International Journal of Innovations in Science & Technology
Not a member yet
813 research outputs found
Sort by
Design of Mega LEO Constellations for Continuous Coverage over Pakistan: Satellite Communication
No full textSatellite communication was effectively done in Geostationary Earth Orbit (GEO) in the past years. Recently the trend has shifted from GEO to Low Earth Orbit (LEO). The objective of our study is to propose a satellite constellation for Pakistan in LEO that will provide continuous coverage over Pakistan. As LEO is much closer to the earth as compared to other orbits such as GEO and High Earth Orbit (HEO) etc. one can achieve benefits like low latency rate, less fuel consumption, and signal transmission loss. In ongoing research, an attempt has been made to design the satellite constellation in LEO using the software, System Tool Kit (STK) which has 2D and 3D environment modeling. In the designed constellation, the satellites pass over Pakistan and access the target area. To get uninterrupted continuous coverage, the number of satellites per plane and the number of orbits is increased. The orbital inclinations were also adjusted to achieve the objective. One of the important tasks for continuous coverage is the concept of satellite handshaking which means that soon a satellite gets away from the line of sight of the ground station antenna; another satellite comes within the line of sight of that antenna. LEO satellites are more favorable for communication purposes as they provide reliable communication as well as higher bandwidth
Significance of Education Data Mining in Student’s Academic Performance Prediction and Analysis
Get PDFData Mining (DM) is relevant to extract the hidden patterns from the voluminous amount of the data. Applying DM, in education is an evolving interdisciplinary research domain, which is also called as educational data mining (EDM). At present, student data about their academics is available to identify important hidden trends to be explored for enhancing student academic performance. In higher education, forecasting student success is essential for helping with course selection and creating individualized study schedules. It helps instructors and managers keep tabs on students, ensure their development, and modify training programs for the best results. Growth and development of any nation depend on educational institutions since they are fundamental social foundations. It is now feasible to use past data for effective learning and prediction of future behavior in a variety of troublesome areas thanks to the development of DM as a potent approach. Educational institutions may make wise judgments and promote improvements in the education sector by utilizing the possibilities of DM supported EDM approaches. It is feasible to pinpoint improvement areas and direct upcoming skill development by examining pupils\u27 performance on various academic evaluations. Furthermore, this procedure lessens the frequency of official warnings and ineffective student expulsions, fostering a more encouraging and fruitful learning atmosphere. In this work, a unique algorithm that combines classification and clustering approaches to predict students\u27 academic success has been suggested. Real-time student datasets from several academic institutes in higher education were used to test the suggested approach. The findings show that the suggested model worked well for predicting students\u27 academic achievement
Investigating Deep Learning Methods for Detecting Lung Adenocarcinoma on the TCIA Dataset
Get PDFLung cancer, one of the deadliest diseases worldwide, can be treated, where the survival rates increase with early detection and treatment. CT scans are the most advanced imaging modality in clinical practices. Interpreting and identifying cancer from CT scan images can be difficult for doctors. Thus, automated detection helps doctors to identify malignant cells. A variety of techniques including deep learning and image processing have been extensively examined and evaluated. The objective of this study is to evaluate different transfer learning models through the optimization of certain variables including learning rate (LR), batch size (BS), and epochs. Finally, this study presents an enhanced model that achieves improved accuracy and faster processing times. Three models, namely VGG16, ResNet-50, and CNN Sequential Model, have undergone evaluation by changing parameters like learning rate, batch size, and epochs and after extensive experiments, it has been found that among these three models, the CNN Sequential model is working best with an accuracy of 94.1% and processing time of 1620 seconds. However, VGG16 and ResNet50 have 95.0% and 93% accuracies along with processing times of 5865 seconds and 9460 seconds, respectively
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
Interfering Factors of Use of E-Commerce Toward Innovative Performance of SMEs by Moderating The Effects of E-commerce Marketing Capabilities
