Search Results (10)

Forest fires pose an escalating global threat, severely impacting ecosystems, public health, and economies. Timely detection, especially during early stages, is critical for effective intervention. In this study, we propose a novel deep learning-based framework that augments the YOLOv4 object detection architecture with a modified EfficientNetV2 backbone and Efficient Channel Attention (ECA) modules. The backbone substitution leverages compound scaling and Fused-MBConv/MBConv blocks to improve representational efficiency, while the lightweight ECA blocks enhance inter-channel dependency modeling without incurring significant computational overhead. Additionally, we introduce a domain-specific preprocessing pipeline employing Canny edge detection, CLAHE + Jet transformation, and pseudo-NDVI mapping to enhance fire-specific visual cues in complex natural environments. Experimental evaluation on a hybrid dataset of forest fire images and video frames demonstrates substantial performance gains over baseline YOLOv4 and contemporary YOLO variants (YOLOv5–YOLOv9), with the proposed model achieving 97.01% precision, 95.14% recall, 93.13% mAP, and 92.78% F1-score. Furthermore, our model outperforms fourteen state-of-the-art approaches across standard metrics, confirming its efficacy, generalizability, and suitability for real-time deployment in UAV-based and edge computing platforms. These findings highlight the synergy between architectural optimization and domain-aware preprocessing for high-accuracy, low-latency wildfire detection systems. Full article

Ginseng is an important medicinal plant widely used in traditional Chinese medicine. Traditional methods for evaluating the visual quality of ginseng have limitations. This study presents a new method for grading ginseng’s appearance quality using an improved DenseNet121 model. We enhance the network’s capability to recognize various channel features by integrating a CA (Coordinate Attention) mechanism. We also use grouped convolution instead of standard convolution in dense layers to lower the number of model parameters and improve efficiency. Additionally, we substitute the ReLU (Rectified Linear Unit) activation function with the ELU (Exponential Linear Unit) activation function, which reduces the problem of neuron death related to ReLU and increases the number of active neurons. We compared several network models, including DenseNet121, ResNet50, ResNet101, GoogleNet, and InceptionV3, to evaluate their performance against our method. Results showed that the improved DenseNet121 model reached an accuracy of 95.5% on the test set, demonstrating high reliability. This finding provides valuable support for the field of ginseng grading. Full article

In submerged landscapes, distinguishing anthropogenic features versus natural ones is often challenging. We have developed a set of criteria to validate the identification of submerged anthropogenic remains that include examining the geological context, sea-level considerations, associated archaeological finds (including coastal survey), and documenting the broader archaeological context. Furthermore, our experience demonstrates that, while progress has been made in applying remote-sensing technologies to detect anthropogenic features on the seabed, there is no substitute for direct, visual assessment by an underwater archaeologist for verification of their anthropogenic status. We have applied these criteria to examine two published case studies detailing suspected anthropogenic stone features on the seabed in the Sicilian Channel. Our examination has led us to conclude that both localities are not anthropogenic features. The Pantelleria Vecchia Bank features represent natural outcrops on a submerged paleo-landscape that were shaped by depositional and erosional processes during transgression and regression periods. The suspected Lampedusa cultic site comprises natural features that are located on a submerged neo-landscape formed due to erosion and retreat of the coastal cliff since the mid-Holocene, when the sea level reached its present level. Full article

Compared to text and images, video can show information more vividly and intuitively via a moving picture; therefore, video is widely used in all walks of life. However, videos uploaded or stored in various video applications have not been treated with any protection, and these videos contain a lot of sensitive information that is more likely to be compromised. To solve this problem, video encryption schemes have been proposed. However, the main concern with existing video encryption schemes is that the private information in the encrypted video should be effectively protected, and, thus, the pixel distribution of the original video can be greatly damaged in the process of encryption, resulting in no or poor visual usability of the encrypted video. To this end, a novel color-video encryption scheme is proposed, which can effectively protect video privacy information while retaining certain visual information, thus enhancing the usability of encrypted videos. Firstly, the R, G, and B channels of the original color video are viewed as a whole for splitting. The dimensions of the blocks are three-dimensional, and permutation encryption is performed in three-dimensional blocks, which eliminates the redundancy of information between the video frame channels. Secondly, after permutation encryption, the channels of the video frame are separated, and then each channel is divided into blocks. The shape of the blocks is a square, and substitution encryption and permutation encryption operations are performed in turn. The whole encryption process is combined with the 2D-LSM chaotic system to improve the security of the scheme, as well as to reduce the time. Extensive experiments have been carried out, and the results show that the proposed scheme allows the encrypted video to retain rough visual information and, at the same time, effectively protects privacy, achieving the goal of encrypted video security and usability. Full article

