Kabita Adhikari

Ultrahigh-frequency radio frequency identification (UHF RFID) sensing systems have emerged as a promising technology for wireless, passive, and cost-effective monitoring applications. However, their performance is highly sensitive to variations in measurement setups, such as tag–reader distance, orientation, and interrogation conditions, which compromise sensing accuracy and severely limit the reliability and robustness of these systems. These challenges are especially pronounced in nonstationary interrogation, such as in robotic pipeline inspections, where mobile crawlers face bends, welds, irregular surfaces, and multipath effects, and in distributed monitoring systems with multiple tag positions. Conventional approaches based on raw received signal strength indicator (RSSI) or turn-on power remain tightly coupled to setup variations, leading to unreliable sensing. To overcome this, we propose a setup-independent response map-based method that integrates frequency- and power-domain RSSI measurements into a multidimensional signature, from which corrosion-specific features are extracted using principal component analysis (PCA) and kernel PCA. A custom UHF RFID tag was developed and validated under six varying tag–reader setups and six different corrosion conditions for undercoating corrosion detection. Compared with the state-of-the-art analog identifier (AID) method, the proposed approach achieves significantly higher stability (average CV 0.4483 versus 1.0783), tighter feature clustering (variance 0.0750 versus 0.1235), and a fivefold reduction in measurement time. These results demonstrate a robust, efficient, and practical solution for high-fidelity, setup-independent UHF RFID-based sensing, ensuring reliable nonstationary and distributed monitoring for advanced industrial applications.

This study focuses on the physical layer security (PLS) performance of a reconfigurable intelligent surface (RIS)-aided vehicular communication network. Motivated by the great potential of RIS-based transmission, we analyze the PLS performance of two scenarios of vehicular networks (both of which have an eavesdropper present): i) vehicle-to-vehicle (V2V) communication when the source employs a RIS-based access point and ii) vehicular adhoc network (VANET) where a RIS-based relay mounted on a building. The performance of the proposed systems are evaluated in terms of the average secrecy capacity (ASC) and the secrecy outage probability (SOP). We present accurate analytical expressions for the two performance metrics and study the impact of various system parameters on the overall performance of the two considered system configurations. In order to validate the analysis, we provide Monte-Carlo simulations throughout the paper. The results demonstrate that the system performance is impacted by various parameters such as the number of RIS elements as well as the location of the RIS-relay. Moreover, up to an order magnitude gain could be achieved within certain regions when the number of RIS cells are doubled, clearly indicating the benefit of employing a RIS configuration.

Bladder cancer claims one life every 3 minutes worldwide. Most patients are diagnosed with non-muscle-invasive bladder cancer (NMIBC), yet up to 70% recur after treatment, triggering a relentless cycle of surgeries, monitoring, and risk of progression. Clinical tools like the EORTC risk tables are outdated and unreliable - especially for intermediate-risk cases. We propose an interpretable AI model using the Tsetlin Machine (TM), a symbolic learner that outputs transparent, human-readable logic. Tested on the PHOTO trial dataset (n=330), TM achieved an F1-score of 0.80, outperforming XGBoost (0.78), Logistic Regression (0.60), and EORTC (0.42). TM reveals the exact clauses behind each prediction, grounded in clinical features like tumour count, surgeon experience, and hospital stay - offering accuracy and full transparency. This makes TM a powerful, trustworthy decision-support tool ready for real-world adoption.

Non-muscle-invasive bladder cancer (NMIBC) is a relentless challenge in oncology, with recurrence rates soaring as high as 70-80%. Each recurrence triggers a cascade of invasive procedures, lifelong surveillance, and escalating healthcare costs - affecting 460,000 individuals worldwide. However, existing clinical prediction tools remain fundamentally flawed, often overestimating recurrence risk and failing to provide personalized insights for patient management. In this work, we propose an interpretable deep learning framework that integrates vector embeddings and attention mechanisms to improve NMIBC recurrence prediction performance. We incorporate vector embeddings for categorical variables such as smoking status and intravesical treatments, allowing the model to capture complex relationships between patient attributes and recurrence risk. These embeddings provide a richer representation of the data, enabling improved feature interactions and enhancing prediction performance. Our approach not only enhances performance but also provides clinicians with patient-specific insights by highlighting the most influential features contributing to recurrence risk for each patient. Our model achieves accuracy of 70% with tabular data, outperforming conventional statistical methods while providing clinician-friendly patient-level explanations through feature attention. Unlike previous studies, our approach identifies new important factors influencing recurrence, such as surgical duration and hospital stay, which had not been considered in existing NMIBC prediction models.

