reinforcement learning

Experimental Push-Off Test Dataset for Shear Transfer Capacity in GFRP-Reinforced Concrete Interfaces

This dataset compiles experimental push-off test results for evaluating the shear transfer capacity of concrete interfaces reinforced with Glass Fiber-Reinforced Polymer (GFRP) reinforcement. The database includes geometric, material, and reinforcement-related parameters used to characterize the tested specimens, including interface shear area, maximum aggregate size, reinforcement ratio and configuration, GFRP bar diameter, tensile strength and elastic modulus, concrete compressive strength, and experimentally measured shear transfer capacity. The dataset was assembled from published experimental studies and was used for the development and evaluation of machine-learning and regression-based predictive models for GFRP-reinforced concrete interfaces. It accompanies the study “Data-Driven Prediction of Shear Transfer Capacity in GFRP-Reinforced Concrete Interfaces” and supports reproducibility, model development, comparative assessment, and future research on shear transfer behavior of GFRP-reinforced concrete interfaces.

Modular Structure Parameter Generation Algorithm for Rapid Assembly and Disassembly in Temporary Environments

In view of the urgent demand for rapid assembly and disassembly of temporary modular structures, this paper proposes a parametric generation algorithm that places disassembly feasibility as a core constraint of scheme generation, prior to the verification stage at the end of design. A linkage representation system for geometric, interface, and logic parameters is established, and the feasible region of parameters is defined by the non‑interference disassembly criterion and the connection reuse threshold as hard constraints. On this basis, a hierarchical cooperative strategy for macro‑topology generation and micro‑parameter optimization is proposed, and two‑way information transfer between the two levels is realized via a differentiable surrogate model. A reversibility‑guided reinforcement learning reward function is designed to enable the generator to evaluate the blocking risk of an action on the subsequent disassembly path in real time during the module‑by‑module addition process. A dynamic connector adapter is developed to adaptively match connector parameters according to local stress distribution. Experiments show that, compared with the standard GNN benchmark in three typical temporary scenarios, the algorithm reduces disassembly time by 24.2%-27.2%, the constraint satisfaction rate reaches 93.2%, and the connection reuse rate increases to 86.4%, and the structural safety margin is maintained in the range of 0.38-0.52. The significant advantages of the proposed mechanism in the co‑optimization of disassembly efficiency and structural performance are verified.

Engineering a Governance-Aware AI Sandbox: Design, Implementation, and Lessons Learned

Collaborative AI experimentation in industry-academia requires environments that support rapid trials while maintaining controlled access, organisational isolation, and traceable workflows. Although interest in AI sandboxes is increasing, practical guidance on designing and building governance-aware experimentation platforms remains limited. This work designs and operationalizes a governance-aware, multi-tenant AI sandbox that supports structured experimentation and produces reusable evaluation evidence across stakeholders. The sandbox was developed in an industry-academia ecosystem using iteratively validated requirements gathered from industrial partners. The solution adopts a layered reference architecture that separates a multi-tenant presentation layer from a backend control plane and isolates execution and data management concerns into dedicated layers. The sandbox supports governed onboarding, project-based collaboration, controlled access to AI services, and traceable experimentation through approval workflows and audit logging. By structuring experiment context and governance decisions as persistent records, the sandbox enables evaluation evidence to be reused and compared across projects and stakeholders. The development experience yields lessons learned and practical considerations that inform deployment and future evolution of governance-aware sandbox platforms.

Strategic Participation on Tokenized Platforms: Balancing Investment and Labor Intensities

Participants on tokenized platforms (i.e., platforms with blockchain implementation) can simultaneously take multiple roles, such as user, investor, and laborer, and draw income from the last two roles. Unlike traditional markets that typically prioritize one means of profitable participation, participants on such platforms need to allocate their efforts on the platform to increase revenue. We developed a decision framework for determining participants’ strategic participation on tokenized platforms to maximize earnings from investment and labor. Individual participants were distinguished from the platform-average participant, and decision-making is cast into two subproblems: (1) ignoring individual actions’ impact on platform state, we constructed strategies based on metrics that characterized model projections of future platform development and derived the metrics from Monte Carlo ensembles; (2) considering individuals’ actions as explicitly influencing the platform state, we formulated the control problem as a Markov decision process and solved it via reinforcement learning (RL). The framework addresses parameter uncertainty from model estimation, system uncertainty in model projection, and input uncertainty during participant-platform interaction. We compared metric-based and RL strategies from the two solution approaches using historical token price series; the results suggest good performance of our decision framework.

