Abstract:
Accurate segmentation and classification of brain tumors are crucial for effective diagnosis and treatment. This study proposes a computer vision-based approach for efficient segmentation and classification of multi-brain tumors using computed tomography (CT) images. Our method leverages advanced image processing techniques and machine learning algorithms to accurately identify and classify brain tumors. The proposed approach achieves high accuracy, sensitivity, and specificity in segmenting and classifying brain tumors, outperforming existing methods. The results demonstrate the potential of our approach to assist radiologists in accurate diagnosis and treatment planning, ultimately improving patient outcomes.
Biography:
Dr. Wali Khan Mashwani, received the M.Sc. degree in mathematics from the University of Peshawar, Khyber Pakhtunkhwa, Pakistan, in 1996, and the Ph.D. degree in Mathematics from the University of Essex, U.K., in 2012. He is currently working as a Professor in Mathematics in the Institute of Numerical Sciences, Kohat University of Science& Technology (KUST), Khyber Pakhtunkhwa. He has remained Director of Institute of Numerical Sciences for more than Six Years. He is aslo remained Dean, Faculty of Physical and Numerical Sciences, Kohat University of Science& Technology (KUST), Khyber Pakhtunkhwa. He has published more than 200 academic papers in peer-reviewed international journals and conference proceedings. His research interests include evolutionary computation, hybrid evolutionary multi-objective algorithms, and decomposition-based evolutionary methods for multi-objective optimization, mathematical programming, numerical analysis, artificial neural networks and Machine Learning and decision making problems.

Abstract:
This study investigates a multivariate sensor dataset collected from mobile robotic platforms to develop an AI-powered framework for autonomous systems. The dataset includes timestamped measurements of temperature, humidity, light intensity, and GPS coordinates, allowing for a multifaceted analysis centered on six primary objectives. First, mobile robot tracking is achieved through geospatial mapping, enabling precise monitoring of movement patterns across various terrains. Second, sensor fusion integrates multiple environmental inputs, enhancing the robot’s contextual awareness and decision-making accuracy. Third, environmental monitoring uses time-series analysis to detect trends, fluctuations, and anomalies in ambient conditions, providing insights into the operational environment over time. Fourth, spatiotemporal analytics connect environmental changes with specific times and locations, offering a dynamic view of how conditions evolve across both spatial and temporal dimensions. Fifth, cluster analysis is applied to identify hidden patterns and group similar environmental states or sensor behaviors. This unsupervised learning method improves interpretability and supports data-driven decisions by revealing structure in high-dimensional sensor data. Finally, predictive maintenance is facilitated by statistical anomaly detection, which flags deviations in sensor behavior that may signal underlying mechanical or system faults. This proactive approach enhances system reliability and reduces downtime. Collectively, these analytical techniques showcase the transformative potential of artificial intelligence and statistical learning in converting raw sensor data into actionable intelligence. The proposed framework enables intelligent navigation, environmental adaptability, and self-diagnostic capabilities, marking a significant step forward in the evolution of cognitive robotics. By leveraging advanced analytics, this research supports the development of autonomous systems that are not only reactive but also anticipatory and context-aware key traits for next-generation robotic platforms operating in complex, real-world dynamic environments.
Biography:
Prof. Monalisha Pattnaik is a Professor and Head of the Department of Statistics at Sambalpur University, Odisha, India. An expert in Artificial Intelligence, Supply Chain Analytics and Operations Research, she has made notable contributions to research and academia. Her interests span Robotics, AI, Advanced OR, Financial Time Series Analysis, Supply Chain Management, Optimization, and more. She has authored over 135 research papers, with more than 60 indexed in SCOPUS and Web of Science, and published 10 books, edited 5 international volumes, and contributed chapters to CRC Press, Apple Academic Press, and Springer. Prof. Pattnaik has been granted 3 patents by the UK and Indian Intellectual Property Offices. Her excellence has been recognized through several awards, including the Jyesta Acharya Award (Hyderabad, 2021–2022), Distinguished Woman Researcher in Operations Research (Chennai, 2024), Rising Women of India Award & Leading Educationist of India Award (New Delhi, 2024), Best Paper Award at RAORBA-2024 (Kolkata). Most recently, she received the Women Researcher Award at the 2nd International Award Ceremony for Women Researchers (VDGOOD, Pondicherry, Sept 2025). Prof. Pattnaik continues to inspire through her dedication to research, innovation, and academic excellence.

