Vishal Singh

Ashwin Agrawal, Robert Thiel, Pooja Jain et al.

Digital Twin (DT) technology is far from being comprehensive and mature, resulting in their piecemeal implementation in practice where some functions are automated by DTs, and others are still performed by humans. This piecemeal implementation of DTs often leaves practitioners wondering what roles (or functions) to allocate to DTs in a work system, and how might it impact humans. A lack of knowledge about the roles that humans and DTs play in a work system can result in significant costs, misallocation of resources, unrealistic expectations from DTs, and strategic misalignments. To alleviate this challenge, this paper answers the research question: When humans work with DTs, what types of roles can a DT play, and to what extent can those roles be automated? Specifically, we propose a two-dimensional conceptual framework, Levels of Digital Twin (LoDT). The framework is an integration of the types of roles a DT can play, broadly categorized under (1) Observer, (2) Analyst, (3) Decision Maker, and (4) Action Executor, and the extent of automation for each of these roles, divided into five different levels ranging from completely manual to fully automated. A particular DT can play any number of roles at varying levels. The framework can help practitioners systematically plan DT deployments, clearly communicate goals and deliverables, and lay out a strategic vision. A case study illustrates the usefulness of the framework.

Alexander G. Olenskyj, Brent S. Sams, Zhenghao Fei et al.

Yield estimation is a powerful tool in vineyard management, as it allows growers to fine-tune practices to optimize yield and quality. However, yield estimation is currently performed using manual sampling, which is time-consuming and imprecise. This study demonstrates the application of proximal imaging combined with deep learning for yield estimation in vineyards. Continuous data collection using a vehicle-mounted sensing kit combined with collection of ground truth yield data at harvest using a commercial yield monitor allowed for the generation of a large dataset of 23,581 yield points and 107,933 images. Moreover, this study was conducted in a mechanically managed commercial vineyard, representing a challenging environment for image analysis but a common set of conditions in the California Central Valley. Three model architectures were tested: object detection, CNN regression, and transformer models. The object detection model was trained on hand-labeled images to localize grape bunches, and either bunch count or pixel area was summed to correlate with grape yield. Conversely, regression models were trained end-to-end to predict grape yield from image data without the need for hand labeling. Results demonstrated that both a transformer as well as the object detection model with pixel area processing performed comparably, with a mean absolute percent error of 18% and 18.5%, respectively on a representative holdout dataset. Saliency mapping was used to demonstrate the attention of the CNN model was localized near the predicted location of grape bunches, as well as on the top of the grapevine canopy. Overall, the study showed the applicability of proximal imaging and deep learning for prediction of grapevine yield on a large scale. Additionally, the end-to-end modeling approach was able to perform comparably to the object detection approach while eliminating the need for hand-labeling.

Ashwin Agrawal, Vishal Singh, Martin Fischer

Despite the Digital Twin (DT) concept being in the industry for a long time, it remains ambiguous, unable to differentiate itself from information models, general computing, and simulation technologies. Part of this confusion stems from previous studies overlooking the DT's bidirectional nature, that enables the shift of agency (delegating control) from humans to physical elements, something that was not possible with earlier technologies. Thus, we present DTs in a new light by viewing them as a means of imparting intelligence and agency to entities, emphasizing that DTs are not just expert-centric tools but are active systems that extend the capabilities of the entities being twinned. This new perspective on DTs can help reduce confusion and humanize the concept by starting discussions about how intelligent a DT should be, and its roles and responsibilities, as well as setting a long-term direction for DTs.

Ashwin Agrawal, Vishal Singh, Martin Fischer

Recent developments in Artificial Intelligence (AI) provide unprecedented automation opportunities in the Architecture, Engineering, and Construction (AEC) industry. However, despite the enthusiasm regarding the use of AI, 85% of current big data projects fail. One of the main reasons for AI project failures in the AEC industry is the disconnect between those who plan or decide to use AI and those who implement it. AEC practitioners often lack a clear understanding of the capabilities and limitations of AI, leading to a failure to distinguish between what AI should solve, what it can solve, and what it will solve, treating these categories as if they are interchangeable. This lack of understanding results in the disconnect between AI planning and implementation because the planning is based on a vision of what AI should solve without considering if it can or will solve it. To address this challenge, this work introduces the LeanAI method. The method has been developed using data from several ongoing longitudinal studies analyzing AI implementations in the AEC industry, which involved 50+ hours of interview data. The LeanAI method delineates what AI should solve, what it can solve, and what it will solve, forcing practitioners to clearly articulate these components early in the planning process itself by involving the relevant stakeholders. By utilizing the method, practitioners can effectively plan AI implementations, thus increasing the likelihood of success and ultimately speeding up the adoption of AI. A case example illustrates the usefulness of the method.

