Explore the vast range of titles available.

There has been increased attention paid to autonomous unmanned aerial vehicles (UAVs) recently because of their usage in several fields. Human action recognition (HAR) in UAV videos plays an important role in various real-life applications. Although HAR using UAV frames has not received much attention from researchers to date, it is still a significant area that needs further study because of its relevance for the development of efficient algorithms for autonomous drone surveillance. Current deep-learning models for HAR have limitations, such as large weight parameters and slow inference speeds, which make them unsuitable for practical applications that require fast and accurate detection of unusual human actions. In response to this problem, this paper presents a new deep-learning model based on depthwise separable convolutions that has been designed to be lightweight. Other parts of the HarNet model comprised convolutional, rectified linear unit, dropout, pooling, padding, and dense blocks. The effectiveness of the model has been tested using the publicly available UCF-ARG dataset. The proposed model, called HarNet, has enhanced the rate of successful classification. Each unit of frame data was pre-processed one by one by different computer vision methods before it was incorporated into the HarNet model. The proposed model, which has a compact architecture with just 2.2 million parameters, obtained a 96.15% success rate in classification, outperforming the MobileNet, Xception, DenseNet201, Inception-ResNetV2, VGG-16, and VGG-19 models on the same dataset. The proposed model had numerous key advantages, including low complexity, a small number of parameters, and high classification performance. The outcomes of this paper showed that the model’s performance was superior to that of other models that used the UCF-ARG dataset.

Satellite images are widely used for remote sensing and defence applications, however, they are subject to a variety of threats. To ensure the security and privacy of these images, they must be watermarked and encrypted before communication. Therefore, this paper proposes a novel watermarked satellite image encryption scheme based on chaos, Deoxyribonucleic Acid (DNA) sequence, and hash algorithm. The watermark image, DNA sequence, and plaintext image are passed through the Secure Hash Algorithm (SHA-512) to compute the initial condition (keys) for the Tangent-Delay Ellipse Reflecting Cavity Map (TD-ERCS), Henon, and Duffing chaotic maps, respectively. Through bitwise XOR and substitution, the TD-ERCS map encrypts the watermark image. The ciphered watermark image is embedded in the plaintext image. The embedded plaintext image is permuted row-wise and column-wise using the Henon chaotic map. The permuted image is then bitwise XORed with the values obtained from the Duffing map. For additional security, the XORed image is substituted through a dynamic S-Box. To evaluate the efficiency and performance of the proposed algorithm, several tests are performed which prove its resistance to various types of attacks such as brute-force and statistical attacks.

This study deals with the optimization of energetic and exergetic parameters of a hybrid-solar dryer to dry basil leaves under determined experimental conditions at three air temperatures (40 °C, 55 °C, and 70 °C) and three bed thickness levels (2, 4, and 6 cm). The optimization of the thermodynamic parameters was performed using the response surface method (RSM) based on the central composite design (CCD) and the desirability function (DF) to maximize the drying rate, exergy efficiency, improvement potential rate and the sustainability index, and to minimize the energy utilization, energy utilization ratio and exergy loss rate. These parameters were calculated on the basis of the first and second laws of thermodynamics as the response variables. Based on the results obtained, it was determined that the optimal conditions for basil drying were at a drying air temperature of 63.8 °C and a bed thickness of 2 cm. At this point, the parameters of the drying rate, energy utilization, energy utilization ratio, exergy efficiency, exergy loss rate, improvement potential rate and sustainability index were obtained with the maximum utility function (D = 0.548) as 0.27, 0.019 (kJ/s), 0.23, 65.75%, 0.016 (kJ/s), 1.10 (kJ/s) and 0.015, respectively.

