Modernizing workflows is imperative to address labor-intensive tasks that hinder productivity and efficiency. Convolutional Neural Networks (CNNs), a prominent technique in Artificial Intelligence, offer transformative potential for automating complex processes and streamlining operations. This study explores the application of CNNs in building accurate classification models for diverse datasets, demonstrating their ability to significantly enhance decision-making processes and operational efficiency. By leveraging a dataset of images, an optimized CNN model has been developed, showcasing high accuracy and reliability in (...) classification tasks. The findings underscore the ability of AI-powered approaches to reduce manual efforts, improve productivity, and support sustainable modernization across various domains. This study is relevant to professionals seeking to embed AI solutions into conventional workflows, offering a pathway to enhanced innovation and efficiency. (shrink)

Computed tomography (CT) films are used to construct cross-sectional pictures of a particular region of the body by using many x-ray readings that were obtained at various angles. There is a general agreement in the medical community at this time that chest CT is the most accurate approach for identifying COVID-19 disease. It was demonstrated that chest CT had a higher sensitivity than reverse transcription polymerase chain reaction (RT-PCR) for the detection of COVID-19 illness. This article presents gray-level co-occurrence matrix (...) (GLCM) texture feature extraction and convolutional neural network (CNN)-enabled optimized diagnostic model for COVID-19 detection. In this diagnostic model, CT scan images of patients are given as input. Firstly, GLCM algorithm is used to extract texture features from the CT scan images. This feature extraction helps in achieving higher classification accuracy. Classification is performed using CNN. It achieves higher accuracy than the k-nearest neighbors (KNN) algorithm and multi-layer preceptor (MLP). The accuracy of GLCM based CNN is 99%, F1 score is 99% and the recall rate is also 98%. CNN has achieved better results than MLP and KNN algorithms for COVID-19 detection. (shrink)

The core objective of this project is to recognize and reconstruct distorted facial images, particularly in the context of accidents. This involves using deep learning techniques to analyze the features of a distorted face and regenerate it into a recognizable form. Deep learning models are wellsuited for this task due to their ability to learn complex patterns and representations from data the input data consists of distorted facial images, typically obtained from MRI scans of accident victims. These images may contain (...) various types of distortions such as swelling, bruising, or other injuries that affect facial appearance. (shrink)

Abstract: Pistachio nuts are a valuable source of nutrition and are widely cultivated for commercial purposes. The accurate classification of different pistachio varieties is important for quality control and market analysis. In this study, we propose a new model for the classification of different pistachio varieties using Convolutional Neural Networks (CNNs). We collected a dataset of pistachio images form Kaggle depository with two varieties (Kirmizi and Siirt). The images were then preprocessed and used to train a CNN (...) model based on VGG16. We evaluated the performance of the VGG16 on a held-out test set. Our results show that the CNN-based model VGG16 performed very well in terms of accuracy and efficiency. The VGG16 model was able to accurately classify different pistachio varieties with an accuracy of over 99.91%. Additionally, the VGG16 was able to generalize well to new and unseen data, demonstrating its ability to handle variability in the pistachio images. This study highlights the potential of CNNs for the classification of different pistachio varieties, and has important implications for the pistachio industry. The results suggest that this approach can be used to improve the quality control process and enhance market analysis. (shrink)

The global catastrophe known as COVID-19 has shattered the world’s socioeconomic structure. Effective and affordable diagnosis techniques are crucial for better COVID-19 therapy and the eradication of bogus cases. Due to the daily upsurge in cases, hospitals only have a small supply of COVID-19 test kits. The study describes a deep Convolutional Neural Network (CNN) design for categorizing chest x-ray images in the diagnosis of COVID-19. The lack of a substantial, high-quality chest x-ray picture collection made efficient and (...) exact CNN categorization problematic. The dataset has been pre-processed using an image enhancement strategy to provide an effective training dataset for the proposed CNN model to achieve performance. The proposed model achieves 99.73% of accuracy, 98.95% of specificity, 99.47% of precision, 99.62% of sensitivity, and 98.71% of F1 score. A comparative study between the proposed model and numerous CNN-based COVID-19 detection algorithms is carried out to demonstrate that it outperforms other models. When evaluated on a separate dataset, the suggested model excelled over all other models, generally and explicitly. (shrink)

A face reveals a lot of information about a person's identity, age, sex, race, and emotional as well as psychological state. Facial expressions are often used in the behavioral interpretation of emotions and play a key role in social interactions. Due to its potential applications such as HCI, behavioral science, automatic facial emotion detection is one of the most intriguing and challenging areas in computer vision. Our Facial Emotion Recognition system performs detection and location of faces in a cluttered scene, (...) facial feature extraction, and facial expression classification. Numerous models were experimented such as decision trees and SVM’s before arriving at a Convolutional Neural Networks (CNN) model. Due to large number of filters, CNNs are efficient for image recognition tasks since they can capture spatial features of the inputs. After observing unbelievable performance with deep learning models, we used deep convolution features to better represent the given image instead of using the traditional handcrafted features. We have proposed and developed a Deep Convolutional Neural Network for classifying human emotions from dynamic facial expressions in real-time. Kaggle’s FER-2013 dataset with seven facial emotions labels as happy, sad, surprise, fear, anger, disgust, and neutral is used to train the model. An overall training accuracy of 92.86% and test accuracy of 64.42% are achieved. Finally, a live video stream connected to a face detector feeds images to the neural network. The network subsequently classifies an arbitrary number of faces per image in real-time simutaneously, wherein appropriate emotions are displayed over the subject’s faces and their probabilities are displayed over a real-time bar graph on a separate window. (shrink)

