International Journal of Innovations in Science & Technology
Not a member yet
813 research outputs found
Sort by
Stereo Vision Based Navigation of Four-Legged Robot Through Unknown Terrain
Get PDFThis research aims to develop a stereo vision-based navigation system for a quadruped robot, enabling it to move autonomously through rough, unfamiliar terrain and detect blockages in sewer pipelines. The robot uses a stereo camera to capture images, which are then processed to create disparity maps and 3D point clouds. These tools help the robot identify and avoid obstacles. Image rectification and 3D mapping are performed using OpenCV, which generates an occupancy grid to distinguish between free and occupied spaces. Based on this grid, the A* algorithm is used to plan the robot\u27s path. To ensure smooth movement, inverse kinematics calculates the required motor angles and applies predefined Bezier curves for stable locomotion
Mobile Legends Win Rate Prediction and Team Recommendation Using Switched Hero Roles
Get PDFMobile Legends Bang Bang (MLBB) falls under the category of a Multi Online Battle Arena game. Games like MLBB require players to have strong skills and strategic gameplay; team composition is an important factor influencing the chances of winning the game. Although there is data currently available for MLBB, two aspects of this game that remain unexplored include: i) win rate prediction using nontraditional roles in heroes, and ii) team composition with switched hero roles. While picking heroes for each team, a team chooses heroes that they know perform well using a traditional role. However, nothing has been mentioned as to what happens when heroes are selected using a nontraditional role. This research aims to address this question by predicting the win rate of heroes with switched roles. This unpredictability will lead to the formation of a team that can have a significant advantage over the enemy team thus leading to victory. The dataset for this study was formulated by focusing on 67 heroes in the game. The win rates were generated with real-time simulations where the ally team members remained unchanged to avoid biased results. Using two model-building approaches, win rate predictions were made using 12 regression algorithms under 5 feature selection settings. The research has shown that LightGBM with AdaBoost as the base estimator provides better results and was used to formulate 5 teams. A recommendation system was designed to optimize team composition from the win rate prediction analysis. To validate the results, we simulated 50 matches with each team, with ally team players remaining the same to avoid biased results. This resulted in a 94% win rate with 47 wins and 3 losses out of a total of 50 matches
Comparative Analysis of Machine Learning Models for Lung Cancer Detection Using CT Scan Images
Get PDFThe CT scan provides useful information but has limitations in detecting subtle patterns. Machine learning models enhance cancer detection by extracting features, reducing errors, and enabling early-stage diagnosis. Unlike earlier studies that focused on single models, this paper compares three models: CNN, RF, and SVM. A total of 995 CT images were resized to 128x128 pixels, representing both healthy individuals and patients across the full range of lung cancer types. Using a feature hierarchy, CNN achieved a 96% validation accuracy, and RF reached 95%, showing robustness. However, SVM with an RBF kernel optimization outperformed the others, achieving over 98% accuracy with superior alignment of hyperplanes, particularly in detecting fine malignant patterns. The key metrics used in this study were sensitivity, specificity, and AUC, all of which showed a low false positive rate for early lung cancer detection, bridging theoretical accuracy and clinical practicality. Data volume and processing resources remain significant challenges for applying machine learning in early lung cancer diagnosis. To address these issues, we suggest hybrid architectures (e.g., CNN-SVM) that combine hierarchical feature learning and hyperplane optimization. These findings could pave the way for AI-based clinical approaches, improving patient diagnosis and treatment.
Building Robust Context Aware IoT Applications: Methods and Strategies for Detecting and Resolving Context Inconsistencies
Get PDFThe Internet of Things (IoT) has revolutionized connectivity, creating a vast network of interconnected devices that seamlessly exchange and analyze data. Within this dynamic IoT ecosystem, context-aware applications have emerged, enabling autonomous responses to events triggered by contextual information, thereby enhancing user experiences and facilitating intelligent decision-making. However, the utilization of contextual data in IoT applications has introduced a key challenge: context inconsistencies. Context inconsistency is defined as the condition in which contextual data collected from multiple sources is inaccurate, incomplete, or conflicting, leading to incorrect processing that may disrupt the behavior of context-aware applications. Context inconsistencies arise from various factors, including sensor noise, communication errors, and contradictory data sources (e.g., two motion detection sensors located in the same area may report different readings, where one sensor detects one person, and the other sensor detects three people). These inconsistencies can significantly impact the reliability and precision of IoT applications, potentially resulting in erroneous decisions and degraded user experiences. To address this critical concern, this research paper undertakes a comprehensive review of contemporary methodologies developed for detecting and resolving context inconsistencies in IoT environments. This study explores various strategies, discusses their features in detail, and contributes by classifying them into different categories for better understanding. Through a detailed examination of the effectiveness, strengths, and limitations of each classified method, the paper aims to offer valuable insights into managing context inconsistencies in IoT applications. More precisely, this paper serves as a valuable resource for researchers, practitioners, and industry professionals in the IoT domain, providing them with a comprehensive understanding of context inconsistency detection and resolution methods
Object Detection in High Resolution Aerial Imagery Using Detection Transformer
