Prerpints.org logo
Preprint
Article

Human-Robot Collaboration in Business Environments: Leveraging GPU-Accelerated Computer Vision and Generative AI for Enhanced Productivity and Safety

Altmetrics

Downloads

120

Views

36

Comments

0

Abi Cit  *

This version is not peer-reviewed

Artificial Intelligence Models, Tools and Applications

Submitted:

16 August 2024

Posted:

19 August 2024

You are already at the latest version

Alerts
Abstract
As businesses increasingly adopt advanced technologies to enhance productivity and safety, the integration of human-robot collaboration (HRC) emerges as a transformative approach. This paper explores the role of GPU-accelerated computer vision and generative AI in optimizing HRC within business environments. By leveraging the computational power of GPUs, real-time data processing, and advanced machine learning algorithms, robots can better interpret complex visual cues and adapt to dynamic workspaces. Generative AI further enables the design of intelligent robotic systems capable of anticipating human actions, optimizing task allocation, and ensuring safety through predictive modeling. This research highlights the potential of these technologies to improve operational efficiency, reduce human error, and create safer, more adaptable workplaces. The implications of such advancements are discussed, providing insights into the future of HRC in various industries.
Keywords: 
Subject: Computer Science and Mathematics  -   Artificial Intelligence and Machine Learning

Introduction

In today’s rapidly evolving business landscape, the synergy between human and robotic labor is increasingly seen as a cornerstone of innovation and efficiency. Human-Robot Collaboration (HRC) goes beyond traditional automation by fostering a shared workspace where humans and robots work together to achieve common goals. This collaborative approach not only amplifies productivity but also introduces new levels of safety and adaptability, critical for maintaining competitive advantages in various industries.
Central to the success of HRC is the ability of robots to understand and respond to their environment in real-time. This is where GPU-accelerated computer vision plays a pivotal role. By harnessing the parallel processing capabilities of Graphics Processing Units (GPUs), robots can process vast amounts of visual data quickly and accurately, allowing them to interpret complex scenarios, recognize objects, and navigate dynamic environments with precision. This capability is essential in business environments where conditions can change rapidly and require immediate robotic response.
Moreover, the integration of generative AI into HRC further enhances these capabilities by enabling robots to predict and adapt to human actions. Generative AI models can simulate various scenarios, allowing robots to anticipate potential issues and optimize task allocation accordingly. This predictive capability not only improves efficiency but also significantly enhances workplace safety by reducing the likelihood of accidents or errors.
This paper delves into the transformative potential of combining GPU-accelerated computer vision and generative AI in human-robot collaboration. It explores how these technologies can be leveraged to create intelligent, adaptable robotic systems that work seamlessly alongside human workers, driving productivity while ensuring a safer working environment. Through a comprehensive analysis of current advancements and future trends, this research aims to provide valuable insights into the next generation of HRC in business environments.

Literature Review

Human-Robot Collaboration

Historical Perspective and Evolution of HRC in Industrial Settings

Human-Robot Collaboration (HRC) has undergone significant evolution since the inception of industrial robotics. Early robotic systems were designed to operate independently of humans, performing repetitive and hazardous tasks within isolated environments to prevent potential harm. However, as industries sought greater efficiency and flexibility, the need for robots capable of working alongside humans became apparent. The concept of HRC emerged from this necessity, evolving from rudimentary interactions to sophisticated collaborations where robots assist, augment, and complement human workers. This section traces the historical development of HRC, highlighting key milestones such as the introduction of collaborative robots (cobots) in the early 2000s and the subsequent advancements that have shaped modern HRC in industrial settings.

Existing Frameworks and Models for Effective HRC

Several frameworks and models have been developed to facilitate effective HRC in various industrial contexts. These frameworks address key aspects such as task allocation, communication protocols, safety measures, and human factors engineering. Notable models include the Shared Control framework, where control is dynamically adjusted between humans and robots based on task requirements, and the Levels of Autonomy (LoA) model, which categorizes the degree of robot autonomy in collaborative tasks. This section reviews existing HRC frameworks and models, emphasizing their contributions to enhancing collaboration, productivity, and safety in industrial environments.