This study investigates the optimization of 3D‐printed polylactic acid (PLA) and hydroxyapatite (HA) composites for biomedical applications, focusing on enhancing mechanical properties through process parameter optimization and surface modification. The response surface methodology (RSM), along with post hoc statistical validation using Tukey's HSD test, was employed to evaluate the influence of nozzle temperature (200°C–240°C), layer height (0.1–0.3 mm), and HA filler ratio (3–9 wt%) on the compressive strength of both untreated and chemically treated composites. Silane treatment was applied to HA to improve interfacial bonding, resulting in a 5%–7% increase in compressive strength compared to untreated samples. The optimal conditions (240°C, 9% HA, 0.3 mm layer thickness) yielded a maximum compressive strength of 75.35 MPa in treated composites and 71.42 MPa for untreated samples. Statistical analysis confirmed that layer thickness and HA content significantly influenced mechanical performance. Contour plots and 3D response surfaces were also incorporated to visualize parameter interactions. Comparison with other optimization techniques demonstrated that RSM effectively minimized experimental runs while achieving superior mechanical properties. These findings suggest that chemically modified PLA/HA composites are promising candidates for load‐bearing biomedical applications. PLA granules and HAP powder are mixed and extruded into filament, which is used for 3D printing test samples. These samples undergo compressive strength testing, and optimization is carried out using response surface methodology (RSM) to analyze the impact of various parameters on strength.

This study investigates the mechanical properties of hybrid composites reinforced with jute, kenaf, and glass fibers, incorporating Aluminum Oxide (Al2O3) as a nanoparticle filler. The effects of three key parameters—fiber orientation, fiber sequence, and weight percentage of Al2O3 on—the tensile and impact strength of the composites were examined. Three levels for each factor were considered: fiber orientation (0°, 45°, and 90°), fiber sequence (1, 2, and 3 layers), and varying Al2O3 content (3%, 4%, and 5%). The response surface methodology (RSM) was employed to optimize the parameters, providing insights into the interactions between these factors and their influence on the composite's mechanical performance. Additionally, artificial neural networks (ANN) were used for prediction modeling. The outcome presented that the ANN model outpaced RSM in terms of accuracy, with a higher correlation between predicted and experimental values. The optimal parameters for achieving the highest tensile and impact strength were determined, with fiber orientation at 90°, fiber sequence at 3, and Al2O3 content at 5%. This study demonstrates the effectiveness of ANN in predicting the mechanical properties of the laminated composite and highlights the significant role of fiber orientation, sequence, and nanoparticle reinforcement in enhancing composite performance. This study examines hybrid composites reinforced with jute, kenaf, and glass fibers, with Aluminum Oxide (Al2O3) as a filler. The effects of fiber orientation, sequence, and Al2O3 content on tensile and impact strength were analyzed. ANN outperformed RSM in predictive accuracy, identifying optimal parameters: 90° fiber orientation, three layers, and 5% Al2O3. Results highlight ANN's potential and the role of fiber and nanoparticle integration in enhancing composite properties.

This study examines the effects of sonication duration, molding temperature, and weight percentage of MWCNTs and nano silica (SiO2) on the inter‐laminar shear strength (ILSS) and Izod impact strength of laminate composites composed of glass fiber‐reinforced polymers and basalt. The laminates were made using the manual lay‐up approach and compression molding, with MWCNTs and SiO2 added in equal amounts (0%, 1%, and 2% by weight). The ASTM D256 and D2344 criteria were adhered to while assessing mechanical properties. A total of 29 trials were made utilizing the Box–Behnken Design (BBD) of response surface technique, with the following independent variables: temperature, sonication duration, filler content, and molding pressure. According to an ANOVA analysis, these traits were significant for both ILSS and Izod impact strength. The ANOVA results also showed that the filler weight (A) is the most significant factor affecting the ILSS and Izod impact strength of hybrid nanocomposites, with molding temperature, pressure, and sonication duration coming in second and third, respectively. For design run orders three and eight, the ILSS values expressed were 24 MPa for the minimum and 40 MPa for the maximum. Izod impact strengths were 203 kJ/m2 in design run order 3 and 167 kJ/m2 in design run order 8. The optimal mechanical performance was determined by optimization using Design Expert 13 software at 2% filler content, 20 min of sonication, 5 MPa pressure, and 75°C molding temperature. This resulted in an impact strength of 201.47 kJ/m2 and an ILSS of 40.25 MPa. When compared to the samples with the lowest performance, these findings show improvements of 40% and 18%, respectively. Additionally, the morphological features of cracked surfaces were revealed by scanning electron microscopy (SEM) examination, which shed light on the structural integrity of the composite. Effects of MWCNTs/SiO2 content, sonication time, molding temperature, and pressure on ILSS and Izod impact strength of glass‐basalt fiber laminates were studied. Optimization achieved 40.25 MPa ILSS and 201.47 kJ/m2 impact strength, confirmed by SEM analysis.

