that potentially affect performance quantitatively.

Prognostic value of FOXA1 in estrogen receptor-negative breast cancer: A systematic review and meta-analysis

Breast cancer remains the most common cancer among women worldwide, and recurrence rates stay high despite current treatments, especially for those with negative estrogen receptor status, where therapies are less effective, and prognosis is worse. Identifying molecules with predictive value for therapy response and prognosis is therefore crucial. In this context, FOXA1 could serve as a potential biomarker to predict the progression of ER-negative tumors. A search was conducted to answer the question, “What is the prognostic value of FOXA1 expression in breast cancer, estrogen receptor negative?” using various databases. Controlled vocabulary and Boolean operators were employed. Only studies reporting overall survival and disease-free survival, defined as the time from evaluation to death or relapse, were included. We identified seven articles evaluating FOXA1 and its relationship with disease-free survival (DFS) or overall survival (OS) in patients with ER-negative breast cancer. Our data indicate that higher FOXA1 expression is associated with improved overall survival (HR = 0.61, CI = 0.45–0.83, p < 0.002) and better disease-free survival (HR = 0.69, CI = 0.51–0.93, p < 0.02). These findings suggest that FOXA1 is linked to a favorable prognosis in terms of overall survival and disease-free survival. Further studies are needed to assess the role of FOXA1 in response to chemotherapy. PROSPERO registration number: CRD42024453750

Exploring farmers’ knowledge, attitudes and control practices on ixodid tick in the context of climate change of South Kivu province, Eastern Democratic Republic of Congo

Machine learning-driven Diabetes Health Tracer (DHT): Optimizing prognosis using RaSK_GraDe and RaSK_GraDeL models

Diabetes mellitus presents a significant global health challenge, particularly in regions like Pakistan, India, and Bangladesh. Machine learning (ML) techniques offer promising solutions for diabetes prediction, surpassing traditional methods in reliability and efficiency. This research conducts a comparative analysis of ML algorithms including Random Forest (RF), Decision Tree (DT), Support Vector Machine (SVM), K-nearest neighbors (KNN), Gradient Boosting (GB), RaSK_GraDe (Proposed Voting), and RaSK_GraDeL (Proposed Stacking). Evaluation is performed using datasets, such as PIMA Indian, Frankfurt Hospitals Diabetes, RTML with Insulin, and the proposed Diabetes Health Tracer (DHT) dataset comprising 2877 observations with nine features. Data pre-processing techniques address missing values, outliers, normalization, and class balancing (SMOTE), enhancing model robustness. Hyperparameter tuning via cross-validation and Random Search optimizes model performance. Additionally, ensemble methods—Voting Classifier (RaSK GraDe) and Stacking Model (RaSK GraDeL with Logistic Regression) are applied, achieving notable accuracies of 98.03% and 98.55%, respectively, on the DHT dataset. The study underscores ML’s potential in diabetes prediction, advocating for personalized treatment and healthcare management advancements.

Clinical outcome prediction in pediatric respiratory infections using hybrid feature selection and a genetic algorithm-optimized machine learning

Abstract Respiratory ailments constitute various pathological conditions affecting the respiratory system, including the airways, pulmonary tissues, and associated structures. When these conditions are left untreated or inadequately managed, they can result in long-term complications, diminished life quality, and higher death rates. To alleviate the strain of respiratory illnesses and promote a more robust population, it is crucial to focus on raising public awareness, facilitating early detection, implementing preventive strategies like immunization, and furthering medical advancements in treatment options. The study presents a comprehensive Machine Learning (ML) method to improve the investigation and classification of respiratory datasets. The technique applies data preprocessing, augmentation, feature selection, genetic algorithms, and ensemble learning techniques on a “Respiratory dataset” and achieves high predicted accuracy while maintaining interpretability. The Synthetic Minority Oversampling Technique (SMOTE) is used to address data imbalance and ensure proper representation of minority class samples. The feature selection module uses various strategies to find relevant characteristics and reduce dimensionality. Machine learning algorithms that are apt for the dataset are employed for predicting the target variable; their performance is measured and analyzed thoroughly. By using Genetic algorithms, Random Forest, XGBoost, and Gradient Boosting are selected as optimal models. The ensemble learning framework combines the 3 optimal models and creates a strong classification system to predict “target variable : Clinical Progression” output. The performance measures of the proposed model achieved an overall accuracy of 95.02% when compared with the existing works and can be applied in healthcare analytics.

