Ritu Raj Lamsal

Dr. Ritu Raj Lamsal

ETSI, University of Malaga, Málaga, Andalusia, Spain
orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 September 2023 in Agriculture
Verified
Journal Article
Open access
PDF file
Ritu Raj LamsalRitu Raj Lamsal
Ritu Raj Lamsal
Karthikeyan PKarthikeyan P
Karthikeyan P
POPABLO OTERO
PABLO OTERO
AQAlfonso Ariza Quintana
Alfonso Ariza Quintana
Nepal, a lower-middle-income country in South Asia, predominantly features smallholder farming communities operating on modest land holdings. These smallholders often adhere to traditional farming methods, relying on familial labor, which has become increasingly inefficient in contemporary agricultural landscapes. To enhance their productivity and efficiency, smallholder farmers require affordable and accessible Internet of Things (IoT)-based systems. However, the prevailing IoT solutions in the market primarily cater to large-scale commercial enterprises, rendering them unsuitable for the specific needs and constraints faced by smallholder farmers. In response to this gap, we have introduced a cost-effective, customizable, scalable, and dependable IoT platform tailored expressly for smallholder farmers. This platform empowers them to visualize, monitor, and control real-time data pertaining to their crops, livestock, and other agricultural assets. To ascertain the efficacy and suitability of our proposed platform, we conducted a comparative analysis with existing counterparts such as Blynk IoT and ThingSpeak IoT, evaluating their respective features and application services against standard requirements. Additionally, we subjected our platform to rigorous server load testing, assessing crucial performance parameters including throughput, response time, user capacity, and data sampling rates. Over an observation period spanning an average of 339 days, our platform successfully processed and stored a substantial volume of data, encompassing 817,633 sensor messages, averaging 2412 messages per day, with a cumulative storage size of 14,238.28 KB. Extrapolating from these results, it is noteworthy that an A0 instance with 20 GB of cloud space can adequately accommodate 200 users at a rate of 100 MB per user, which is adequate for the smallholder needs. Furthermore, the purposed platform was deployed inside a polyhouse to perform off-season grafting of citrus plants. The achieved success rate of 84% closely approached the success rate of 90–95% observed during on-season grafting. These empirical findings, coupled with the extensive data gathered during our research, underscore the reliability and performance of our proposed IoT platform for smallholder farmers.

1 November 2023 in Journal of The Institution of Engineers (India): Series B
Verified
Journal Article
Closed access
PDF file
Ritu Raj LamsalRitu Raj Lamsal
Ritu Raj Lamsal
ADAnurodh Devkota
Anurodh Devkota
MBMadhu Sudhan Bhusal
Madhu Sudhan Bhusal

8 July 2024 in Agriengineering
Verified
Journal Article
Open access
PDF file
Ritu Raj LamsalRitu Raj Lamsal
Ritu Raj Lamsal
UAUmesh Kumar Acharya
Umesh Kumar Acharya
Karthikeyan PKarthikeyan P
Karthikeyan P
POPABLO OTERO
PABLO OTERO
AQAlfonso Ariza Quintana
Alfonso Ariza Quintana
Citrus fruit cultivation, especially mandarin oranges, is crucial to the economy of Nepal’s hilly regions due to their ideal geoclimatic conditions. Despite its economic importance, the sector faces several challenges, such as inadequate grafting techniques, low-quality saplings, and ineffective post-harvest storage. This paper explores these issues and proposes innovative solutions through the use of Internet of Things (IoT) technology. To address these challenges, we identified key areas for improvement. First, we focused on extending grafting practices during the off-season to ensure a higher success rate and better-quality saplings. Second, we examined different post-harvest storage methods to determine their effectiveness in terms of shelf life, decay loss, and quality of fruit. In addition to exploring post-harvest strategies, this paper provides preharvest recommendations for farmers, emphasizing methods to enhance fruit quality and longevity through effective pre-storage practices. Our IoT-based approach introduces off-season grafting in polyhouses and advanced monitoring for post-harvest storage. The results are promising: We achieved grafting success rates of 91% for acid lime and 92% for local mandarin orange varieties. Additionally, our research compared different post-harvest storage methods for mandarin oranges, including room, cellar, and cold chamber. We assessed these methods based on shelf life, physiological weight loss, and the total soluble solids (TSS) to titratable acidity (TA) ratio. The cold chamber proved to be the most effective method, offering superior conditions for storing mandarin oranges. The IoT-based monitoring system played a crucial role in maintaining optimal temperature, humidity, and gas content within the cold chamber, resulting in reduced post-harvest losses and extended shelf life. These findings highlight the transformative potential of IoT technology in mandarin orange cultivation and post-harvest storage.

