Ekaterina Dmitrieva
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ekaterina Dmitrieva has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
G. Lavanya
Assistant Professor, GRIET, Bachupally, Hyderabad, Telangana
2 shared publicationsKshama Sharma
K R Mangalam University, Gurgaon, India
2 shared publicationsVinod Balmiki
Uttaranchal University, Dehradun248007, India
2 shared publicationsAchyut Sharma
GD Goenka University, Sohna, Haryana, India
1 shared publicationAnjali Vyas
GD Goenka University, Sohna, Haryana, India
1 shared publicationAnshika Prakash
K R Mangalam University, Gurgaon, India
1 shared publication
Latest Publications
- Open Access
- 12 January 2024
- Published by EDP Sciences in BIO Web of Conferences
- Vol. 86, 01069
AI Evolution in Industry 4.0 and Industry 5.0: An Experimental Comparative Assessment
This paper provides a thorough analysis of the development of artificial intelligence (AI) in the context of Industry 4.0 and the soon-to-be Industry 5.0. Important conclusions come from the data, such as the startling 900% increase in AI applications between 2010 and 2018, which corresponds to a 60% rise in the proportion of industrial enterprises using AI at that time. Moreover, our analysis shows that Industry 4.0's AI integration has resulted in a notable 200% cost reduction and a cumulative 400% boost in production efficiency. Our study delves into the rapid deployment of critical technologies like 5G connectivity and quantum computing within the framework of Industry 5.0. The usage of 5G connectivity has increased by 200% in only two years, while quantum computing has seen a staggering 1000% growth in acceptance over the course of eight years. These findings demonstrate the fast technological transition occurring in Industry 5.0. Furthermore, by 2033, the research predicts a startling 400% increase in human-machine cooperation and an anticipated 133% decrease in mistake rates. The research highlights how Industry 4.0's deep consequences of AI development and Industry 5.0's revolutionary possibilities will impact manufacturing in the future.
- 12 January 2024
- Published by EDP Sciences in BIO Web of Conferences
- Vol. 86, 01069
Open AccessAI Evolution in Industry 4.0 and Industry 5.0: An Experimental Comparative Assessment
This paper provides a thorough analysis of the development of artificial intelligence (AI) in the context of Industry 4.0 and the soon-to-be Industry 5.0. Important conclusions come from the data, such as the startling 900% increase in AI applications between 2010 and 2018, which corresponds to a 60% rise in the proportion of industrial enterprises using AI at that time. Moreover, our analysis shows that Industry 4.0's AI integration has resulted in a notable 200% cost reduction and a cumulative 400% boost in production efficiency. Our study delves into the rapid deployment of critical technologies like 5G connectivity and quantum computing within the framework of Industry 5.0. The usage of 5G connectivity has increased by 200% in only two years, while quantum computing has seen a staggering 1000% growth in acceptance over the course of eight years. These findings demonstrate the fast technological transition occurring in Industry 5.0. Furthermore, by 2033, the research predicts a startling 400% increase in human-machine cooperation and an anticipated 133% decrease in mistake rates. The research highlights how Industry 4.0's deep consequences of AI development and Industry 5.0's revolutionary possibilities will impact manufacturing in the future.
- Open Access
- 12 January 2024
- Published by EDP Sciences in BIO Web of Conferences
- Vol. 86, 01062
IoT and AI Integration: An Experiment on Smart Manufacturing Efficiency in Industry 5.0
In line with the Industry 5.0 paradigm, this empirical research offers a data-driven investigation of the revolutionary effects of combining IoT and AI in smart manufacturing. The findings show a notable 1.52% gain in production efficiency, which is attributed to post-implementation temperature increases of 36.2°C and humidity decreases of 44.8%. A decrease in faults found (2) led to a 0.76% increase in quality scores (93.1) for quality control. With fewer maintenance hours (2.3) and downtime (52 minutes), maintenance practices were more effective. These results highlight the concrete advantages of integrating IoT and AI in smart manufacturing, putting it at the vanguard of Industry 5.0's revolutionary landscape and improving productivity, quality, and maintenance.
