AI is making labour-intensive HRM operations like hiring, performance review, and employee engagement more efficient and effective. The incorporation of AI technology in HRM could change several sectors. Through effic...
详细信息
In this paper, the text drawn by the user in the air is captured by the computer's camera, followed by the identification of that text. So, the video camera will be turned on at the time of capturing the written t...
详细信息
It's a perpetual human quest and a constant effort of science to develop and design equipment and aids to help physically challenged people live their lives independently and confidently. blindness and visual impa...
It's a perpetual human quest and a constant effort of science to develop and design equipment and aids to help physically challenged people live their lives independently and confidently. blindness and visual impairment are prevalent disabilities that inhibit the independence of the patient and increase the reliance on family members, friends, and guide dogs for navigation and other daily duties. The proposed work outlines a reliable, low-cost, and power-efficient solution that enables safe and secure navigation for visually impaired people. Many researchers have worked on and proposed solutions to the typical problems, but those works have some shortcomings that are addressed in this study. Existing technologies have not focused on optimizing power consumption and reliability, thereby reducing the life of the system. It is vital to reduce power consumption in order to extend the operating lifetime of devices that use batteries as a power source. A methodology has been put forward to address the crucial concern of a gadget that is left on for an extended period of time without being switched off to improve the overall performance of the system. The iot is entrusted with taking into account heterogeneous equipment that might be severely constrained by its nature and pose problems in the hardware layer of the system. So methods to make the system reliable, accurate, and resistant to failures are inscribed in this study. Additionally, existing systems aren’t economical compared to the offered features, lack automation, and lack audio feedback, particularly notifying obstacles. This study proposes audio feedback in multiple languages and automates the command execution, thereby making it effortless for impaired people to engage with the product. Also, the present state of technology faces challenges in locating the misplaced stick, which means the person has to be dependent on loved ones, friends, or caretakers to find the stick. The proposed automated and handy Smart S
The presentation summarizes a groundbreaking cognitive training program designed specifically for those who suffer from cognitive impairments or neurodevelopmental abnormalities. The work creates a dynamic platform fo...
详细信息
Cyber security is one the most challenging task in today's world. Most of the existing Li-Fi technology in wireless sensor network is to detect the data within the short range of distance less accuracy. In this re...
详细信息
Aortic Aneurysm (A2) remains a leading cause of morbidity and mortality worldwide, necessitating innovative approaches for accurate prediction and early intervention. This study proposes a novel ensemble learning fram...
详细信息
Heart attacks remain a primary cause of global mortality, highlighting the urgent need for systems that enable early detection and intervention. This study proposes a Smart iot-based system designed to detect and moni...
详细信息
ISBN:
(数字)9798331518592
ISBN:
(纸本)9798331518608
Heart attacks remain a primary cause of global mortality, highlighting the urgent need for systems that enable early detection and intervention. This study proposes a Smart iot-based system designed to detect and monitor heart attack symptoms in real-time, thus facilitating timely medical response. The system integrates wearable sensors to collect continuous data on heart rate, stress levels, and positional changes, which is then processed through Arduino IDE and transmitted to an iot server. Machine learning algorithms, including Support Vector Regression (SVR) and Artificial Neural Networks (ANN), are employed to analyze these signals for abnormal patterns indicative of a potential heart attack. Major findings indicate that this system accurately detects heart rate irregularities, and stress fluctuations and can alert healthcare providers, significantly improving remote monitoring capabilities. The implications of this study suggest that iot-enabled monitoring systems can substantially enhance patient outcomes by allowing for early diagnosis and proactive care in remote settings, thereby reducing the risk of fatal heart events.
Portable electronic gadgets and high-performance computing systems have increased demand for low-power, high-performance integrated circuits (ICs). VLSI technology, which creates integrated circuits with dozens to mil...
详细信息
The ever-growing global population has heightened resource consumption and waste generation, emphasizing the quick need for effective waste management to safeguard the environment. Unfortunately, the recycling industr...
详细信息
ISBN:
(数字)9798331540661
ISBN:
(纸本)9798331540678
The ever-growing global population has heightened resource consumption and waste generation, emphasizing the quick need for effective waste management to safeguard the environment. Unfortunately, the recycling industry grapples with persistent challenges, primarily in accurate trash classification, a critical factor for successful recycling. Manual sorting, often prone to errors due to subjective human judgment, hampers the recycling process, contributing to inefficiencies. Furthermore, the inherent risks associated with direct contact during the sorting of hazardous materials pose serious health concerns for the workers involved. In response to these challenges, we propose a revolutionary solution: the Trash Classification and Recycling Assistant utilizing YOLO variants V5-V7. This system, rooted in image classification techniques, seeks to elevate the precision of trash sorting. Notably, YOLO variant V7 emerges as the frontrunner, showcasing remarkable accuracy improvements. by utilizing the capabilities of advanced technology, this innovative approach not only streamlines waste sorting processes but also mitigates health risks linked to manual handling of toxic materials. The integration of YOLO variants V5-V7 represents a pivotal step towards ushering in a new era of efficiency and accuracy in recycling practices, thus significantly contributing to the overarching goal of environmental sustainability.
Eichhornia crassipes, commonly referred to as water hyacinth and thought to be one of the most aggressive aquatic macrophytes, is an emerging threat to both ecosystems and economies. The potential for rapid proliferat...
详细信息
ISBN:
(数字)9798331528140
ISBN:
(纸本)9798331528157
Eichhornia crassipes, commonly referred to as water hyacinth and thought to be one of the most aggressive aquatic macrophytes, is an emerging threat to both ecosystems and economies. The potential for rapid proliferation induces blockage of waterways, decreased biodiversity, degraded water quality, and reduced fishery and recreational values; it demands advanced monitoring and management techniques. Our research proposes a better approach for identification of water hyacinth growth stages with greater accuracy by applying the latest deep-learning models so as to take more stringent control measures. We enhanced our dataset by incorporating high-resolution images from diverse aquatic environments, including Kaikondrahalli Lake in bangalore and Anasagar Lake in Ajmer, adding to existing images sourced from Kaggle. Three pre-trained CNN models based on transfer learning, namely ResNet50, VGG16, and InceptionV3,have been taken into consideration and evaluated with great care for their efficacy in classification. Among them, InceptionV3outperformed, with training accuracy of 98.43% and testing accuracy of 99.80%. These models were further integrated into a custom SimpleCNN architecture improving the robustness in classification through Ensemble Learning. The performance obtained from the current study notably surpassed the benchmark accuracy of 86.2% set by Dyrmann et al. in their CNN-based multi-class classification study.
暂无评论