International Journal of Interpreting Enigma Engineers (IJIEE)

Automated Detection of Large Animals in Road Scene Environments Using Deep Learning

2025-06-19T10:18:57+00:00

Automated detection of large animals in road scenes plays a crucial role in enhancing the safety of autonomous vehicles, particularly in regions where wildlife-related accidents are common. This paper introduces a deep learning-based explanation for detecting and classifying ten large animal classes within road scene environments, such as dogs, horses, cows, and bears. A specialized dataset was fetched using selected classes from the COCO and Open Images V5 datasets, annotated in the COCO format. Four advanced object detection models were trained and evaluated with the EfficientDet-D1, RetinaNet R-50-FPN, Faster R-CNN R-50-FPN, and Cascade R-CNN R-50-FPN. Results show that RetinaNet R-50-FPN achieved the highest mean Average Precision (mAP) of 0.83 for one joint class and 0.69 for ten classes while also delivering the fastest inference speed at 50.6 FPS for one-class detection and 45.2 FPS for multi-class detection. EfficientDet-D1 achieved a mAP of 0.89 for one joint class and 0.77 for ten classes, offering competitive performance but with slightly slower inference speeds. The findings highlight RetinaNet as the most effective and efficient model for real-time large animal detection in road scenes, offering significant potential for integration into modern autonomous driving systems.

Enhanced Detection of Fraud in Unified Payments Interface (UPI) Transactions Using Gradient Boosting Method

2025-06-20T03:10:57+00:00

The widespread use of the Unified Payments Interface (UPI), which allows for smooth real-time transactions, has significantly changed digital payment systems.However, this growth has also led to a surge in fraudulent activities. This study presents an advanced fraud detection model based on the Gradient Boosting algorithm, renowned for its superior classification performance on imbalanced datasets. The model leverages advanced feature engineering to extract transactional, behavioral, and temporal features from real-world UPI transaction data. The model achieves a high predicted accuracy of 98.4% with a precision of 97.8%, recall of 96.9%, and F1-score of 97.3% through meticulous hyperparameter optimization. These results outperform several baseline classifiers. The proposed scalable framework significantly enhances the security and trustworthiness of UPI-based digital payment systems.

Plant Disease Detection Using Deep Learning

2025-06-20T06:17:27+00:00

Plants are becoming a significant energy source and the main cause of the global warming issue. In plant systems, the harm caused by endemic, re-emerging, and emerging diseases is significant and may result in financial loss. Furthermore, crop diseases both directly and indirectly contribute to environmental harm and the development of infectious diseases in humans. Since these illnesses are spreading throughout the world, they are harming not only the plant's ability to operate normally but also the plant's financial situation by drastically lowering the amount of crops that are grown. Many diseases cause crop output to lose its quality; occasionally, these diseases even manifest themselves imperceptibly. Farmers predict illnesses based on their personal experience, but this is incorrect. Agriculture now serves far more purposes than just feeding the world's expanding population. In India, where agriculture supports over 70% of the population, this is crucial. This indicates that it feeds a sizable population. Plant diseases can have a direct or indirect impact on human health as well as the economy. We require a quick, automatic method to identify these plant diseases. Various methods of digital image processing are used to analyze diseases. In order to identify plant diseases, we conducted a survey on several digital image processing methods in this research.

Pneumonia Detection Using Chest Radiographs With Novel EfficientNetV2L Model

2025-06-20T08:29:59+00:00

The diagnosis is one of the best solution for finding the health problems and Inaccurate diagnosis of pneumonia might lead to serious health problems. For diagnosis, traditional chest X-rays are used; however, manual interpretation is laborious and prone to human mistake. Therefore, we have created a powerful deep learning method that allows for automatic pneumonia identification using chest radiographs. BeginningCNN models that are now in use include ResNetV2, ResNet50, VGG16, EfficientNetV2L, Xception, and NasNetMobile. We first integrate Xception and NasNetMobile to facilitate classification. Next, we emphasize the sites of irregularities in chest pictures using object identification techniques from YOLOv5x6, YOLOv5s6, YOLOv8n, and YOLOv9n. The proposed framework achieves an accuracy of 91.75%, surpassing several industry standards such as COVID-Net (87.00%), DenseNet121 (84.00%), and CheXNet (76.80%). The diagnostic model's claimed precision of 92.30%, recall of 91.10%, F1-score of 91.70%, and AUC of 0.935 demonstrate its balance and high reliability. This combination categorization and detection technology not only improves diagnostic accuracy but also speeds up and improves the decision-making process for doctors.

A Deep Neural Framework for Emotion Detection in Hindi Textual Data

2025-06-20T09:48:29+00:00

Emotion identification from textual data is crucial for understanding human emotions in applications such as user behaviour analysis, targeted content delivery, and mental health monitoring. Even though English has advanced significantly, emotion detection in Hindi, a widely spoken language lacking enough resources, is still tricky because of data, grammatical complexity, and NLP tools. This study presents a deep neural network (DNN)-based framework for emotion classification in Hindi sentences. Our approach includes Hindi-specific preprocessing using the iNLTK library, comparative evaluation of multiple encoding techniques (Bag of Words, TF-IDF, Word2Vec), and training a robust DNN model to classify text into five emotion classes: joy, sadness, anger, suspense, and neutral. Experimental results on the BHAV dataset demonstrate that our DNN model achieves a balanced accuracy of 94.91%, outperforming traditional classifiers such as Naive Bayes, SVC, Logistic Regression, Decision Trees, and Boosted Trees. The confusion matrix and training-validation curves confirm the model's generalization capabilities and minimal overfitting. Our outcomes underscore the significance of deep learning in low-resource language settings and set the groundwork for future improvements in multimodal emotion detection, code-mixed data handling, and deployment in real-time Hindi NLP applications.