- 12 January 2024
- Published by EDP Sciences in BIO Web of Conferences
- Vol. 86, 01062
Open AccessIoT and AI Integration: An Experiment on Smart Manufacturing Efficiency in Industry 5.0
In line with the Industry 5.0 paradigm, this empirical research offers a data-driven investigation of the revolutionary effects of combining IoT and AI in smart manufacturing. The findings show a notable 1.52% gain in production efficiency, which is attributed to post-implementation temperature increases of 36.2°C and humidity decreases of 44.8%. A decrease in faults found (2) led to a 0.76% increase in quality scores (93.1) for quality control. With fewer maintenance hours (2.3) and downtime (52 minutes), maintenance practices were more effective. These results highlight the concrete advantages of integrating IoT and AI in smart manufacturing, putting it at the vanguard of Industry 5.0's revolutionary landscape and improving productivity, quality, and maintenance.
- Open Access
- 12 January 2024
- Published by EDP Sciences in BIO Web of Conferences
- Vol. 86, 01096
Edge Computing and AI: Advancements in Industry 5.0- An Experimental Assessment
This empirical research evaluated, via experimentation, how Edge Computing and Artificial Intelligence (AI) work together in the context of Industry 5.0. With a high satisfaction rating of 88%, participants in the Edge Computing condition saw an astonishing 18% decrease in task completion times. Similarly, in the AI integration scenario, participants rated AI's value at 86%, and they saw a significant 12% reduction in task completion times and a noteworthy 7% drop in mistake rates. Significantly, with an astounding 21% gain in work completion times, the Edge Computing and AI combo had the largest performance boost. These results highlight how Edge Computing and AI may dramatically improve industrial efficiency and performance in the context of Industry 5.0, providing insightful information for businesses looking to use these technologies to streamline processes and spur innovation.
- 12 January 2024
- Published by EDP Sciences in BIO Web of Conferences
- Vol. 86, 01096
Open AccessEdge Computing and AI: Advancements in Industry 5.0- An Experimental Assessment
This empirical research evaluated, via experimentation, how Edge Computing and Artificial Intelligence (AI) work together in the context of Industry 5.0. With a high satisfaction rating of 88%, participants in the Edge Computing condition saw an astonishing 18% decrease in task completion times. Similarly, in the AI integration scenario, participants rated AI's value at 86%, and they saw a significant 12% reduction in task completion times and a noteworthy 7% drop in mistake rates. Significantly, with an astounding 21% gain in work completion times, the Edge Computing and AI combo had the largest performance boost. These results highlight how Edge Computing and AI may dramatically improve industrial efficiency and performance in the context of Industry 5.0, providing insightful information for businesses looking to use these technologies to streamline processes and spur innovation.
- Open Access
- 12 January 2024
- Published by EDP Sciences in BIO Web of Conferences
- Vol. 86, 01102
Data Analytics for Dynamic Urban Operations: A Test-Based Study on Data Analytics Efficiency
This paper explores the field of data analytics for dynamic urban operations and provides a systematic analysis of the importance and possible implications of this field. Our investigation indicates significant data volumes in an urban setting that is data-rich: 500 GB are generated by traffic sensors, 300 GB by environmental monitors, 150 GB by mobile apps, and 75 GB by emergency calls. A variety of analytics techniques, each with a different processing time, are built upon these data sources. These techniques include descriptive, predictive, prescriptive, and diagnostic analytics. The outcomes, which include 90% accuracy, an average processing time of 40 minutes, 80% resource utilization, and 4.2 user satisfaction ratings, highlight the benefits of data analytics. According to the comparison study, diagnostic analytics has a score of 7.8, indicating room for development, while prescriptive analytics leads with an efficiency score of 8.4. As urban stakeholders and academics work to improve urban systems and solve urban issues, the results give a thorough understanding of the effectiveness and application of data analytics in the context of dynamic urban operations.
- 12 January 2024
- Published by EDP Sciences in BIO Web of Conferences
- Vol. 86, 01102
Open AccessData Analytics for Dynamic Urban Operations: A Test-Based Study on Data Analytics Efficiency
This paper explores the field of data analytics for dynamic urban operations and provides a systematic analysis of the importance and possible implications of this field. Our investigation indicates significant data volumes in an urban setting that is data-rich: 500 GB are generated by traffic sensors, 300 GB by environmental monitors, 150 GB by mobile apps, and 75 GB by emergency calls. A variety of analytics techniques, each with a different processing time, are built upon these data sources. These techniques include descriptive, predictive, prescriptive, and diagnostic analytics. The outcomes, which include 90% accuracy, an average processing time of 40 minutes, 80% resource utilization, and 4.2 user satisfaction ratings, highlight the benefits of data analytics. According to the comparison study, diagnostic analytics has a score of 7.8, indicating room for development, while prescriptive analytics leads with an efficiency score of 8.4. As urban stakeholders and academics work to improve urban systems and solve urban issues, the results give a thorough understanding of the effectiveness and application of data analytics in the context of dynamic urban operations.