Ritvik Rastogi, Vishal Singh, Tejas Chaudhari et al.

Competitive STEM examinations such as JEE and NEET require multi-step symbolic reasoning, precise numerical computation, and deep conceptual understanding across physics, chemistry, and mathematics. Recent large language models perform strongly on common reasoning benchmarks, yet they remain difficult to deploy at scale, where millions of student doubts demand domain-specific, consistently structured problem solving. We introduce Aryabhata 2, a reasoning-focused language model for competitive STEM examinations, trained via reinforcement-learning post-training. Using PhysicsWallah's internal question banks, we construct a high-quality training curriculum and post-train GPT-OSS-20B through reinforcement learning with verifiable rewards. Training combines prolonged reinforcement learning with broadened exploration via progressively larger rollout group sizes. We evaluate Aryabhata 2 on competitive examination benchmarks, including JEE Main, JEE Advanced, and NEET, as well as out-of-distribution reasoning datasets such as AIME, HMMT, MMLU-Pro, MMLU-Redux 2.0, and GPQA. Results show that Aryabhata 2 outperforms its base model GPT-OSS-20B on competitive STEM reasoning while requiring substantially fewer output tokens (up to 64\% fewer).

Manish Verma, Vivek Sharma, Vishal Singh

This paper presents the development of an AI powered software platform that leverages advanced large language models (LLMs) to transform technology scouting and solution discovery in industrial R&D. Traditional approaches to solving complex research and development challenges are often time consuming, manually driven, and heavily dependent on domain specific expertise. These methods typically involve navigating fragmented sources such as patent repositories, commercial product catalogs, and competitor data, leading to inefficiencies and incomplete insights. The proposed platform utilizes cutting edge LLM capabilities including semantic understanding, contextual reasoning, and cross-domain knowledge extraction to interpret problem statements and retrieve high-quality, sustainable solutions. The system processes unstructured patent texts, such as claims and technical descriptions, and systematically extracts potential innovations aligned with the given problem context. These solutions are then algorithmically organized under standardized technical categories and subcategories to ensure clarity and relevance across interdisciplinary domains. In addition to patent analysis, the platform integrates commercial intelligence by identifying validated market solutions and active organizations addressing similar challenges. This combined insight sourced from both intellectual property and real world product data enables R&D teams to assess not only technical novelty but also feasibility, scalability, and sustainability. The result is a comprehensive, AI driven scouting engine that reduces manual effort, accelerates innovation cycles, and enhances decision making in complex R&D environments.

Theshani Nuradha, Vishal Singh, Mark M. Wilde

The hockey-stick divergence is a fundamental quantity characterizing several statistical privacy frameworks that ensure privacy for classical and quantum data. In such quantum privacy frameworks, the adversary is allowed to perform all possible measurements. However, in practice, there are typically limitations to the set of measurements that can be performed. To this end, here, we comprehensively analyze the measured hockey-stick divergence under several classes of practically relevant measurement classes. We prove several of its properties, including data processing and convexity. We show that it is efficiently computable by semi-definite programming for some classes of measurements and can be analytically evaluated for Werner and isotropic states. Notably, we show that the measured hockey-stick divergence characterizes optimal privacy parameters in the quantum pufferfish privacy framework. With this connection and the developed technical tools, we enable methods to quantify and audit privacy for several practically relevant settings. Lastly, we introduce the measured hockey-stick divergence of channels and explore its applications in ensuring privacy for channels.

Vijayalaxmi Sahadevan, Sushil Mario, Yash Jaiswal et al.

Ontology-based knowledge graphs (KG) are desirable for effective knowledge management and reuse in various decision making scenarios, including design. Creating and populating extensive KG based on specific ontological models can be highly labour and time-intensive unless automated processes are developed for knowledge extraction and graph creation. Most research and development on automated extraction and creation of KG is based on extensive unstructured data sets that provide contextual information. However, some of the most useful information about the products and services of a company has traditionally been recorded as structured data. Such structured data sets rarely follow a standard ontology, do not capture explicit mapping of relationships between the entities, and provide no contextual information. Therefore, this research reports a method and digital workflow developed to address this gap. The developed method and workflow employ rule-based techniques to extract and create a Function Behaviour-Structure (FBS) ontology-based KG from legacy structured data, especially specification sheets and product catalogues. The solution approach consists of two main components: a process for deriving context and context-based classification rules for FBS ontology concepts and a workflow for populating and retrieving the FBS ontology-based KG. KG and Natural Language Processing (NLP) are used to automate knowledge extraction, representation, and retrieval. The workflow's effectiveness is demonstrated via pilot implementation in an industrial context. Insights gained from the pilot study are reported regarding the challenges and opportunities, including discussing the FBS ontology and concepts.