GPU-Accelerated Computer Vision

Overview of Computer Vision in Robotics

Computer vision is a cornerstone technology in robotics, enabling robots to perceive and interact with their surroundings. It encompasses various tasks such as object detection, recognition, and spatial awareness, which are essential for autonomous navigation, manipulation, and interaction. In the context of HRC, computer vision allows robots to interpret visual cues from their environment, recognize human actions, and respond appropriately. This section provides an overview of the fundamental concepts and techniques in computer vision as applied to robotics, with a focus on its role in enhancing human-robot interactions.

The Role of GPU Acceleration in Enhancing Computer Vision Algorithms

The advent of GPU acceleration has significantly improved the performance of computer vision algorithms, enabling real-time processing of complex visual data. GPUs excel at parallel processing, making them ideal for the computationally intensive tasks involved in computer vision, such as deep learning-based image recognition and 3D scene reconstruction. This section explores the impact of GPU acceleration on the speed and accuracy of computer vision algorithms, particularly in the context of HRC, where timely and precise visual interpretation is crucial for seamless collaboration and safety.

Generative AI in Robotics

Exploration of Generative AI Models

Generative AI models, including Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs), have opened new avenues for innovation in robotics. These models are capable of generating new data, simulating scenarios, and facilitating adaptive learning, making them invaluable tools for enhancing robot autonomy and decision-making. In HRC, generative AI can be used to anticipate human actions, optimize task execution, and adapt to changing conditions in real time. This section examines the principles and applications of generative AI models in robotics, highlighting their potential to revolutionize HRC by enabling more intelligent and responsive robotic systems.

Potential of Generative AI for Scenario Planning, Real-Time Decision-Making, and Adaptive Learning in HRC

The integration of generative AI into HRC holds the promise of transforming how robots plan, decide, and learn in collaborative environments. By simulating various scenarios, generative AI can help robots anticipate potential challenges, optimize their behavior, and make informed decisions in real time. Additionally, adaptive learning capabilities enable robots to continuously improve their performance based on interactions with humans and the environment. This section explores the potential applications of generative AI in HRC, with a focus on scenario planning, real-time decision-making, and adaptive learning, and discusses the implications for enhancing productivity and safety in collaborative workspaces.

Safety and Productivity in HRC

Current Challenges and Solutions for Ensuring Safety in Collaborative Workspaces

Safety remains a critical concern in HRC, as the close proximity between humans and robots increases the risk of accidents. Traditional safety measures, such as physical barriers and emergency stop buttons, are often insufficient in dynamic collaborative environments. Consequently, new approaches, including real-time monitoring, predictive safety systems, and adaptive safety protocols, have been developed to mitigate risks. This section reviews the current challenges associated with ensuring safety in HRC and discusses innovative solutions that leverage advanced technologies, such as GPU-accelerated computer vision and generative AI, to create safer collaborative workspaces.

Metrics and Case Studies on Productivity Improvements through Advanced Robotics

The adoption of advanced robotics in HRC has led to significant productivity gains across various industries. Metrics such as task completion time, error rates, and overall output provide quantifiable evidence of these improvements. Moreover, case studies from industries such as manufacturing, logistics, and healthcare demonstrate the practical benefits of integrating HRC into business operations. This section presents key metrics and case studies that illustrate the impact of advanced robotics on productivity, highlighting the role of GPU-accelerated technologies and generative AI in driving these enhancements.

Methodology

Research Design

Experimental Setup for Assessing Effectiveness

The research is designed to evaluate the effectiveness of GPU-accelerated computer vision and generative AI in enhancing human-robot collaboration (HRC) within business environments. The experimental setup involves deploying collaborative robots (cobots) equipped with GPU-accelerated computer vision systems and generative AI models in controlled business settings. These settings will be selected to represent typical HRC scenarios, such as assembly lines, logistics operations, and healthcare environments, where robots work alongside human employees to complete tasks.
The effectiveness of the technologies will be assessed through a series of tasks that require real-time interaction between humans and robots. These tasks will be designed to test the robots' ability to recognize and respond to human actions, navigate dynamic environments, and adapt to changing conditions. The performance of the cobots will be measured against predefined benchmarks, including task completion rates, error rates, and safety incidents, to determine the impact of the integrated technologies on HRC outcomes.

