International Journal of Innovations in Science & Technology
Not a member yet
813 research outputs found
Sort by
Salat Postures Detection Using a Hybrid Deep Learning Architecture
Get PDFSalat, a fundamental act of worship in Islam, is performed five times daily. It entails a specific set of postures and has both spiritual and bodily advantages. Many people, notably novices and the elderly, may trouble with maintaining proper posture and remembering the sequence. Resources, instruction, and practice assist in addressing these issues, emphasizing the need of prayer sincerity. Our contribution in the research is two-fold as we have developed a new dataset for Salat posture detection and further a hybrid model Media Pipe+3DCNN. Dataset is developed of 46 individuals performing each of the three compulsory Salat postures of Qayyam, Rukku and Sajdah and model was trained and tested with 14019 images. Our current research is a solution for correct posture detection which can be used for all ages. We examined the Media Pipe library design as a methodology, which leverages a multistep detector machine learning pipeline that has been proven to work in our research. Using a detector, the pipeline first locates the person\u27s region-of-interest (ROI) within the frame. The tracker then forecasts the pose landmarks and division mask in between the ROIs using the ROI cropped frame as input. A 3D convolutional neural network (3DCNN) was also utilized to extract features and classification from key-points retrieved from the Media Pipe architecture. With real-time evaluation, the newly built model provided 100% accuracy and a promising result. We analyzed different evaluation matrices such as Loss, Precision, Recall, F1-Score, and area under the curve (AUC) to give validation process authenticity; the results are 0.03, 1.00, 0.01, 0.99, 1.00 and 0.95. accordingly
V/F Method to Control the Speed of a Three Phase Induction Motor Using Micro Compiler
Get PDFAC motors with induction drives are frequently working in industrial settings. The foundation of the sector is electric drive. Modern manufacturing is centered on the reliable induction motor. Due to their widespread use in various appliances as well as industrial automation and control, induction motors are frequently referred to as the workhorse of the industry. Although induction motors are constant speed, we often need variable speed for various industrial operations. For each wash cycle, a washing machine needs to run at a different speed. Mechanical gears were working in the past to achieve variable speed. However, modern power electronics and control systems have made such strides that we are able to replace the antiquated gear systems with electronic component-based motor control. Such an application of electronics enhances the motor\u27s dynamic and steady state properties in addition to controlling its speed. Although there are other ways to regulate the speed of motors using variable/adjustable speed drives (VSD/ASD), we will only examine the V/F approach, which is a scalar form of speed control in this article. The speed management of induction motors is now simpler because to advancements in semiconductor technology and the usage of microcontrollers. The frequency and supply voltage affect the speed of an induction motor, so in this case we will adjust the frequency of the supply to alter the speed. In this system, the user-defined speed of the induction motor can be changed. By adjusting the IGBTs\u27 firing angles, the discrepancy between the actual speed and the reference speed is reduced. The system is put to the test, and experimental findings for variable speed under varied load situations are recognized. In this process, the single-phase ac voltage (220V AC) is first converted into dc voltage (440V DC). This dc voltage is applied to an inverter, which again transforms it into three phase ac voltage, but its use allows us to adjust both the voltage level and frequency
Detection And Quantification of Lung Nodules Using 3D CT images
No full textIn computer vision image detection and quantification play an important role. Image Detection and quantification is the process of identifying nodule position and the amount of covered area. The dataset which we have used for this research contains 3D CT lung images. In our proposed work we have taken 3D images and those are high-resolution images. We have compared the accuracy of the existing mask and our segmented images. The segmentation method that we have applied to these images is Sparse Field Method localized region-based segmentation and for Nodule detection, I have used ray projection. The ray projection method is efficient for making the point more visible by its x, y, and z components. like a parametric equation where the line crossing through a targeted point by that nodule is more dominated. The Frangi filter was to give a geometric shape to the nodule and we got 90% accurate detection. The high mortality rate associated with lung cancer makes it imperative that it be detected at an early stage. The application of computerized image processing methods has the potential to improve both the efficiency and reliability of lung cancer screening. Computerized tomography (CT) pictures are frequently used in medical image processing because of their excellent resolution and low noise. Computer-aided detection systems, including preprocessing and segmentation methods, as well as data analysis approaches, have been investigated in this research for their potential use in the detection and diagnosis of lung cancer. The primary objective was to research cutting-edge methods for creating computational diagnostic tools to aid in the collection, processing, and interpretation of medical imaging data. Nonetheless, there are still areas that need more work, such as improving sensitivity, decreasing false positives, and optimizing the identification of each type of nodule, even those of varying size and form
Revolutionizing Cryptography: A Cutting-Edge Substitution Box Design Through Trigonometric Transformation