Abstract:
Unmanned aerial vehicles (UAVs) are crucial for enhancing coverage, capacity, and ultra-reliable low-latency communication (URLLC) in 5G and 6G networks. However, challenges such as signal blockages, energy constraints, user mobility, and equitable resource allocation limit efficient UAV deployment. This paper introduces a novel Graph Neural Network–Deep Reinforcement Learning (GNN–DRL) framework that combines graph-based spatial feature extraction with multi-agent DRL (including DDQN, DDPG, and Actor-Critic) and Proximal Policy Optimization (PPO) for adaptive UAV placement, trajectory optimization, and interference management. The framework models the network as a dynamic graph to capture spatial dependencies, formulates a multi-objective optimization problem balancing coverage, energy efficiency, fairness, and blockage-aware probability, and employs PPO for stable policy updates. Extensive simulations in urban (high-blockage) and rural (low-blockage) environments evaluate performance against baselines like DQN, DDPG, MADDPG, TRPO, and static placement. Results show the GNN–DRL approach achieves up to 95% coverage (vs. 75-90% for baselines), 20–30% energy reduction (80-85 Wh vs. 95-120 Wh), improved fairness with load variance as low as 5-8 Mbps² (vs. 12-25 Mbps²), and rapid adaptability in 2–3 seconds. It also delivers URLLC-compliant latency of 0.9 ms, with ablation studies confirming tunable trade-offs and scalability analyses supporting large networks (up to 1000 UAVs/5000 users with 4s computation time). This work advances AI-native wireless systems, offering a scalable solution for autonomous UAV-assisted networks in dynamic 5G/6G scenarios.
Biography:
Mr. Workeneh Geleta Negassa earned his B.Sc. in Electrical and Electronics Technology in 2008 and his M.Sc. in Electronics and Communication Technology in 2014, both from Adama University, Adama, Ethiopia. He is currently pursuing a Ph.D. in Electronics and Communication Engineering at Adama Science and Technology University. He has authored over 10 papers in reputable journals. His research interests include cooperative UAV communications, signal processing, advanced wireless technologies (including 5G and beyond), the Internet of Things, cybersecurity, machine learning, and fog/edge computing.

Abstract:
Accurate assessment of plant health is crucial for preventing crop stress, reducing disease, and maximizing yield. Traditionally, plant health monitoring is labor-intensive and prone to errors, creating a restriction for timely and accurate decision-making. Recent advances in technology have made it easier to detect plant health issues, including tools like Croptix, which uses spectroscopic sensors to monitor plant condition. In this research, we propose a vision-based system that automatically detects and targets a leaf’s midrib in an outdoor environment, therefore automating the process of capturing plant health metrics with Croptix. A simple convolutional neural network (CNN) is trained to locate leaves and identify the coordinates of their midribs using computer vision techniques. A decision process is incorporated into the vision system to determine which leaves to grab on the plant and how many measurements to record. This information is then used to guide a robotic arm, equipped with the Croptix sensor as an end-effector, to precisely measure plant health at each leaf’s center. By enabling more accurate and non-invasive health monitoring, this approach has the potential to improve crop management, yield, and labor shortage in field settings.
Biography:
Dr.Shirin Ghatrehsamani is an assistant professor in Mechatronics and Intelligent Sensing and Controls in the Agricultural and Biological Engineering Department at Penn State University, PA, USA. Her area of specialization is Precision Technology, Automation and Robotics, Computational Modeling and Mechanization.

