The idea behind this research is to develop a camera-based motion-sensing game tool for cervical rehabilitation. Many people today prefer to engage in virtual games and seem to avoid doing any physical activity or engaging in a sport. The demand for immersive technology in the virtual world is at an all-time high. In this work, a camera-based motion detection system enables video game players to take their virtual reality experience up a notch by enabling them to use body movements to guide their games, and in turn allow the players to engage in some physical activity that too without the use of specialized hardware, a simple camera for input in this case. The proposed methodology consisted of hardware and software components and their integration. The software implementation is done using Python and C++. The calibration of the controller and testing of the proposed methodology ensures accuracy and reliability with reduced processing time. The application can easily be deployed on mobile as well as computer which will allow the users to use it remotely and help in improving their mobility. In future, the work can easily be expended for handson experience to adherence in cervical rehabilitation.

Image-to-image translation is the process of transforming an image from one domain to another, where the goal is to learn the mapping between an input image and an output image. This task has been generally performed by using a training set of aligned image pairs on fewer cores-based CPU-based architecture, which mainly aims to transfer images from a source domain to a target domain while preserving the content representations by consuming more execution time. Due to its broad range of applications in numerous computer vision and image processing problems, including image synthesis, segmentation, style transfer, restoration, and pose estimation, GPU-based Image-to-image has attracted growing attention and made enormous progress in recent years. It can be utilized for a variation of principles, including photo enhancement, object transformation, season transfer, and collection style transfer. Only CPU and only GPU-based architecture are difficult in order to speed up the image processing task, especially during re-rendering the same scene under various illuminations characteristic for day, night, or dawn. To address this issue, in this work, we are proposing the Hybrid CPU-GPU-based architecture with HiDT technology for implementing the image translation works at tremendous speed. On the hybrid CPU-GPU-based architecture, it is possible to train a multi-domain image-to-image translation model with HiDT on variable size of dataset unaligned images without domain labels using this technology when it is integrated into an application. The speed of the mentioned application can be achieved by using emerging technologies such as pix2pixHD and HiDT on hybrid architecture, where pix2pixHD is a deep learning-based technique for high-resolution photorealistic image-to-image translation, and it is implemented in PyTorch. This article represents Impact of Hybrid Architecture on Machine Learning-based Image-toImage Translation Using HiDT.

We introduce an innovative approach to Medical Visual Question Answering (VQA) by fine-tuning the Idefic 9b model on a combined dataset from SLAKE and VQARAD. Our methodology focuses on loading the model using a 4bit quantization method, striking a balance between computational efficiency and model performance. To enhance the model’s ability to adapt to specific tasks, we employ Low Rank Adaptation (LORA) to fine-tune the model’s attention layers. This technique contributes to reducing the model’s trainable parameters. For evaluation purposes, we employ the BLEU (Bilingual Evaluation Understudy) scores, a widely accepted metric in Natural Language Processing, to evaluate the generated responses quality. The results of our approach in the field of Medical VQA are promising, paving the way for the development of more advanced and efficient models in the future. This paper aims to offer insights into the effective application of fine-tuning techniques, showcasing their impact on enhancing the performance of VQA models in the medical domain.

With more and more teaching learning activities being shifted to online mode, the education system has seen a drastic paradigm shift in the recent times. Learner opinion has emerged as an important metric for gaining valuable insights about teaching–learning process, student satisfaction, course popularity, etc. Traditional methods for opinion mining of learner feedback are tedious and require manual intervention. The author, in this work has proposed a hybrid bio-inspired metaheuristic feature selection approach for opinion mining of learner comments regarding a course. Experimental work is conducted over a real-world education dataset comprising of 110 K learner comments (referred to as Educational Dataset now onwards) collected from Coursera and learner data from academic institution MSIT. Based on the experimental results over the collected dataset, the proposed model achieves an accuracy of 92.24%. Further, for comparative analysis, results of the proposed model are compared with the ENN models for different embeddings, viz., Word2Vec, tf-idf and domain-specific embedding for the SemEval-14 Task 4. The hybrid bio-inspired metaheuristic model outperforms the pre-existing models for the standard dataset too.

Medical records may exclusively be disclosed for the purpose of research. Medical researchers can only access the medical records of patient if they are de-identified because of data protection and privacy laws. De-Identified data means the process of removing or masking protected health information (PHI) in order to reduce the risk that subjects identify be connected with data. Automatic de-identification classifiers The goal is to make it affordable to de-identify large amounts of medical records. Current classifiers are trained on costly manually pseudonymized records from a single source, limiting their applicability to new data sources. To improve this, we need larger, more diverse datasets for training more versatile de-identification tools. We propose a method to convert medical text into a secure format without the need for pseudonymization, making it easier to share training data securely.

