In the realm of facial expression recognition (FER), the identification and classification of seven universal emotional states, surprise, disgust, fear, happiness, neutrality, anger, and contempt, are of paramount importance. This research focuses on the application of convolutional neural networks (CNNs) for the extraction and categorization of these expressions. Over the past decade, CNNs have emerged as a significant area of research in human-computer interaction, surpassing previous methodologies with their superior feature learning capabilities. While current models demonstrate exceptional accuracy in recognizing facial expressions within controlled laboratory datasets, their performance significantly diminishes when applied to real-time, uncontrolled datasets. Challenges such as degraded image quality, occlusions, variable lighting, and alterations in head pose are commonly encountered in images sourced from unstructured environments like the internet. This study aims to enhance the recognition accuracy of FER by employing deep learning techniques to process images captured in real-time, particularly those of lower resolution. The objective is to augment the accuracy of FER in real-world datasets, which are inherently more complex and collected under less controlled conditions, compared to laboratory-collected data. The effectiveness of a deep learning-based approach to emotion detection in photographs is rigorously evaluated in this work. The proposed method is exhaustively compared with manual techniques and other existing approaches to assess its efficacy. This comparison forms the foundation for a subjective evaluation methodology, focusing on validation and end-user satisfaction. The findings conclusively demonstrate the method's proficiency in accurately recognizing emotions in both laboratory and real-world scenarios, thereby underscoring the potential of deep learning in the domain of facial emotion identification.

Although online shopping has become more and more popular, keeping clients is still a big problem. Satisfaction, which is mostly dependent on comprehending and establishing trust with customers, is what determines whether or not a business can retain its customers. In the ever-changing world of e-commerce, this study examines the relationship between consumer loyalty, happiness, and service quality, with a focus on brand trust. The findings indicate that several aspects of service quality, including order processing, speed, convenience, and quality of communication from couriers, have a big impact on how satisfied customers are with their online purchases. The most powerful element influencing pleasure, however, turned out to be ease. The relationship’s key mediator is brand trust. As a result, consumer loyalty is increased and uncertainty is decreased. In particular, in developing e-commerce countries such as Pakistan, the study emphasizes how important it is to enhance consumer happiness, service quality, and brand credibility. By stressing the mediating function of brand trust and highlighting the dynamics in emerging nations, this research adds to the body of current work. It emphasizes how crucial trust and quality customer service are to creating long-lasting, customer-focused e-commerce enterprises. While acknowledging its limits, the study provides useful insights and avenues for further cross-country research.

Amid the COVID-19 pandemic, the imperative for alternative biometric attendance systems has arisen. Traditionally, fingerprint and facial recognition have been employed; however, these methods posed challenges in adherence to Standard Operational Procedures (SOPs) set during the pandemic. In response to these limitations, iris detection has been advanced as a superior alternative. This research introduces a novel machine learning approach to iris detection, tailored specifically for educational environments. Addressing the restrictions posed by COVID-19 SOPs, which permitted only 50% of student occupancy, an automated e-attendance mechanism has been proposed. The methodology comprises four distinct phases: initial registration of the student's iris, subsequent identity verification upon institutional entry, evaluation of individual attendance during examinations to assess exam eligibility, and the maintenance of a defaulter list. To validate the efficiency and accuracy of the proposed system, a series of experiments were conducted. Results indicate that the proposed system exhibits remarkable accuracy in comparison to conventional methods. Furthermore, a desktop application was developed to facilitate real-time iris detection.

Over the last decade, there has been a huge increase in the number of images, in which visual information has become increasingly important. If images are to be utilized, they must be organized into databases, from which they can be searched based on different criteria. Content-Based Image Retrieval (CBIR) frameworks have become a mainstream subject of research due to their ability to retrieve images based on actual visual content rather than manually assigned textual descriptions. In the CBIR framework, the analysis and interpretation of image information in large and diverse image databases are evidently complex because there is no prior information about the size or scale of individual structures within the images to be analyzed. In CBIR, retrieval is based on visual image features, which can be extracted automatically from images with the help of human intervention through a technique known as relevance feedback. Nonetheless, efficient methods for differentiating the visual content of images are complex to develop. Therefore, rather than providing a perfect solution, CBIR systems must be able to exploit partial solutions to the problem of image understanding. In this paper, an implementation of a CBIR framework is introduced that not only attempts to efficiently capture user intent based on feedback but also provides query suggestions that help users formulate better queries to retrieve desired results efficiently. The proposed technique is straightforward to implement and scales efficiently to large datasets. Extensive experiments on diverse real-world datasets using image similarity measures have revealed the superiority of the proposed method over existing algorithms.

Information security is important in the digital era, with encryption emerging as a fixed solution to safeguard sensitive data from unauthorized access. This paper provides an overview of encryption by categorizing cryptographic algorithms into symmetric and asymmetric, along with hashing. Symmetric cryptography uses a single key for encryption and decryption, and asymmetric cryptography utilizes distinct public and private keys. Hashing maps input messages into compact bit strings. The literature survey explores the performance analysis of encryption algorithms, focusing on Rivest Shamir Adleman (RSA), Data Encryption Standard (DES), and Advanced Encryption Standard (AES), considering parameters like computation time and memory usage. Furthermore, the comparative analysis of encryption algorithms, including AES, RSA, and 3DES, is discussed. The paper delves into the motivation for cryptography in secure document transfer systems, emphasizing the need for confidentiality, integrity, and availability. Finally, the study presents detailed insights into AES, RSA, and 3DES encryption standards, highlighting their principles and applications.

Detection of bone fractures using modern technology has significant implications in medical analysis and artificial intelligence. This importance is especially pronounced in the realm of deep learning. Deep learning techniques find extensive application in the field of medicine and disease classification. The early identification of bone fractures is crucial for efficient treatment planning and patient care. Our research proposes a transfer learning-based model for predicting bone fractures using a dataset of bone X-ray images. These images will be classified into two categories: normal and bone fracture, based on extracted features. Our proposed model, the Bone Fracture Detection Transfer Learning Algorithm (BFDTLA), achieved an average accuracy of 97% on the dataset. The BFDTLA model demonstrated superior performance when compared to previous quantitative and qualitative research studies. This research focuses on the early detection of bone fractures using transfer learning algorithms, emphasizing the significance of accurate and timely diagnosis.