Search Results (79)

Numerous valuable information is available on the Internet, and many individuals rely on mass media as their primary source of information. Various views, comments, expressions, and opinions on social networks have been a tremendous source of information. Harvesting free, resourceful information through social media makes text mining a powerful tool for analyzing public opinions on various issues across diverse social networks. Various research projects have implemented text sentiment analysis through machine and deep learning approaches. Social media text often expresses sentiment through complex syntax and negation (e.g., implicit and double negation and nested clauses), which many classifiers mishandle. We propose hybrid negation, a clause-aware approach that combines (i) explicit/implicit/double-negation rules, (ii) dependency-based scope detection, (iii) a TextBlob back-off for phrase polarity, and (iv) an MLP-learned clause-weighting module that aggregates clause-level scores. Across 156,539 tweets (three-class sentiment), we evaluate six negation strategies and 228 model configurations with and without SMOTE (applied strictly within training folds). Hybrid Negation achieves 98.582% accuracy, 98.196% precision, 98.189% recall, and 98.193% F1 with BERT, outperforming rule-only and antonym/synonym baselines. Ablations show each component contributes to the model’s performance, with dependency scope and double negations offering the largest gains. Per-class results, confidence intervals, and paired tests with multiple-comparison control confirm statistically significant improvements. We release code and preprocessing scripts to support reproducibility. Full article

The detection of subsurface stromatolites remains challenging due to their complex morphology and heterogeneous composition. This study assesses the combined application of Electrical Resistivity Tomography (ERT) and Ground Penetrating Radar (GPR) for identifying microbialites in two contrasting geological and climatic settings: the Neoproterozoic Salitre Formation in Brazil and the Mesozoic microbialite-bearing limestones in northern Spain. High-resolution ERT profiles processed with raster-based blob detection algorithms revealed subcircular high-resistivity anomalies consistent with the studied microbialite morphologies, with strong resistivity contrasts observed between microbialites and host matrices despite variations in absolute values linked to lithology and soil moisture. In parallel, GPR surveys analyzed with a peak detection algorithm delineated domal reflectors and clusters of high-amplitude reflections that directly captured the internal architecture of stromatolitic buildups. With decimetric vertical resolution, GPR offered unrivaled insights into internal morphology, complementing the broader-scale imaging capacity of ERT. The complementary strengths of both methods are clear: ERT excels at mapping distribution and stratigraphic context, while GPR provides unparalleled resolution of internal structures. Crucially, this work advances previous efforts by explicitly demonstrating that integrated ERT-GPR approaches, when combined with algorithm-based interpretation, can resolve microbialite morphology, distribution and internal architecture with a level of objectivity not previously achieved. Beyond methodological refinement, these findings open new avenues for reconstructing microbialite development and preservation in ancient carbonate systems and hold strong potential for application in other geological contexts where complex carbonate structures challenge traditional geophysical imaging. Full article

Laboratories are complex and dynamic environments where diverse hazards—including toxic gas leakage, volatile solvent combustion, and unexpected fire ignition—pose serious threats to personnel safety and property. Traditional monitoring systems relying on single-type sensors or manual inspections often fail to provide timely warnings or comprehensive hazard perception, resulting in delayed response and potential escalation of incidents. To address these limitations, this study proposes a multi-node laboratory safety monitoring and early warning system integrating multi-source sensing, heterogeneous communication, and cloud–edge collaboration. The system employs a LoRa-based star-topology network to connect distributed sensing and actuation nodes, ensuring long-range, low-power communication. A Raspberry Pi-based module performs real-time facial recognition for intelligent access control, while an OpenMV module conducts lightweight flame detection using color-space blob analysis for early fire identification. These edge-intelligent components are optimized for embedded operation under resource constraints. The cloud–edge–app collaborative architecture supports real-time data visualization, remote control, and adaptive threshold configuration, forming a closed-loop safety management cycle from perception to decision and execution. Experimental results show that the facial recognition module achieves 95.2% accuracy at the optimal threshold, and the flame detection algorithm attains the best balance of precision, recall, and F1-score at an area threshold of around 60. The LoRa network maintains stable communication up to 0.8 km, and the system’s emergency actuation latency ranges from 0.3 s to 5.5 s, meeting real-time safety requirements. Overall, the proposed system significantly enhances early fire warning, multi-source environmental monitoring, and rapid hazard response, demonstrating strong applicability and scalability in modern laboratory safety management. Full article