Selection Criteria for Business Environments and Robotic Systems

The selection of business environments and robotic systems for this study is based on specific criteria to ensure relevance and applicability of the findings. The chosen business environments must involve complex tasks that require close human-robot interaction, such as those in manufacturing, logistics, or healthcare. Additionally, these environments should have a history of using or being conducive to the integration of robotic systems, making them ideal for studying the impact of advanced technologies on HRC.
The robotic systems selected for this study will include state-of-the-art cobots capable of real-time data processing and decision-making. These cobots will be equipped with GPU-accelerated hardware and software to support advanced computer vision and generative AI functionalities. The selection criteria also include the robots' adaptability to various tasks and their ability to operate safely in close proximity to humans.

Technological Implementation

Integration of GPU-Accelerated Computer Vision Systems in Cobots

The implementation of GPU-accelerated computer vision in cobots involves integrating high-performance GPUs with the robots' existing hardware and software architectures. This integration will enable the cobots to process visual data in real-time, enhancing their ability to detect, recognize, and respond to objects and human actions within their environment. The computer vision systems will utilize deep learning algorithms, such as convolutional neural networks (CNNs), to perform tasks like object detection, pose estimation, and motion tracking.
To optimize the performance of these systems, the cobots will be equipped with advanced sensors, including RGB-D cameras and LiDAR, to capture detailed environmental data. The GPU-accelerated computer vision systems will process this data on-the-fly, enabling the cobots to make rapid decisions and adapt their actions based on real-time visual feedback.

Implementation of Generative AI Models for Adaptive Learning and Decision-Making

Generative AI models, such as Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs), will be implemented in the cobots to enhance their adaptive learning and decision-making capabilities. These models will be trained on large datasets of human-robot interactions, allowing the cobots to simulate various scenarios and predict potential outcomes. The generative AI models will enable the cobots to anticipate human actions, optimize task allocation, and adjust their behavior in response to environmental changes.
In real-time HRC scenarios, the cobots will use the generative AI models to make decisions on-the-fly, such as determining the most efficient way to complete a task or avoiding potential safety hazards. The models will also facilitate continuous learning, enabling the cobots to improve their performance over time based on accumulated experience and feedback from human collaborators.

Data Collection

Methods for Collecting Data on Productivity and Safety

Data collection will focus on key metrics related to productivity and safety in HRC scenarios. Productivity data will include task completion rates, error rates, and time-to-completion for various tasks performed by the cobots in collaboration with human workers. Safety data will encompass incident reports, near-miss occurrences, and other indicators of safety risks in the collaborative workspace.
Data will be collected using a combination of automated logging systems and manual observations. Automated systems will capture data such as task timings, error logs, and sensor readings, while manual observations will provide qualitative insights into the human-robot interactions, including potential safety concerns and areas for improvement.

Tools and Sensors for Monitoring and Analyzing Human-Robot Interactions

To monitor and analyze human-robot interactions, the research will employ a range of tools and sensors. These will include motion capture systems to track the movements of both humans and robots, wearable sensors to monitor human physiological responses, and environmental sensors to detect changes in the workspace that could affect safety or productivity.
In addition, specialized software tools will be used to analyze the collected data, identifying patterns and correlations between the use of GPU-accelerated computer vision, generative AI, and the observed HRC outcomes. These tools will also facilitate the visualization of data, enabling a clearer understanding of how the implemented technologies impact HRC dynamics.

