Abstract
In this work, we assess the impact of self-supervised learning (SSL) approaches on the detection of gastritis atrophy (GA) and intestinal metaplasia (IM) conditions. GA and IM are precancerous gastric lesions. Detecting these lesions is crucial to intervene early and prevent their progression to cancer. A set of experiments is conducted over the Chengdu dataset, by considering different amounts of annotated data in the training phase. Our results reveal that, when all available data is used for training, SSL approaches achieve a classification accuracy on par with a supervised learning baseline, (81.52% vs 81.76%). Interestingly, we observe that in low-data regimes (here represented as retaining only 12.5% of annotated data for training), the SSL model guarantees an accuracy gain with respect to the supervised learning baseline of approximately 1.5% (73.00% vs 71.52%). This observation hints at the potential of SSL models in leveraging unlabeled data, thus showcasing more robust performance improvements and generalization. Experimental results also show that SSL performance is significantly dependent on the specific data augmentation techniques and parameters adopted for contrastive learning, thus advocating for further investigations into the definition of optimal data augmentation frameworks specifically tailored for gastric lesion detection applications.

Abstract
Context. The amount of adaptive optics (AO) telemetry generated by visible/near-infrared ground-based observatories is ever greater, leading to a growing need for a standardised data exchange format to support performance analysis, AO research, and development activities that involve large-scale telemetry mining, processing, and curation. Aims. This paper introduces the Adaptive Optics Telemetry (AOT) data exchange format as a standard for sharing AO telemetry from visible/infrared ground-based observatories. AOT is based on the flexible image transport system (FITS) and aims to provide unambiguous and consistent data access across various systems and configurations, including natural and single- or multiple-laser guide-star AO systems. Methods. We designed AOT with a focus on two key use cases: atmospheric turbulence parameter estimation and point-spread function reconstruction. We prototyped and tested the design using existing AO telemetry datasets from multiple systems: single conjugate with natural and laser guide stars, tomographic systems with multi-channel wavefront sensors, and single- and multi-wavefront correctors in systems featuring either a Shack-Hartmann or Pyramid as the main wavefront sensor. Results. The AOT file structure has been thoroughly defined, with specified data fields, descriptions, data types, units, and expected dimensions. To support this format, we have developed a Python package that enables the data conversion, reading, writing, and exploration of AOT files; it has been made publicly available and is compatible with a general-purpose Python package manager. We have demonstrated the flexibility of the AOT format by packaging data from five different instruments, installed on different telescopes.

Abstract
Retailers face increasing competitive pressure to determine how best to deliver products purchased online to the end customer. Grocery retailers often require attended home delivery where the customer must be present to receive the delivery. For attended home delivery to function, the retailer and customer must agree on a delivery time slot that works for both parties. Using online data from a grocery retailer, we observe customer preferences for three delivery service attributes associated with each time slot: speed, precision, and timing. We define speed as the expected time between the placement of an order and its delivery, precision as the duration of the offered time slot, and timing as the availability of choices across times of the day and days of the week. We show that customers not only value speed as an attribute of delivery service but that precision and timing are also key drivers of the customer's time slot selection process. We also observe substantial customer heterogeneity in the willingness of customers to pay for time slots. Customers that differ in their loyalty to the retailer, basket value, basket size, and basket composition exhibit distinct differences in their willingness to pay. We show that retailers with the capability to tailor their time slot offerings to specific customer segments have the potential to generate approximately 9% more shipping revenue than those who cannot. Our findings inform practitioners seeking to design competitive fulfillment strategies and academics customer behavior in the attended home context.

Abstract
This paper introduces the Kabsch Marker Estimation Algorithm (KMEA), a new, robust multi-marker localization method designed for Autonomous Mobile Robots (AMRs) within Industry 4.0 (I4.0) settings. By integrating the Kabsch Algorithm, our approach significantly enhances localization robustness by aligning detected fiducial markers with their known positions. Unlike conventional methods that rely on a limited subset of visible markers, the KMEA uses all available markers, without requiring the camera's extrinsic parameters, thereby improving robustness. The algorithm was validated in an I4.0 automated warehouse mockup, with a four-stage methodology compared to a previously established marker estimation algorithm for reference. On the one hand, the results have demonstrated the KMEA's similar performance in standard controlled scenarios, with millimetric precision across a set of error metrics and a mean relative error (MRE) of less than 1%. On the other hand, KMEA, when faced with challenging test scenarios with outliers, showed significantly superior performance compared to the baseline algorithm, where it maintained a millimetric to centimetric scale in error metrics, whereas the other suffered extreme degradation. This was emphasized by the average reduced results of error metrics from 86.9% to 92% in Parts III and IV of the test methodology, respectively. These results were achieved using low-cost hardware, indicating the possibility of even greater accuracy with advanced equipment. The paper details the algorithm's development, theoretical framework, comparative advantages over existing methods, discusses the test results, and concludes with comments regarding its potential for industrial and commercial applications by its scalability and reliability.

Abstract
In today's knowledge-driven economy, collaboration among stakeholders is essential for the framing of innovative trends, with knowledge-intensive business services (KIBS) playing a core role in addressing market demand. Users' involvement in shaping products and services has been considered in innovation ecosystem frameworks. Fewer risks in service/product development, and more sustainability and market acceptance, are a few of the benefits arising from including the user community (UC) in innovation partnerships. However, the need for resources, absorptive capacity and tacit knowledge, among other capabilities, is often a reason for overlooking this important contributor. KIBS possess a vast knowledge base, cater to digital tools, and mediate and propel innovation with different partners, benefiting from exclusive cognitive proximity to remix extant knowledge with emergent information from communities into new products and services. The aim of this study is to assess and quantify the effect of the collaboration with UC through three active forms of collaboration (co-creation, mass customization, and personalization) on different innovation types developed in KIBS. The significance of the user community was proven across all innovation types. Robustness analysis confirmed the results for both P-KIBS and T-KIBS. P-KIBS may be better suited to co-creation policies for product and service innovation, personalization of processes, and organizational and marketing innovations. T-KIBS can focus on mass customization, ensuring good innovation success. Additionally, co-creation with user community is best for product innovation.

Abstract
Telecommunications and computer vision have evolved separately so far. Yet, with the shift to sub-terahertz (sub-THz) and terahertz (THz) radio communications, there is an opportunity to explore computer vision technologies together with radio communications, considering the dependency of both technologies on Line of Sight. The combination of radio sensing and computer vision can address challenges such as obstructions and poor lighting. Also, machine learning algorithms, capable of processing multimodal data, play a crucial role in deriving insights from raw and low-level sensing data, offering a new level of abstraction that can enhance various applications and use cases such as beamforming and terminal handovers. This paper introduces CONVERGE, a pioneering vision-radio paradigm that bridges this gap by leveraging Integrated Sensing and Communication (ISAC) to facilitate a dual View-to-Communicate, Communicate-to-View approach. CONVERGE offers tools that merge wireless communications and computer vision, establishing a novel Research Infrastructure (RI) that will be open to the scientific community and capable of providing open datasets. This new infrastructure will support future research in 6G and beyond concerning multiple verticals, such as telecommunications, automotive, manufacturing, media, and health.