Search

The COVID-19 pandemic precipitated an abrupt transition to online learning, impacting students with disabilities uniquely. This study examines the experiences of 62 such students in the new educational paradigm, employing a mixed-methods approach. Quantitative data were collected through surveys and questionnaires to assess privacy and security concerns arising from online learning tools. Qualitative insights were gathered via interviews and focus groups, revealing that while students appreciate the flexibility of online learning, they express a critical need for enhanced guidance and support. Neurodiverse students, in particular, emphasized the necessity of a secure online environment. Addressing these challenges, our research integrates blockchain and machine learning technologies to enhance biometric authentication. Specifically, the Highly Secure Blockchain-Based Compressive Sensing (HSBCS) system is proposed, ensuring data integrity and improving accessibility for Personal Records. Preliminary testing of the HSBCS system showed promising results, with an average accuracy rate of 95% in biometric authentication among visually impaired students. Moreover, participants reported a 30% increase in perceived security and ease of access to their Personal Records compared to traditional authentication methods. These findings underscore the potential of integrating advanced technologies to meet the unique educational needs of students with disabilities while enhancing data security and accessibility in online learning environments.

An autonomous, power-assisted Turtlebot is presented in this paper in order to enhance human mobility. The turtlebot moves from its initial position to its final position at a predetermined speed and acceleration. We propose an intelligent navigation system that relies solely on individual instructions. When there is no individual present, the Turtlebot remains stationary. Turtlebot utilizes a rotating Kinect sensor in order to perceive its path. Various angles were examined in order to demonstrate the effectiveness of the system in experiments conducted on a U-shaped experimental pathway. The Turtlebot was used as an experimental device during these trials. Based on the U-shaped path, deviations from different angles were measured to evaluate its performance. SLAM (Simultaneous Localization and Mapping) experiments were also explored. We divided the SLAM problem into components and implemented the Kalman filter on the experimental path to address it. The Kalman filter focused on localization and mapping challenges, utilizing mathematical processes considering both the system's knowledge and the measurement tool. This approach allowed us to achieve the most accurate system state estimation possible. The significance of this work extends beyond the immediate application, as it lays the groundwork for advancements in wheelchair navigation research by Dynamic Control. The experiments conducted on a U-shaped pathway not only validate the efficacy of our algorithm but also provide valuable insights into the intricacies of navigating in both forward and reverse directions. These insights are pivotal for refining the navigation algorithm, ultimately contributing to the development of more robust and user-friendly systems for individuals with mobility challenges. The data used for this purpose included actuator input, vehicle location, robot movement sensors, and sensor readings representing the world state. The study provides a strong foundation for future wheelchair navigation research by Dynamic Control. Consequently, we found that navigating the Turtlebot in the reverse direction resulted in a 5%–6% increase in diversion compared to forward navigation, providing valuable insight into further improvement of the navigation algorithm.

This paper presents a pansharpening technique based on the non-subsampled contourlet transform (NSCT) and convolutional autoencoder (CAE). NSCT is exceptionally proficient at presenting orientation information and capturing the internal geometry of objects. First, it’s used to decompose the multispectral (MS) and panchromatic (PAN) images into high-frequency and low-frequency components using the same number of decomposition levels. Second, a CAE network is trained to generate original low-frequency PAN images from their spatially degraded versions. Low-resolution multispectral images are then fed into the trained convolutional autoencoder network to generate estimated high-resolution multispectral images. Third, another CAE network is trained to generate original high-frequency PAN images from their spatially degraded versions. The result of low-pass CAE is fed to the trained high-pass CAE to generate estimated high-resolution multispectral images. The final pan-sharpened image is accomplished by injecting the detailed map of the spectral bands into the corresponding estimated high-resolution multispectral bands. The proposed method is tested on QuickBird datasets and compared with some existing pan-sharpening techniques. Objective and subjective results demonstrate the efficiency of the proposed method.

Abstract Remote sensing image fusion plays important roles in numerous applications, including monitoring, metrology, and agriculture. Image fusion gathers essential information from several image sources and consolidates them into a single image called a fused image. The fused image involves relevant data, and it is more informative than any other images extracted from one source. This study proposed a pansharpening technique based on image filtering utilising a bilateral filter to generate high‐frequency details from panchromatic image. The various types of side window guided filters are employed to enhance the multispectral band from panchromatic image and then used these filters to adjust spatial data misfortune that happens when images are combined. Experimental results demonstrated that the proposed method provides consistent results concise with reported by the previous research in terms of subjective and objective assessments on remote sensing data.

COVID-19 detection from medical imaging is a difficult challenge that has piqued the interest of experts worldwide. Chest X-rays and computed tomography (CT) scanning are the essential imaging modalities for diagnosing COVID-19. All researchers focus their efforts on developing viable methods and rapid treatment procedures for this pandemic. Fast and accurate automated detection approaches have been devised to alleviate the need for medical professionals. Deep Learning (DL) technologies have successfully recognized COVID-19 situations. This paper proposes a developed set of nine deep learning models for diagnosing COVID-19 based on transfer learning and implementation in a novel architecture (SEL-COVIDNET). We include a global average pooling layer, flattening, and two dense layers that are fully connected. The model’s effectiveness is evaluated using balanced and unbalanced COVID-19 radiography datasets. After that, our model’s performance is analyzed using six evaluation measures: accuracy, sensitivity, specificity, precision, F1-score, and Matthew’s correlation coefficient (MCC). Experiments demonstrated that the proposed SEL-COVIDNET with tuned DenseNet121, InceptionResNetV2, and MobileNetV3Large models outperformed the results of comparative SOTA for multi-class classification (COVID-19 vs. No-finding vs. Pneumonia) in terms of accuracy (98.52%), specificity (98.5%), sensitivity (98.5%), precision (98.7%), F1-score (98.7%), and MCC (97.5%). For the COVID-19 vs. No-finding classification, our method had an accuracy of 99.77%, a specificity of 99.85%, a sensitivity of 99.85%, a precision of 99.55%, an F1-score of 99.7%, and an MCC of 99.4%. The proposed model offers an accurate approach for detecting COVID-19 patients, which aids in the containment of the COVID-19 pandemic.