The accuracy levels of VGG19 and 3D CNN are compared using the performance metrics. This comparison helps in identifying which model performs better in the task of facial reconstruction from distorted images. Visualizing the results in the form of a graph provides a clear and concise way to understand the comparative performance of the algorithms. The ultimate goal of this project is to develop a system that can accurately reconstruct distorted faces, which can be invaluable in identifying accident victims or (...) assisting in medical treatments. By providing a reliable method for facial reconstruction, this technology can potentially save lives and improve outcomes for individuals involved in accidents. (shrink)

House price prediction is a critical task in real estate analytics, influenced by various factors such as location, economic conditions, and property features. Traditional machine learning models rely heavily on structured data, while recent advancements in deep learning enable the integration of unstructured data such as images. This paper presents a novel hybrid approach that combines structured numerical data with image-based features using Regionbased Convolutional Neural Networks (R-CNN). The proposed model improves predictive accuracy by leveraging both property (...) characteristics and visual information. Experimental results demonstrate that the hybrid approach outperforms conventional methods in terms of mean absolute error and root mean squared error. (shrink)

Brain-related diseases are among the most difficult diseases due to their sensitivity, the difficulty of performing operations, and their high costs. In contrast, the operation is not necessary to succeed, as the results of the operation may be unsuccessful. One of the most common diseases that affect the brain is Alzheimer’s disease, which affects adults, a disease that leads to memory loss and forgetting information in varying degrees. According to the condition of each patient. For these reasons, it is important (...) to classify memory loss and to know the patient at what level and his assessment of Alzheimer's disease through CT scans of the brain. In this thesis, we review ways and techniques to use deep learning classification to classifying the Alzheimer's Disease The proposed method used to improve patient care, reduce costs, and allow fast and reliable analysis in large studies. The model will be designed using Python language for implementing the system, which is very useful for doctors, classifying the Alzheimer's Disease, was used. The model used 70% from image for training and 30% from image for validation, our trained model achieved an accuracy of 100% on a held-out test set. (shrink)

The system utilizes a convolutional neural network (CNN), renowned for its proficiency in image classification tasks. A dataset comprising diverse bird species images is preprocessed and augmented to enhance model robustness and generalization. The model architecture is designed to extract intricate features, enabling accurate identification even in challenging scenarios such as varying lighting conditions, occlusions, or similar species appearances. The model's performance is evaluated using metrics such as accuracy, precision, recall, and F1-score, ensuring comprehensive validation. Results indicate significant (...) accuracy improvements over traditional machine learning approaches, demonstrating the potential of deep learning in species identification. This project holds promise for applications in wildlife monitoring, ecological research, and educational tools, promoting awareness and conservation efforts. Future work may include integrating the system into mobile applications or deploying it for real-time bird species identification in field conditions. (shrink)

This project, Bird Species Identification Using Deep Learning, proposes an advanced system leveraging the power of deep learning to accurately identify bird species from images. The system utilizes a convolutional neural network (CNN), renowned for its proficiency in image classification tasks. A dataset comprising diverse bird species images is preprocessed and augmented to enhance model robustness and generalization. The model architecture is designed to extract intricate features, enabling accurate identification even in challenging scenarios such as varying lighting conditions, (...) occlusions, or similar species appearances. The model's performance is evaluated using metrics such as accuracy, precision, recall, and F1-score, ensuring comprehensive validation. R. (shrink)

. The accuracy levels of VGG19 and 3D CNN are compared using the performance metrics. This comparison helps in identifying which model performs better in the task of facial reconstruction from distorted images. Visualizing the results in the form of a graph provides a clear and concise way to understand the comparative performance of the algorithms. The ultimate goal of this project is to develop a system that can accurately reconstruct distorted faces, which can be invaluable in identifying accident victims (...) or assisting in medical treatments. By providing a reliable method for facial reconstruction, this technology can potentially save lives and improve outcomes for individuals involved in accidents. (shrink)

The health of plants plays a crucial role in ensuring agricultural productivity and food security. Early detection of plant diseases can significantly reduce crop losses, leading to improved yields. This paper presents a novel approach for plant disease recognition using deep learning techniques. The proposed system automates the process of disease detection by analyzing leaf images, which are widely recognized as reliable indicators of plant health. By leveraging convolutional neural networks (CNNs), the model identifies various plant diseases (...) with high accuracy. The experimental setup includes a dataset consisting of healthy and diseased leaf images of different plant species. The dataset is preprocessed to remove noise and augmented to address the issue of class imbalance. The CNN model is then trained, validated, and tested on this dataset. (shrink)

