As artificial intelligence (AI) transitions from research to deployment, creating the appropriate datasets and data pipelines to develop and evaluate AI models is increasingly the biggest challenge. ...Automated AI model builders that are publicly available can now achieve top performance in many applications. In contrast, the design and sculpting of the data used to develop AI often rely on bespoke manual work, and they critically affect the trustworthiness of the model. This Perspective discusses key considerations for each stage of the data-for-AI pipeline—starting from data design to data sculpting (for example, cleaning, valuation and annotation) and data evaluation—to make AI more reliable. We highlight technical advances that help to make the data-for-AI pipeline more scalable and rigorous. Furthermore, we discuss how recent data regulations and policies can impact AI.It has become rapidly clear in the past few years that the creation, use and maintenance of high-quality annotated datasets for robust and reliable AI applications requires careful attention. This Perspective discusses challenges, considerations and best practices for various stages in the data-to-AI pipeline, to encourage a more data-centric approach.
We propose a novel approach to learn and recognize natural scene categories. Unlike previous work, it does not require experts to annotate the training set. We represent the image of a scene by a ...collection of local regions, denoted as codewords obtained by unsupervised learning. Each region is represented as part of a "theme". In previous work, such themes were learnt from hand-annotations of experts, while our method learns the theme distributions as well as the codewords distribution over the themes without supervision. We report satisfactory categorization performances on a large set of 13 categories of complex scenes.
Despite a growing interest in environmentally sustainable practices, consumers continue to prioritize taste, quality, and price above environmental concerns when purchasing food products. Previous ...studies have shown that environmental claims or messages may not uniformly enhance product perceptions. This research examines strategic approaches to framing substantively identical environmental benefit claims differently across product types to enhance consumers' sensory and quality evaluations as well as their willingness‐to‐pay for sustainable foods. Results from two experiments show that consumers' assessments of sustainable utilitarian and hedonic food products can be enhanced if environmental claims are strategically framed in accordance with the nature of product types. The alignment of utilitarian food products with an environment‐focus frame that emphasizes environmental benefits and hedonic food products with a self‐focus frame that stresses the personal relevance of these protections and benefits can enhance consumers' experienced tastiness, quality evaluations, and willingness‐to‐pay for sustainable foods.
Plenty of researches have been carried out, focusing on the measures of distance, similarity, and correlation between intuitionistic fuzzy sets (IFSs). However, most of them are single-valued ...measures and lack of potential for efficiency validation. In this paper, a new vector valued similarity measure for IFSs is proposed based on OWA operators. The vector is defined as a two-tuple consisting of the similarity measure and uncertainty measure, in which the latter is the uncertainty of the former. OWA operators have the ability to aggregate all values in the universe of discourse of IFSs, and to determine the weights according to specific applications. A framework is built to measure similarity between IFSs. A series of definitions and theorems are given and proved to satisfy the corresponding axioms defined for IFSs. In order to illustrate the effectiveness of the proposed vector valued similarity measure, a classification problem is used as an application.
This research aims to investigate the effectiveness of the adoption of external reference price (ERP) in influencing consumers' pay-what-you-want (PWYW) final payments across different product types. ...Results from two experiments show the effectiveness of using ERP as an anchor heavily depends on the nature of the product category. For hedonic products, the absence of an ERP, compared to the presence of one, leads to higher perceived quality and PWYW payments. The results are the opposite for utilitarian products. This study contributes to PWYW literature by investigating how product types affect consumers’ perceived quality of the product offered and their PWYW payments.
To explore the potential of utilising radiomics analysis and machine-learning models that incorporate intratumoural and peritumoural regions of interest (ROIs) for predicting brain metastasis (BM) in ...newly diagnosed lung cancer patients.
The study comprised 183 lung cancer patients (training cohort: n=146; validation cohort: n=37) whose radiomics features were extracted from plain computed tomography (CT) images of the primary lesion. Four machine-learning algorithms (logistic regression LR, support vector machine SVM, k-nearest neighbour algorithm KNN, and random forest RF) were employed to develop predictive models. Model diagnostic performance was assessed through receiver operating characteristic (ROC) analysis, and clinical utility was evaluated using decision curve analysis (DCA). Finally, the radiomics model's generalisation ability was further validated in the prediction of metachronous brain metastasis (MBM).