Get PDFObject detection in high-resolution aerial imagery has received much attention nowadays due to its applications in geosciences, urban planning, disaster management, and surveil- lance. However, there exist challenges such as scale variation, cluttered backgrounds, occlusions, and less annotated datasets. Traditional CNNs have shown great promise, yet they fail to detect long-distance dependencies and complicated spatial relationships. This paper evaluates the function of DETR for object detection in aerial images. Unlike CNN-based detectors that depend on region proposal networks and anchor-based methods, DETR depends on a full end-to-end transformer architecture along with a direct set prediction method that removes the requirement for hand-designed priors. With extensive experiments carried out on datasets like Airbus Aircraft, Rare Planes, and DOTA, observations show that DETR performs better with mAP scores that are as much as 18% higher than ResNet-based architectures. Fur- Furthermore, we propose a hybrid model that is DETR-CNN, which partners both the strength of feature extraction from CNNs and the global attention mechanisms in DETR, thereby improving the accuracy of detection on both Horizontal and Oriented Bounding Box detections. Our results show that transformer-based models are most effective in aerial object detection, which bodes well for remote sensing, autonomous surveillance, and disaster response applications. This study presents an end-to-end DETR-based method for object detection in aerial imagery, demonstrating improvements in accuracy and simplicity over traditional methods
Improved Improved Millimeter Wave Patch Antenna for Next-Generation and Beyond Networks
No full textThis paper presents an optimization of a compact, ultra-wideband (UWB) rectangular microstrip patch antenna (MSPA), tailored for next-generation mm-wave wireless applications. The proposed UWB antenna offers significant enhancements in gain and bandwidth. It achieves an impressive bandwidth of 36 GHz, covering the V-band (40–75 GHz), essential for high-capacity satellite communication, as well as the 61.25GHz ISM band and most of the 60GHz WiGig band. Simulations performed using CST MW Studio 2021 demonstrate that the antenna achieves a maximum efficiency of 93.3% at 44.2 GHz and a minimum efficiency of 63.1% at 66.2 GHz. A maximum realized gain is 10.2 dB at 55.8 GHz, with the lowest realized gain being 4 dB at 65 GHz. These results underscore the antenna\u27s suitability for future 5G handheld devices and other high-frequency applications. Comparative analysis with existing designs is provided, highlighting the proposed antenna’s superior performance metrics
Enhanced Trapezoidal Modulation in MMC: Comparative Analysis with Traditional Modulation Methods
Get PDFHVDC transmission and renewable energy systems extensively use Modular Multilevel Converters (MMC) because they provide outstanding scalability and modular architectural features. The performance quality of MMCs depends predominantly on which modulation technique engineers implement. This work studies Nearest Level Modulation (NLM) and conventional Trapezoidal Modulation alongside an enhanced Trapezoidal Modulation method to identify the top choice for high-voltage power implementations. The main goal of this research is to optimize modulation techniques for improving MMC harmonic performance and switching efficiency. Each modulation strategy is simulated through MATLAB/Simulink-based testing under identical operating situations. Product testing indicates NLM shows lower switching losses as well as superior power distribution efficiency but the updated Trapezoidal Modulation design combines reduced THD performance with simple implementation methods. The method\u27s innovative aspect depends on the modified trapezoidal waveform synthesis from a fundamental-frequency triangular signal enabling simplified implementation as well as lower THD and avoiding the need for high switching frequencies used in conventional approaches. The research delivers critical knowledge about MMC modulation selection which systems designers and manufacturers can use to optimize converter operation based on specific applications
A Compact Slotted Micro-Strip Patch Antenna Operating at 28 GHz for 5 G-IoT Applications
Get PDFThis paper aims to present a compact slotted microstrip patch antenna for 5 G-IoT applications operating at a 28 GHz frequency. The antenna structure is modeled on an FR4 substrate with a compact size of 12 mm × 13 mm (substrate height = 1.6 mm, Epsilon = 4.3, and loss tangent = 0.02). The antenna comprises a patch on top of a dielectric substrate and a defected ground plane (DGS) on the bottom side. Slots and curves are incorporated in the patch radiator to achieve the desired resonating frequency of 28 GHz. Simulation results demonstrate a return loss of –22 dB, a bandwidth of 4.64 GHz, a VSWR of 1.16, a gain of 3.2 dBi, and an efficiency of 60%. These attributes make the antenna appropriate for a range of 5 G-IoT applications, including smart cities, industrial IoT, and autonomous systems where high data throughput and reliable connectivity are essential. The overall results depict that the proposed design is a good candidate for deployment in 5 G-enabled IoT ecosystems
Enhancing Students’ Learning Outcomes Using Gamification
Get PDFGamification has emerged as a promising strategy to improve student engagement, motivation, and academic performance. This study investigates the impact of gamification on second-grade mathematics learning by comparing traditional teaching methods with a gamified approach using the Matific.com platform. Employing a quasi-experimental design, the study involved 40 students divided into control and experimental groups, with data collected through pre- and post-tests and motivation surveys. Statistical analysis revealed that students exposed to gamified learning demonstrated significantly higher academic performance and motivation levels compared to those taught through conventional methods. The results indicate that gamification not only enhances cognitive outcomes but also fosters emotional engagement, suggesting its potential as a scalable and effective tool in early-grade education. This research contributes practical insights for educators and policymakers seeking to integrate innovative methods into traditional classrooms, especially within underperforming education systems like Pakistan’s
Investigating The Impact of Perovskite Layer Thickness Variation on The Performance of Perovskite Solar Cells
Get PDFThe present risk of the depletion of the non-renewable sources of energy at an alarming rate has encouraged man to lookup for new ways to produce power and move towards "Renewable Energy Resources". One major source of energy is the heat and intensity from the Sunlight using the Perovskite Solar Cells. This technology has captured extensive attention worldwide in previous few years due to its high efficiency, fast development, low-cost and easy manufacturing process. In this research, the thickness variation of different types of perovskite layers and their impacts on the functioning of the perovskite solar cells have been explored using SCAPS software. The absorption coefficient of semiconducting material is exponentially related to the thickness, so if absorption coefficient is high, lesser thickness can absorb more light. But to avoid the excessive resistance and to lessen the production cost, the thickness should be in the range of the depletion region width. Much smaller thickness yields weak static electric fields in the depletion region. The designs of different perovskite solar cell structures will be simulated and their effects will be critically analyzed in order to have detailed study