International Journal of Innovations in Science & Technology
Not a member yet
813 research outputs found
Sort by
Elevating Group Recommendations and Collective Decisions Through Prioritized User Activities in Groups
Get PDFGroup modeling encompasses various areas of interest, including recommendations, movie watching, exercise performance, and the formation of social media groups with similar interests. Similarly, the GRS has numerous practical applications, such as books, movies, and television program recommendations. Various collaborative techniques, such as Least Misery, Average Voting, and Most Pleasure, to name a few, have been employed to enhance group recommendations. However, these methods are not without limitations, often introducing biases and yielding irrelevant suggestions. For example, group of people watching television, the active user having a remote control is paramount. Active user(s), who engage in activities like channel switching, rating, expressing preferences, and commenting, should hold significant influence. This study proposed and integrates active user engagement and feedback into the recommendation process, by considering user activities as feedback. The proposed system employs a filtering mechanism that emphasizes the user’s activities, facilitating the prediction of relevant suggestions to group users. The experiments utilized the well-established benchmark dataset Movie Lens. The effectiveness of the proposed approach is evaluated using standard metrics such as precision, recall, and F-score. The results show that recommending active items to actively engaged user(s) significantly benefits most of the group users, yielding an improved suggestion. This study may help practitioners to build more robust recommender systems for groups
A Machine Learning Prediction of Mechanical Properties in Reinforcement Bars: A Data-Driven Approach
No full textIntroduction/Importance of Study: This study addresses the pressing need for precise prediction of mechanical properties in steel reinforcement bars (rebars) through a data-driven approach utilizing machine learning techniques.
Novelty statement: Our research provides a solution to the challenge of predicting mechanical properties in rebars using advanced machine learning algorithms, filling a critical gap in existing methodologies.
Material and Method: Our study utilized a meticulously curated dataset comprising over 10,300 samples of diverse rebar types manufactured through industrial methods. We leveraged the latest PyCaret model to integrate machine learning algorithms, with a focus on training and rigorously testing linear regression models. Data preprocessing involved thorough cleaning using Python libraries such as Pandas and NumPy, supplemented by cross-validation techniques to ensure robust model generalization.
Result and Discussion: The core findings of our study revolve around the linear regression model algorithm trained within the machine learning framework, enabling precise determination of key mechanical properties including Yield Strength (YS) and ultimate Tensile Strength (UTS). Additionally, we explored the Ratio of UTS to YS (UTS/YS) as a critical mechanical property, incorporating essential input features such as weight percent of carbon (C), manganese (Mn), silicon (Si), carbon equivalent (Ceq), quenching parameters (Q), and diameter (d).
Concluding Remarks: Our research offers valuable insights into the application of machine learning for the precise prediction of mechanical properties in reinforcement bars, contributing to enhanced quality control and optimization in the steel manufacturing industry
Alex Net-Based Speech Emotion Recognition Using 3D Mel-Spectrograms
Get PDFSpeech Emotion Recognition (SER) is considered a challenging task in the domain of Human-Computer Interaction (HCI) due to the complex nature of audio signals. To overcome this challenge, we devised a novel method to fine-tune Convolutional Neural Networks (CNNs) for accurate recognition of speech emotion. This research utilized the spectrogram representation of audio signals as input to train a modified Alex Net model capable of processing signals of varying lengths. The IEMOCAP dataset was utilized to identify multiple emotional states such as happy, sad, angry, and neutral from the speech. The audio signal was preprocessed to extract a 3D spectrogram that represents time, frequencies, and color amplitudes as key features. The output of the modified Alex Net model is a 256-dimensional vector. The model achieved adequate accuracy, highlighting the effectiveness of CNNs and 3D Mel-Spectrograms in achieving precise and efficient speech emotion recognition, thus paving the way for significant advancements in this domain
Home Automation Using Internet of Things and Machine Learning
Get PDFThis paper proposes an energy-efficient home automation system leveraging the Internet of Things (IoT) and machine learning. The system, implemented in Python on a Raspberry Pi, enables remote control of appliances (lights, televisions, air conditioners) via a web interface accessible from any local network device. Machine learning is introduced in the second phase, utilizing linear regression to automate appliance management based on historical data stored in a database. This work demonstrates the feasibility of IoT and machine learning for cost-effective and efficient home automation, laying the groundwork for the future development of database-driven smart homes with advanced machine learning algorithms
Beyond CNNs: Encoded Context for Image Inpainting with LSTMs and Pixel CNNs
Get PDF