The COVID-19 outbreak has had a significant influence on the health of people all across the world, and preventing its further spread requires an early and correct diagnosis. Imaging using X-rays is often used to identify respiratory disorders like COVID-19, and approaches based on machine learning may be used to automate the diagnostic process. In this research, we present a deep learning approach for COVID-19 identification in X-ray pictures utilizing global thresholding. Our framework consists of two main components: (1) global (...) thresholding to preprocess X-ray images and extract features, and (2) a Convolutional Neural Network (CNN) for classifying the images as positive (indicating COVID-19) or negative (indicating no COVID-19). Global thresholding is used to convert X-ray images into binary images, which can highlight the features of interest, such as lung opacity. The Network is instructed to use a dataset consisting of X-ray pictures that have been labeled with the COVID-19 status of each image. The usefulness of our approach was shown by experimental findings obtained using a dataset of X-ray pictures that were made accessible to the public. We achieve high accuracy in COVID-19 detection, outperforming traditional machine learning techniques. Our framework is also able to correctly identify COVID-19 in images that were misclassified by human experts. (shrink)

rd species identification plays a vital role in biodiversity conservation and ecological studies, offering insights into habitat health and species distribution. Traditional methods for identifying bird species are time-intensive and prone to human error, necessitating automated solutions. This project, Bird Species Identification Using Deep Learning, proposes an advanced system leveraging the power of deep learning to accurately identify bird species from images. The system utilizes a convolutional neural network (CNN), renowned for its proficiency in image classification tasks. A (...) dataset comprising diverse bird species images is preprocessed and augmented to enhance model robustness and generalization. (shrink)

The system utilizes a convolutional neural network (CNN), renowned for its proficiency in image classification tasks. A dataset comprising diverse bird species images is preprocessed and augmented to enhance model robustness and generalization. The model architecture is designed to extract intricate features, enabling accurate identification even in challenging scenarios such as varying lighting conditions, occlusions, or similar species appearances. The model's performance is evaluated using metrics such as accuracy, precision, recall, and F1-score, ensuring comprehensive validation. Results indicate significant (...) accuracy improvements over traditional machine learning approaches, demonstrating the potential of deep learning in species identification. (shrink)

Bird species identification plays a vital role in biodiversity conservation and ecological studies, offering insights into habitat health and species distribution. Traditional methods for identifying bird species are time-intensive and prone to human error, necessitating automated solutions. This project, Bird Species Identification Using Deep Learning, proposes an advanced system leveraging the power of deep learning to accurately identify bird species from images. The system utilizes a convolutional neural network (CNN), renowned for its proficiency in image classification tasks.

Maritime transport plays a pivotal role in global trade, yet it faces challenges due to corrosion, which deteriorates metallic surfaces of vessels, leading to potential safety hazards and financial burdens. Traditional corrosion detection methods such as visual inspections are inefficient, time-consuming, and often subjective. This paper proposes a deep learning-based solution utilizing Convolutional Neural Networks (CNNs) to detect and assess corrosion on marine vessel surfaces. Our proposed solution not only automates the detection process but also enhances accuracy, (...) ensuring early identification and effective management of corrosion. Through rigorous experimentation, the model demonstrated high accuracy, significantly improving the corrosion detection process for the maritime industry. (shrink)

We investigate the application of Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM) networks, and a hybrid CNN-LSTM model for forecasting air pollution levels based on historical data. Our experimental setup uses real-world air quality datasets from multiple regions, containing measurements of pollutants like PM2.5, PM10, CO, NO2, and SO2, alongside meteorological data such as temperature, humidity, and wind speed. The models are trained, validated, and tested using a split dataset, and their accuracy is evaluated using (...) performance metrics like Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and R-squared. (shrink)

With the proliferation of sophisticated cyber threats, traditional malware detection techniques are becoming inadequate to ensure robust cybersecurity. This study explores the integration of deep learning (DL) techniques into malware detection systems to enhance their accuracy, scalability, and adaptability. By leveraging convolutional neural networks (CNNs), recurrent neural networks (RNNs), and transformers, this research presents an intelligent malware detection framework capable of identifying both known and zero-day threats. The methodology involves feature extraction from static, dynamic, and (...) hybrid malware datasets, followed by training DL models to classify malicious and benign software with high precision. A robust experimental setup evaluates the framework using benchmark malware datasets, yielding a 96% detection accuracy and demonstrating resilience against adversarial attacks. Real-time analysis capabilities further improve response times, reducing the risk of potential damage. The study also incorporates visualization tools to provide interpretable insights into model decisions, enhancing transparency for cybersecurity practitioners. Concluding with a discussion on the challenges and future prospects, this research paves the way for scalable, AI-driven solutions to combat evolving cyber threats. (shrink)

By leveraging convolutional neural networks (CNNs), the model identifies various plant diseases with high accuracy. The experimental setup includes a dataset consisting of healthy and diseased leaf images of different plant species. The dataset is preprocessed to remove noise and augmented to address the issue of class imbalance. The CNN model is then trained, validated, and tested on this dataset. The results indicate that the deep learning model achieves a classification accuracy of over 95% for most plant (...) diseases. Additionally, the system is designed to provide real-time feedback to farmers, helping them take immediate corrective action. This automated approach eliminates the need for expert human intervention and can be deployed on mobile devices for ease of use in rural areas. The potential future applications of this system include integration with precision agriculture techniques and expansion to a wider range of crops. (shrink)