Abstract:
Automated vehicles have the potential to further reduce safety risks by transfer of driving functions from humans to a sophisticated socio-technical system. As a learning system, safety is rather an emergent development property than static; safety cases suffer from inherent lack of data. The homologation procedure has not been fully established and harmonized. While in the US the self-certification approach backed by voluntary guidance is pursued Europe continues to follow type-approval approach. Implementation regulation is put into force with safety requirements which asks the manufacturer to demonstrate absence of unreasonable risk to occupants and other road users. The underlying question “How safe is safe enough? is answered in form of semantic qualitative requirements, safety features of conventional vehicles are referenced for comparison. The need for amending quantitative target values has been expressed.  Although limited proposals exist shared and meaningful quantitative measurements are scarce, acceptance criteria from a societal perspective are missing; this work attempts to fill this gap. As “safety” is essential and deserves a broader than a just technical-mathematical view, contextual factors like socio-economic and cultural aspects are considered. Outlined regulations and accepted risks in comparable domains, e.g. rail transport and aviation, are used to deduce target values. We conclude all humans are equal, should be primary subject of protection, put the “objective” risk in focus and consider the aggregated accident risk of occupants and other road users as metric. Making use of accident statistics, we propose a value of 3×10^-9 fatalities (resp. 4×10^-8 fatalities and seriously injured people) per hour of operation, to be considered tolerable. The corresponding values for not-tolerable risks are ten times higher with a cost-benefit regime in between in accordance with the ALARA principle These target values are put forward to stakeholders inside and outside industries for the launch phase and should be verified by continuous monitoring and evaluation of event statistics and adapted, potentially further sharpened.
Biography:
Wolfgang Kröger is Professor emeritus at ETH Zurich/Department of Mechanical and Process Engineering. As a member of the SATW he heads its topical platform of autonomous mobility. His seminal work lies in reliability, risk and vulnerability analysis of large-scale technical systems including complex engineered networks controlled by cyber-physical systems. He engaged himself in shaping and operationalizing the concept of sustainability and – more recently – of resilience of future systems. His ongoing research interest and contributions to the development and certification of automated/ autonomous vehicles, regarded as a cornerstone of future mobility concepts are matter of growing interest. He has published about 40 reviewed papers, books, and edited volumes only in the last 15 years, served on international review groups and notable advisory boards.

Abstract:
As organizations strive for operational excellence, the integration of Robotic Process Automation (RPA) and Generative AI (Gen AI) has become pivotal in transforming business processes. In this session, I will share my experiences as an RPA Project Manager at Bayer, highlighting real-world cases that illustrate how these technologies can be effectively leveraged to enhance efficiency and drive innovation. The presentation will begin with an overview of RPA and Gen AI, discussing their unique capabilities and how they complement each other in the automation landscape. I will present specific case studies from Bayer, where we successfully implemented RPA solutions to automate repetitive tasks, resulting in a 30% increase in productivity and significant cost savings. One notable project involved automating the data entry process in our supply chain management system, which not only reduced errors but also allowed our team to focus on more strategic activities. A key highlight of our Gen AI initiatives is the development of our own customized ChatGPT solution. This innovative tool empowers users to create their own virtual assistants tailored to specific business needs. By leveraging advanced natural language processing capabilities, employees can design virtual assistants that streamline communication, provide instant access to information, and automate routine inquiries. For example, one department utilized this technology to create a virtual assistant that handles employee onboarding queries, significantly reducing the workload on HR personnel and improving the onboarding experience for new hires. This initiative not only showcased our commitment to innovation but also demonstrated how Gen AI can enhance user engagement and operational efficiency. Choosing the right technology for automation initiatives is crucial. I will share insights on how to assess business needs and select the most suitable solutions, emphasizing the importance of stakeholder engagement and a clear understanding of process requirements. Attendees will learn about the key factors to consider when evaluating RPA and Gen AI tools, including scalability, ease of integration, and alignment with organizational goals. Additionally, I will address common challenges faced during implementation, such as resistance to change and the need for upskilling employees. By fostering a culture of innovation and collaboration, organizations can overcome these hurdles and successfully implement automation solutions that drive measurable results. This session aims to equip attendees with practical knowledge and strategies for harnessing the power of RPA and Gen AI to transform their operations. Join me to discover how these technologies are not just tools but catalysts for change, enabling organizations to thrive in the digital age.