Power-based Side-Channel Analysis (SCA) began with visual-based examinations and has progressed to utilize data-driven statistical analysis. Two distinct classifications of these methods have emerged over the years; those focused on leakage exploitation and those dedicated to leakage detection. This work primarily focuses on a leakage detection-based schema that utilizes Welch’s t-test, known as Test Vector Leakage Assessment (TVLA). Both classes of methods process collected data using statistical frameworks that result in the successful exfiltration of information via SCA. Often, statistical testing used during analysis requires the assumption that collected power consumption data originates from a normal distribution. To date, this assumption has remained largely uncontested. This work seeks to demonstrate that while past studies have assumed the normality of collected power traces, this assumption should be properly evaluated. In order to evaluate this assumption, an implementation of Tiny-AES-c with nine unique substitution-box (s-box) configurations is conducted using TVLA to guide experimental design. By leveraging the complexity of the AES algorithm, a sufficiently diverse and complex dataset was developed. Under this dataset, statistical tests for normality such as the Shapiro-Wilk test and the Kolmogorov-Smirnov test provide significant evidence to reject the null hypothesis that the power consumption data is normally distributed. To address this observation, existing non-parametric equivalents such as the Wilcoxon Signed-Rank Test and the Kruskal-Wallis Test are discussed in relation to currently used parametric tests such as Welch’s t-test. Full article

Alternative methods of presenting the information contained in mathematical images, which are adapted to the needs of blind people, are significant challenges in modern education. This article presents an alternative multimodal method that substitutes the sense of sight with the sense of touch and hearing to convey graphical information. The developed method was evaluated at a center specializing in the education of the blind in Poland, on a group of 46 students aged 15–19. They solved a set of 60 high school-level problems on geometry, mathematical analysis, and various types of graphs. We assessed the mechanisms introduced for the sense of touch and hearing, as well as the overall impression of the users. The system usability scale and the NASA task load index tests were used in the evaluation. The results obtained indicate an overall increase in user satisfaction and usefulness of the proposed approach and a reduction in the workload during exercise solving. The results also show a significant impact of the proposed navigation modes on the average time to reach objects in the drawing. Therefore, the presented method could significantly contribute to the development of systems supporting multimodal education for people with blindness. Full article

Finned tubes increase the convective heat transfer in heat exchangers, reducing the total energy consumption of integrated industrial processes. Due to its stability and robustness, Computational Fluid Dynamics (CFD) commercial software is generally utilized for analyzing complex systems; however, its licensing is expensive. Nowadays, open-source software is a viable substitute for proprietary software. This work presents a CFD analysis of the hydrodynamics of a finned tube using the OpenFOAM and SALOME Meca platforms. The results are compared with experimental data and CFD using the commercial software Fluent, both previously reported in the open literature. This work studies the fluid flow pattern around a tube with six 45-degree-angled fins, and the working fluid, air, is considered as an incompressible fluid. Special attention is paid to calculating the pressure coefficient distribution for the internal and external surfaces of the inclined fins. Open-source platforms allow researchers to visualize how the airflow interacts with the cylinder and the fin surfaces to form a fluid structure, formerly known as a horseshoe vortex system. The findings of the analysis of flow dynamics in the channel between inclined fins and in the wake help explain the results obtained in experimental tests and are relevant for the configuration of a bank of tubes with inclined fins. Full article

Technological advances enable the capture and management of complex data sets that need to be correctly understood. Visualisation techniques can help in complex data analysis and exploration, but sometimes the visual channel is not enough, or it is not always available. Some authors propose using the haptic channel to reinforce or substitute the visual sense, but the limited human haptic short-term memory still poses a challenge. We present the haptic tuning fork, a reference signal displayed before the haptic information for increasing the discriminability of haptic icons. With this reference, the user does not depend only on short-term memory. We have decided to evaluate the usefulness of the haptic tuning fork in impedance kinesthetic devices as these are the most common. Furthermore, since the renderable signal ranges are device-dependent, we introduce a methodology to select a discriminable set of signals called the haptic scale. Both the haptic tuning fork and the haptic scale proved their usefulness in the performed experiments regarding haptic stimuli varying in frequency. Full article