ARTIFICIAL INTELLIGENCE IN DRUG RESPONSE PREDICTION AND PHARMACOLOGICAL THERAPY OPTIMIZATION: ADVANCES, CHALLENGES, AND FUTURE PERSPECTIVES

Driven by artificial intelligence, or AI, today's medicinal science has the potential of rapidly transforming a doctor's knowledge of patient reactions to a variety of medications. In clinical practice, one has seen that sometimes a given medication is effective and sometimes ineffective in a patient. This difference could be caused by genetics, lifestyle, disease conditions, environmental exposure or none of the above. With the advent of AI, drug response prediction and optimization are now better supported with many various approaches. Random Forest (RF) and Support Vector Machine (SVM) are some of the common machine learning algorithms employed to predict the activity of a particular drug, identify the biomarkers and classify patients as responders and non-responders. These techniques aid doctors with the informed decisions, particularly regarding chemotherapy. Gradient Boosting models also predict clinical risks and bad drug reactions with lot of precision, such as XGBoost, and LightGBM. The use of complex biological patterns by deep learning models is enhancing the field of pharmacology research further. The use of Artificial neural Networks (ANNs) to explore drug interactions with the target and to simulate Pharmacokinetics – the mechanisms of body uptake, distribution and disposition of drugs. CNNs also are extremely effective when performing image analysis tasks, such as detecting tumors or modeling and assessing the effectiveness of cancer medications with medical images. The Recurrent Neural Networks (RNNs) are designed to see data changing over time and so help doctors stay abreast of patients' progress and predict their long-term outcomes. More sophisticated AI techniques are making a large impact too. Graphical models are used to describe complex molecular and drug–drug network data and graphical networks are used in Graph Neural Networks (GNNs) to understand the relationships between different molecules and drugs. This is really important to identify safe and effective combined therapies. Drug Safety Monitoring and Evidence-Based Decision Making can be enhanced through the use of Natural Language Processing (NLP), as this technology can extract valuable information from clinical notes, research articles, and electronic health records. Using Reinforcement Learning (RL), flexible treatment plans can be developed by optimising the dose of drug administration in real-time. Pro-bayarian networks: Bayes models when a doctor doesn’t know what to do. Combination of clinical with multi-omics data (including genomic, transcriptomic, and proteomic data) is one of the most powerful of AI. Such a combination helps understand disease mechanisms and patient variability better, resulting in improved patient stratification, personalized dosages and therapeutic outcomes.

ARTIFICIAL INTELLIGENCE IN DRUG RESPONSE PREDICTION AND PHARMACOLOGICAL THERAPY OPTIMIZATION: ADVANCES, CHALLENGES, AND FUTURE PERSPECTIVES

Driven by artificial intelligence, or AI, today's medicinal science has the potential of rapidly transforming a doctor's knowledge of patient reactions to a variety of medications. In clinical practice, one has seen that sometimes a given medication is effective and sometimes ineffective in a patient. This difference could be caused by genetics, lifestyle, disease conditions, environmental exposure or none of the above. With the advent of AI, drug response prediction and optimization are now better supported with many various approaches. Random Forest (RF) and Support Vector Machine (SVM) are some of the common machine learning algorithms employed to predict the activity of a particular drug, identify the biomarkers and classify patients as responders and non-responders. These techniques aid doctors with the informed decisions, particularly regarding chemotherapy. Gradient Boosting models also predict clinical risks and bad drug reactions with lot of precision, such as XGBoost, and LightGBM. The use of complex biological patterns by deep learning models is enhancing the field of pharmacology research further. The use of Artificial neural Networks (ANNs) to explore drug interactions with the target and to simulate Pharmacokinetics – the mechanisms of body uptake, distribution and disposition of drugs. CNNs also are extremely effective when performing image analysis tasks, such as detecting tumors or modeling and assessing the effectiveness of cancer medications with medical images. The Recurrent Neural Networks (RNNs) are designed to see data changing over time and so help doctors stay abreast of patients' progress and predict their long-term outcomes. More sophisticated AI techniques are making a large impact too. Graphical models are used to describe complex molecular and drug–drug network data and graphical networks are used in Graph Neural Networks (GNNs) to understand the relationships between different molecules and drugs. This is really important to identify safe and effective combined therapies. Drug Safety Monitoring and Evidence-Based Decision Making can be enhanced through the use of Natural Language Processing (NLP), as this technology can extract valuable information from clinical notes, research articles, and electronic health records. Using Reinforcement Learning (RL), flexible treatment plans can be developed by optimising the dose of drug administration in real-time. Pro-bayarian networks: Bayes models when a doctor doesn’t know what to do. Combination of clinical with multi-omics data (including genomic, transcriptomic, and proteomic data) is one of the most powerful of AI. Such a combination helps understand disease mechanisms and patient variability better, resulting in improved patient stratification, personalized dosages and therapeutic outcomes.