Analysis

Techniques for Evaluating the Impact on HRC Outcomes 

The analysis will involve a combination of quantitative and qualitative techniques to evaluate the impact of GPU-accelerated computer vision and generative AI on HRC outcomes. Quantitative analysis will focus on statistical comparisons of productivity and safety metrics before and after the implementation of the technologies. Time-series analysis and regression models will be employed to identify trends and measure the magnitude of improvements in task completion rates and safety incidents.
Qualitative analysis will include thematic analysis of observation notes and interviews with human collaborators, aiming to capture the subjective experiences of working with the cobots. This analysis will provide insights into the perceived benefits and challenges of HRC, contributing to a more comprehensive understanding of the technologies' impact.

Statistical Methods for Correlating Technology Use with Productivity and Safety Metrics

To correlate the use of GPU-accelerated computer vision and generative AI with productivity and safety metrics, statistical methods such as Pearson correlation, multiple regression analysis, and ANOVA (Analysis of Variance) will be employed. These methods will help determine the strength and significance of the relationships between the implemented technologies and the observed outcomes.
Additionally, predictive modeling techniques will be used to assess the potential long-term impacts of these technologies on HRC. These models will simulate future scenarios based on the collected data, providing insights into how continued advancements in GPU-accelerated computing and generative AI could further enhance productivity and safety in collaborative workspaces.

Expected Results

Productivity Gains

Hypotheses on Streamlining Task Execution and Reducing Downtime

The integration of GPU-accelerated computer vision and generative AI in human-robot collaboration (HRC) is expected to significantly streamline task execution. By enabling real-time data processing and decision-making, these technologies will allow robots to complete tasks more efficiently and with greater accuracy. The hypothesis is that GPU-accelerated computer vision will enhance the robots’ ability to recognize objects, track movements, and navigate complex environments, reducing the time spent on task reorientation or error correction. Additionally, generative AI will enable robots to predict and adapt to human actions, thereby minimizing delays and reducing overall downtime.

Expected Improvements in Workflow Efficiency and Throughput

The anticipated productivity gains from these technologies include measurable improvements in workflow efficiency and throughput. Specifically, it is expected that task completion rates will increase due to faster and more accurate robot performance, while error rates will decrease as robots become better at interpreting and responding to their surroundings. This should lead to a more seamless integration of robotic systems into existing workflows, reducing bottlenecks and improving overall throughput. The research predicts that businesses adopting these technologies will experience a marked increase in output, driven by the enhanced capabilities of the robots to perform tasks in collaboration with human workers.

Safety Enhancements

Predictions on the Reduction of Human-Robot Interaction Incidents

One of the key expected results of this research is a significant reduction in incidents related to human-robot interactions. With GPU-accelerated computer vision providing robots with improved situational awareness, and generative AI enabling predictive modeling of human behavior, it is anticipated that the frequency of accidents or near-miss occurrences will decrease. Robots will be better equipped to detect potential hazards, such as unexpected human movements or changes in the environment, and react accordingly to avoid collisions or unsafe interactions.

Anticipated Advancements in Real-Time Hazard Detection and Prevention

The research also predicts advancements in real-time hazard detection and prevention. GPU-accelerated computer vision systems are expected to enhance the robots’ ability to continuously monitor their surroundings, identifying and responding to potential dangers in milliseconds. Coupled with generative AI, which allows for adaptive learning and scenario planning, these systems will enable robots to preemptively address hazards before they escalate into serious incidents. This proactive approach to safety is expected to create safer work environments, where human workers can confidently collaborate with robots without fear of injury or harm.

Case Studies

Potential Case Studies Showcasing Successful Integration

The research anticipates that several case studies will emerge, demonstrating the successful integration of GPU-accelerated computer vision and generative AI in real-world business environments. These case studies may include manufacturing facilities where robots equipped with these technologies have optimized assembly lines, reducing production times and improving product quality. Another potential case study could involve logistics operations where robots have enhanced the efficiency of sorting and packaging tasks, leading to faster order fulfillment and reduced operational costs.
Additionally, healthcare environments may provide case studies where the integration of these technologies has improved patient care by enabling robots to assist in tasks such as patient monitoring, medication delivery, or surgical procedures. These case studies will serve as practical examples of how advanced robotics can transform business operations, offering insights into the tangible benefits of adopting GPU-accelerated computer vision and generative AI in HRC.