Towards a more integrative environmental assessment: Infauna as tool for Zostera marina conservation management

Seagrasses are highly sensitive to human-induced disturbances and global environmental changes. Since the 1980s, Zostera marina meadows along the West Swedish coast (Skagerrak) have declined significantly, as evidenced by changes in morpho-anatomical traits, reductions in area coverage, and shifts in associated communities. However, infaunal assemblages within Z. marina meadows remain understudied compared to epifaunal communities and have not been previously used as indicators of seagrass regression. To investigate spatial variability in infaunal composition, we analysed samples from 15 coastal stations at depths of 1.5–3 m depth. Using an n-dimensional hypervolume framework, we assessed functional differences between infaunal and epifaunal communities. We examined infaunal community descriptors—such as species richness and individual abundance—biotic indices, environmental drivers (including wave exposure and Z. marina biomass), and correlations with epifauna. Variability in infaunal composition across sampling stations was primarily driven by differences in the abundance of dominant taxa, including the polychaete Capitella capitata , oligochaetes, nematodes, and chironomids. Several coastal stations, such as Marstrand and Finsbo, were classified as moderately polluted, though biotic indices, i.e., AMBI, M-AMBI and ISI, showed discrepancies. Spatial patterns in infaunal assemblages were mainly influenced by Z. marina biomass and maximum fetch, with a good representation of oligochaetes and chironomids in exposed stations. These findings suggest that infauna respond differently from epifauna but provide valuable additional insights into the ecological status, functional traits, and trophic diversity of Z. marina meadows. Integrating multiple community components is essential for a more comprehensive understanding of the processes and patterns driving seagrass ecosystem regression.

Synergistic catalytic ozonation of humic acid in water over activated alumina modified with cerium and manganese oxides

Quantitative and qualitative changes in substance-related administrative offences in road traffic during the SARS-CoV-2 pandemic in Munich

Introduction The SARS-CoV-2 pandemic beginning in 2020 led to significant restrictions on social life and mobility, raising concerns about increased substance use across the general population. To investigate whether the pandemic resulted in quantitative or qualitative changes in alcohol and/or drug use in the context of road traffic, a retrospective analysis of toxicological findings was conducted in the city of Munich, considering the local pandemic-related restrictions. Materials and methods A total of 6,210 blood samples were analyzed from individuals suspected of committing substance-related administrative traffic offences under §24a of the German Road Traffic Act between January 1, 2019, and July 31, 2021. Samples were examined for the presence of substances, their concentrations, and the type of vehicle involved. The cohort was stratified into pre-pandemic and pandemic periods, with March 16, 2020 set as the cut-off date. The pandemic period was further subdivided based on the severity of imposed restrictions. Statistical comparisons were performed using Fisher’s exact test, t-tests, ANOVA, and logistic regression. Results Cannabis was the most frequently detected substance (66.2% pre-pandemic; 67.4% during the pandemic), followed by alcohol (11.7% vs. 10.8%) and cocaine (5.7% vs. 5.2%). Only minor differences were observed between the pre-pandemic and pandemic periods, as well as across phases of mild versus severe restrictions. Notably, THC-COOH concentrations were higher during the pandemic. Alcohol levels were elevated during phases of light restrictions and reduced during periods of strict lockdown. Cannabis was most commonly detected in car drivers, whereas alcohol was more frequently found in e-scooter riders, particularly during less restrictive phases. Conclusion Substance detection patterns among drivers in Munich showed overall stability during the COVID-19 pandemic, with cannabis remaining the most commonly identified drug. However, shifts in substance concentrations and differences by vehicle type and restriction severity suggest subtle changes in consumption behavior. These findings underscore the need for continued surveillance and context-specific traffic safety measures.