Learning from agile software development

Self-organized Learning in Software Factory: Experiences and Lessons Learned

What Can Software Startuppers Learn from the Artistic Design Flow? Experiences, Reflections and Future Avenues

Why Early-Stage Software Startups Fail: A Behavioral Framework

Software startups are newly created companies with little operating history and oriented towards producing cutting-edge products. As their time and resources are extremely scarce, and one failed project can put them out of business, startups need effective practices to face with those unique challenges. However, only few scientific studies attempt to address characteristics of failure, especially during the early-stage. With this study we aim to raise our understanding of the failure of early-stage software startup companies. This state-of-practice investigation was performed using a literature review followed by a multiple-case study approach. The results present how inconsistency between managerial strategies and execution can lead to failure by means of a behavioral framework. Despite strategies reveal the first need to understand the problem/solution fit, actual executions prioritize the development of the product to launch on the market as quickly as possible to verify product/market fit, neglecting the necessary learning process.

Software development in startup companies: A systematic mapping study

Context: Software startups are newly created companies with no operating history and fast in producing cutting-edge technologies. These companies develop software under highly uncertain conditions, tackling fast-growing markets under severe lack of resources. Therefore, software startups present a unique combination of characteristics which pose several challenges to software development activities. Objective: This study aims to structure and analyze the literature on software development in startup companies, determining thereby the potential for technology transfer and identifying software development work practices reported by practitioners and researchers. Method: We conducted a systematic mapping study, developing a classification schema, ranking the selected primary studies according their rigor and relevance, and analyzing reported software development work practices in startups. Results: A total of 43 primary studies were identified and mapped, synthesizing the available evidence on software development in startups. Only 16 studies are entirely dedicated to software development in startups, of which 10 result in a weak contribution (advice and implications (6); lesson learned (3); tool (1)). Nineteen studies focus on managerial and organizational factors. Moreover, only 9 studies exhibit high scientific rigor and relevance. From the reviewed primary studies, 213 software engineering work practices were extracted, categorized and analyzed. Conclusion: This mapping study provides the first systematic exploration of the state-of-art on software startup research. The existing body of knowledge is limited to a few high quality studies. Furthermore, the results indicate that software engineering work practices are chosen opportunistically, adapted and configured to provide value under the constrains imposed by the startup context.

Towards Abstraction and Automation in Software Engineering

Novel software development approaches are embracing abstraction and automation techniques. It is claimed that abstraction and automation techniques increase the productivity, improve the reusability and lower the complexity of the projects. In this study we address these new frontiers of software development by investigating on one novel proposal, namely the Ball. The Ball is an information ecosystem for authorised information containing web content, digital content as well as service development and integration. It is claimed to improve the reusability, productivity and security of software development while lowering the complexity. While improving the software developer’s productivity it should produce smaller and more reasonable software systems, leading to a better reusability and a shorter learning phase for new developers. Up to now there exists no evidence to support these claims. In this study we analyse the Ball ecosystem from multiple perspectives. We compare it to related approaches in order to find its advantages and disadvantages. In order to provide empirical data we replicated a study where a mobile information system was developed using three different technologies. The results of this study show that the Ball ecosystem has the potential to improve the productivity of software development. However, it