The Internet of Things (IoT) consist of a network of interconnected nodes constantly communicating, exchanging, and transferring data over various network protocols. Intrusion detection systems using deep learning are a common method used for providing security in IoT. However, traditional deep learning IDS systems do not accurately classify the attack and also require high computation time. Thus, to solve this issue, herein, we propose an advance Intrusion detection framework using Self-Attention Progressive Generative Adversarial Network (SAPGAN) framework for detecting security threats in IoT networks. In our proposed framework, at first, the IoT data are gathered. Then, the data are fed to pre-processing. In pre-processing, it restored the missing value using Local least squares. Then the preprocessing output is fed to feature selection. At feature selection, the optimum features are compiled using a modified War Strategy Optimization Algorithm (WSOA). Based upon the optimum features, the intruders were categorized into two categories named Anomaly and Normal using the proposed framework. Numerous attacks are assembled, including camera-based flood, DDoS, RTSP brute force, etc. We have compared our proposed framework using state of the art model and efficiency of 23.19%, 27.55%, and 18.35% higher accuracy and 14.46%, 26.76%, and 13.65% lower computational time compared to traditional models.

This “Sales forecasting application” is a web-based solution that assists vendors in forecasting their sales based on various events and features and planning their inventory accordingly. This allows these vendors to maximize profit while meeting surplus demand or avoiding waste during niche demand periods. The Sales Forecasting Application makes use of cutting-edge data analysis methods, such as machine learning and predictive modelling, to examine historical data sales, trends in market, seasonality, and other pertinent variables. The application’s complex algorithms and integration of many data sources enable it to produce forecasts that are specifically suited to each business’s particular characteristics. The Sales Forecasting Application has a number of noteworthy qualities and advantages. First of all, it gives organizations the ability to precisely forecast sales volumes, revenue, and demand trends for particular time frames, such weeks, months, or quarters. Organizations can optimize inventory levels, modify marketing plans, and enhance overall operational efficiency thanks to the forecasting accuracy. The programme uses machine learning algorithms to improve forecasts over time by continuously learning from new data. The tool makes sure that organizations stay ahead of the curve and make flexible, data-driven decisions by altering predictions in response to shifting market conditions. This application will assist in visualizing historical sales, identifying good promotional activities, and better planning future sales and investments. The intended audience of this report is vendors who can use this in their daily routine. This application aims to make an impression by offering vendors a simple solution for planning promotional events and understanding the need for future planning. The goal is to assist them in making better decisions by providing metrics and prediction models. The experimental results shows that open feature has more impact on the future sales which obtain 0.8 values as compared to the promo feature.

Social media is a strong Internet platform that allows people to voice their thoughts about numerous events happening in real time at multiple locations. People comment and express their thoughts on any social media post. Meanwhile, fake news or misleading information is disseminated regarding exciting occurrences that occur in real time. A large number of Internet users read and distribute such false and fake material without knowing the nature or legitimacy of the news. This has a detrimental influence on people’s perceptions of the particular event. Classical techniques are utilized to determine the type of news distributed on Twitter, Instagram, YouTube, and Facebook. However, these techniques fail to take into account characteristics such as news-generating location, consistency, timing, and novelty. It eventually leads to a scenario in which individuals form incorrect ideas and have misleading perceptions regarding any startling news. The spread of misleading thoughts and remarks has a significant impact on real-world action results. This research article addresses these difficulties by developing a system for detecting fake news using deep learning techniques and models. To determine the originality of the news, place of generation, and longevity, two deep learning models are developed artificial neural network and a mixed classifier model of convolution neural networks and long short-term memory. This aids in detecting bogus news and removing it from the server where it is stored. The tests utilizing these coupled models increase the detection of false information in social media. Furthermore, geo-map is used in this research to aids in the regulation of fake news flowing on social media regarding unique occasions occurring all over the world.