- Open Access
- 12 January 2024
- Published by EDP Sciences in BIO Web of Conferences
- Vol. 86, 01097
Security and Privacy in AI-Driven Industry 5.0: Experimental Insights and Threat Analysis
This empirical research offers important insights from simulated industrial situations as it examines security and privacy in AI-driven Industry 5.0. When responding to security problems, participants' remarkable average reaction time of 14 minutes demonstrated their preparedness. On a 5-point rating scale, the clarity and openness of privacy rules were scored 3.8 overall; however, differences between 3.5 and 4.2 indicated the range of privacy issues. These results highlight the need of well-defined security procedures, thorough training, and easily available, transparent privacy regulations in order to manage the ethical integration of AI into Industry 5.0 and promote stakeholder confidence and data protection.
- 12 January 2024
- Published by EDP Sciences in BIO Web of Conferences
- Vol. 86, 01097
Open AccessSecurity and Privacy in AI-Driven Industry 5.0: Experimental Insights and Threat Analysis
This empirical research offers important insights from simulated industrial situations as it examines security and privacy in AI-driven Industry 5.0. When responding to security problems, participants' remarkable average reaction time of 14 minutes demonstrated their preparedness. On a 5-point rating scale, the clarity and openness of privacy rules were scored 3.8 overall; however, differences between 3.5 and 4.2 indicated the range of privacy issues. These results highlight the need of well-defined security procedures, thorough training, and easily available, transparent privacy regulations in order to manage the ethical integration of AI into Industry 5.0 and promote stakeholder confidence and data protection.
- Open Access
- 12 January 2024
- Published by EDP Sciences in BIO Web of Conferences
- Vol. 86, 01098
Real-Time Traffic Management in Smart Cities: Insights from the Traffic Management Simulation and Impact Analysis
Using simulation and empirical data analysis, this research examines the efficacy of real-time traffic control in smart cities. Traffic data collected in real time from strategically placed sensors shows that traffic volume was reduced by 8.33% on Main Street after a traffic light timing change was implemented. Traffic volume at Highway Junction was also significantly reduced by 5.56% as a result of traffic sign updates. On the other hand, interventions result in a relatively small decrease in traffic volume (2.78%) in the City Center. The influence of these actions is shown by the traffic simulation models, which show average vehicle speeds rising from 25 to 28 mph on Main Street, 45 to 50 mph at Highway Junction, and 30 to 32 mph in the Residential Area. The aforementioned research highlights the crucial function of data-driven decision-making in traffic management, guaranteeing effective distribution of resources and quantifiable enhancements in urban mobility. Urban planners and legislators may use these discoveries to build smart cities that are more accessible, sustainable, and efficient.
- 12 January 2024
- Published by EDP Sciences in BIO Web of Conferences
- Vol. 86, 01098
Open AccessReal-Time Traffic Management in Smart Cities: Insights from the Traffic Management Simulation and Impact Analysis
Using simulation and empirical data analysis, this research examines the efficacy of real-time traffic control in smart cities. Traffic data collected in real time from strategically placed sensors shows that traffic volume was reduced by 8.33% on Main Street after a traffic light timing change was implemented. Traffic volume at Highway Junction was also significantly reduced by 5.56% as a result of traffic sign updates. On the other hand, interventions result in a relatively small decrease in traffic volume (2.78%) in the City Center. The influence of these actions is shown by the traffic simulation models, which show average vehicle speeds rising from 25 to 28 mph on Main Street, 45 to 50 mph at Highway Junction, and 30 to 32 mph in the Residential Area. The aforementioned research highlights the crucial function of data-driven decision-making in traffic management, guaranteeing effective distribution of resources and quantifiable enhancements in urban mobility. Urban planners and legislators may use these discoveries to build smart cities that are more accessible, sustainable, and efficient.