After feature screening, 22 radiomics features were identified as highly predictive, of which nine were derived from the peritumour region. All four machine-learning models demonstrated predictive capability, with SVM showing superior efficiency and robustness. The area under the ROC curve (AUC) of SVM was 0.918 in the training cohort and 0.901 in the validation cohort. DCA indicated the highest net benefit. Furthermore, the time-dependent ROC curve exhibited predictive efficacy for MBM occurrence across 1-, 2-, and 3-year follow-up periods, with all AUC values exceeding 0.7.
The optimal SVM model integrating intratumoural and peritumoural radiomics features was confirmed and defined as an imaging biomarker for predicting BM in newly diagnosed lung cancer patients, underscoring its potential to significantly impact clinical diagnosis and treatment.
•22 radiomic features identified as predictors.•Developed four effective machine learning models.•SVM optimally predicts initial brain metastasis.•SVM also forecasts subsequent brain metastasis.
Mammalian folate metabolism is comprised of cytosolic and mitochondrial pathways with nearly identical core reactions, yet the functional advantages of such an organization are not well understood. ...Using genome-editing and biochemical approaches, we find that ablating folate metabolism in the mitochondria of mammalian cell lines results in folate degradation in the cytosol. Mechanistically, we show that QDPR, an enzyme in tetrahydrobiopterin metabolism, moonlights to repair oxidative damage to tetrahydrofolate (THF). This repair capacity is overwhelmed when cytosolic THF hyperaccumulates in the absence of mitochondrially produced formate, leading to THF degradation. Unexpectedly, we also find that the classic antifolate methotrexate, by inhibiting its well-known target DHFR, causes even more extensive folate degradation in nearly all tested cancer cell lines. These findings shed light on design features of folate metabolism, provide a biochemical basis for clinically observed folate deficiency in QDPR-deficient patients, and reveal a hitherto unknown and unexplored cellular effect of methotrexate.
Display omitted
•Formate from mitochondrial serine metabolism protects cytosolic THF from degradation•Methotrexate causes degradation of cytosolic folate by a similar pathway•QDPR can reverse THF oxidation and preserve cytosolic folate levels•This role of QDPR can explain the folate deficiency in patients with QDPR mutations
Stratification of folate metabolism into distinct cytosolic and mitochondrial compartments enables repair of oxidative-stress-induced damage to folate metabolites while maintaining overall cellular pools of this nutrient.
The viability of online dynamic pricing, or differential pricing for the same product from the same seller, is still debatable given the contradictory findings reported in both modeling and ...behavioral price research. This paper examines tactical ways for online merchants to mitigate consumers’ negative reactions when adopting dynamic pricing strategies. In three experiments, we show that using various price-framing tactics, compared to no framing, can induce price-disadvantaged consumers to perceive their ostensibly similar transactions differently relative to their comparative other parties. As the degree of perceived transaction dissimilarity increases, price-disadvantaged consumers’ perceived price fairness, trust, and repurchase intentions are enhanced. We further compare different price framing tactics and demonstrate that they have different effects on consumers across different product price levels, customer segments, and framing formats. The paper concludes with theoretical and managerial implications of the research.
Current approaches to object category recognition require datasets of training images to be manually prepared, with varying degrees of supervision. We present an approach that can learn an object ...category from just its name, by utilizing the raw output of image search engines available on the Internet. We develop a new model, TSI-pLSA, which extends pLSA (as applied to visual words) to include spatial information in a translation and scale invariant manner. Our approach can handle the high intra-class variability and large proportion of unrelated images returned by search engines. We evaluate tire models on standard test sets, showing performance competitive with existing methods trained on hand prepared datasets
While negative moods (e.g., anxiety and depression) deriving from environmental problems have become a common public concern, little is known about how consumers’ negative mood states affect their ...green purchase intentions, especially when consumers hold ambivalent attitudes toward buying green products. This paper addresses these issues through four studies of Chinese consumers. Our findings demonstrate that highly ambivalent attitudes toward green products decrease green purchase intentions (Study 1). This negative effect is weakened when consumers are in a more (as opposed to less) anxious mood (Studies 2 and 3) but strengthened when consumers are in a more (as opposed to less) depressed mood (Study 4). Both effects are more prominent among low‐ambivalence consumers than high‐ambivalence consumers. This research shows that not all negative mood states have the same influence on consumers’ green purchase decision making.