Sports players strive to be the epitome of human excellence, pushing the barrier of skill and execution with training, focus and direction, amplified by regular training and practice. This could be attributed to various factors such as response to stimuli, physical factors, psychological factors etc. The present study incorporated the prediction of the most suited playing position of elite male football players using machine learning approaches based on their Anthropometric Parameters (AP–11 parameters) and Motor Fitness Parameters (MFP–7 parameters). Of the features analysed, results identified the position indicative nature of some parameters among6 AP (Height, Body Mass Index, Basal Metabolic Rate, Fat

This research paper aims to introduce a new system that can efficiently parse video content by detecting and storing objects in each frame. The system utilizes advanced computer vision techniques to identify objects in real time, which enables users to search for specific objects based on textual queries. The system employs advanced object detection algorithms to pinpoint regions of interest in video frames and present users with an easy-to-understand visual representation. This paper provides a comprehensive overview of the system, including its design, implementation, and evaluation. The emphasis is on demonstrating the system’s effectiveness in accurately identifying and retrieving objects from extensive video datasets. The results demonstrate the system’s potential applications in video analysis, content indexing, and search-driven retrieval. The robust performance showcased in this research indicates immediate practical implications for the system, with implications for various domains. This work not only underscores the system’s utility in current applications but also lays the groundwork for further exploration and advancements in this dynamic research domain.

Surveillance systems are critical components of modern security and forensic investigation, and their efficacy is strongly reliant on precise object detection in video recordings. This study looks into the use of deep neural networks to improve object detection in surveillance films for crime scene analysis. This study investigates the capabilities of cutting-edge deep learning architectures in recognizing and classifying objects in various surveillance contexts. The study’s findings are extensive, including detection accuracy metrics for numerous item classes such as “Person,” “Vehicle,” and “Suspicious Item.” Precision values range from 0.78 to 0.92, recall values range from 0.82 to 0.90, and F1 scores range from 0.80 to 0.90, demonstrating the models’ ability to recognize objects accurately, but with variances among item categories. This study also looks into computational performance, offering information about inference times and GPU utilization. Inference times for ResNet-50 and YOLOv3 are 15 ms and 20 ms, respectively, with GPU use percentages of 75% and 90%. These findings provide useful information for picking models that fulfill real-time processing needs while optimizing computational resources. The research also examines the connection between video resolution, detection speed (up to 30 frames per second), and average detection accuracy. Lower resolutions allow for faster processing, but at the expense of accuracy, whilst higher resolutions provide finer details at the expense of larger computational needs. These trade-offs are critical considerations when building surveillance systems to meet certain operational requirements.

Parkinson’s disease, a neurodegenerative disorder, affects millions of people worldwide. Early detection is critical for effective treatment and management. Early detection of Parkinson’s disease is challenging due to the lack of accessible and non-invasive screening methods. Current diagnostic techniques often require specialized equipment and invasive procedures, limiting their feasibility for widespread screening. There is a need for cost-effective and accessible approaches that can accurately detect early stages of Parkinson’s disease. The model requires a high degree of precision in distinguishing between these patterns, which is a significant challenge to overcome. In this research work, we proposed a novel approach for detecting early stages of Parkinson’s disease by analyzing hand-drawn spirals and waves in photographs.

The significance of how information is obtained and helps to make proper decisions has been highlighted by the fast growth of the smart business and analytics processing. Big data in clinical applications opens up newer avenues for analysing and gaining insight from large amounts of data. The traditional methods to health data management have had mixed results. Because of its unique features, conventional methods are incapable of managing and processing large data. The article that follows demonstrates a variety of methods for processing large data, including machine learning and statistics methods. The article also discusses the different technologies for storing big data, as well as their benefits and drawbacks in the context of healthcare big data.

Our automated answer script evaluation system utilizes advanced Natural Language Processing (NLP) techniques for precise grading. Incorporating keyword extraction, text recognition, and a viva evaluator, the system enhances assessment accuracy, significantly improving efficiency and reducing educator workload. Providing timely feedback to students, it fosters improved performance. The proposed methodology showcases a substantial improvement in grading speed and objectivity, contributing to the evolution of educational assessment practices. This paper reviews recent advancements, detailing related works, the proposed methodology with mathematical models and a comprehensive block diagram, meticulous test case evaluation, performance metrics, and a state-of-the-art comparison. Results demonstrate the system's effectiveness, highlighting its novel contributions. The paper concludes with discussions on limitations, future prospects, and an acknowledgment of recent research contributions in the field.

Pre-processing of data in the abstract techniques are by far important and the duration process involved in the flow of information discovery. The convolution pre-processing is determined by the source of data from which we are retrieving. The aim of the paper is to find out how important is pre-processing methods to discover the interesting pattern of user session data and also how to use pre-processing method on mining the textual data. We work on transactional and sequence model for weblog files in text format, text representation and sequence rule analysis is been considered as work model. We make an analysis by comparing four datasets which comprises of different data quality of text and it will be pre-processed in different measures like data will be determined with paragraph sequence, data is determined with sentence sequence, data is determined with paragraph sequence excluding stop words. We utilise the impact of these advanced techniques of pre-processing on both quality and quantity of data measurable in case of paragraph sequence identification.

