International Journal of Innovations in Science & Technology
Not a member yet
813 research outputs found
Sort by
Deep Learning-Based Multiclass Classification of Diseases in Cucumber Fruit: Enhancing Agriculture Diagnosis
Get PDFAgriculture plays a key role in the economies of many developing nations. cucumber is cultivated vegetable that are grown in large quantities, but the production is regularly affected by diseases, with its yield loss impacted by diseases which include Belly Rot and Pythium Fruit Rot. Early and accurate disease diagnosis is critical for minimizing economic losses and improving crop quality. Traditional method techniques are based on visual identification and time-consuming and often inaccurate, especially for the early stages of the disease. In this work, we aim to tackle these problems and present an automatic cucumber disease classification system by transfer learning. Three convolutional neural network models (pre-trained VGG16, MobileNetV2 and ResNet-50) were retrained on a set of 2400 images containing two disease classes and one normal class. The images were preprocessed with the Contrast Limited Adaptive Histogram Equalization (CLAHE) and background removal by deep learning segmentation to eliminate the background noise and focus only on the informative feature of the image. The models were trained and tested by using training, validation, and test sets with the respective accuracies of 95.28%, 98.06%, and 57.5%. MobileNetV2 showed superior performance to all other models including the highest precision, recall, and F1 score of 0.98, confirming that it was robust and appropriate for real-time disease classification. The results demonstrate that the transfer learning method is conducive to improving the issues of lack of labeled samples and variations in image acquisition and strength, thus providing a reliable model for early disease detection in cucumbers. The system we propose can support farmers and agronomists in early disease management decisions and reduce chemical usage. In the future, we will increase the data set with more disease classes, and develop a mobile APP for field level disease detection
Analysis of Social Media Imagery for Crisis Management Applications
Get PDFSocial media data holds immense potential for real-time disaster response. This study explores leveraging deep learning to automatically detect disaster-related information across various social media platforms. By analyzing the performance of different models in identifying relevant content, we aim to reduce information gathering delays and support timely rescue efforts. Faster information gathering translates to quick deployment of rescue teams, potentially saving lives and minimizing property damage. We evaluate these models on a benchmark dataset and explore the potential of combining them for even greater accuracy. Among the models, VGG16 achieved an accuracy of 81% in identifying disaster-related content. Additionally, exploring different fusion techniques for combining these models further improved accuracy to 83% with Hybrid Fusion. This research offers valuable insights for future exploration of deep learning techniques in disaster management
Bioremediation of Textile Disperse Dyes using White-Rot Fungi Trametes versicolor
Get PDFDisperse dyes, frequently used in textile dyeing processes, present a particular challenge because of their recalcitrant nature. With an emphasis on wastewater effluent treatment, white-rot fungi Trametes versicolor were used. The fungus was cultured on different media and optimized various biochemical parameters (temperature, pH, inoculum size, dye concentration, and culturing time). After their biomass, disperse Red-I (DR1) and disperse Blue-I (DB1), and textile wastewater were biodegraded with the fungi T. versicolor. The growth of T. versicolor is time taking but maximum degradation by T. versicolor (0.02 to -0.11 during 3 days) is observed. In DB1 solutions and wastewater, absorbance values started at different points. However, the efficiency of fungi was found to be more than 80%. The potential of degradation of fungi in wastewater treatment can be further maximized to reduce environmental impact
Comparative Analysis of Different Feeding Techniques and Different Substrates on the Performance of 5G Micro-strip Patch Antenna
Get PDFWireless communication is evolving rapidly to meet growing demands for higher data rates and seamless connectivity, especially with the rise of the Internet of Things (IoT). Among the latest advancements, 5G technology stands out by enabling ultra-fast data transmission, high capacity, and efficient spectrum utilization through millimeter-wave frequencies. This study presents a comparative analysis of six Microstrip Patch Antennas (MPAs) designed for 5G applications, addressing the challenge of limited space and increasing performance demands. The novelty of this work lies in the evaluation of how substrate materials and feeding techniques influence MPA performance, providing insights not thoroughly addressed in prior research. The antennas were designed using three substrates1: FR-4 (εr = 4.4), 2-Rogers RT5880 (εr = 2.2), and 3- Taconic RF-35TC (εr = 3.5)—and two feeding techniques: Microstrip line feed and coaxial probe feed. All antennas were tuned to resonate at 38 GHz, suitable for 5G millimeter-wave applications. Feeding technique also significantly affects impedance matching and Gain. It is found out that using Roggers RT Duroid 5880 substrate with Microstrip feedline technique provides the highest gain whereas the largest bandwidth is achieved using coaxial feed with FR4 substrate. A quarter-wave transformer was additionally implemented for optimal impedance matching between the source and antenna. The findings guide substrate and feed selection in compact 5G antenna designs
Design of a Modified Wilkinson Power Divider for Ultra-Wideband Antipodal Vivaldi Antenna Arrays
Get PDFThis paper presents the design of a two-way Modified Wilkinson power divider (MWPD) feeding network for a two-element Antipodal Vivaldi Antenna (AVA) array, operating in the 3–10 GHz ultra-wideband (UWB) frequency range. The proposed feeding network is optimized by incorporating bent corners, which help reduce unintended radiation and improve signal distribution. Additionally, the antenna design is enhanced using a compact structure to improve radiation performance and impedance matching. The design, simulation, and optimization of both the feeding network and antenna array are conducted using CST Microwave Studio. Experimental validation confirms that the proposed array meets UWB specifications, making it a suitable candidate for wideband communication and imaging applications