Usable time estimation and suitable battery selection for electric tractor considering agricultural operational load

Ethical and legal considerations of artificial intelligence applications in psychiatric violence risk assessment: A scoping review protocol

Violence risk assessment is a critical component of psychiatric practice, with significant clinical, ethical, and legal implications. Psychiatric patients at high risk of violence often face interventions including restraints, intramuscular injections, and involuntary hospitalization. Agitated and aggressive behaviours from patients have been linked to high hospital costs due to increased length of stay, readmissions, increased medication use, staff injury, and need for high acuity monitoring. Traditional risk assessment tools can be time intensive and have poor generalizability to civil populations. Recent advances in artificial intelligence (AI) have the potential for enhancing the precision of violence risk assessments. Although AI can address the technical issues of risk assessment, its implementation will raise new ethical and legal challenges. In psychiatry, AI-assisted violence risk assessment intersects with mental health law, particularly criteria for preventive detention and the ethical boundaries of AI-driven decisions. There have been some early concerns about racial bias, lack of transparency, accountability, and disruption to current practices in psychiatric care. To our knowledge, there have been no efforts to synthesize the ethical and legal implications for this particular use case. To address these gaps, we conducted a scoping review to map the literature on the ethical and legal considerations of AI in violence risk assessment in acute psychiatry.

MAPK14 and its associated lncRNAs are up-regulated in lung tumors

Accurate semi-supervised automatic speech recognition for ordinary and characterized speeches via multi-hypotheses-based curriculum learning

How can we build accurate transcription models for both ordinary speech and characterized speech in a semi-supervised setting? ASR (Automatic Speech Recognition) systems are widely used in various real-world applications, including translation systems and transcription services. ASR models are tailored to serve one of two types of speeches: 1) ordinary speech (e.g., speeches from the general population) and 2) characterized speech (e.g., speeches from speakers with special traits, such as certain nationalities or speech disorders). Recently, the limited availability of labeled speech data and the high cost of manual labeling have drawn significant attention to the development of semi-supervised ASR systems. Previous semi-supervised ASR models employ a pseudo-labeling scheme to incorporate unlabeled examples during training. However, these methods rely heavily on pseudo labels during training and are therefore highly sensitive to the quality of pseudo labels. The issue of low-quality pseudo labels is particularly pronounced for characterized speech, due to the limited availability of data specific to a certain trait. This scarcity hinders the initial ASR model’s ability to effectively capture the unique characteristics of characterized speech, resulting in inaccurate pseudo labels. In this paper, we propose a framework for training accurate ASR models for both ordinary and characterized speeches in a semi-supervised setting. Specifically, we propose MOCA ( M ulti-hyp o theses-based C urriculum learning for semi-supervised A sr ) for ordinary speech and MOCA-S for characterized speech. MOCA and MOCA-S generate multiple hypotheses for each speech instance to reduce the heavy reliance on potentially inaccurate pseudo labels. Moreover, MOCA-S for characterized speech effectively supplements the limited trait-specific speech data by exploiting speeches of the other traits. Specifically, MOCA-S adjusts the number of pseudo labels based on the relevance to the target trait. Extensive experiments on real-world speech datasets show that MOCA and MOCA-S significantly improve the accuracy of previous ASR models.

RABEM: risk-adaptive Bayesian ensemble model for fraud detection

Piezoelectric row-column sensing system on table tennis rackets for hit and rotation measurement

Wearable sensing systems are often constrained by the number of available signal channels: expanding the sensor number typically improves human motion monitoring but drives up hardware complexity. In this paper, a row-column sensing method is proposed to address this limitation in the context of table tennis impact monitoring. The hit sensing position on the racket is decomposed into orthogonal row and column coordinates, with only one single striped piezoelectric PVDF (Polyvinylidene fluoride) flexible sensor placed on each axis. By combining the signals on each row and column, the hitting position is analytically obtained. In a 5 × 5 layout this architecture reduces required signal pathways from 25 to 10 (five rows plus five columns) while delivering same spatial accuracy. Additionally, the denser set of impact locations also enables detection of ball spin. In‑plane and out‑of‑plane rotations produce distinct stress distributions across the racket surface, which the array captures through differential row and column signal patterns. This approach can be extended to other wearable or sports devices that need higher spatial resolution without proportional increases in channel count, and it shows clear potential for advancing table tennis training, officiating, and performance analysis.

Individual differences in anthropomorphism help explain social connection to AI companions