LC International Journal of STEM (ISSN: 2708-7123)
Not a member yet
120 research outputs found
Sort by
Automated Robust Facial Expression Recognition using Transfer Learning ResNet50
Get PDFThe human face is a convenient, fast, and accurate source of communication. Facial expressions convey internal human emotion developed using different facial traits. Affective computing works on developing systems for Facial Expression Recognition (FER) using machine learning tools and it remains an active research area for the research community. This paper proposes a deep learning-based model ResNet50 for facial expression recognition. We further applied transfer learning and fine-tuning techniques with the proposed model to improve the generalization. The model is trained and validated at the FER2013 dataset and tested with some unseen images from MMA facial expression dataset. The model archives validation accuracy of 86.32% which is comparable with existing research
Research Comparative Analysis of OCR Models for Urdu Language Characters Recognition
Get PDFThere have been many research works to digitalize Urdu Characters through machine learning algorithms. The algorithms that were already used for Urdu Optical Character Recognition [OCR] are Convolutional Neural Network [CNN], Recurrent Neural Network [RNN], and Transformer etc. There are also many machine learning algorithms that have not been used for Urdu OCR e.g Support Vector Machine, Graph Neural Network etc. This research paper proposes a comparative study between the performances of the already implemented Urdu OCR on some of following algorithms like Convolutional Neural Network/ Transformer Model it also proposed a new implemented Urdu OCR using on Support Vector Machine algorithm
A Comparative Analysis on Diabetes Datasets Using Data Mining Techniques
Get PDFIn past, many researchers have been worked on the early diagnosis of diabetes disease. They used different diabetes datasets for the prediction of diabetes disease. Diabetes disease is one of the chronic diseases and becoming a cause of death among peoples. So many factors involved which cause diabetes disease and in this way a huge amount of data increasing about diabetes disease.In this paper, we compared different cases of diabetes disease based on two different Pima Indian diabetes datasets. From previous studies we found that different deep learning and machine learning methods had been applied to these two datasets but achieved very efficient methods used to diagnose diabetes. Also, determine the research gap in the application of different methods in the biomedical field
Enhanced Facial Expression Recognition via Deep Transfer Learning and Augmentation
Get PDFFacial Expression is one of the key parts of non-verbal communication. Facial Expression Recognition is the major application of surveillance, automation, health care, and education. Deep learning is important in different fields of computer vision due to its ability to process and analyze large volumes of data, extract features, and correctly classification of images. This research empirically evaluates the performance of a pre-trained model on augmented datasets for facial expression recognition. The study includes preprocessing techniques, data augmentation, and transfer learning using the ResNet50 model. The experiments are conducted on a dataset containing images of three facial expressions: happy, sad, and surprised. The results indicate significant improvements in accuracy as the dataset size and preprocessing techniques increase. In particular, Cubic Support Vector Machine (SVM) and Linear Cubic SVM consistently outperform other classifiers, achieving an impressive accuracy of 99.7% on the augmented dataset. The research demonstrates the potential of data augmentation and preprocessing in enhancing facial expression recognition systems
What Factors are Challenging to Manage a Project in Industry 4.0?
Get PDFOne of the main causes of the earlier industrial revolutions was the speed at which technology was developing. However, in terms of technological advancement and socioeconomic impact, it is anticipated that the fourth industrial revolution (Industry 4.0) and its integrated technology dissemination progress will expand dramatically. Industry 4.0 creates new organizational business models and human-centered manufacturing systems that have an effect on society, the environment, and the entire value chain. The Industry 4.0 is improving things so much that they are improving things even more. However, there are dangers and difficulties associated with developing a project in any Industry 4.0 area. Making a project will undoubtedly require some sort of difficulties. This essay examines the difficulties of putting Industry 4.0 into practice
Enhancing Vehicle Classification Accuracy: A Convolutional Neural Network (CNN) Based Model
Get PDFUsing the convolutional neural network (CNN) fine-tuned method, this article introduces a vehicle categorization system. The system's goal is to properly categorize popular vehicle types in the domestic market, which will help with traffic control, monitoring, and traffic accident prevention. The efficacy of VGG-16 and Inception V3 architectures is demonstrated by their evaluation of a real-world dataset consisting of 2000 photos of vehicles. While VGG-16 attains an accuracy of 99.11%, Inception V3 reaches an accuracy of 96.43%. In terms of overall accuracy, VGG-16 outperforms Inception V3, highlighting the importance of architectural decisions in achieving accurate vehicle classification. The suggested technique significantly improves computer vision applications in the domain of vehicle classification, making valuable contributions to traffic management and accident prevention efforts
Review Paper on IoT Based Smart Applications, Home Automation