Manish Verma, Vivek Sharma, Vishal Singh

This paper introduces a novel, multi stage hybrid intelligence framework for pruning patent portfolios to identify high value assets for technology transfer. Current patent valuation methods often rely on retrospective indicators or manual, time intensive analysis. Our framework automates and deepens this process by combining a Learning to Rank (LTR) model, which evaluates patents against over 30 legal and commercial parameters, with a unique "Need-Seed" agent-based system. The "Need Agent" uses Natural Language Processing (NLP) to mine unstructured market and industry data, identifying explicit technological needs. Concurrently, the "Seed Agent" employs fine tuned Large Language Models (LLMs) to analyze patent claims and map their technological capabilities. The system generates a "Core Ontology Framework" that matches high potential patents (Seeds) to documented market demands (Needs), providing a strategic rationale for divestment decisions. We detail the architecture, including a dynamic parameter weighting system and a crucial Human in the-Loop (HITL) validation protocol, to ensure both adaptability and real-world credibility.

Ashwin Agrawal, Martin Fischer, Vishal Singh

Recent technological developments and advances in Artificial Intelligence (AI) have enabled sophisticated capabilities to be a part of Digital Twin (DT), virtually making it possible to introduce automation into all aspects of work processes. Given these possibilities that DT can offer, practitioners are facing increasingly difficult decisions regarding what capabilities to select while deploying a DT in practice. The lack of research in this field has not helped either. It has resulted in the rebranding and reuse of emerging technological capabilities like prediction, simulation, AI, and Machine Learning (ML) as necessary constituents of DT. Inappropriate selection of capabilities in a DT can result in missed opportunities, strategic misalignments, inflated expectations, and risk of it being rejected as just hype by the practitioners. To alleviate this challenge, this paper proposes the digitalization framework, designed and developed by following a Design Science Research (DSR) methodology over a period of 18 months. The framework can help practitioners select an appropriate level of sophistication in a DT by weighing the pros and cons for each level, deciding evaluation criteria for the digital twin system, and assessing the implications of the selected DT on the organizational processes and strategies, and value creation. Three real-life case studies illustrate the application and usefulness of the framework.

Mehak Gupta, Vishal Singh, Akshay Agarwal et al.

Presentation attacks are posing major challenges to most of the biometric modalities. Iris recognition, which is considered as one of the most accurate biometric modality for person identification, has also been shown to be vulnerable to advanced presentation attacks such as 3D contact lenses and textured lens. While in the literature, several presentation attack detection (PAD) algorithms are presented; a significant limitation is the generalizability against an unseen database, unseen sensor, and different imaging environment. To address this challenge, we propose a generalized deep learning-based PAD network, MVANet, which utilizes multiple representation layers. It is inspired by the simplicity and success of hybrid algorithm or fusion of multiple detection networks. The computational complexity is an essential factor in training deep neural networks; therefore, to reduce the computational complexity while learning multiple feature representation layers, a fixed base model has been used. The performance of the proposed network is demonstrated on multiple databases such as IIITD-WVU MUIPA and IIITD-CLI databases under cross-database training-testing settings, to assess the generalizability of the proposed algorithm.

Avinash Barnwal, Hari Pad Bharti, Aasim Ali et al.

Predicting the direction of assets have been an active area of study and a difficult task. Machine learning models have been used to build robust models to model the above task. Ensemble methods is one of them showing results better than a single supervised method. In this paper, we have used generative and discriminative classifiers to create the stack, particularly 3 generative and 6 discriminative classifiers and optimized over one-layer Neural Network to model the direction of price cryptocurrencies. Features used are technical indicators used are not limited to trend, momentum, volume, volatility indicators, and sentiment analysis has also been used to gain useful insight combined with the above features. For Cross-validation, Purged Walk forward cross-validation has been used. In terms of accuracy, we have done a comparative analysis of the performance of Ensemble method with Stacking and Ensemble method with blending. We have also developed a methodology for combined features importance for the stacked model. Important indicators are also identified based on feature importance.