Discussion

Implications for Business Environments

Transformative Potential of Enhanced HRC Across Industries

The adoption of GPU-accelerated computer vision and generative AI in human-robot collaboration (HRC) holds the potential to significantly transform various industries. In manufacturing, these technologies can revolutionize production lines by enabling robots to work more closely and efficiently with human operators, leading to faster production cycles, higher product quality, and reduced operational costs. For example, in industries requiring precision assembly, such as electronics or automotive manufacturing, robots equipped with advanced vision systems can handle delicate tasks with minimal human intervention, increasing both speed and accuracy.
In logistics, enhanced HRC can streamline processes such as sorting, packaging, and inventory management. Robots with advanced situational awareness and adaptive learning capabilities can operate alongside human workers to optimize warehouse operations, reduce errors, and improve order fulfillment times. This can lead to substantial improvements in supply chain efficiency, ultimately benefiting businesses with faster turnaround times and lower costs.
In healthcare, the integration of these technologies into medical robotics can enhance patient care by enabling robots to assist with tasks such as patient monitoring, surgical procedures, and medication delivery. Enhanced HRC can improve the precision and reliability of these tasks, leading to better patient outcomes and increased efficiency in healthcare delivery.

Challenges and Limitations

Obstacles in Technology Adoption

Despite the promising potential of GPU-accelerated computer vision and generative AI in HRC, several challenges and limitations must be considered. One significant obstacle is the cost associated with adopting these advanced technologies. The initial investment in high-performance GPUs, sensors, and AI software can be substantial, potentially limiting access for small and medium-sized enterprises (SMEs). Additionally, the ongoing costs of maintaining and updating these systems can further strain resources, particularly in industries with tight profit margins.
Training is another critical challenge. The successful implementation of these technologies requires a workforce that is skilled in operating and troubleshooting advanced robotic systems. This necessitates investment in training programs, which can be time-consuming and costly. Moreover, there may be resistance to change among workers who fear that increased automation could lead to job displacement, further complicating the adoption process.
Technical barriers also pose significant challenges. The integration of GPU-accelerated computer vision and generative AI into existing robotic systems can be complex, requiring significant expertise in both hardware and software engineering. Additionally, ensuring seamless communication between robots and human collaborators, particularly in dynamic environments, can be difficult to achieve and maintain.

Ethical and Regulatory Concerns

The adoption of advanced HRC technologies raises several ethical and regulatory concerns. From an ethical standpoint, there is a need to ensure that these technologies are implemented in a manner that benefits all stakeholders, including workers who may be affected by increased automation. Issues related to data privacy and security are also critical, particularly in healthcare and other sensitive industries where robots may have access to personal or confidential information.
Regulatory concerns include ensuring that the deployment of HRC technologies complies with existing safety standards and labor laws. As robots become more autonomous and capable of making decisions in real-time, there may be a need for new regulations to address the potential risks associated with their use. This includes ensuring that robots are equipped with fail-safes and that there are clear guidelines for accountability in the event of an accident or system failure.

Future Directions

Recommendations for Further Research

To fully realize the potential of GPU-accelerated computer vision and generative AI in HRC, further research is needed in several key areas. One priority is the development of more advanced AI models that can better predict and respond to human behavior in real-time. This includes exploring new architectures for generative AI, such as those that can learn and adapt to complex environments with minimal supervision.
Another area for future research is the advancement of sensor technologies. While current systems provide significant improvements in situational awareness, there is still room for enhancement, particularly in terms of improving accuracy and reducing latency. Research into multi-modal sensor systems that combine visual, auditory, and tactile data could lead to more robust and versatile HRC solutions.

