EBE. Afreen Banu

E. Afreen Banu

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

E. Afreen Banu has a total of 17 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Aeroponics Techniques for Improved Farming Using Artificial and Deep Learning techniques

    by C. Amuthadevi, E. Afreen Banu, S. Sampath Kumar, S. Karthick, A. Kistan, M. Sudhakar

    This chapter will delve into the integration of aeroponics into artificial intelligence and deep learning techniques for agricultural productivity and its sustainability. This is a no-soil farming method where plants grow in a nutrient-rich mist. Therein lies a couple of major advantages: water efficiency and an accelerated pace of plant growth. The reasoning behind the inclusion of AI and deep learning techniques lies in the computer vision and predictive analytics ability—how best it can help determine if this has the potential to optimally run aeroponic systems. Monitoring the health of a plant and the environmental state in real time, using AI-driven sensors and deep learning for analytics, is capable of identifying data patterns in predicting growth and optimizing practices for the delivery of nutrients. Some specific successful cases and novel innovations are exemplified next, showing how new breakthroughs can solve the existing challenges of agriculture, improve yield quality, and ultimately reduce resource consumption.


  • AI and Machine Learning in Earthquake Prediction

    by U. V. Anbazhagu, R. Sonia, Rakesh Kumar Grover, E. Afreen Banu, C. Jothikumar, M. Sudhakar

    This chapter explores how AI and ML can be applied towards earthquake prediction to potentially impact the enhancement in precision and timeliness of the forecast of seismic events. The traditional methods have been taking advantage of geological data, whereas a data-driven approach from AI/ML leverages massive data streams, historical, and real-time seismic data. Some of the main ML algorithms used in pattern identification for seismic activities include neural networks, deep learning, and SVM. The chapter delves into how these technologies come together with the data on geospatially, sensor networks, and real-time monitoring to produce better predictions of earthquakes. Data quality, algorithmic transparency, and the complexity of seismic phenomena are also considered issues. This new area of research will well be worth developing to enhance the quality of early warning systems and decrease the destructive losses in lives and infrastructures caused by earthquakes.


  • Advances in Computational Visual Information Processing for Neuroscience and Healthcare Applications

    by E. Afreen Banu, Chalumuru Suresh, V. Nyemeesha, Mannepalli Venkata Krishna Rao, B. Muthuraj, S. Muthuvel

    Advances in visual information processing have revolutionized computational neuroscience and healthcare by enhancing our understanding of neural mechanisms and developing new medical solutions. Techniques like deep learning algorithms, convolutional neural networks, and computer vision applications have provided unprecedented insights into brain activity and visual organ function. These technologies also enhance our ability to model and simulate cognitive processes, making them crucial in understanding and improving medical outcomes. Visual information processing enhances healthcare diagnostics, medical imaging, and treatment personalization, ranging from radiology to pathology. It integrates advanced technology with neural interfaces and AI, revolutionizing patient care and neurological research. Further, ethical considerations, data privacy, and the challenge of transforming complex visual data into actionable insights for healthcare professionals and neuroscientists are discussed in this chapter.