The representations of deep convolutional neural networks (CNNs) are formed from generalizing similarities and abstracting from differences in the manner of the empiricist theory of abstraction (Buckner, Synthese 195:5339–5372, 2018). The empiricist theory of abstraction is well understood to entail infinite regress and circularity in content constitution (Husserl, Logical Investigations. Routledge, 2001). This paper argues these entailments hold a fortiori for deep CNNs. Two theses result: deep CNNs require supplementation by Quine’s “apparatus of identity and quantification” in (...) order to (1) achieve concepts, and (2) represent objects, as opposed to “half-entities” corresponding to similarity amalgams (Quine, Quintessence, Cambridge, 2004, p. 107). Similarity amalgams are also called “approximate meaning[s]” (Marcus & Davis, Rebooting AI, Pantheon, 2019, p. 132). Although Husserl inferred the “complete abandonment of the empiricist theory of abstraction” (a fortiori deep CNNs) due to the infinite regress and circularity arguments examined in this paper, I argue that the statistical learning of deep CNNs may be incorporated into a Fodorian hybrid account that supports Quine’s “sortal predicates, negation, plurals, identity, pronouns, and quantifiers” which are representationally necessary to overcome the regress/circularity in content constitution and achieve objective (as opposed to similarity-subjective) representation (Burge, Origins of Objectivity. Oxford, 2010, p. 238). I base myself initially on Yoshimi’s (New Frontiers in Psychology, 2011) attempt to explain Husserlian phenomenology with neural networks but depart from him due to the arguments and consequently propose a two-system view which converges with Weiskopf’s proposal (“Observational Concepts.” The Conceptual Mind. MIT, 2015. 223–248). (shrink)

E-commerce platforms are flooded with a large variety of products, particularly clothing, making it challenging for users to find relevant items. In this paper, we present a methodology for building an efficient Clothing Classifier using deep learning techniques with the Keras library. We leverage Convolutional Neural Networks (CNNs), which are well-suited for image classification tasks, to categorize clothing items into predefined categories (e.g., shirts, pants, dresses, shoes). This paper demonstrates the process from data collection, pre-processing, model design, (...) and evaluation to create an image classifier capable of identifying clothing types in an e-commerce setting. (shrink)

Facial recognition is a computer vision task that involves identifying or verifying individuals based on their facial features. It has widespread applications in security, authentication, and human-computer interaction. Supervised learning techniques have become the foundation for facial recognition systems, as they enable the model to learn from labeled data to recognize patterns and make predictions. This paper explores the use of supervised learning algorithms, such as Support Vector Machines (SVM), Convolutional Neural Networks (CNN), and k-Nearest Neighbors (k-NN), (...) for facial recognition tasks. We will demonstrate how these algorithms can be used to accurately identify individuals by learning from training datasets with labeled facial images. (shrink)

Bird species identification plays a vital role in biodiversity conservation and ecological studies, offering insights into habitat health and species distribution. Traditional methods for identifying bird species are time-intensive and prone to human error, necessitating automated solutions. This project, Bird Species Identification Using Deep Learning, proposes an advanced system leveraging the power of deep learning to accurately identify bird species from images. The system utilizes a convolutional neural network (CNN), renowned for its proficiency in image classification tasks. A (...) dataset comprising diverse bird species images is preprocessed and augmented to enhance model robustness and generalization. The model architecture is designed to extract intricate features, enabling accurate identification even in challenging scenarios such as varying lighting conditions, occlusions, or similar species appearances. The model's performance is evaluated using metrics such as accuracy, precision, recall, and F1-score, ensuring comprehensive validation. Results indicate significant accuracy improvements over traditional machine learning approaches, demonstrating the potential of deep learning in species identification. This project holds promise for applications in wildlife monitoring, ecological research, and educational tools, promoting awareness and conservation efforts. Future work may include integrating the system into mobile applications or deploying it for real-time bird species identification in field conditions. (shrink)

Abstract: Context: grapevine leaves are an important agricultural product that is used in many Middle Eastern dishes. The species from which the grapevine leaf originates can differ in terms of both taste and price. Method: In this study, we build a deep learning model to tackle the problem of grape leaf classification. 500 images were used (100 for each species) that were then increased to 10,000 using data augmentation methods. Convolutional Neural Network (CNN) algorithms were applied to build (...) this model specifically using the pre-trained model on top of the VGG16 architecture. Then, dense layers were added to classify the output of the Convolutional layers and classify outputs to the five classes (species) the leaf belonged to. Results: It was found that feature extraction without fine-tuning the convolutional layers yielded poor results, about 86% accuracy, while training the whole network along with some data preprocessing gave the best results, about 99.45% accuracy on the testing dataset. Conclusions: The proposed CNN model is an effective one for the problem of classification of grape leaf species. (shrink)

This project aims to develop an intelligent system that can accurately identify and classify medicinal herbs using advanced machine learning techniques and image processing. Medicinal herbs have been a cornerstone of traditional medicine for centuries, and the ability to identify them with precision can play a significant role in modern healthcare, research, and conservation efforts. This system utilizes deep learning models to analyze images of plants and herbs, enabling the identification of species based on their physical features such as shape, (...) size, color, and texture of leaves, flowers, and stems. The system incorporates Convolutional Neural Networks (CNNs), a powerful technique in image recognition, to achieve high accuracy in classifying different medicinal plants. The dataset used for training includes a wide variety of herbs known for their medicinal properties, ensuring the system's versatility and reliability. The user-friendly interface allows users to upload images of plants, after which the system processes the image, compares it with the trained dataset, and provides a possible match along with information about the herb's medicinal uses, benefits, and any potential side effects. This project can serve as an essential tool for herbalists, researchers, and the general public to access accurate information about medicinal plants. (shrink)