ur paper presents some creative advancements in the image in-painting techniques for small, simple images for example from the CIFAR10 dataset. This study primarily targeted on improving the performance of the context encoders through the utilization of several major training methods on Generative Adversarial Networks (GANs). To achieve this, we upscaled the network Wasserstein GAN (WGAN) and compared the discriminators and encoders with the current state-of-the-art models, alongside standard Convolutional Neural Network (CNN) architectures. Side by side to this, we also explored methods of Latent Variable Models and developed several different models, namely Pixel CNN, Row Long Short Term Memory (LSTM), and Diagonal Bidirectional Long Short-Term Memory (BiLSTM). Moreover, we proposed a model based on the Pixel CNN architectures and developed a faster yet easy approach called Row-wise Flat Pixel LSTM. Our experiments demonstrate that the proposed models generate high-quality images on CIFAR10 while conforming the L2 loss and visual quality measurement
A Comparative Analysis of BER Performance for NOMA in the Presence of Rayleigh Fading and Impulse Noise
Get PDFImportance of Study: This research investigates the integration of wired and wireless communication in Smart Grid (SG) systems, addressing the challenges posed by impulse noise and the increasing demand for bandwidth.
Novelty statement: The study explores the impact of impulse noise models on Non-Orthogonal Multiple Access (NOMA) performance within fading environments, offering insights into optimizing bandwidth utilization in multi-user SG communication.
Material and Method: Numerical simulations validate the derived closed form of the bit error rate (BER) equation, utilizing a NOMA downlink system. The performance parameters for assessing the effects of impulse noise in a Rayleigh fading channel include instantaneous signal-to-noise ratio (SNR), bit error rate, disturbance ratio, and the trade-off between spectral efficiency and energy efficiency.
Result and Discussion: The research reveals that NOMA demonstrates promising performance in SG communication despite the presence of impulse noise, with BER decreasing rapidly with increasing signal-to-noise ratio (SNR). The study highlights a performance trade-off between impulse noise and fading, emphasizing the importance of accurate SNR levels for power allocation in NOMA systems.
Concluding Remarks: This study contributes novel insights into the robustness of NOMA under realistic SG conditions, offering valuable implications for enhancing reliability and efficiency in SG communication infrastructure
Osteochondroma Identification Through Transfer Learning and Convolutional Neural Networks
Get PDFAccurate and timely diagnosis of musculoskeletal conditions like osteochondroma is pivotal in ensuring effective treatment and improved patient outcomes. However, traditional diagnostic methods relying on manual interpretation of medical images can be susceptible to human errors, potentially leading to misdiagnosis or delayed detection. Previous studies have explored Deep Learning (DL) techniques for automated disease detection, but they often face challenges such as limited dataset availability and generalization capabilities across diverse imaging modalities. This research addresses these gaps by proposing a robust Convolutional Neural Network (CNN) framework for osteochondroma identification, leveraging transfer learning and data augmentation techniques. The ResNet-50 architecture, pre-trained on a large dataset, is fine-tuned with dense layers and an output layer for binary classification. Extensive data pre-processing and offline augmentation strategies enhance model performance and generalizability. The proposed model achieves an impressive 97.67% accuracy on the test dataset, demonstrating its effectiveness in distinguishing between normal and osteochondroma cases. Furthermore, its generalizability is validated by training and testing on the publicly available Potato Leaf Disease dataset, showcasing consistent performance in multi-class classification scenarios. While the model exhibits promising results, future work could explore integrating more extensive and diverse datasets and investigating advanced architectures for improved accuracy and computational efficiency. The implications of this research extend to empowering medical practitioners with accurate and swift osteochondroma diagnostics, ultimately contributing to enhanced patient care in orthopaedics
AI-Driven Weed Classification for Improved Cotton Farming in Sindh, Pakistan
Get PDFThis research study proclaims the combination of artificial intelligence and also IoT in precision agriculture, highlighting weed discovery plus cotton plant monitoring in Sindh, Pakistan. The uniqueness lies in creating a deep learning-based computer system vision application to develop a durable real-time weed category system, dealing with a problem not formerly solved. The study entailed gathering datasets utilizing mobile cams under varied ecological problems. A CNN version was educated utilizing the open-source Cotton Weeds dataset, annotated with clinical problems such as Broadleaf and Horse Purslane. Examinations used a Wireless Visual Sensor Network (WVSN) with Raspberry Pi for real-time photo catching as well as category. The CNN version, readjusted to identify in between cotton along with Horse Purslane weed accomplished a precision of 86% and also an ROC AUC rating of 0.93. Efficiency metrics consisting of precision-recall, as well as F1 rating, suggest the model\u27s viability for various other weed category jobs. Nonetheless, obstacles such as photo top-quality variants and also equipment constraints were kept in mind. The research ends that using artificial intelligence as well as IoT in farming can dramatically improve plant return plus assist lasting methods for future generations
Comparative Assessment of Object-based and Pixel-based Approaches for Crop Cover Classification
Get PDFIntroduction/Importance of Study: Accurate crop identification and classification are crucial for effective agro-based planning and ensuring food availability. Reliable classification helps optimize agricultural productivity and resource management.