Background: Non-muscle-invasive Bladder Cancer (NMIBC) is notorious for its high recurrence rate of 70-80%, imposing a significant human burden and making it one of the costliest cancers to manage. Current prediction tools for NMIBC recurrence rely on scoring systems that often overestimate risk and lack accuracy. Machine learning (ML) and artificial intelligence (AI) are transforming oncological urology by leveraging molecular and clinical data to enhance predictive precision.Methods: This comprehensive review critically examines ML-based frameworks for predicting NMIBC recurrence. A systematic literature search was conducted, focusing on the statistical robustness and algorithmic efficacy of studies. These were categorised by data modalities (e.g., radiomics, clinical, histopathological, genomic) and types of ML models, such as neural networks, deep learning, and random forests. Each study was analysed for strengths, weaknesses, performance metrics, and limitations, with emphasis on generalisability, interpretability, and cost-effectiveness. Results: ML algorithms demonstrate significant potential, with neural networks achieving accuracies of 65–97.5%, particularly with multi-modal datasets, and support vector machines averaging around 75%. Models combining multiple data types consistently outperformed single-modality approaches. However, challenges include limited generalisability due to small datasets and the "black-box" nature of advanced models. Efforts to enhance explainability, such as SHapley Additive ExPlanations (SHAP), show promise but require refinement for clinical use.Conclusion: This review illuminates the nuances, complexities and contexts that influence the real-world advancement and adoption of these AI-driven techniques in precision oncology. It equips researchers with a deeper understanding of the intricacies of the ML algorithms employed. Actionable insights are provided for refining algorithms, optimising multimodal data utilisation, and bridging the gap between predictive accuracy and clinical utility. This rigorous analysis serves as a roadmap to advance real-world AI applications in oncological care, highlighting the collaborative efforts and robust datasets necessary to translate these advancements into tangible benefits for patient management.

Switched model predictive control (S-MPC) and recurrent neural networks with long short-term memory (RNN-LSTM) are powerful control methods that have been extensively studied for the energy management of microgrids (MGs). These methods ease constraint satisfaction, computational demands, adaptability, and comprehensibility, but typically one method is chosen over the other. The S-MPC method dynamically selects optimal models and control strategies based on the system’s operating mode and performance objectives. On the other hand, integration of auto-regressive (AR) control with these powerful control methods improves the prediction accuracy and the adaptability of the system conditions. This paper compares the two control approaches and proposes a novel algorithm called switched auto-regressive neural control (S-ANC) that combines their respective strengths. Using a control formulation equivalent to S-MPC and the same controller model for learning, the results indicate that pure RNN-LSTM cannot provide constraint satisfaction. The novel S-ANC algorithm can satisfy constraints and deliver comparable performance to MPC, while enabling continuous learning. The results indicate that S-MPC optimization increases power flows within the MG, resulting in efficient utilization of energy resources. By merging the AR and LSTM, the model’s computational time decreased by nearly 47.2%. In addition, this study evaluated our predictive model’s accuracy: (i) the R-squared error was 0.951, indicating a strong predictive ability, and (ii) mean absolute error (MAE) and mean square error (MSE) values of 0.571 indicate accurate predictions, with minimal deviations from the actual values.

Switched model predictive control (S-MPC) and recurrent neural network with long short-term memory (RNN-LSTM) are powerful control methods that have been extensively studied for energy management in microgrids (MGs). These methods are complementary in terms of constraint satisfaction, computational demand, adaptability, and comprehensibility, but typically one method is chosen over the other. The S-MPC method selects optimal models and control strategies dynamically based on the system’s operating mode and performance objectives. On the other hand, integration of auto-regressive (AR) with these powerful control methods improves prediction accuracy and system conditions’ adaptability. This paper compares the two approaches to control and proposes a novel algorithm called Switched Auto-regressive Neural Control (S-ANC) that combines their respective strengths. Using a control formulation equivalent to S-MPC and the same controller model for learning, the results indicate that pure RNN-LSTM cannot provide constraint satisfaction. The novel S-ANC algorithm can satisfy constraints and deliver comparable performance to MPC while enabling continuous learning. Results indicate that S-MPC optimization increases power flows within the MG, resulting in efficient utilization of energy resources. By merging the AR and LSTM, the model’s computational time decreased by nearly 47.2%. Also, this study evaluated our predictive model’s accuracy: (i) R-squared error is 0.951, indicating strong predictive ability, and (ii) mean absolute error (MAE) and mean square error (MSE) values of 0.571 indicate accurate predictions with minimal deviations from actual values.