OpenAI created and published ChatGPT, an AI chatbot, in November 2022. It was developed using supervised and reinforcement learning methods and is based on OpenAI's GPT-3.5 and GPT -4 families of big language models. The creation of Artificial Intelligence has started a new era in the field of computer science. Although it was first established in 1950, by, now known as the father of artificial intelligence, John McCarthy, and before that by Alan Turning who explored its mathematical possibilities, Technology is generally ranked using a sigmoid curve, wherein you have a slow take off as the technology is invented, followed by an explosion of growth depending on how useful it is. That results in improvement in the technology as people find more real world practical applications for it, and then it reaches a stagnation point where you can't improvise the tech anymore. We believe that Artificial Intelligence would be the start of a new sigmoid curve. Artificial Intelligence has now reached a new peak after the maturation of ChatGPT. Currently, AI has a gradual growth rate of 21 % per annum, creating a new market in this highly competitive industry. This paper represented the ChatGPT features, paradigm and data analysis process.

Due to the recent rise in the pollution levels in most metropolitan cities, we realized the lack of awareness and prevention measure taken by the general public to reduce it. If we are not aware of the pollution around us, we won't know what to do. On top of that Air is not visible to the naked eye, and it is no doubt that the tiny particles will also not be visible to the naked eye. Air is what keeps living things alive, a high level of pollution in that needs to be monitored and maintained. This suggests the urgent need of an asset that can predict the air pollution levels in the future as well as create awareness and cautions about the hazardous effects of air pollution. A Mobile Application called AIRFACTOR is developed as it is easily accessible to any user, which will help its users gain more knowledge about air pollution and air pollutants in general. Along with that it will also show the near real-time levels of pollution for the city of Bangalore, and also the Air Quality Index that changes over time. The paper aims to acknowledge that the pollutant PM2.5 is not the only pollutant that degrades the air quality, but other pollutants are also present, and thus predicts the levels of the pollutants PM 10 and CO.

Animals play an important role in ecology. Their existence is critical to the ecosystem's equilibrium. However, an increasing number of wildlife are becoming endangered and on the edge of extinction. As a result, humans designated forest areas (sanctuaries and national parks) as safe havens for these creatures to avoid extinction. However, numerous animals resulted in the death of poor health and a lack of attention. Wildlife location tracking combined with a monitoring system is utilized to avoid such tragedies. This technology tracks the animal's health using a heart rate sensor, and by using the Global Positioning System, we are able to get the specific coordinates of each individual animal (GPS). This project's purpose is to determine the movement of wildlife species in national parks as well as in reserved forests. This setup would comprise a temperature sensor that can detect the heat of each animal, in addition to a heart rate sensor that may scale the animal's heart rate in BPM. A temperature sensor is used to monitor this.. It keeps track of the animal's body temperature in real-time. A communication would be sent to the access point if the temperature varies. Likewise, any animal would have a number of heartbeats per unit of time, therefore the proposed system keeping a track of the animal's heartbeat and sends out a message to the access point when the heartbeat has been out of range. The GPS module sends the animal's location, temperature, and pulse rate to the controller, who then sends the information to the app on a PC or laptop via Wi-Fi, which works as a communication medium. Location tracking and health monitoring are the two main applications proposed in the suggested system. The GPS-based position tracking system is used to get the coordinates of the animal. The health monitoring unit uses temperature and pulse rate sensors to measure the animal's temperature and count the animal's heart rate.

Data security is paramount in this modern era. Many corporations have established selective or their own cryptography schemes for information gathering and communication. The need of securing sensitive information is ever-so-increasing due to the rise of cyber thefts and online scams. Visual cryptography is a popular cryptographic technique that consists of hiding visual information like audio, video, image, text etc., in such a manner that nobody but the authorized groups who have complete access to the encrypted data, can collectively or individually reveal the original information. In this paper, we elaborate on two proposed visual cryptographic techniques for image encryption: one uses Caesar Cipher and RSA with a modified (k, N) share generation algorithm, and the other uses chaotic logistic mapping and DNA encoding. To analyze the security and robustness of these proposed algorithms, we will be performing several security tests such as time complexity, histograms, number of pixel change ratio, peak signal-to-noise ratios, information entropy, mean square error, and many other tests.