Image captioning has seen remarkable advancements with the integration of deep learning techniques, notably Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks, for generating descriptive captions for images. Despite these improvements, capturing intricate details and context remains a challenge. This project introduces an enhanced image captioning model that integrates transformers with an attention mechanism to address these limitations. By leveraging CNNs for feature extraction and LSTMs for sequence generation, while utilizing transformers to apply sophisticated (...) attention to significant image regions, the proposed model aims to generate more contextually rich and coherent captions. Experimental results indicate that incorporating transformers with attention mechanisms leads to a significant enhancement in caption accuracy and descriptiveness, surpassing traditional CNN-LSTM models. This advancement is particularly beneficial in various applications, including assistive technologies for the visually impaired, content-based image retrieval systems, automatic image annotation for digital asset management, and improved human-computer interaction. This approach represents a substantial step forward in achieving more precise and detailed image captioning, with potential impacts across numerous fields. (shrink)

The ongoing COVID-19 pandemic has caused a global health crisis, and accurate diagnosis and early detection are essential for successful management of the outbreak. Convolutional neural networks and pre-processed chest X-ray pictures are the two main components of the unique proposed method for the identification of COVID-19, which is presented in this paper (CNNs). Image enhancement and segmentation are performed during the pre-processing stage. These operations increase the overall quality and contrast of the pictures, which in turn (...) makes it simpler for the CNN to recognise significant aspects of the images. The CNN model was trained using a large dataset of pre- processed X-ray pictures that included both COVID-19 positive and negative instances. The dataset was used to train the model. In comparison to more conventional diagnostic approaches, and this strategy was successful in achieving high levels of accuracy, sensitivity, and specificity in the detection of COVID-19. Moreover, this model designed an automated reporting system that saves time and costs by providing healthcare providers with diagnostic reports that are both prompt and accurate. This research demonstrates the viability of using CNNs and pre-processed X-ray images for the purpose of early identification of COVID-19 and offers an important resource for the efficient management of this worldwide health concern. (shrink)

One key aspect in the design of autonomous vehicles is the implementation of real-time object detection which includes identifying and classifying obstacles present in the environment of the vehicle . The system will also be able to capture live or recorded videos and accurately identify and classify the objects within the video streams in very active situations requiring low turnaround times so that the vehicle is able to make the necessary safe driving critical choices . more recent state of the (...) art deep learning frameworks that tackle the object detection problem are Region Based Convolutional Nural network R-CNN and its variants fast R-cnn and faster R-cnn more approximately Fixes models’ Execution Speed. Another object detection system presented in the year 2015 is known as the YOLO system which is focused on fast predictive capabilities and for use in motion pictures. BDD100K dataset for video based deep driving understanding in 100k videos and 10 tasks which are designed to assess how far the algorithm gets in its objective of Image Recognition in driverless cars. The dataset has geographical, environment and weather variability, which is beneficial for training models that have a high likelihood of encountering drastic changes. (shrink)

Abstract: Alzheimer's disease (AD) is one of the most common types of dementia. Symptoms appear gradually and end with severe brain damage. People with Alzheimer's disease lose the abilities of knowledge, memory, language and learning. Recently, the classification and diagnosis of diseases using deep learning has emerged as an active topic covering a wide range of applications. This paper proposes examining abnormalities in brain structures and detecting cases of Alzheimer's disease especially in the early stages, using features derived from medical (...) images. The entire brain image was passed on through the transmission of Xception learning architectures. The Convolutional Neural Network (CNN) was constructed with the help of separable convolution layers that It can automatically learn general features from imaging data for classification. (shrink)

Traffic sign detection and recognition (TSDR) is a critical aspect of autonomous driving and intelligent transportation systems. Traditional methods of traffic sign detection rely on handcrafted features and classical machine learning algorithms, which often struggle to achieve high accuracy in complex real-world environments. In contrast, deep learning techniques, particularly Convolutional Neural Networks (CNNs), have shown remarkable performance in both detecting and recognizing traffic signs in diverse conditions. This paper reviews the application of deep learning methods for TSDR, (...) focusing on recent advancements in the use of CNNs, Region-based CNNs (R-CNNs), and YOLO (You Only Look Once) for real-time detection and recognition of traffic signs. We discuss the challenges, including the variability of traffic signs, environmental factors, and computational requirements, and present solutions proposed in the literature. The paper also highlights future directions for improving the robustness, accuracy, and speed of traffic sign detection and recognition systems, with an emphasis on real-time applications. (shrink)

Cloud computing has revolutionized the storage and management of data by offering scalable, cost-effective, and flexible solutions. However, it also introduces significant security concerns, particularly related to data leakage, where sensitive information is exposed to unauthorized entities. Data leakage can result in substantial financial losses, reputational damage, and legal complications. This paper proposes a deep learning-based framework for detecting data leakage in cloud environments. By leveraging advanced neural network architectures, such as Long Short-Term Memory (LSTM) and Convolutional (...) class='Hi'>Neural Networks (CNNs), the model detects abnormal data access patterns that may indicate leakage. The system operates in real-time, continuously monitoring data interactions between users and the cloud. A large dataset containing normal and abnormal access logs is used to train and validate the model, ensuring it can effectively differentiate between legitimate and malicious activity. The performance of the model is evaluated using metrics such as accuracy, precision, recall, and F1-score, with the system achieving over 96% accuracy in identifying potential data leaks. Furthermore, the proposed solution is designed to be scalable and adaptable, making it suitable for dynamic cloud environments with evolving threats. Future enhancements to the system include integrating multi-cloud support and refining the model’s ability to detect sophisticated insider threats. This research highlights the importance of leveraging deep learning for real-time, proactive cloud security. (shrink)