Expanding the Reach of HRC Technologies

While this research focuses on business environments, there is considerable potential for expanding these technologies into public and service sectors. For example, in public safety, robots equipped with advanced computer vision and AI could assist in disaster response or crowd management, improving the efficiency and safety of operations. In the service sector, robots could be deployed in retail or hospitality settings to enhance customer experiences, providing personalized service and assistance.
Exploring these applications will require further interdisciplinary research that brings together expertise from robotics, AI, ethics, and industry-specific knowledge. As HRC technologies continue to evolve, their potential to transform not only business environments but also broader societal contexts becomes increasingly apparent. This opens up new opportunities for innovation and collaboration, paving the way for a future where humans and robots work together seamlessly across all areas of life.

Conclusions

Summary of Findings

This research explores the transformative potential of GPU-accelerated computer vision and generative AI in human-robot collaboration (HRC). The anticipated benefits of these technologies include significant productivity gains through faster task execution, reduced downtime, and enhanced workflow efficiency. GPU-accelerated computer vision is expected to improve robots' ability to navigate and interact with their environment, while generative AI will enable adaptive learning and predictive decision-making, allowing for smoother and more effective collaboration between humans and robots.
In addition to productivity enhancements, these technologies are also predicted to substantially improve safety in collaborative workspaces. By enabling real-time hazard detection and proactive prevention strategies, GPU-accelerated computer vision and generative AI are expected to reduce the frequency of human-robot interaction incidents, creating safer work environments. The potential for these advancements is supported by case studies showcasing successful integrations in various industries, highlighting the practical benefits of adopting these cutting-edge technologies in real-world settings.

Final Thoughts

The future of human-robot collaboration is poised for significant advancements, driven by the ongoing development and integration of advanced technologies such as GPU-accelerated computer vision and generative AI. These innovations will not only enhance productivity and safety in business environments but also redefine the way humans and robots work together across a wide range of industries. As these technologies continue to evolve, they will unlock new possibilities for more intelligent, responsive, and efficient collaboration, ultimately leading to more innovative and competitive business operations.
However, the successful implementation of these technologies will require addressing challenges related to cost, training, technical barriers, and ethical considerations. By navigating these challenges, businesses can fully harness the power of HRC to drive growth, safety, and innovation in the years to come. The continued exploration and refinement of these technologies will be crucial in ensuring that the future of HRC is one of seamless integration, where human and robot capabilities complement each other to achieve shared goals.