Novelty Statement: This study innovatively compares pixel-based and object-based approaches for machine learning-oriented classification methods to develop crop-type maps in Rahim Yar Khan, Pakistan.
Material and Method: Utilizing the Google Earth Engine (GEE) cloud computing platform, pre-processing steps were applied to Synthetic Aperture Radar Sentinel-1 and Sentinel-2 data. Integration of Sentinel-1 (VV, VH) and Sentinel-2 satellite bands enabled the computation of various indices and the production of composite images for subsequent analysis. The primary objective was to evaluate the effectiveness of these approaches in classifying major crops: cotton, rice, and sugarcane. Time-specific images were employed to leverage crop seasonality; for instance, an August composite image was prioritized for cotton, while September composites were used for rice and sugarcane classification. The study utilized two object-based segmentation approaches: Simple Non-Iterative Clustering (SNIC) on the GEE platform and Object-Based Image Analysis (OBIA) using Multi-Resolution Segmentation in E-Cognition software. The Random Forest (RF) machine learning algorithm was applied to both pixel-based and object-based approaches. Field sample data, including cotton, rice, sugarcane, orchards, and other crops, were used for classification, validation, and accuracy assessment. A comparative analysis was conducted to evaluate the performance of pixel-based and object-based methods.
Result and Discussion: The RF algorithm applied to pixel-based approaches using Sentinel-1 and Sentinel-2 imagery bands with composite indices demonstrated superior results. The pixel-based RF classification achieved 98% accuracy with a kappa coefficient of 92%. In comparison, RF applied to SNIC in GEE achieved 96% accuracy with a kappa coefficient of 95%, while OBIA in E-Cognition attained an accuracy of 89%.
Concluding Remarks: The study concludes that tuning the segmentation parameters in both E-Cognition and SNIC algorithms can enhance the accuracy of object-based classification
Ecotourism Potential Assessment for District Lower Chitral-Pakistan Using Integration of GIS and Remote Sensing
Get PDFEcotourism is a sustainable and responsible tourism approach that emphasizes the protection of natural ecosystems while offering visitors immersive experiences. This study evaluates the ecotourism potential of District Lower Chitral, Pakistan, using an integrated approach that combines Geographic Information Systems (GIS) and Remote Sensing technologies. Planning for ecotourism development is a multi-criteria process that often involves spatial analysis. A Multi-Criteria Decision Analysis (MCDA) model was employed to assess ecotourism suitability in District Lower Chitral. Eighteen variables, selected based on local knowledge and expert opinion, were considered, encompassing natural beauty, infrastructure, and physical parameters of the area. The study\u27s results indicate that the majority of the study area has a moderate potential for ecotourism, covering 3,141.026 km² (51.33%) of the total area. Additionally, 103.3733 km² (1.69%) was classified as "Very Highly" suitable for ecotourism, and 1,750 km² (26.61%) was deemed "Highly" suitable. Areas classified as having low suitability measured 1,118.666 km² (18.28%), while the very low suitability category covered the smallest proportion, with 5.645 km² (0.09%)