31 January 2025
Verified
Book Chapter
Closed access
GPGaliveeti Poornima
Galiveeti Poornima
SASukruth Gowda M. A.
Sukruth Gowda M. A.
Ritu Raj LamsalRitu Raj Lamsal
Ritu Raj Lamsal
The integration of computer vision and IoT is transforming healthcare by enabling precise diagnostics, real-time monitoring, and personalized care. This chapter explores the synergy of these technologies, highlighting their role in disease detection, smart medical devices, and remote patient management. It addresses challenges such as data privacy, interoperability, and ethical concerns, while showcasing real-world applications and future directions. By leveraging AI-driven innovations, the convergence of computer vision and IoT holds immense potential to revolutionize healthcare, driving efficiency, accessibility, and improved patient outcomes globally.

17 September 2025 in Research Square
Verified
Preprint
Open access
PDF file
Ritu Raj LamsalRitu Raj Lamsal
Ritu Raj Lamsal
SLSkand Lamsal
Skand Lamsal
The technical complexity associated with traditional machine learning (ML) tools often impedes early-stage learners and non-programmers from exploring artificial intelligence (AI). This paper presents a pedagogically intuitive approach using Google’s Teachable Machine a no-code platform that allows users to create ML models via a graphical interface. We conducted an educational experiment where novice learners built an image classifier to distinguish between animal classes. Our experiment involved the classification of four animal class Cat, Dog, Monkey, and Tiger using a minimal dataset of just 3–5 images per class to ensure simplicity for beginners. Using transfer learning with MobileNet architecture and basic training settings (50 epochs, 0.001 learning rate), the model achieved high classification accuracy 100% for visually distinct classes and up to 97% for more similar ones. The platform’s ability to export trained models to TensorFlow, TensorFlow Lite, expands its potential for real-world deployment. This study concludes that GUI-based ML tools can democratize AI education and discuss their integration with IoT applications, making it accessible, interactive, and impactful for beginners.

26 September 2025 in Research Square
Verified
Preprint
Open access
PDF file
Ritu Raj LamsalRitu Raj Lamsal
Ritu Raj Lamsal
MBMamta Bhattarai
Mamta Bhattarai
The relentless scaling of complementary metal-oxide-semiconductor (CMOS) technology, as dictated by Moore's Law, has driven the semiconductor industry through multiple transistor architecture revolutions. The planar bulk MOSFET, after decades of dominance, was succeeded by the three-dimensional FinFET at the 22/16 nm node to overcome severe short-channel effects (SCEs). However, as scaling continues to the 5 nm node and beyond, the limitations of the FinFET have become apparent. This literature review examines the journey from FinFETs to the next-generation architecture: the Gate-All-Around (GAA) Nanosheet Field-Effect Transistor (NSFET). It covers the motivations for this transition, the advantages and challenges of nanosheet technology, and the future roadmap towards forksheet and complementary FET (CFET) architectures. This paper presents a comparative analysis of power and delay characteristics between 5nm FinFET and 3nm Gate All Around (GAA) Nanosheet technologies using the educational EDA tool. A standard CMOS inverter is used as a test vehicle for this analysis. Simulation results demonstrate a significant improvement in the power-delay product (PDP) for the 3nm Nanosheet technology, improvement in propagation delay compared to the 5nm FinFET, primarily due to superior electrostatic control enabling lower supply voltage operation. The findings underscore the critical importance of the transition to GAA architectures for next-generation applications in Artificial Intelligence (AI), Machine Learning (ML), and the Internet of Things (IoT), where computational efficiency and ultra-low power consumption are paramount.