Get PDFThis paper proposes an innovative approach to enhance the robustness of substitution boxes in cryptography by employing chaotic mapping. Our methodology leverages chaotic mapping to construct a robust 8 × 8 S-box that adheres to the requirements of a bijective function. An illustrative example of such an S-box is presented, accompanied by a comprehensive analysis employing established metrics such as nonlinearity, bijection, bit independence, strict avalanche effect, linear approximation probability, and differential uniformity. To evaluate its strength, we benchmark the performance of our proposed S-box against recently investigated counterparts. Our findings reveal that our approach to S-box construction is both pioneering and efficacious in fortifying substitution boxes for cryptography. Given the escalating frequency of cyber threats and hacking incidents, safeguarding online communication and personal information has become increasingly challenging. Cryptography plays a pivotal role in addressing these challenges by transforming data into a more secure format. In this research, we introduce a novel, lightweight algorithm grounded in trigonometric principles, which significantly enhances security and reduces susceptibility to hacking attempts. Comparative evaluations demonstrate the superior performance of our algorithm over established methods such as the Hill cipher, Blowfish, and DES. While conventional approaches prioritize security, they often incur delays due to increased computational load. Our objective is to expedite cryptographic processes without compromising security, achieved through the strategic application of trigonometric principles. Our algorithm capitalizes on trigonometric functions and operations to introduce confusion, thereby thwarting hacking attempts. Extensive research and testing substantiate that our algorithm excels in both security and speed compared to traditional methods. By seamlessly integrating trigonometric concepts into a streamlined design, our algorithm proves to be practical for real-world applications, offering a robust solution for safeguarding data on the Internet
Restrictions, Challenges and Opportunities for AI and ML
Get PDFArtificial intelligence (AI) refers to a collection of techniques that are being developed to address a wide variety of practical problems. Machine learning (ML) is the backbone of artificial intelligence (AI), comprising a suite of algorithms and techniques designed to solve the issues of categorization, clustering, and prediction. There are bright prospects for putting AI and ML to use in the real world. As a result, there is a lot of study being done in this field. However, mainstream adoption of AI in industry and its widespread use in society are still in their infancy. For understanding the obstacles involved with mainstream AI implementations, both the AI (internal problems) and societal (external problems) viewpoints are required. With this in mind, we can determine what has to happen first to get AI technology into the hands of industry and the public. This article identifies and discusses some of the obstacles to using artificial intelligence in resource-based economies and societies. Publications in the field form the basis for the systematic application of AI&ML technology. This methodical approach makes it possible to define institutional, human resource, societal, and technological constraints. This paper provides a roadmap for future research in artificial intelligence and machine learning that will help us overcome current obstacles and broaden the range of these technologies\u27 potential uses
Addressing Illicit Tobacco Growth in Pakistan: Leveraging AI and Satellite Technology for Precise Monitoring and Effective Solutions
Get PDFThe market share of illicit tobacco products in Pakistan has seen a significant surge in recent years. In 2022, it reached a staggering 42.5%. Since January 2023, there has been a sharp 32.5% increase in volumes of Duty Not Paid (DNP) products and a remarkable 67% surge in the quantities of smuggled cigarettes. This rise can be attributed to the unregistered and unlicensed tobacco cultivation in Pakistan. This sector has largely relied on conventional methods for data collection in the field, primarily managed by the country\u27s crop statistical departments. The utilization of cutting-edge artificial intelligence techniques and satellite imagery for generating crop statistics has the potential to address this issue effectively. We established a synergy by combining images from two remote sensing satellites and collected field data to detect tobacco crops using Recurrent Neural Networks (RNN). The results affirm the effectiveness of these techniques in detecting and estimating the acreage of tobacco crops in the observed areas, particularly in a union council of the Swabi region. We conducted surveys to collect training and validation data through our proprietary smartphone application, GeoSurvey. The collected data was subsequently refined, preprocessed, and organized to prepare it for use with our deep learning algorithm. The model we developed for the detection and acreage estimation of tobacco crops is called Convolutional Long Short-Term Memory (ConvLSTM). We created two datasets from the acquired satellite images for comparison. Our experimentation results demonstrated that the use of ConvLSTM for the synergy of Sentinel-2 and Planet-Scope imagery yields higher training and validation accuracy, reaching 98.09% and 96.22%, respectively. In comparison, the use of time series Sentinel-2 images alone achieved training and testing accuracy of 97.78% and 95.56%
Non-Manual Gesture Recognition using Transfer Learning Approach