Get PDFThis paper discusses internet of things and their applications in various domains such as healthcare, manufacturing, retail, transportation, etc. It highlights the importance of IoT technology in enabling devices and sensors to communicate and exchange data, leading to more efficient and connected systems. The paper explores different applications of IoT, including smart agriculture, smart cities, smart energy, and smart traffic monitoring systems, smart environment, and smart home automation. It also addresses the challenges and problems associated with IoT, such as privacy and security issues, handling big data, connectivity, data transmission, and compatibility. The literature review section examines the development of IoT in smart homes, identifies challenges and hindrances to widespread adoption, and discusses intelligent home automation systems. The survey analysis focuses on the gaps in IoT implementation, including security, interoperability, scalability, data management, ethical concerns, edge computing, and legal/regulatory frameworks. Overall, the paper provides an overview of IoT-based smart applications, their benefits, challenges, and future prospects
Producing of High Quality Colored Images using Scalable Image Processing Techniques
Get PDFOne of the many digital approaches that came from the image processing domain is picture enhancement. These approaches are employed to enhance the perceptibility of images, or to transform the image into a format more suitable for human or machine analysis, and to highlight intricate elements that might otherwise remain indistinct. The primary topic of this thesis is the utilization of the pseudo color approach, which is an image enhancement technique, to convert grayscale intensity images into color-coded images. An investigation into the various forms of pseudo color techniques that have been created in the past has been done in this work. Using the spectra returned by the Fourier transform of the input picture, the Pseudo color method applies three distinct digital filters—a high pass filter, a band pass filter, and a low pass filter—to achieve the desired effect: The Red, Green, and Blue components of the CRT electron cannons are then given the three filtered outputs that are generated, which are subsequently projected onto the screen. Therefore, a comprehensive package has been developed to execute the necessary procedures for generating the colored image. This bundle comprises two primary components. The initial one facilitates the execution of Fourier transformations and filtering operations. For the second part, a computed color table is used to mix the three components of Red, Green, and Blue to make and show the desired color. This means that each pixel in the original image will have a new value that matches the new color, which creates a new colored image. Also, Combining optimal partitioning with dynamic programming with a representation of the image for space-filling curve, we offer a novel algorithm for pseudo-coloring in this paper. The algorithm permits the fine-to-coarse assignment of triplet colors to the pixels of an image, thereby producing a pseudo-colored image that preserves either structure or detail. This is accomplished by initially considering the original gray levels in the image and then systematically decreasing them by optimal partitioning until reaching a specific number, which can include reducing the image to only two colors for a binary representation. The number of colors is output by the algorithm, and the specific allocation of colors is determined by the nature of the problem being addressed. Two sets of medical photos are used to illustrate how the algorithm is applied
School Leader`s Perceptions about STEAM Education to develop STEAM Schools in Pakistan
Get PDFThe purpose of this study is to gain an understanding of the School leaders’ perception about STEAM education to develop STEAM schools in Karachi. This study unveils the background information, aims, scope, objectives and researcher`s interest in selecting the topic for research. This study was conducted with three school leaders working in private STEAM schools in Karachi. Qualitative research design was used to conduct the study about the perception of School leaders who have implemented STEAM Education in schools. Data was collected from three STEAM schools in Karachi. Semi- structured interviews were used to collect the data which were design to explore the perceptions of School leaders about STEAM education. This study aimed to have better understanding about leaders’ own experiences, their preferred teaching style, their vision of STEAM instruction, and their practices feedback at school level. Data was coded and categorized into themes by thematic analysis technique to analyze the data. This study identified that knowledge about STEAM education, Perceived importance of STEAM Education, Integration of STEAM education, Practices of STEAM education and future perspectives of STEAM education are the main factors to develop STEAM schools in Pakistan. Findings of the study revealed that school leader should have background knowledge about STEAM education. School leaders should devise some activities at initial level and align traditional subjects with STEAM subjects in order to integrate STEAM in school. Professional development training for teachers is needed to practice STEAM in classes. School leader emphasized on importance of STEAM education that STEAM prepares students for the world beyond and develop 21st century skills. School leaders believed that students studied in STEAM schools successfully pursue their careers in the field of science and Technology. This study also has some limitations and discusses some recommendation for the implementation of STEAM education in Schools
Word-Graph Construction Techniques for Context Analysis
Get PDFA Nomo-Word Graph Construction Analysis Method (NWGC-AM) is used to graph let the corresponding construction phrases into essential and non-essential citation groups. NMCS-NR, or Nomo Maximum Common Sub-graph edge resemblance, Maximum Common Subgraph Directed Edge resemblance (MCS-DER), and Maximum Common Subgraph Resemblance. The graph resemblance metrics used in this work are called Undirected Edges Resemblance (MCS-UER). The tests included five distinct classifiers: Random Forest, Naive Bayes, K-Nearest Neighbors (KNN), Decision Trees, and Support Vector Machines (SVM). Four sixty-one citations made up the annotated dataset used for the studies. The Decision Tree classifier exhibits superior performance, attaining an accuracy rate of 0.98