he health of plants plays a crucial role in ensuring agricultural productivity and food security. Early detection of plant diseases can significantly reduce crop losses, leading to improved yields. This paper presents a novel approach for plant disease recognition using deep learning techniques. The proposed system automates the process of disease detection by analyzing leaf images, which are widely recognized as reliable indicators of plant health. By leveraging convolutional neural networks (CNNs), the model identifies various plant diseases (...) with high accuracy. The experimental setup includes a dataset consisting of healthy and diseased leaf images of different plant species. The dataset is preprocessed to remove noise and augmented to address the issue of class imbalance. The CNN model is then trained, validated, and tested on this dataset. (shrink)

Cloud computing has revolutionized the storage and management of data by offering scalable, cost-effective, and flexible solutions. However, it also introduces significant security concerns, particularly related to data leakage, where sensitive information is exposed to unauthorized entities. Data leakage can result in substantial financial losses, reputational damage, and legal complications. This paper proposes a deep learning-based framework for detecting data leakage in cloud environments. By leveraging advanced neural network architectures, such as Long Short- Term Memory (LSTM) and Convolutional (...) Neural Networks (CNNs), the model detects abnormal data access patterns that may indicate leakage. The system operates in real-time, continuously monitoring data interactions between users and the cloud. A large dataset containing normal and abnormal access logs is used to train and validate the model, ensuring it can effectively differentiate between legitimate and malicious activity. The performance of the model is evaluated using metrics such as accuracy, precision, recall, and F1-score, with the system achieving over 96% accuracy in identifying potential data leaks. Furthermore, the proposed solution is designed to be scalable and adaptable, making it suitable for dynamic cloud environments with evolving threats. Future enhancements to the system include integrating multi- cloud support and refining the model’s ability to detect sophisticated insider threats. This research highlights the importance of leveraging deep learning for real-time, proactive cloud security. (shrink)

We investigate the application of Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM) networks, and a hybrid CNN-LSTM model for forecasting air pollution levels based on historical data. Our experimental setup uses real-world air quality datasets from multiple regions, containing measurements of pollutants like PM2.5, PM10, CO, NO2, and SO2, alongside meteorological data such as temperature, humidity, and wind speed. The models are trained, validated, and tested using a split dataset, and their accuracy is evaluated using (...) performance metrics like Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and R-squared. (shrink)

This study explores the application of deep learning and image processing techniques for the detection of skin cancer. Leveraging convolutional neural networks (CNNs) and advanced image processing algorithms, the proposed system aims to accurately identify and classify skin lesions. The model is trained on a diverse dataset, encompassing various skin conditions, to enhance its diagnostic capabilities. Results demonstrate the potential for automated and reliable skin cancer detection, offering a promising approach for early diagnosis and improved patient outcomes. (...) The deep learning model is trained on a comprehensive dataset, including various types of skin lesions and conditions, to ensure robust performance across a spectrum of cases. Image preprocessing techniques are employed to enhance feature extraction and improve the model's ability to discern subtle patterns indicative of skin cancer. The study further investigates the interpretability of the deep learning model, employing techniques to visualize and understand the decision-making process. This transparency aids in building trust in the system's predictions and facilitates collaboration between AI and medical practitioners. As the landscape of healthcare continues to evolve, the combination of deep learning and image processing offers a scalable and efficient solution for skin cancer detection, fostering advancements in early intervention and personalized patient care. (shrink)

Speech Emotion Recognition (SER) is an essential component in human-computer interaction, enabling systems to understand and respond to human emotions. Traditional emotion recognition methods often rely on handcrafted features, which can be limited in capturing the full complexity of emotional cues. In contrast, deep learning approaches, particularly convolutional neural networks (CNNs), recurrent neural networks (RNNs), and long short-term memory (LSTM) networks, offer more robust solutions by automatically learning hierarchical features from raw audio data. This (...) paper reviews recent advancements in deep learning-based speech emotion recognition, discusses the various architectures used, and evaluates the challenges in real-world applications. We focus on the application of deep learning models to enhance the accuracy and robustness of SER, particularly in noisy environments. The study also discusses future directions for research, including multimodal emotion recognition and transfer learning to address challenges such as small datasets and cross-domain applications. (shrink)

Abstract : Background: Vegetable agriculture is very important to human continued existence and remains a key driver of many economies worldwide, especially in underdeveloped and developing economies. Objectives: There is an increasing demand for food and cash crops, due to the increasing in world population and the challenges enforced by climate modifications, there is an urgent need to increase plant production while reducing costs. Methods: In this paper, Lemon classification approach is presented with a dataset that contains approximately 2,000 images (...) belong to 3 species at a few developing phases. Convolutional Neural Network (CNN) algorithms, a deep learning technique extensively applied to image recognition was used, for this task. The results: found that CNN-driven lemon classification applications when used in farming automation have the latent to enhance crop harvest and improve output and productivity when designed properly. The trained model achieved an accuracy of 99.48% on a held-out test set, demonstrating the feasibility of this approach. (shrink)