Digital Dermatologist: An AI-Powered Mobile App for Early Detection of Skin Diseases
Get PDFAn increasing number of people are experiencing skin problems, causing overcrowding in hospitals and clinics. This situation highlights the need for a quicker and more convenient way to diagnose these conditions. To address this, we have developed a mobile application that uses artificial intelligence (AI) to detect skin diseases. The app provides fast and useful information about skin issues through AI. Its user-friendly design makes it easy for anyone to use, even without technical knowledge. This tool helps people monitor their skin health and reduces the burden on healthcare facilities. By using the app, users can identify skin problems early and receive guidance on possible treatments
AI-Enhanced Pneumonia Detection with Visual Interpretability
Get PDFPneumonia is a serious lung infection that can be life-threatening, particularly for young children, the elderly, and people with weakened immune systems. Early detection is crucial but difficult because pneumonia signs on X-rays can be subtle. Many AI tools can help diagnose pneumonia, but they often work like “black boxes,” making it hard for doctors to trust their decisions. This study introduces a mobile app that uses Convolutional Neural Networks (CNNs) to detect pneumonia from X-rays. To improve transparency, we use Explainable AI (XAI) to highlight the areas of the X-ray that influenced the diagnosis. Additionally, we integrate a Large Language Model (LLM) to generate clear, structured medical reports. Our goal is to create a trustworthy and user-friendly tool for doctors in real-world settings
A Comparative Analysis of SaaS and PaaS Cloud-Based E-Learning Platforms in Terms of Cost-Effectiveness and Scalability
Get PDFEducational institutions must evaluate Software as a Service against Platform as a Service for their e-learning cloud deployment because their cost models differ while trade-offs in scalability and customization needs exist. The research examines SaaS and PaaS cloud platforms to help educational institutions select better options through assessments of their value for money and flexibility and user satisfaction measures. A mixed quantitative and qualitative research design involved collecting data from twenty institutions which were equally distributed between SaaS and PaaS subscribers. These results were supplemented by interviews with IT administration personnel. The research used subscription fees and infrastructure costs as quantitative data alongside user capacity and response times under load. At the same time it collected qualitative information about usability alongside customization flexibility and security perceptions of the solutions.
Institutions working with restricted budgets should choose SaaS platforms because they provide cost-effective subscription payments at 4,380.72 annually) and specialized technical knowledge. User satisfaction surveys highlighted SaaS’s ease of adoption (75% satisfaction) versus PaaS’s customization advantages (40% extensive customization satisfaction), though both models achieved comparable security satisfaction (70–75%).
The study concludes that SaaS is optimal for institutions prioritizing affordability and simplicity, while PaaS suits those requiring long-term scalability and tailored solutions. Recommendations include hybrid cloud models to balance cost-efficiency and flexibility. These insights aim to empower educational stakeholders in aligning cloud adoption strategies with institutional goals and resource constraints.
Institutions working with restricted budgets should choose SaaS platforms because they provide cost-effective subscription payments at 4,380.72 annually) and specialized technical knowledge. User satisfaction surveys highlighted SaaS’s ease of adoption (75% satisfaction) versus PaaS’s customization advantages (40% extensive customization satisfaction), though both models achieved comparable security satisfaction (70–75%).
The study concludes that SaaS is optimal for institutions prioritizing affordability and simplicity, while PaaS suits those requiring long-term scalability and tailored solutions. Recommendations include hybrid cloud models to balance cost-efficiency and flexibility. These insights aim to empower educational stakeholders in aligning cloud adoption strategies with institutional goals and resource constraints
NeuroWise: AI-Based NLP Model for Early Alzheimer’s Detection Using Clinical Text
Get PDFAlzheimer\u27s disease (AD) is a background neurodegenerative illness that affects millions of people worldwide. Early diagnosis and management are important for successful intervention and better patient outcomes. This study introduces a method of AD diagnosis using NLP from clinical notes and medical records. Machine learning algorithms are used for symptom classification and prediction from text data, yielding high accuracy and scalability. The suggested technique provides an affordable solution for early diagnosis, allowing increased access to cognitive healthcare
A Comprehensive Study on Innovative AAC Solution for Enhancing Communication in Speech-Impaired Children
Get PDFAugmentative and Alternative Communication (AAC) systems serve as crucial communication tools for children who face speech and language difficulties. This paper outlines the design and development of an AAC mobile application specifically tailored to address the communication needs of children, allowing them to effectively express their thoughts and feelings. The app is created with the flexible Flutter framework and Visual Studio Code. Key features include symbol-based communication, text-to-speech, customizable symbols, and voice output, all suited to the specific requirements of speech-impaired youngsters. The user-friendly design emphasizes accessibility with vivid iconography for increased interaction. The software is evaluated in the paper using user satisfaction measures, real-world usage in educational contexts, and visual input from user interactions. A comparative analysis with existing AAC apps highlights the strengths of the proposed solution. The conclusion emphasizes the crucial role AAC apps play in aiding communication for children with hearing impairments. Future improvements include real-time capabilities, advanced feature extraction, and collaborative elements for user-caregiver communication, aiming to advance accessibility and efficacy in communication tools for this user group. This research contributes significantly to enhancing communication tools for children with speech impairments