As tools for developing, distributing, tracking, and managing a variety of training and educational materials online, Learning Management Systems (LMS) have become increasingly popular as tools for developing, distributing, tracking, and managing a variety of types of training and educational materials online. The evolution of Learning Management Systems (LMSs) has been dramatic since they were introduced in the 1990s. They have emerged as powerful applications for managing curricula, providing rich content courseware, assessing and evaluating student performance, and facilitating dynamic collaboration between educators and students. We can expect many changes in the structure, the functionalities, and the implementation of the learning management system in the near future as a result of a number of research fields exploring various technologies related to the learning management system. Our daily lives will be impacted by a wide variety of aspects as a result of the Internet of Things (IoT), as we move forward. There are several components to a learning management system that can be enhanced with the use of IoT capabilities that are discussed throughout this paper. In addition to its impact on many aspects of the learning management system, the Internet of Things will also bring to the learning management system a number of enhancements and changes that are expected to enhance the functionality of the system. An IoT-enhanced learning management system is one of the outcomes of a three-year research project that Arts, Science, and Technology University (AUL) is conducting as part of its Distance Learning program. It is intended to provide a brief overview of the project and the implementation plan for each component along with a description of the anticipated effects and the benefits that are anticipated to be derived from it. Locating objects in images and videos is one of the most fundamental and challenging tasks. Object classification, counting of objects, and object monitoring have received much attention in recent years. An in-depth literature review focusing on object detection is presented here.
Read MoreDoi: https://doi.org/10.54216/JISIoT.100101
Vol. 10 Issue. 1 PP. 08-20, (2023)
The security and privacy fields and multimedia biometrics have been widely used today for personal authentication. Sclera and Palm-print of humans are one of the fastest, accurate, reliable, and secure biometric techniques for identification and verification based on unique features. The majority of the biometric systems are based on the global features, which may lead to weak performance in cases of poor-quality biometric images, therefore, swarm intelligence techniques are used to improve recognition accuracy, reliability, and quickness. In this paper, an enhancement shark smell optimization (ESSO) is proposed to build an efficient hybrid identification system depend on the sclera and palm-print images. The SIFT algorithm used to extract features from the biometric images. The optimal key-points from this feature are obtained using ESSO and chaotic map, and finally, generation digital signature using a 256-MD5 algorithm for each user. The Package of the NIST tests proves that the generated keys are random, unpredictable, uncorrelated, and robust against different kinds of attacks.
Read MoreDoi: https://doi.org/10.54216/JISIoT.100102
Vol. 10 Issue. 1 PP. 21-32, (2023)
Image watermarking preserves digital content. This study introduces a new watermarking approach employing Sub-Band Discrete Cosine Transform and Deep neural networks, GRNN and CNN. The method embeds robust, invisible watermarks in greyscale photos and compares the two neural network topologies. The watermark is added using sub-band DCT. Watermark embedding in low-frequency sub-bands resists photo processing. The binary watermark modifies sub-band DCT coefficients to determine embedding intensity, resisting signal deterioration, and assaults. GRNN and CNN neural networks extract watermarks accurately. CNN extracts hierarchical features from images, enabling robust watermark recovery even under distortions, whereas non-parametric GRNN stores the whole training data to create predictions. The watermarking approach is tested on several greyscale photos. PSNR, SSIM, MSE, and NCC measure performance. The watermark tests noise addition, compression, and filtering. Compare GRNN and CNN's watermark extraction strengths and shortcomings to assess image watermarking suitability.
Read MoreDoi: https://doi.org/10.54216/JISIoT.100103
Vol. 10 Issue. 1 PP. 33-47, (2023)
The "climate in the weather" (CW) approach, which combines the scientific and everyday sense of climate, has been proposed. The CW is based on the in-depth idea of E. E. Fedorov to classify regional climates as an ensemble of daily weather states. We have transformed this idea into a nonparametric method of processing meteorological series, where each member of the series is mapped to quantiles of corresponding distributions, and then new time series are formed, where meteorological variables are replaced by their quantiles. Next, the members of the new quantized series are combined in weather states. In this work, by using quantiles combination of monthly temperature and precipitation, we construct four CW states - "cold and dry", "cold and rainy", "warm and rainy", "warm and dry". Then we demonstrate the possibility of the CW approach to analyze space-time climate similarity and climate change in the Mesopotamian River system. The application of 16 CW states is also discussed. The climate change dynamical assessment (CCDA) showed that the Euphrates (Tigris) tributaries values varied from 13 to 19% (13-25%) with a clear increase in Greater Zab, Lesser Zab, Adhaim, and Dyala basins. The analysis of CW-altered states demonstrated that climate change is occurred due to an increase in temperature, a decrease in precipitation, and mixed changes simultaneously. In each of the basins, there were a different number of such changes. The "climate in weather" approach developed can be used for processing multidimensional meteorological time series data and outlining the general conception of the regional climate.
Read MoreDoi: https://doi.org/10.54216/JISIoT.100104
Vol. 10 Issue. 1 PP. 48-65, (2023)
In this research, we employed a deep convolutional neural network, often known as a Deep CNN, to propose a novel approach to the detection of illnesses in the leaves of plants. In order to train the Deep CNN model, a dataset that is already accessible is employed. This dataset contains photographs of the leaves of 39 distinct plant species. Six different methods of data augmentation were utilized, including image inversion, gamma correction, noise injection, principal component analysis (PCA), color enhancement, rotation, and scaling. We came to the conclusion that adding more data to a model can improve its accuracy. The proposed model was trained using many epochs, batch sizes, and dropout percentages over the course of its development. When utilizing validation data, the suggested model performs better than methods of transfer learning that are commonly utilized. Extensive simulations demonstrate that the proposed model is capable of an astounding 83.12% accuracy in data classification. The proposed research is more accurate than the many machine learning technologies that are currently in use. In addition to that, we put the suggested model through our consistency and reliability testing.
Read MoreDoi: https://doi.org/10.54216/JISIoT.100105
Vol. 10 Issue. 1 PP. 66-75, (2023)
The rapid proliferation of the Internet of Things (IoT) has paved the way for transformative innovations, and this paper explores its profound impact on the realm of elderly care within smart homes. We present a pioneering IoT-based approach for human activity recognition, addressing the critical need for accurate and non-intrusive monitoring of elderly individuals. Our IoT-based approach begins with data preprocessing, where raw sensor data is refined using median filtering, reducing noise and ensuring high-quality inputs for our model. We apply the "series_to_supervised" transformation to convert the sensor data into a supervised learning format, which is critical for training the GRU-based activity recognition model. The heart of our approach lies in the federated distillation-based training strategy. Edge devices within the IoT network locally train their GRU models using their datasets while sharing knowledge with a central server and other edge devices. Knowledge distillation further enhances the model's performance by transferring knowledge from the global model to the edge devices. Experimental analysis demonstrated an impressive accuracy of 95% and an F1-score of 0.94, Our system excels in recognizing and classifying a wide range of human activities, from daily routines to emergencies.
Read MoreDoi: https://doi.org/10.54216/JISIoT.100106
Vol. 10 Issue. 1 PP. 76-83, (2023)