: The integration of Machine Learning (ML) in Real-Time Biomedical Signal Processing has unlocked new possibilities in the field of telemedicine, especially when combined with the high-speed, low-latency capabilities of 5G networks. As telemedicine grows in importance, particularly in remote and underserved areas, real-time processing of biomedical signals such as ECG, EEG, and EMG is essential for accurate diagnosis and continuous monitoring of patients. Machine learning algorithms can be used to analyze large volumes of biomedical data, enabling faster and (...) more precise detection of anomalies. This paper proposes a novel system for machine learning-based real-time biomedical signal processing that leverages the capabilities of 5G networks to enhance the transmission, processing, and analysis of critical medical data in telemedicine applications. The system integrates convolutional neural networks (CNNs) for signal classification, anomaly detection, and predictive analysis, ensuring that patients receive timely and accurate medical feedback. Additionally, the 5G network’s low latency and high bandwidth provide seamless data transmission, improving remote diagnostics and enabling high-quality teleconsultations. This paper evaluates the current challenges in real-time biomedical signal processing in telemedicine, discusses the potential of machine learning and 5G networks, and presents an innovative solution for improving healthcare delivery through this integrated approach. (shrink)

Computer vision, or image recognition, analyses and interprets visual data in real-world scenarios like images and videos. AI and ML research focusses on object, scene, action, and feature identification because of its usefulness in image processing. Neural networks and deep learning have improved image recognition systems significantly in recent years. Early image recognition used template matching to identify objects. A photo is compared to a stored template using similarity measures like correlation to get the best match. There are (...) several constraints, especially with distorted, scaled, or noisy images. Template matching is computationally expensive. CNNs are the most common deep learning architecture for computer vision. CNNs automatically learn visual input hierarchies. They include pooling, convolutional, and fully connected layers. Regional patterns like shapes, textures, and edges in the input image are filtered by convolutional layers. Pooling layers reduce feature map spatial dimensions, making feature extraction consistent and robust. Thick layers, or fully linked layers, classify or regress using learning features. CNN training requires a big labelled dataset. This research article introduces a deep learning model for the classification and recognition of images. The input data for this model is the Images Data Set. The GenNet Algorithm is employed to derive critical features. The accuracy of classification results is enhanced through the use of preprocessing and feature extraction. The classification model is generated using Convolution Neural Network, AlexNet, ResNet, and VGG. (shrink)

Abstract: Lemons are an important fruit that have a wide range of uses and benefits, from culinary to health to household and beauty applications. Deep learning techniques have shown promising results in image classification tasks, including fruit quality detection. In this paper, we propose a convolutional neural network (CNN)-based approach for detecting the quality of lemons by analysing visual features such as colour and texture. The study aims to develop and train a deep learning model to classify lemons (...) based on their quality, evaluate the model's performance, compare it to traditional machine learning approaches, and identify key factors that affect the model's performance. The dataset used in the study consists of approximately 2533 images of lemons and an empty surface, divided into training, test, and validation data, and includes images of both good and bad quality lemons under different lighting conditions. The deep learning model achieved an accuracy of 99.74% on the test dataset and outperformed traditional machine learning approaches. The developed model has the potential to improve efficiency and accuracy in lemon quality control in the agriculture and food industry. (shrink)

Abstract: The integration of Artificial Intelligence (AI) into medical imaging represents a transformative shift in healthcare, offering significant improvements in diagnostic accuracy, efficiency, and patient outcomes. This paper explores the application of AI technologies in the analysis of medical images, focusing on techniques such as convolutional neural networks (CNNs) and deep learning models. We discuss how these technologies are applied to various imaging modalities, including X-rays, MRIs, and CT scans, to enhance disease detection, image segmentation, and diagnostic (...) support. Additionally, the paper addresses the challenges faced in AI-driven medical imaging, including data quality, model interpretability, and ethical considerations. By examining recent advancements and real-world case studies, this paper provides insights into the current state of AI in medical imaging and its potential future directions. The findings highlight the ongoing evolution of AI technologies and their crucial role in advancing medical diagnostics and treatment strategies. (shrink)

Electrocardiogram (ECG) signal analysis is a critical task in healthcare for diagnosing cardiovascular conditions such as arrhythmias, heart attacks, and other heart-related diseases. With the growth of Internet of Things (IoT) networks, real-time ECG monitoring has become possible through wearable devices and sensors, providing continuous patient health monitoring. However, real-time ECG signal analysis in IoT environments poses several challenges, including data latency, limited computational power of IoT devices, and energy constraints. This paper proposes a framework for Optimized Machine Learning (...) Algorithms designed to analyze ECG signals in real time within IoT networks. The proposed system leverages lightweight machine learning models, including support vector machines (SVM) and convolutional neural networks (CNNs), optimized to run efficiently on low-power IoT devices while maintaining high accuracy. The system addresses the computational limitations of IoT devices by employing edge computing techniques that distribute the processing load between IoT devices and edge servers. Additionally, data compression and feature extraction techniques are applied to reduce the size of the data transmitted over the network, thereby minimizing latency and bandwidth usage. This paper reviews the current advancements in real-time ECG analysis, explores the challenges posed by IoT environments, and presents the optimized machine learning algorithms that enhance real-time monitoring of heart health. The system is evaluated for its performance in terms of accuracy, energy efficiency, and data transmission speed, showing promising results in improving real-time ECG signal analysis in resource-constrained IoT networks. (shrink)