The development of data mining with data protection and data utility can manage distributed data efficiently. This paper revisits the concepts and techniques of privacy-preserving Random Decision Tree (RDT). In existing systems, cryptography-based techniques are effective at managing distributed information. Privacy-preserving RDT handles distributed information efficiently. Privacy-preserving RDT gives better precision data mining while preserving information and reducing the calculation time. This paper deals with this headway in privacy-preserving data mining technology utilizing emphasized approach of RDT. RDT gives preferable productivity and information privacy than cryptographic technique. Various data mining tasks utilize RDT, like classification, relapse, ranking, and different classifications. Privacy-preserving RDT utilizes both randomization and the cryptographic method, giving information privacy for some decision tree-based learning tasks; this is an effective technique for data mining with privacy-preserving distributed information. Thus, in horizontal partitioning of the dataset, parties gather information for various entities but have data for all attributes. On the other hand, various associations may gather different data about a similar set of people. Thus, in vertically partitioned data, all parties gather data for the same collection of items. In all of these cases, both horizontal and vertical partitioning of datasets is somewhat inaccurate.

Facial recognition is crucial for safety and security, especially for identifying people. This paper applies facial recognition to a database of facial images by analyzing the images and subsequently assigning a set of unique features to each one. The process of extracting features from the input image is accomplished using the gabor wavelet transform. t-SNE (tdistributed Stochastic Neighbor Embedding) select and reduce the dimension of features, thus specifying various aspects within the input image. These features are then used in a classification step, where a multiclass Support Vector Machine (SVM) is employed to categorize the face. Three popular databases (Yale, ORL and JAFFE) were the sources of the images used to evaluate the effectiveness of the proposed technique. The results show the system’s high accuracy in identifying facial images. Specifically, our method achieved a 97.78% accuracy rate on the Yale, 97.50 % in the ORL databases and 100 % in the JAFFE databases, outperforming traditional methods by 2%. These results approved the system’s accuracy in recognizing facial images.

ICT giants include cloud computing and distributed systems. Researchers have ignored the idea of merging distributed systems and cloud computing to examine millisecond execution times and megabyte capacity. The system used Google’s API to download files to the cloud. The system sent files to the principal server. Now there are two ways to calculate execution time accurately. The first scenario uses threads to construct clients and servers. Second, pool threads are used. This article examines file capacity and execution time. The system demonstrated how cloud computing influences distributed systems’ execution time and capacity in these two circumstances. According to the testing, the first scenario (multi threads) takes less time than the second (pool threads), although not significantly. 4874 milliseconds are needed to transfer 50 files, each weighing 90 MB, utilizing multiple threads. However, it takes 5541 milliseconds to send these files using the pool threads. Keep in mind that utilizing the first scenario is bad for computer hardware. In order to load files into the system, this work used hash table software structure in conjunction with network technologies like TCP sockets, APIs, threads, and thread pool techniques between the client and servers.

Nowadays, we are living in a dangerous environment and our health system is under the threatened causes of Covid19 and other diseases. The people who are close together are more threatened by different viruses, especially Covid19. In addition, limiting the physical distance between people helps minimize the risk of the virus spreading. For this reason, we created a smart system to detect violated social distance in public areas as markets and streets. In the proposed system, the algorithm for people detection uses a pre-existing deep learning model and computer vision techniques to determine the distances between humans. The detection model uses bounding box information to identify persons. The identified bounding box centroid's pairwise distances of people are calculated using the Euclidean distance. Also, we used jetson nano platform to implement a low-cost embedded system and IoT techniques to send the images and notifications to the nearest police station to apply forfeit when it detects people’s congestion in a specific area. Lastly, the suggested system has the capability to assist decrease the intensity of the spread of COVID-19 and other diseases by identifying violated social distance measures and notifying the owner of the system. Using the transformation matrix and accurate pedestrian detection, the process of detecting social distances between individuals may be achieved great confidence. Experiments show that CNN-based object detectors with our suggested social distancing algorithm provide reasonable accuracy for monitoring social distancing in public places, as well.