Get PDFIndividuals with limited hearing and speech rely on sign language as a fundamental nonverbal mode of communication. It communicates using hand signs, yet the complexity of this mode of expression extends beyond hand movements. Body language and facial expressions are also important in delivering the entire information. While manual (hand movements) and non-manual (facial expressions and body movements) gestures in sign language are important for communication, this field of research has not been substantially investigated, owing to a lack of comprehensive datasets. The current study presents a novel dataset that includes both manual and non-manual gestures in the context of Pakistan Sign Language (PSL). This newly produced dataset consists of. MP4 format films containing seven unique motions involving emotive facial expressions and accompanying hand signs. The dataset was recorded by 100 people. Aside from sign language identification, the dataset opens up possibilities for other applications such as facial expressions, facial feature detection, gender and age classification. In this current study, we evaluated our newly developed dataset for facial expression assessment (non-manual gestures) by YOLO-Face detection methodology successfully extracts faces as Regions of Interest (RoI), with an astounding 90.89% accuracy and an average loss of 0.34. Furthermore, we have used Transfer Learning (TL) using VGG16 architecture to classify seven basic facial expressions and succeeded with 100% accuracy. In summary, our study produced two different datasets, one with manual and non-manual sign language gestures, the second with Asian faces to find seven basic facial expressions. With both the dataset, our validation techniques found promising results
Accountable and Trustworthy IoT Networks, Based on Blockchain
Get PDFThe term "Internet of Things" (IoT) refers to a situation in which intelligent things are linked to a network or the internet. IoT objects have become more prevalent over the past several years in many industries, and fields, and are now used in all facets of our life. The privacy of data is a crucial problem as the number of devices rises. Researchers in this discipline have employed a variety of strategies to address this issue. Regrettably, there is less accountability, data protection, and traceability with these solutions. In this study, a blockchain-based network architecture for accountability, privacy, and traceability is designed (TDA). Blockchain technologies are referred to as a distributed ledger of transaction records, which time-stamped information about a transaction\u27s lifetime. Persistence, decentralization, and audibility are three of blockchain\u27s key characteristics. The budget is reduced and efficiency is increased thanks to these characteristics. This study also discusses the performance of the suggested architecture in order to strengthen the TDA architecture
Investigating the Influence of Familiarity in a Three-Dimensional Soundscape of Multisensory Factors Shaping Fetal Perception
Get PDFThe ability of human fetuses to recognize their mother\u27s voice was studied in this research. Sixty full-term fetuses were randomly divided into two groups: those who were read a taped recording by their mothers or those who were read the same recording by a female stranger. Unfortunately, our in-depth acoustic research showed no discernible difference beyond a fleeting shadow in the here and now. To explore the duration spent moving across all intervals, the frequency of movements in each temporal realm, and the epoch at which the very first movement occurred, we employed the powerful tool of repeated measures analysis of variance (ANOVA) in the name of scientific research. A peaceful calm pervaded the delicate balance of information, creating an air of mystery. Experience has shown to influence fetal sound processing since different behaviors have been discovered in reaction to familiar and unfamiliar sounds. It lends credence to the idea that there is some interplay between the genetic expression of brain development and the experience of a given species, which is central to the epigenetic model of speech perception. The speaker is roughly 10 centimeters above the mother\u27s belly, and the average sound pressure level (SPL) is 95 dB. No stimulation, no sound (from mother or stranger), and no stimulation lasts two minutes. The fetal heart rate increases for 4 minutes when the mother\u27s voice is present, while the fetal heart rate lowers for 4 minutes when an unfamiliar voice is present. Our investigations, however, went far beyond the domain of pulsations and reverberations. We looked at the period beginning five seconds before the onset of sound and continuing for another five seconds to reevaluate the complex dance of fetal movement
Remote Sensing Study of Mobile Networks: An Assessment of Technological Challenges
Get PDFThe current era is witnessing a notable shift in the logistics and transportation sector due to the advent of Advanced Technologies (ATs). ATs, or smart technologies, encompass the use of artificial intelligence and data science methodologies, including machine learning and big data analysis, to establish cognitive comprehension and autonomous capabilities in relation to an entity. This study investigates the efficacy of remote sensing techniques in analyzing mobile network coverage for optimizing logistic applications. With the proliferation of mobile technologies, seamless connectivity has become integral for efficient logistical operations. Presently, numerous implementations of ATs have exhibited considerable potential in augmenting the efficiency and efficacy of diverse logistical operations and transportation systems. Moreover, the emergence of these innovative technologies presents significant modelling complexities for conventional optimization techniques, hence offering promising avenues for the exploration and development of novel optimization strategies within the realm of logistics and transportation research. The study aims to provide insights into areas with limited or inadequate network coverage, facilitating strategic planning for logistical operations. By integrating remote sensing findings with logistic frameworks, this research contributes to enhancing the efficiency, reliability, and responsiveness of logistical networks in regions with varying degrees of mobile network connectivity. The focus of our investigation is to thoroughly examine and engage in discourse regarding the technological challenges faced by researchers during the creation of optimization approaches as a result of the use of ATs