By leveraging convolutional neural networks (CNNs), recurrent neural networks (RNNs), and transformers, this research presents an intelligent malware detection framework capable of identifying both known and zero-day threats. The methodology involves feature extraction from static, dynamic, and hybrid malware datasets, followed by training DL models to classify malicious and benign software with high precision. A robust experimental setup evaluates the framework using benchmark malware datasets, yielding a 96% detection accuracy and demonstrating resilience against adversarial attacks. (...) Real-time analysis capabilities further improve response times, reducing the risk of potential damage. The study also incorporates visualization tools to provide interpretable insights into model decisions, enhancing transparency for cybersecurity practitioners. Concluding with a discussion on the challenges and future prospects, this research paves the way for scalable, AI-driven solutions to combat evolving cyber threats. (shrink)

Abstract: Classifying sea animals is an important problem in marine biology and ecology as it enables the accurate identification and monitoring of species populations, which is crucial for understanding and protecting marine ecosystems. This paper addresses the problem of classifying 19 different sea animals using convolutional neural networks (CNNs). The proposed solution is to use a pretrained MobileNetV2 model, which is a lightweight and efficient CNN architecture, and fine-tune it on a dataset of sea animals. The results (...) of the study show that the fine-tuned MobileNetV2 model is able to achieve an accuracy of 85% on the classification task, which is competitive with the state-of-the-art methods. Additionally, the study also found that data augmentation and regularization techniques such as dropout were important for preventing overfitting and improving the performance of the model. This study demonstrates the potential of using pretrained models and efficient CNN architectures for classifying sea animals, and it provides insights into the challenges and best practices for solving this important problem in marine biology and ecology. (shrink)

Abstract: In recent years, the outbreak of various poultry diseases has posed a significant threat to the global poultry industry. Therefore, the accurate and timely detection of chicken diseases is critical to reduce economic losses and prevent the spread of diseases. In this study, we propose a method for classifying chicken diseases using a convolutional neural network (CNN). The proposed method involves preprocessing the chicken images, building and training a CNN model, and evaluating the performance of the model. (...) The dataset used in this study comprises chicken images of three different diseases: Newcastle disease, avian influenza, and infectious bursal disease. The proposed method achieved an overall F1-score of 99.04% in classifying the chicken diseases. The results demonstrate the effectiveness of using CNN in classifying chicken diseases and provide a promising approach for early detection and diagnosis of poultry diseases. (shrink)

Abstract: The integration of Artificial Intelligence (AI) into medical imaging marks a transformative advancement in healthcare, significantly enhancing diagnostic accuracy, efficiency, and patient outcomes. This paper delves into the application of AI technologies in medical image analysis, with a particular focus on techniques such as convolutional neural networks (CNNs) and deep learning models. We examine how these technologies are employed across various imaging modalities, including X-rays, MRIs, and CT scans, to improve disease detection, image segmentation, and diagnostic (...) support. Furthermore, the paper discusses the challenges associated with AI-driven medical imaging, such as data quality, model interpretability, and ethical considerations. By analyzing recent advancements and real-world case studies, this paper offers insights into the current landscape of AI in medical imaging and explores its potential future directions. The findings underscore the ongoing evolution of AI technologies and their pivotal role in advancing medical diagnostics and treatment strategies. (shrink)

Abstract: Rice is one of the most important staple crops in the world and serves as a staple food for more than half of the global population. It is a critical source of nutrition, providing carbohydrates, vitamins, and minerals to millions of people, particularly in Asia and Africa. This paper presents a study on using deep learning for the classification of different types of rice. The study focuses on five specific types of rice: Arborio, Basmati, Ipsala, Jasmine, and Karacadag. A (...) dataset of 75,000 images was collected and annotated, consisting of 15,000 images for each of the five types of rice. The deep learning system uses convolutional neural networks (CNNs) to classify images of rice grains based on their physical characteristics. The performance of the deep learning system was evaluated using metrics such as accuracy, precision, recall, and F1-score. The results show that the proposed deep learning system was able to achieve high accuracy in classifying the different types of rice, outperforming traditional image processing techniques. This study provides valuable insights into the potential of deep learning for classifying different types of rice and can be useful for applications such as quality control in rice processing industries and research in crop science. The large size of the dataset, 15,000 images for each type of rice, helped the deep learning system to learn the features of each type of rice, and increase the performance of the classifier. The attained overall accuracy of the proposed model (99.96%), Precision (99.96%), Recall (99.96%) and F1-score (99.96%). Thus, the proposed model proved that it leaned the five categories of rice and it can generalize these categories and it is effective. (shrink)

Sign Language Recognition (SLR) aims to translate sign language into text or speech in order to improve communication between deaf-mute people and the general public. This task has a large social impact, but it is still difficult due to the complexity and wide range of hand actions. We present a novel 3D convolutional neural network (CNN) that extracts discriminative spatial-temporal features from photo datasets. This article is about classification of sign languages are not universal and are usually not (...) mutually intelligible although there are also similarities among different sign languages. They are the foundation of local Deaf cultures and have evolved into effective means of communication. Although signing is primarily used by the deaf and hard of hearing, hearing people also use it when they are unable to speak, when they have difficulty speaking due to a health condition or disability (augmentative and alternative communication), or when they have deaf family members, such as children of deaf adults. In this article we use the 43500 image in the dataset in size 64*64 pixel by use CNN Architecture and achieved 100% accuracy. (shrink)