The rapidly growing number of COVID-19 infected and death cases has had a catastrophic worldwide impact. As a case study, the total number of death cases in Algeria is over two thousand people (increased with time), which drives us to search its possible trend for early warning and control. In this paper, the proposed model for making a time-series forecast for daily and total infected cases, death cases, and recovered cases for the countrywide Algeria COVID-19 dataset is a two-layer dropout gated recurrent unit (TDGRU). Four performance parameters were used to assess the model’s performance: mean absolute error (MAE), root mean squared error (RMSE), R2, and mean absolute percentage error (MAPE). The results generated with TDGRU are compared with actual numbers as well as predictions with conventional time-series techniques, such as autoregressive integrated moving average (ARIMA), machine learning model of linear regression (LR), and the time series-based deep learning method of long short-term memory (LSTM). The experiment results on different time horizons show that the TDGRU model outperforms the other forecasting methods that deliver correct predictions with lower prediction errors. Furthermore, since this TDGRU is based on a relatively simpler architecture than the LSTM, in comparison to LSTM-based models, it features a significantly reduced number of parameters, a shorter training period, a lower memory storage need, and a more straightforward hardware implementation.

The healthcare sector is one of the most rapidly growing sectors globally. With the ever-growing technology, patient care, regulatory compliance, and digital transformation, there is an increased need for healthcare sectors to collaborate with all stakeholders - both within the healthcare ecosystem and in concurring industries. In recent times, telemedicine has proven to provide high quality, affordable, and predominantly adapted healthcare services. However, telemedicine suffers from several risks in implementation, such as data breach, restricted access across medical fraternity, incorrect diagnosis and prescription, fraud, and abuse. In this work, introduce blockchain-based framework that would unlock the future of the healthcare sector and improved services. Our proposed solution utilizing Ethereum smart contracts to develop a transparent, tamper-proof telemedicine healthcare framework, and ensure the integrity of sensitive patient data eliminating a central administrator. Moreover, the smart contract regulates the interaction between all the parties involved in the network and keeps the patient meticulously informed about the transactions in the network.

This paper addresses traffic engineering (TE) issues in software-defined vehicular networking (SDVN). A brief analysis of the features of SDVN, which improves the efficiency of TE in SDVN, is presented. The feasibility of using multi-path routing with TE is substantiated. A procedure and an example of the formation of multiple routes based on a modified wave routing algorithm are given. Considering the features of the SDVN technology, a modified TE method is proposed, which reduces both the time complexity of forming multiple paths and the path reconfiguration time. The dynamic path reconfiguration algorithm is presented.

Organizations share an evolving interest in adopting a cloud computing approach for Internet of Things (IoT) applications. Integrating IoT devices and cloud computing technology is considered as an effective approach to storing and managing the enormous amount of data generated by various devices. However, big data security of these organizations presents a challenge in the IoT-cloud architecture. To overcome security issues, we propose a cloud-enabled IoT environment supported by multifactor authentication and lightweight cryptography encryption schemes to protect big data system. The proposed hybrid cloud environment is aimed at protecting organizations' data in a highly secure manner. The hybrid cloud environment is a combination of private and public cloud. Our IoT devices are divided into sensitive and nonsensitive devices. Sensitive devices generate sensitive data, such as healthcare data; whereas nonsensitive devices generate nonsensitive data, such as home appliance data. IoT devices send their data to the cloud via a gateway device. Herein, sensitive data are split into two parts: one part of the data is encrypted using RC6, and the other part is encrypted using the Fiestel encryption scheme. Nonsensitive data are encrypted using the Advanced Encryption Standard (AES) encryption scheme. Sensitive and nonsensitive data are respectively stored in private and public cloud to ensure high security. The use of multifactor authentication to access the data stored in the cloud is also proposed. During login, data users send their registered credentials to the Trusted Authority (TA). The TA provides three levels of authentication to access the stored data: first-level authentication - read file, second-level authentication - download file, and third-level authentication - download file from the hybrid cloud. We implement the proposed cloud-IoT architecture in the NS3 network simulator. We evaluated the performance of the proposed architecture using metrics such as computational time, security strength, encryption time, and decryption time.

Magnetic resonance imaging (MRI) is precise and efficient for interpreting the soft and hard tissues. Moreover, for the detailed diagnosis of varied diseases such as knee rheumatoid arthritis (RA), segmentation of the knee magnetic resonance image is a challenging and complex task that has been explored broadly. However, the accuracy and reproducibility of segmentation approaches may require prior extraction of tissues from MR images. The advances in computational methods for segmentation are reliant on several parameters such as the complexity of the tissue, quality, and acquisition process involved. This review paper focuses and briefly describes the challenges faced by segmentation techniques from magnetic resonance images followed by an overview of diverse categories of segmentation approaches. The review paper also focuses on automatic approaches and semiautomatic approaches which are extensively used with performance metrics and sufficient achievement for clinical trial assistance. Furthermore, the results of different approaches related to MR sequences used to image the knee tissues and future aspects of the segmentation are discussed.