No full textThe performance of Small and Medium-sized Enterprises (SMEs), crucial to technological innovation within business and management, is a key obstacle to industrialization and creating a reaction to the changes. In the current study, the relationship between Technological, Organizational, and Environmental (TOE) aspects and the innovative performance of SMEs is mediated and moderated by the use of e-commerce and the efficiency of e-commerce marketing. In the present study, data were gathered through both face-to-face and online methods from proprietors and managers of SMEs operating in six prominent cities in Pakistan. Nearly 274 participants were randomly chosen to participate in the data collection. While 250 completed surveys were used for the analyses due to the unfinished survey report. The current study employed SPSS 25 to calculate the descriptive statistics, Smart Partial Least Square (PLS) 3.3.2 to analyze the data, and SEM to calculate the inferential statistics. The study\u27s findings indicate that the environmental component, the use of e-commerce, and the technology factor (technology readiness) are all positively correlated. Similarly, there is a negative association between organizational factors (adoption cost) and the use of e-commerce. In contrast, there is a positive relationship between the use of e-commerce and the innovative performance of SMEs (IP). The usage of e-commerce does not mediate adoption cost and innovative performance, but Technology Readiness (TR), Government Support (GS), and Innovative Performance (IP) do. The utilization of e-commerce and innovative performance and e-commerce marketing capabilities do not moderately correlate
Evaluating Future Climate Projections in Upper Indus Basin through GFDL-ESM2M Model
Get PDFThis study aims to examine the future climate projections in the Upper Indus Basin (UIB). The Global Climate Model (GFDL-ESM2M) data was utilized to analyze two variables, namely precipitation and temperatures. The study focused on three distinct time periods: near century (2020-2040), mid-century (2041-2070), and end of century (2071-2099). This process involved the utilization of a downscaling technique that relied on the RCP4.5 scenario. The Mann-Kendall (MK) and Sen\u27s slope estimate test will be employed to analyze the parameters of temperature and precipitation, enabling the identification of yearly, seasonal, and monthly patterns. The application of the MK and Sen\u27s slope estimate approaches revealed a lack of statistical significance in the observed upward trend in yearly precipitation and temperature. Over the course of nearly a century, the average Coefficient of Variation for temperature exhibited a range of -67.5% to 308.9%. During the midcentury period, there was observed variation in the mean monthly rainfall across all months. Notably, the month of March exhibited the highest average rainfall of 274.2mm, while September had the lowest average rainfall of 31.9mm. The data exhibited a positive skewness, suggesting that there was a tendency for higher levels of rainfall towards the end of each month compared to the beginning. The data indicates that there is an upward trend in precipitation throughout the mid-century period in comparison to the near century, but a downward trend is observed towards the conclusion of the century. The temperature readings exhibit a constant upward trend from the early part of the century to the middle of the century, followed by a subsequent increase from the middle of the century to the end of the century. Furthermore, the data revealed that the highest amount of precipitation is experienced during the spring season, whereas the lowest amount of rainfall is recorded during autumn throughout all temporal intervals
Urban Green Spaces and Subjective Well-being: Exploring the Impact on Overall Life Satisfaction Through ML Techniques
Get PDFThe existence of green infrastructure plays a pivotal role within an urban setting, actively contributing to various facets of life. Urban greenness has positive association between increased utilization and higher levels of life satisfaction. But Lahore, a city experiencing rapid growth, is facing a significant challenge as its expansion leads to a reduction in green infrastructure. This decline in green spaces raises serious concerns about the city\u27s long-term sustainability. Therefore, the study aimed to investigate the connection between urban green spaces and subjective well-being, specifically overall life satisfaction. In response to this challenge, this study employs advanced computer science algorithms, including Artificial Neural Networks (ANN), Convolutional Neural Networks (CNN), k-Nearest Neighbors (KNN), and Artificial Intelligence (AI), to investigate the connection between urban green spaces and subjective well-being, with a specific focus on overall life satisfaction. For this, primary data was collected an online survey and 1050 respondents were analyzed. The results found that the accessibility of urban green spaces within convenient distances and frequent visits to these areas play a vital role in human life satisfaction, the overall effect of urban green spaces on subjective well-being was found positive (beta = 0.781, R2 = 0.610, at p < 0.000). Therefore, it is concluded that UGSs in an accessible range are essential for high-level subjective well-being
Remote Sensing Assessment of Small Dam Sites in Swat District, Pakistan: Inferences from Water Resource Scenarios