Microgrids (MGs) are a growing energy industry segment and represent a paradigm shift from remote central power plants to more localized distributed generation. Controlling MGs represents a challenge mainly due to their complexity and the different properties each asset in the MG has. Various methods have been proposed to address this challenging problem of MG control. Some of these methods are considered the optimal operation of MG assets. Other works are based on a systems approach and address the scalability and simplicity of synthesizing a MG’s energy management system (EMS). ε-variables based logical control strategies, which are practical methods to model control strategies in MGs, can make the control structure more scalable. However, this method is not optimal. On the other hand, Switched Model Predictive Control (S-MPC) is an advanced method utilized to control power systems while satisfying several constraints to achieve an optimal solution based on various criteria. Nevertheless, its implementation is not straightforward. Therefore, to overcome these existing problems, this paper proposes a novel systems approach method called an extended optimal ε-variable method developed by combining the ε-variable based control method with the S-MPC method. This unique method has demonstrated a significant improvement in optimizing an MG’s energy management and enhanced the adaptation and scalability of a control structure of the MG. Our results show that the proposed extended optimal ε-variable method: (i) reduces the operational cost of MG by nearly 35%; (ii) reduces the usage of the battery energy storage system by 42%, and (iii) enhances the practicality of photovoltaic (PV) usage by 28%. Our novel extended optimal ε-variable technique also increases the adaptation and scalability of the control structure of the MG significantly by translating the results of S-MPC to the ε-variable method.

All existing physiological tremor filtering algorithms, developed for robotic microsurgery, use nonlinear phase prefilters to isolate the tremor signal. Such filters cause phase distortion to the filtered tremor signal and limit the filtering accuracy. We revisited this long-standing problem to enable filtering of the physiological tremor without any phase distortion. We developed a combined estimation-prediction paradigm that offers zero-phase type filtering. The estimation is achieved with the mathematically modified recursive singular spectrum analysis algorithm, and the prediction is delivered with the standard extreme learning machine. In addition, to limit the computational cost, we developed two moving window versions of this structure, which are appropriate for real-time implementation. The proposed paradigm preserved the natural phase of the filtered tremor. It achieved the key performance index of error limitation below 10\mum, yielding the estimation accuracy larger than 70%, at a time delay of 36 ms only. Both moving window versions of the proposed approach restricted the computational cost considerably while offering the same performance. It is the first time that the effective estimation of the physiological tremor is achieved, without any prefiltering and phase distortion. This proposed method is feasible for real-time implantation. Clinical translation of the proposed paradigm can significantly enhance the outcome in hand-held surgical robotics.

Background: The transition in the education system was parallel to the humankind and the technological revolution has been increasing issues in the education system around the globe. The shift in education system tends to understand how learning styles of students affect education quality with completely different forms of e-learning. Education 4.0 tackles society's desire in the 'innovative age'. Such education training will demonstrate the ability of the learner to use the latest technology to help the learner adapt as per the changes in society. Students in education 4.0 become more self-reliant in their own education, pressuring educators to accept a new function as administrators who might influence the learners across their education process. This paper aims to explore pandemic as a driver of enhancement of Education 4.0 in Nepal in terms of school level technology change. The paper applies the thorough review of the literature on Education 4.0 in wider perspective as well as in Nepalese context. Objective: This paper aims to analyze the enhancement of education 4.0 in Nepal in terms of review from school level technology change. Results: It is observed that education 4.0 is a very necessary reform in the education system in Nepal. The major need of the time is the upliftment of the education sector from the traditional ones and makes the implementation of education 4.0. It helps in the improvement of digital competencies in all level, and the use of digital technologies for teaching and learning. The research regarding the changes in the education system has been conducted in various nations around the globe. Conclusions: It is found that the learners mostly prefer those technology with whom they are more familiar such as use audio/video conferencing technologies rather than any other tools. Education revolution is not an easy task for the developing countries as there is a lack of local research regarding the new technologies in educational sectors. Nepal has tremendous opportunities to drastically reform education in an offer to address deep structural inequalities. Originality: This paper is original and not published anywhere else.