The halide anions are essential for supporting life. Therefore, halide anion analyses are of paramount importance. For this reason, we have performed both qualitative and quantitative ana- lyses of halides (chloride, bromide, iodide) using the Tl(III) complex of azodye, 4-(2-pyridylazo)re- sorcinol (PAR), a potential new chemical reagent/sensor that utilizes the substitution reaction whereas the Tl(III)PAR complex reacts with a halide to yield a more stable thallium(III)-halide while releasing the PAR ligand in a process accompanied by color change of the solution. The experimental conditions (e.g., pH, ratio metal ion-to-ligand ratio, etc.) for the substitution reaction between the metal complex and a halide were optimized to achieve increased sensitivity and a lower limit of detection (chloride 7 mM, bromide 0.15 mM, iodide 0.05 mM). It is demonstrated that this single chemosensor can, due to release of colored PAR ligand and the associated analyte-specific changes in the UV/VIS spectra, be employed for a multicomponent analysis of mixtures of anions (chloride + bromide, chloride + iodide, bromide + iodide). The spectrophotometric data evaluated by artificial neural networks (ANNs) enable distinguishing among the halides and to determine halide species concentrations in a mixture. The Tl(III)-PAR complex was also used to construct sensor arrays utilizing a standard 96-well plate format where the output was recorded at several wavelengths (up to 7) using a conventional plate reader. It is shown that the data obtained using a digital scanner employing only three different input channels may also be successfully used for a subsequent ANN analysis. The results of all approaches utilized for data evaluation were similar. To increase the practical utility of the chemosensor, we have developed a test paper strip indicator useful for routine naked-eye visual determination of halides. This test can also be used for halide anion determination in solutions using densitometer. The methodology described in this paper can be used for a simple, inexpensive, and fast routine analysis both in a laboratory as well as in a field setting. Full article

In Phase I, we collected data on five subjects yielding over 90% positive performance in Magnetoencephalographic (MEG) mid-and post-movement activity. In addition, a driver was developed that substituted the actions of the Brain Computer Interface (BCI) as mouse button presses for real-time use in visual simulations. The process was interfaced to a flight visualization demonstration utilizing left or right brainwave thought movement, the user experiences, the aircraft turning in the chosen direction, or on iOS Mobile Warfighter Videogame application. The BCI’s data analytics of a subject’s MEG brain waves and flight visualization performance videogame analytics were stored and analyzed using the Hadoop Ecosystem as a quick retrieval data warehouse. In Phase II portion of the project involves the Emotiv Encephalographic (EEG) Wireless Brain–Computer interfaces (BCIs) allow for people to establish a novel communication channel between the human brain and a machine, in this case, an iOS Mobile Application(s). The EEG BCI utilizes advanced and novel machine learning algorithms, as well as the Spark Directed Acyclic Graph (DAG), Cassandra NoSQL database environment, and also the competitor NoSQL MongoDB database for housing BCI analytics of subject’s response and users’ intent illustrated for both MEG/EEG brainwave signal acquisition. The wireless EEG signals that were acquired from the OpenVibe and the Emotiv EPOC headset can be connected via Bluetooth to an iPhone utilizing a thin Client architecture. The use of NoSQL databases were chosen because of its schema-less architecture and Map Reduce computational paradigm algorithm for housing a user’s brain signals from each referencing sensor. Thus, in the near future, if multiple users are playing on an online network connection and an MEG/EEG sensor fails, or if the connection is lost from the smartphone and the webserver due to low battery power or failed data transmission, it will not nullify the NoSQL document-oriented (MongoDB) or column-oriented Cassandra databases. Additionally, NoSQL databases have fast querying and indexing methodologies, which are perfect for online game analytics and technology. In Phase II, we collected data on five MEG subjects, yielding over 90% positive performance on iOS Mobile Applications with Objective-C and C++, however on EEG signals utilized on three subjects with the Emotiv wireless headsets and (n < 10) subjects from the OpenVibe EEG database the Variational Bayesian Factor Analysis Algorithm (VBFA) yielded below 60% performance and we are currently pursuing extending the VBFA algorithm to work in the time-frequency domain referred to as VBFA-TF to enhance EEG performance in the near future. The novel usage of NoSQL databases, Cassandra and MongoDB, were the primary main enhancements of the BCI Phase II MEG/EEG brain signal data acquisition, queries, and rapid analytics, with MapReduce and Spark DAG demonstrating future implications for next generation biometric MEG/EEG NoSQL databases. Full article