References

  1. Beckman, F.; Berndt, J.; Cullhed, A.; Dirke, K.; Pontara, J.; Nolin, C.; Petersson, S.; Wagner, M.; Fors, U.; Karlström, P.; Stier, J.; Pennlert, J.; Ekström, B.; Lorentzen, D.G. (2021). Digital Human Sciences: New Objects – New Approaches. [CrossRef]
  2. Yadav, A.B. The Development of AI with Generative Capabilities and Its Effect on Education.
  3. Sadasivan, H. (2023). Accelerated Systems for Portable DNA Sequencing (Doctoral dissertation).
  4. Sarivudeen, A.L.; Sheham, A.M. (2013). Corporate governance practices and environmental reporting: A study of selected listed companies in Sri Lanka. In Proceedings of Annual International Research Conference on Innovative Perspective in Business (pp. 284-291).
  5. Dunn, T.; Sadasivan, H.; Wadden, J.; Goliya, K.; Chen, K.Y.; Blaauw, D.; Narayanasamy, S.; et al. (2021, October). Squigglefilter: An accelerator for portable virus detection. In MICRO-54: 54th Annual IEEE/ACM International Symposium on Microarchitecture (pp. 535-549).
  6. Akash, T.R.; Reza, J.; Alam, M.A. (2024). Evaluating financial risk management in corporation financial security systems.
  7. Yadav, A.B. (2023). Design and Implementation of UWB-MIMO Triangular Antenna with Notch Technology.
  8. Sadasivan, H.; Maric, M.; Dawson, E.; Iyer, V.; Israeli, J.; Narayanasamy, S. Accelerating Minimap2 for accurate long read alignment on GPUs. Journal of biotechnology and biomedicine 2023, 6, 13. [Google Scholar] [CrossRef] [PubMed]
  9. Sarifudeen, A.L.; Wanniarachchi, C.M. University students' perceptions on Corporate Internet Financial Reporting: Evidence from Sri Lanka. The journal of contemporary issues in business and government 2021, 27, 1746–1762. [Google Scholar]
  10. Sadasivan, H.; Channakeshava, P.; Srihari, P. Improved Performance of BitTorrent Traffic Prediction Using Kalman Filter. arXiv preprint 2020, arXiv:2006.05540. [Google Scholar]
  11. Yadav, A.B. (2023, November). STUDY OF EMERGING TECHNOLOGY IN ROBOTICS: AN ASSESSMENT. In " ONLINE-CONFERENCES" PLATFORM (pp. 431-438).
  12. Sadasivan, H.; Stiffler, D.; Tirumala, A.; Israeli, J.; Narayanasamy, S. Accelerated dynamic time warping on GPU for selective nanopore sequencing. bioRxiv 2023, 2023-03. [Google Scholar] [CrossRef]
  13. Yadav, A.B. (2023, April). Gen AI-Driven Electronics: Innovations, Challenges and Future Prospects. In International Congress on Models and methods in Modern Investigations (pp. 113-121).
  14. Sadasivan, H.; Patni, A.; Mulleti, S.; Seelamantula, C.S. Digitization of Electrocardiogram Using Bilateral Filtering. Innovative Computer Sciences Journal 2016, 2, 1–10. [Google Scholar]
  15. Yadav, A.B.; Patel, D.M. Automation of Heat Exchanger System using DCS. JoCI 2014, 22, 28. [Google Scholar]
  16. Oliveira, E.E.; Rodrigues, M.; Pereira, J.P.; Lopes, A.M.; Mestric, I.I.; Bjelogrlic, S. Unlabeled learning algorithms and operations: Overview and future trends in defense sector. Artificial Intelligence Review 2024, 57. [Google Scholar] [CrossRef]
  17. Sheikh, H.; Prins, C.; Schrijvers, E. Mission AI. In Research for policy. 2023. [CrossRef]
  18. Sheham, A.M.; Sarifudeen, A.L.; Gunapalan, S. (2015). Corporate social responsibility expenditure on the financial performance of financial institutions with the special reference of Rural Development Bank (RDB).
  19. Sami, H.; Hammoud, A.; Arafeh, M.; Wazzeh, M.; Arisdakessian, S.; Chahoud, M.; Wehbi, O.; Ajaj, M.; Mourad, A.; Otrok, H.; Wahab, O.A.; Mizouni, R.; Bentahar, J.; Talhi, C.; Dziong, Z.; Damiani, E.; Guizani, M. The Metaverse: Survey, Trends, Novel Pipeline Ecosystem & Future Directions. IEEE Communications Surveys & Tutorials 2024, 1. [Google Scholar] [CrossRef]
  20. Yadav, A.B.; Shukla, P.S. (2011, December). Augmentation to water supply scheme using PLC & SCADA. In 2011 Nirma University International Conference on Engineering (pp. 1-5). IEEE.
  21. Venkatesh, V.; Morris, M.G.; Davis, G.B.; Davis, F.D. User Acceptance of Information Technology: Toward a Unified View. MIS Quarterly 2003, 27, 425. [Google Scholar] [CrossRef]
  22. Vertical and Topical Program. (2021). [CrossRef]
  23. By, H. (2021). Conference Program. [CrossRef]
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.
Copyright: This open access article is published under a Creative Commons CC BY 4.0 license, which permit the free download, distribution, and reuse, provided that the author and preprint are cited in any reuse.
Prerpints.org logo

Preprints.org is a free preprint server supported by MDPI in Basel, Switzerland.

facebook logotwitter logolinkedin logo
MDPI Initiatives
Important Links
Subscribe

Disclaimer

Terms of Use

Privacy Policy

© 2024 MDPI (Basel, Switzerland) unless otherwise stated