Get PDFIn a world where water is indispensable, Pakistan grapples with the challenge of ensuring its availability. Freshwater demand from domestic, industrial, and agricultural uses has strained the country\u27s reservoirs. Financial and political barriers have hindered the construction of large dams, making it imperative to seek alternative solutions. However, small dams have the potential to address Pakistan\u27s water security concerns. This study uses advanced technology, engineering expertise, socioeconomic factors, and environmental awareness to find multi-purpose small dam sites in Swat District, Pakistan. Water storage and community and economic development are goals. This study examines criteria using RS and GIS. Dam site selection considers rainfall patterns, slopes, land use, soil types, and drainage density. The study uses Elevation Area Capacity (EAC) curves to view potential reservoirs. The map divides areas into High, Moderate, and Low suitability. This analysis yields some sites where R4 is impressive for its suitability and storage capacity of 358,237 at 2080 m. R1 and R2 are promising with moderate suitability and large storage capacities of 121,346 and 271,964, respectively. These sites are more than numbers on a map they represent local aspirations. Their benefits include electricity, flood protection, irrigation, and drinking water. Small dams are progress catalysts with low maintenance and political support. This study concludes that socioeconomic and environmental factors should be considered when engineering small dams. This small dam can store water and provide essential services to local communities and economies. These multi-purpose small dams advance water security
An Optimal Feature Extraction Technique for Glioma Tumor Detection from Brain MRI
Get PDFA brain tumor is defined by the uncontrolled proliferation of brain tissue cells, defying the typical cellular regulation mechanisms governing growth. The most significant challenge associated with brain tumors lies in their timely diagnosis and accurate stage determination. Accurate detection of tumors from MRI scans can not only assist doctors in their examination but also provide crucial information for appropriate and timely treatment decisions. In this paper, a comprehensive analysis is presented based on comparisons between state-of-the-art dimensionality reduction and classification algorithms. We used a dataset containing brain MRI scans, including both tumor and non-tumor cases, which was split into training and testing sets. After preprocessing the data, we implemented four feature extraction algorithms to obtain different sets of features. Consequently, these sets of features were used to train five classifiers to analyze the accuracy. Based on these results, optimal feature extraction and brain tumor classification technique is selected. The results indicate that the Linear Discriminant Analysis (LDA) technique extracted highly informative features, leading to an impressive accuracy of 92.84%. This highlights the effectiveness of LDA in significantly enhancing the performance of the brain tumor classification process, making it the prime choice for feature extraction that aligns seamlessly with the research\u27s intuition. It has higher accuracy with all the classifiers
Evolving Security Landscape of the Internet of Things: Assessing Advantages and Challenges
Get PDFIn light of the widespread integration of the Internet of Things (IoT), it is crucial for organizations to prioritize their attention towards establishing resilient system security. The presence of any vulnerability within a system has the potential to result in system failure or a cyberattack, hence causing significant repercussions on a wide scale. This encompasses a set of measures and protocols designed to safeguard against cyber threats that especially exploit vulnerabilities in physically interconnected IoT devices. The security teams responsible for managing IoT security are currently facing a range of challenges, including but not limited to inventory management, operational complexities, variety in IoT devices, ownership concerns, increasing data volumes, and emerging threats. This review provides a critical analysis of the existing body of research pertaining to the subject of security in the context of the IoT. The focus is mostly on the present state of affairs, practical implementations, and the issues that are associated with this domain. Moreover, it delves into the prospective prospects and opportunities that are anticipated in this particular domain. Lately, there has been a noticeable surge in interest among scholars hailing from diverse academic disciplines and geographical locations, all focusing on the improvement of internet network security. The assurance of data integrity, confidentiality, authentication, and authorization is imperative in light of the substantial volume of data that traverses network devices. Nevertheless, the field of IoT security exhibits significant potential for further development. The IoT has become a popular technology paradigm that facilitates the integration of diverse objects and systems. Yet, the extensive use of the IoT has generated apprehensions regarding security, specifically pertaining to the safeguarding of data and the integrity of networks