VOLUME 11, ISSUE 10, OCTOBER 2023

Abstract: This paper presents a literature review on the Biomarker discovery. The advent of omics technologies like genomics, proteomics, transcriptomics, and metabolomics helped the researchers to discover novel biomarkers that can be used to diagnose, predict, and monitor the progress of disease. A number of computational approaches like machine learning and deep learning have been developed to identify biomarkers by using omics data. The integration of different omics known as multi omics has also been used by researchers for biomarker discovery. This paper presents a comprehensive survey of the recent progress in the identification of biomarkers.

Keywords: Biomarkers, Multi omics data, Machine learning, Deep learning.

Abstract: Plant quality and productivity are significantly impacted by plant diseases.Plant disease detection can be done via digital image processing. In the field of digital image processing, deep learning has recently done significantly better than conventional methods. Experts are now particularly interested in the study area of deep learning-based plant disease diagnosis. Plant diseases and pest detection issues are defined in this study, and the effectiveness of the methods is contrasted with conventional ones. This article reviews the current literature on classification networks, detection networks, and segmentation networks for deep learning-based plant disease and pest detection. The advantages and disadvantages of each strategy are examined in light of the variations in network structure. We compare the effectiveness of earlier studies using common datasets.This study investigates potential challenges associated with deep learning-based plant disease and pest identification in practical contexts. Along with potential research directions and resolutions to the problems, a number of recommendations are also provided. Finally, this paper analyses and predicts the potential future directions for deep learning-based plant disease and pest detection.

Abstract: Recent advancements in web technology have given rise to numerous online shopping websites. However, online shopping comes with certain disadvantages. One notable challenge is the difficulty in visualizing how a particular garment would appear when worn, given the diverse variations in body size, shape, hair, and skin color across the human population. Ensuring the fit of clothing is of paramount importance to both customers and retailers. Our approach centers around assessing how a chosen garment complements the user's body and replicating its real-world appearance. This is achieved by identifying critical points on the garment and the user's body dimensions through image processing techniques. In this paper, we present an application designed, implemented, and tested to enhance the virtual dressing room experience

Keywords: Virtual Dressing Room, Body Image Cloth Mapping, Convolutional Neural Network (CNN).

Abstract: This paper presents a single Voltage Difference Transconductance Amplifier (VDTA) based active filter design with a supply voltage of ± 900mV. The circuit configuration uses an nMOS transistor as an active resistor.

The Cadence Virtuoso tool is used to obtain gain and phase characteristics, noise calculation, and frequency response under various temperatures. Filter response was observed by varying different values of capacitors. The proposed circuit was implemented in gpdk180nm technology with a power consumption of 910.5μW and an area is 2867.99μm2.

Keywords: Active Resistance, Active Filters, Universal Filter, VDTA.

Abstract: Traffic sign classification is one of the most important aspect to be considered in our day to day life. Traditionally, traffic signs have been categorized using standard computer vision methods, but it also takes lot of time to manually process important features of the image. To solve This problem, many people are using deep learning techniques.

In this paper we have proposed a method for Traffic sign classification.

Keywords: Advanced Driver Assistance, traffic sign classification, deep learning, convolution neural networks.

Abstract: In today's rapidly evolving business landscape, the integration of Artificial Intelligence (AI technology within Management Information Systems (MIS) has gained significant attention as a transformative approach to enhancing decision-making processes. The aim of this research was to assess the extent of integration of Artificial Intelligence(AI) technology within Management Information Systems (MIS) of County Governments in Kenya. The findings show that Artificial intelligence integration within MIS in County Governments in Kenya were partially Integrated. These findings are anticipated to contribute to the growing discourse surrounding the level of AI integration within MIS in enhancing decision-making processes, while offering practical recommendations for organizations seeking to harness the potential of these technologies to drive improved decision-making outcomes in the Kenyan context

Keywords: Artificial Intelligence, Management Information Systems, Integration, County Governments

Abstract: As wearable technology continues to evolve and become a ubiquitous part of everyday life, its adoption hinges not only on functionality and usability but also on its social acceptability. Social acceptability refers to how comfortable individuals feel wearing and using technology in the presence of others, particularly in public or semi-public spaces. While technical performance and health benefits are often central in the design of wearable devices, social factors—such as perceived judgment, appearance, and cultural norms—can significantly influence whether a user chooses to adopt and consistently use the technology.

This paper presents a comprehensive study aimed at understanding the social acceptability of wearable devices through the lens of user-centered design. We investigate how factors such as device aesthetics, feedback modality (visual, auditory, haptic), and visibility affect users’ comfort and willingness to use wearable devices in various social contexts. Furthermore, we explore how demographic variables—such as age, gender, occupation, and cultural background—shape user perceptions and acceptance of wearable technology.

To address these questions, we conducted a mixed-methods study involving 60 participants from diverse backgrounds. Participants were provided with a custom-designed wrist-worn prototype with health-monitoring features and subtle interactive feedback systems. Over the course of one week, participants integrated the wearable into their daily lives, including both private settings (home, personal time) and public environments (workplace, transit, social gatherings). Data collection methods included pre-study surveys, in-situ observations, post-use questionnaires, and follow-up semi- structured interviews.

Our results reveal that while most participants appreciated the functionality of the wearable device, social context had a significant influence on their comfort levels. For example, usage in professional or social settings often triggered concerns about standing out, drawing attention, or being perceived as “too techy” or “showing off.” Participants expressed a strong preference for discreet and minimalistic design elements, particularly in scenarios where social judgment was a concern. Moreover, the perceived purpose of the device influenced social acceptability: wearables seen as health-related or medical were more socially accepted than those viewed as lifestyle accessories.

The study also highlights notable generational differences. Older participants were more cautious and self-aware about using technology in public, often citing unfamiliarity or fear of being misunderstood. Younger users, while generally more open, were still selective about when and where they used the device—indicating that even among tech-savvy individuals, social acceptability remains a key consideration.

Based on our findings, we offer a set of design recommendations to improve the social acceptability of wearable devices. These include incorporating customizable privacy settings, designing for context-aware responsiveness (e.g., auto- silencing in meetings), and ensuring clear communication of the device’s purpose through visual and branding cues. Ultimately, we argue that improving the social compatibility of wearable technology is essential to fostering user trust, comfort, and long-term engagement.

This research contributes to the growing field of human-centered wearable design by foregrounding the social dimensions of technology use. By placing user perception and societal norms at the core of design thinking, developers can create wearables that are not only functional and usable but also socially acceptable and desirable.

Keywords: Wearable Technology, Social Acceptability, User-Centered Design, Human-Computer Interaction, Technology Adoption, Aesthetics and Perception, Cultural Norms, Public Use of Technology, Health Wearables, User Experience (UX), Mixed-Methods Study