Computer Science

Permanent URI for this collectionhttps://dspace.summituniversity.edu.ng/handle/123456789/164

Browse

Filter results by year or month
Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Development of a Restricted Access and Energy-Efficient IoT-Based Greenhouse System for Tropical Climates
    (Springer Nature Switzerland AG 2025, 2025-10-01) Erinosho C. Tolulope, Amusa A. Kamoli, Abayomi Abdultaofeek, and Lawal Azeez
    Agriculture as a cornerstone of global food production, faces sustainability and environmental impact issues. Conventional greenhouses while aiding crop production, often contribute to high energy consumption and substantial greenhouse gas (GHG) emissions. They are also vulnerable to the introduction of diseases due to uncontrolled access. Theoretical frameworks highlight the greenhouse effect and the impact of climate change on traditional agricultural methods, emphasizing the urgency of alternative sustainable practices. This paper introduces and implements a Radio Frequency Identification (RFID) and Internet of Things (IoT)-based energy-efficient greenhouse system for tropical climates applications. The system employs a solar energy source, an Arduino microcontroller, and various units for soil moisture, temperature monitoring, and RFID-based access control. The Arduino system enhances security by managing a list of approved RFID card (UIDs), granting access only to authorized users, and activating a buzzer for unauthorized access attempts. Performance tests of the prototype demonstrated superior results in temperature and soil resistance management compared to open-field farming, thus highlighting its potential for increased yield, resource efficiency, and enhanced farm security. This eco-friendly system is particularly suitable for deployment in energy-deprived tropical regions, offering improved farm yield and robust protection for greenhouse operations.
  • No Thumbnail Available
    Item
    Speech to speech translation with translatotron: A state of the art review
    (Elsevier B.V., 2025-10-20) Kala R. Jules, Adetiba Emmanuel, Abayomi Abdultaofeek, Oluwatobi E. Dare, Ifijeh H. Ayodele
    A speech-to-speech translation using cascade-based methods has been considered a benchmark for a very long time. Still, it is plagued by many issues, like the time to translate a speech from one language to another and compound errors. These issues are because cascade-based methods use a combination of other methods, such as speech recognition, speech-to-text transcription, text-to-text translation, and finally, text-to-speech transcription. Google proposed Translatotron, a sequence-to-sequence direct speech-to-speech translation model that was designed to address the issues of compound errors associated with cascade-based models. Today, there are 3 versions of the Translatotron model: Translatotron 1, Translatotron 2, and Translatotron 3. Translatotron 1 is a proof of concept to demonstrate direct speech-to-speech translation. This first approach was found to be less effective than the cascade model, but it was producing promising results. Translatotron 2 was an improved version of Translatotron 1 with results similar to the cascade-based model. Translatotron 3, the latest version of the model, significantly improves the translation and is better than the cascade model at some points. This paper presents a complete review of speech-to-speech translation using Translatotron models. We will also show that Translatotron is the best model to bridge the language gap between African Languages and other well-formalized languages.