Search

Your search keyword '"Kotecha P."' showing total 19 results
Start Over Author "Kotecha P." Publication Year Range This year
19 results on '"Kotecha P."'

1. IndicMMLU-Pro: Benchmarking Indic Large Language Models on Multi-Task Language Understanding

Author

KJ, Sankalp, Kumar, Ashutosh, Balaji, Laxmaan, Kotecha, Nikunj, Jain, Vinija, Chadha, Aman, and Bhaduri, Sreyoshi

Subjects
Computer Science - Computation and Language, Computer Science - Artificial Intelligence
Abstract

Known by more than 1.5 billion people in the Indian subcontinent, Indic languages present unique challenges and opportunities for natural language processing (NLP) research due to their rich cultural heritage, linguistic diversity, and complex structures. IndicMMLU-Pro is a comprehensive benchmark designed to evaluate Large Language Models (LLMs) across Indic languages, building upon the MMLU Pro (Massive Multitask Language Understanding) framework. Covering major languages such as Hindi, Bengali, Gujarati, Marathi, Kannada, Punjabi, Tamil, Telugu, and Urdu, our benchmark addresses the unique challenges and opportunities presented by the linguistic diversity of the Indian subcontinent. This benchmark encompasses a wide range of tasks in language comprehension, reasoning, and generation, meticulously crafted to capture the intricacies of Indian languages. IndicMMLU-Pro provides a standardized evaluation framework to push the research boundaries in Indic language AI, facilitating the development of more accurate, efficient, and culturally sensitive models. This paper outlines the benchmarks' design principles, task taxonomy, and data collection methodology, and presents baseline results from state-of-the-art multilingual models.

Published
2025

2. Extraction Of Cumulative Blobs From Dynamic Gestures

Author

Naulakha, Rishabh, Gaur, Shubham, Lodha, Dhairya, Tulsyan, Mehek, and Kotecha, Utsav

Subjects
Computer Science - Computer Vision and Pattern Recognition, 68T45, 68U10, I.2.10, I.5.1, H.5.2
Abstract

Gesture recognition is a perceptual user interface, which is based on CV technology that allows the computer to interpret human motions as commands, allowing users to communicate with a computer without the use of hands, thus making the mouse and keyboard superfluous. Gesture recognition's main weakness is a light condition because gesture control is based on computer vision, which heavily relies on cameras. These cameras are used to interpret gestures in 2D and 3D, so the extracted information can vary depending on the source of light. The limitation of the system cannot work in a dark environment. A simple night vision camera can be used as our camera for motion capture as they also blast out infrared light which is not visible to humans but can be clearly seen with a camera that has no infrared filter this majorly overcomes the limitation of systems which cannot work in a dark environment. So, the video stream from the camera is fed into a Raspberry Pi which has a Python program running OpenCV module which is used for detecting, isolating and tracking the path of dynamic gesture, then we use an algorithm of machine learning to recognize the pattern drawn and accordingly control the GPIOs of the raspberry pi to perform some activities.

Published
2025

9. Procalcitonin-guided duration of antibiotic treatment in children hospitalised with confirmed or suspected bacterial infection in the UK (BATCH): a pragmatic, multicentre, open-label, two-arm, individually randomised, controlled trial