Biography:
Meritxell Corbeto González is an accomplished RPA Project Manager with a strong engineering background and over five years of experience in leading automation initiatives across diverse industries. Currently working at Bayer, she specializes in identifying opportunities for process optimization through Robotic Process Automation (RPA) and innovative technology solutions. Meritxell is certified in PMI Project Management, Scrum Master, Scrum Product Owner, and Advanced RPA Developer by UiPath Academy. Known for her exceptional communication skills and adaptability, she excels in dynamic environments and is passionate about leveraging new technologies to enhance operational efficiency. As a speaker at industry congresses and an instructor for online RPA modules, Meritxell is dedicated to sharing her knowledge and inspiring future generations of engineers. She holds a degree in Air Navigation Engineering from EETAC (UPC) and is currently finalizing an Executive MBA. Meritxell is committed to promoting diversity and inclusion in technology, advocating for women’s representation in engineering fields

Abstract:
The integration of AI-driven methodologies into robotics has become pivotal for advancing automation in high-precision manufacturing, where robotic arms face persistent challenges in controlling absolute positioning accuracy due to nonlinear and random errors. While traditional neural network-based error prediction models offer potential, their performance is often hindered by measurement noise in training samples, leading to slow convergence and suboptimal accuracy. This research introduced a novel Fuzzification-Back Propagation Neural Network (F-BPNN) model, designed to enhance robotic arm positioning accuracy through training data preprocessing by fuzzification and positioning error predicting by neural network. The proposed model leverages fuzzification to preprocess joint rotation angles and directions, transforming raw data into error contributions that mitigate the impact of measurement uncertainties. By integrating a two-dimensional fuzzification process, based on error and error fluctuation, the model optimizes input data for training a BPNN, enabling efficient nonlinear mapping between joint errors and positioning errors of robotic arm’s end. This AI-driven approach not only simplifies samples used by network training but also accelerates training by reducing parameter sensitivity to noise. Experimental validation on one 6-DOF UR5 robotic arm demonstrates significant improvements: training time is reduced by >50 %, mean square error of the model decreases by 2.94 %, and average absolute positioning error of the UR5 robotic arm after compensation is slashed by 59.22 % (from 0.206 mm to 0.084 mm), comparable to existing real-time compensation standards. The model can be easily transplanted into embedded systems to provide a methodology for new design of robotic arm error compensators. By bridging fuzzification with neural network, this work exemplified how hybrid AI techniques can address critical challenges in robotic automation. The results underscore the potential of composite neural network models to predict error in industrial robotics, paving the way for smarter, self-correcting robotic systems in next-generation manufacturing, particularly in high-precision domains like aerospace assembly and microelectronics. Future research will focus on refining fuzzy interval partitioning and expanding the model’s applicability to complex and sophisticated multi-joint collaborative robots, further aligning with the vision of AI-driven automation as a cornerstone of Industry 4.0.
Biography:
Jiang Liu is a Ph. D candidate in the School of Aerospace at Harbin Institute of Technology (HIT), Heilongjiang Province, China. He earned his Master Degree of Engineering from HIT in 2022 and Bachelor Degree of Engineering from Wuhan University of Technology, Hubei Province, China, in 2020. During his graduate studies, he worked on AI-driven solutions for real-time positioning error compensation in industrial robotic arms and contributed to the development of high-precision 2D motion stages. Currently, his research interests include positioning error prediction in industrial robotic arms, fuzzification-neural network modeling, and advanced packaging technologies for integrated circuits, with an emphasis on wafer hybrid bonding techniques.