SKShaeen Kalathil

Shaeen Kalathil

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Shaeen Kalathil has a total of 18 co-authors. Here are the top co-authors by number of shared publications:

  • Adnan Zaman

    Microelectronics and Semiconductor Institute, King Abdulaziz City for Science and Technology (KACST), Riyadh 11442, Saudi Arabia

    1 shared publication
  • Amal BaQais

    Department of Chemistry, College of Science, Princess Nourah Bint Abdulrahman University, P.O. Box 84428, Riyadh, 11671, Saudi Arabia

    1 shared publication
  • Areej Malibari

    Department of Industrial and Systems Engineering, College of Engineering, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh 11671, Saudi Arabia

    1 shared publication
  • Fadwa Alrowais

    Princess Nourah Bint Abdulrahman University

    1 shared publication
  • Orwel P V

    MCA Department, Federal Institute of Science and Technology, Angamaly, 683577, India

    1 shared publication
  • P M Ameer

    ECE Department, National Institute of Technology Calicut, Kattangal, 673601, India

    1 shared publication

Latest Publications

  • Open Access

    A Deep Learning Approach to Classification of Diseases in Date Palm Leaves

    by Sameera V Mohd Sagheer, Orwel P V, P M Ameer, Amal BaQais, Shaeen Kalathil

    The precise identification of date palm tree diseases is essential for maintaining agricultural productivity and promoting sustainable farming methods. Conventional approaches rely on visual examination by experts to detect i... | Find, read and cite all the research you need on Tech Science Press


  • Open Access

    Optimizing the Indium Tin Oxide Layer Characteristics toward a Low-Cost Dust-Cleaning Process for Solar Panels

    by Salman Alfihed, Reema Abdulaziz Altuwaijri, Sara Ahmed Alsalman, Adnan Zaman, Shaeen Kalathil

    The deposition of dust particles on solar panel modules constitutes a significant challenge, leading to a potential reduction in solar cell performance. This work tackles this issue by investigating the surface modification of a layer of transparent indium tin oxide (ITO), with a detailed analysis of the influence of its characteristics via different annealing conditions/processing. The ITO layer has been studied to enhance its characteristics for dust removal applications. Of particular note is that the developed ITO layer can be applied to dust removal using electrostatic or magnetic-based approaches. Thus, the correlation between annealing gas (using Argon, Oxygen, and Nitrogen), annealing temperature, and annealing ramping rate is explored with the obtained surface topography, as well as electrical and optical properties. The developed ITO layers annealed in the Argon medium at 600°C with an annealing ramping rate of 50°C/s showed smooth surface roughness, the highest electrical conductivity, and a relatively low refractive index. Such findings can play a crucial role in the future implementation of using the enhanced ITO layer for dust mitigation in solar panels, thus improving their long-term performance.

  • Advances in Wearable Sensors for Real-Time Internet of things based Biomechanical Analysis in High-Performance Sports

    by Shaeen Shaeen, Ranjan K. Pradhan, R. Manikandan, P. Sivaraman, Sarihaddu Kavitha, Shaeen Kalathil, Vilas Alagdeve

    Interest in wearable technology and the need for eco-friendly solutions have spurred new methodologies. This research examines how sophisticated deep learning and biomimetic designs benefit each other. The results may change smart technology forever. The introduction highlights the global appeal of wearable technology and the importance of environmental considerations in design. Deep learning and biomimicry are a fresh and exciting combination that might increase smart device accuracy, energy efficiency, and biomimicry. This project seamlessly integrates biomimetic design elements with deep learning methods. Biomimicry affects wearable technology design and functioning. However, deep learning techniques based on artificial neural networks boost user flexibility and predictive analytics. The controlled experiment allows a thorough examination of a number of datasets designed to cover a wide range of biomimetic settings and user behaviours. The data prove that the proposed technique beats alternatives across several performance parameters. Integrating biomimetic principles with deep learning systems boosts accuracy. This proves the system's reliability. The biomimetic method is eco-friendly since energy efficiency grows dramatically. Biological mimicry indications show that the suggested strategy resembles natural systems. A new exploratory method enhances sustainable technologies. Integrating biomimicry and deep learning efficiently enhances gadget performance and meets environmental standards. This research emphasizes the transformational power of nature-friendly technology, changing our worldview. Our study helps ensure that upcoming wearable technologies are cutting-edge and ecologically beneficial. Deep learning and biomimetic designs are converging, marking a tipping point in sustainable technology. This helps move toward an eco-friendly future.


  • Open Access

    Early Detection of Alzheimer’s Disease Using Polar Harmonic Transforms and Optimized Wavelet Neural Network

    by Shabana Urooj, Satya P. Singh, Areej Malibari, Fadwa Alrowais, Shaeen Kalathil

    Effective and accurate diagnosis of Alzheimer’s disease (AD), as well as early-stage detection, has gained more and more attention in recent years. For AD classification, we propose a new hybrid method for early detection of Alzheimer’s disease (AD) using Polar Harmonic Transforms (PHT) and Self-adaptive Differential Evolution Wavelet Neural Network (SaDE-WNN). The orthogonal moments are used for feature extraction from the grey matter tissues of structural Magnetic Resonance Imaging (MRI) data. Irrelevant features are removed by the feature selection process through evaluating the in-class and among-class variance. In recent years, WNNs have gained attention in classification tasks; however, they suffer from the problem of initial parameter tuning, parameter setting. We proposed a WNN with the self-adaptation technique for controlling the Differential Evolution (DE) parameters, i.e., the mutation scale factor (F) and the cross-over rate (CR). Experimental results on the Alzheimer’s disease Neuroimaging Initiative (ADNI) database indicate that the proposed method yields the best overall classification results between AD and mild cognitive impairment (MCI) (93.7% accuracy, 86.0% sensitivity, 98.0% specificity, and 0.97 area under the curve (AUC)), MCI and healthy control (HC) (92.9% accuracy, 95.2% sensitivity, 88.9% specificity, and 0.98 AUC), and AD and HC (94.4% accuracy, 88.7% sensitivity, 98.9% specificity and 0.99 AUC).