Author

Waldron, Cherry-Ann, Pallmann, Philip, Schoenbuchner, Simon, Harris, Debbie, Brookes-Howell, Lucy, Mateus, Céu, Bernatoniene, Jolanta, Cathie, Katrina, Faust, Saul N, Hinds, Lucy, Hood, Kerenza, Huang, Chao, Jones, Sarah, Kotecha, Sarah, Nabwera, Helen M, Patel, Sanjay, Paulus, Stéphane C, Powell, Colin V E, Preston, Jenny, Xiang, Huasheng, Thomas-Jones, Emma, Carrol, Enitan D, Carrol, Enitan D, Hawkins, Rachael, Thomas-Jones, Emma, Waldron, Cherry-Ann, Kotecha, Sarah, Maboshe, Waku, Harris, Debbie, Goddard, Mark, Pallmann, Philip, Schoenbuchner, Simon, Brookes-Howell, Lucy, Henley, Josie, Milosevic, Sarah, Prout, Hayley, Smallman, Kim, Channon, Sue, Clarkstone, Sam, Evans, Judith, Hood, Kerry, Powell, Colin VE, Mateus, Céu, Xiang, Huasheng, Faust, Saul N, Huang, Chao, Jones, Sarah, Nabwera, Helen, Dee, Sarah, Duncan, Lisa, Hawkins, Rachael, Johnston, Joanne, Lambert, Caroline, Mususka, Phoebe, Siner, Sarah, Whitbread, Jenny, Bernatoniene, Jolanta, Schadenberg, Alvin, Bingham, Tracey, Boal, Helen, Carter, Victoria, Clayton, Evangeline, Coy, Karen, Critchley, Mia, Dymond, Sandra, Goenka, Anu, Jordan, Zoe, Hamdollah-Zadeh, Maryam, Hopgood, David, Laskey, Anna, Marsh, Melanie, Roderick, Marion, Seymour, Elyna, Vergnano, Stefania, Cathie, Katrina, Faust, Saul N, Patel, Sanjay, Owens, Daniel, Beed, Leonora, Bingham, Victoria, Bowens, Donna, Burke, Susan, Cadnam, Sophie, Cook, Amber, Cornish, Emily, Cutler, Jessica, Ensom, Ruth, Etherington, Nichola, Griffiths, Aimee, Hardy, Anna, Johnston, Jane, Mayes, Rebecca, McCorkell, Jenni, Mcgailey, Lisa, McKay, Sarah, Mellish, Christie, Munro, Alastair, Oxford, Caitlin, Pond, Jenny, Postlewaite, Catherine, Price, Gabrielle, Roberts, Genevieve, Salter, Sally, Sparks, Laura, Taylor, Andrea, Thomas, Philippa, Van Der Harg, Emy, Vanner, Nina, Wilson, Charlotte, Paulus, Stéphane, Douglas, Claire, Harmer, Rebecca, Hopton, Sarah, Miller, Danielle, Oliver, Zoe, Stamford, Imogen, Taylor, Clare, Hinds, Lucy, Beachill, John, Clark, Carolyn, Gormley, Stuart, Harrison, Rachel, Redfern, Kim, Shackleton, Janet, Edwards, Martin, Muller, Jennifer, Yendle, Louise, Dallow, Helen, Holt, Susie, Saladi, Murthy, Burchett, Caroline, De Beger, Sarah, Nyirenda, Maggie, Capozzi, Lisa, Ekani, Melanie, Gardiner, Emma, McMaster, Paddy, Newport, Rachel, O'Connor, Grainne, Philbin, Jenny, Rishton, Chloe, Sarwar, Zainab, Scott, Chloe, Solanki, Anita, Kamath, Prakash, Newport, Rachel, O'Connor, Grainne, Padmakumar, Beena, Philbin, Jenny, Rishton, Chloe, Sarwar, Zainab, Scott, Chloe, Williamson, John-Paul, Birch, Simon, Czekaj, Marta, Gribbin, Andrew, Collinson, Andrew, Black, Chris, Barker-Kirby, Charlotte, Bowen, Ruth, Lindsey, Kim, McGraw Allen, Kate, Webber, Jo, Ludman, Sian, Chamberlain, Emma, Palfrey, Heather, Purchall, Megan, Wilkins, Suzanne, Wilson, Stacy, Okike, Ifeanyichukwu, Hayman, Melanie, Miketa, Laura, Robinson, Gisela, Smith, Coral, Unsworth, Vanessa, Tighe, Mark P, Langston, Oana, Power, Sue, Roff, Amy, and Rojas-Jimenz, Erika

Abstract

Procalcitonin is a rapid response biomarker specific for bacterial infection, which is not routinely used in the UK National Health Service. We aimed to assess whether using a procalcitonin-guided algorithm would safely reduce the duration of antibiotic therapy compared with usual care, in which C-reactive protein is the commonly used biomarker.

Published
2025
Full Text
View/download PDF

12. Efficacy, durability and safety of faricimab for patients with neovascular age-related macular degeneration: 48-week results from the phase 3 LUCERNE China subpopulation

Author

Zou, Wenjun, Jiang, Qin, Wang, Yanling, Wei, Wenbin, Sun, Xiaodong, Basu, Karen, Chen, Qiuyu, Kotecha, Aachal, Li, Sijing, Liu, Ruyuan, Patel, Vaibhavi, and Chen, Youxin

Abstract

To evaluate the efficacy, durability and safety of intravitreal faricimab versus aflibercept over 48 weeks in patients with neovascular age-related macular degeneration (nAMD) from the LUCERNE China subpopulation.

Published
2025
Full Text
View/download PDF

18. Deep Learning-Driven Analysis of a Six-Bar Mechanism for Personalized Gait Rehabilitation

Author

Khan, Naveed Ahmad, Hussain, Shahid, Spratford, Wayne, Goecke, Roland, Kotecha, Ketan, and Jamwal, Prashant K.

Abstract

Recent advances in robotics and artificial intelligence have highlighted the potential for the integration of computational intelligence in enhancing the functionality and adaptability of robotic systems, particularly in rehabilitation. Designing robotic exoskeletons for the lower limb rehabilitation of post-stroke patients requires frequent adjustments to accommodate individual differences in leg anatomy. This complex engineering challenge necessitates a deep understanding of human physiology, robotics, and optimization to develop adaptive robotic systems and also to swiftly quantify the required adjustments and implement them for each patient. The conventional approaches, which mostly rely on heuristics and manual tuning, often struggle to achieve optimal results. This paper presents a novel method that integrates a genetic algorithm with a deep learning approach to generate a gait trajectory of the ankle joint from a six-bar linkage mechanism of fixed dimensions. Later, using the same approach, the inverse kinematics solution for this mechanism is also devised whereby, the set of the link dimensions of the six-bar linkage mechanism is obtained for the given gait trajectory of an individual to achieve customization. We simulated the kinematic behavior of the six-bar linkage mechanism within defined mechanical constraints and utilized the generated data for training a feedforward neural network and long short-term memory models. The proposed model, when trained, can produce accurate lengths for the desired gait trajectories in the sagittal plane and vice versa, which further validates our proposed approach for inverse kinematics solution. Moreover, to evaluate the efficiency of deep learning models, we have conducted an extensive error-based, comparative, and sensitivity analysis using different performance indices. The results highlight the potential of the proposed deep-learning-driven approach in the design analysis of gait rehabilitation robots.

Published
2025
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results