Tourist reviews provide essential insights into travellers experiences and public perceptions of destinations. In Kazakhstan, however, sentiment analysis, particularly using ensemble learning, remains underexplored for evaluating such reviews. This study proposes a hybrid stacking ensemble for sentiment analysis of English-language tourist reviews about Kazakhstan, integrating four complementary approaches: VADER, TextBlob, Stanza, and Local Context Focus Mechanism with Bidirectional Encoder Representations from Transformers (LCF-BERT). Each model contributes distinct analytical capabilities, including lexicon-based polarity detection, rule-based subjectivity evaluation, generalised star-rating estimation, and contextual aspect-oriented sentiment classification. The evaluation utilised a cleaned dataset of 11,454 TripAdvisor reviews collected between February 2022 and June 2025. The ensemble aggregates model outputs through majority and weighted voting strategies to enhance robustness. Experimental results (accuracy 0.891, precision 0.838, recall 0.891, and F1-score 0.852) demonstrate that the proposed method KazSATR outperforms individual models in overall classification accuracy and exhibits superior capacity for aspect-level sentiment detection. These findings underscore the potential of the hybrid ensemble as a practical and scalable tool for the tourism sector in Kazakhstan. By leveraging multiple analytical paradigms, the model enables tourism professionals and policymakers to better understand traveller preferences, identify service strengths and weaknesses, and inform strategic decision-making. The proposed approach contributes to advancing sentiment analysis applications in tourism research, particularly in underrepresented geographic contexts. Full article

Biodiversity monitoring requires the discovery of multi-target tracking. The main requirement is not to reduce the localization error but the continuity of the tracks: a high ratio between the duration of the track and the lifetime of the target. To this end, we present an algorithm for detecting and tracking mobile underwater targets that utilizes reflections from active acoustic emission of broadband signals received by a rigid hydrophone array. The method overcomes the problem of a high false alarm rate by applying a tracking approach to the sequence of received reflections. A 2D time–distance matrix is created for the reflections received from each transmitted probe signal by performing delay and sum beamforming and pulse compression. The result is filtered by a 2D constant false alarm rate (CFAR) detector to identify reflection patterns that correspond to potential targets. Closely spaced signals for multiple probe transmissions are combined into blobs to avoid multiple detections of a single target. The position and velocity are estimated using the debiased converted measurement Kalman filter. The results are analyzed for simulated scenarios and for experiments in the Adriatic Sea, where six Global Positioning System (GPS)-tagged gilt-head seabream fish were released and tracked by a dedicated autonomous float system. Compared to four recent benchmark methods, the results show favorable tracking continuity and accuracy that is robust to the choice of detection threshold. Full article

This study presents an automated computer vision system for assessing the cleanliness of plastic mirror caps used in the automotive industry after a washing process. These components are highly visible and require optimal surface conditions prior to painting, making the detection of residual contaminants critical for quality assurance. The system acquires high-resolution monochrome images under various lighting configurations, including natural light and infrared (IR) at 850 nm and 940 nm, with different angles of incidence. Four blob detection algorithms—adaptive thresholding, Laplacian of Gaussian (LoG), Difference of Gaussians (DoG), and Determinant of Hessian (DoH)—were implemented and evaluated based on their ability to detect surface impurities. Performance was assessed by comparing the total detected blob area before and after the cleaning process, providing a proxy for both sensitivity and false positive rate. Among the tested methods, adaptive thresholding under 30° natural light produced the best results, with a statistically significant z-score of +2.05 in the pre-wash phase and reduced false detections in post-wash conditions. The LoG and DoG methods were more prone to spurious detections, while DoH demonstrated intermediate performance but struggled with reflective surfaces. The proposed approach offers a cost-effective and scalable solution for real-time quality control in industrial environments, with the potential to improve process reliability and reduce waste due to surface defects. Full article

The early detection of cancerous lesions is a challenging task given the cancer biology and the variability in tissue characteristics, thus rendering medical image analysis tedious and time-inefficient. In the past, conventional computer-aided diagnosis (CAD) and detection methods have heavily relied on the visual inspection of medical images, which is ineffective, particularly for large and visible cancerous lesions in such images. Additionally, conventional methods face challenges in analyzing objects in large images due to overlapping/intersecting objects and the inability to resolve their image boundaries/edges. Nevertheless, the early detection of breast cancer lesions is a key determinant for diagnosis and treatment. In this study, we present a deep learning-based technique for breast cancer lesion detection, namely blob detection, which automatically detects hidden and inaccessible cancerous lesions in unsupervised human breast histology images. Initially, this approach prepares and pre-processes data through various augmentation methods to increase the dataset size. Secondly, a stain normalization technique is applied to the augmented images to separate nucleus features from tissue structures. Thirdly, morphology operation techniques, namely erosion, dilation, opening, and a distance transform, are used to enhance the images by highlighting foreground and background pixels while removing overlapping regions from the highlighted nucleus objects in the image. Subsequently, image segmentation is handled via the connected components method, which groups highlighted pixel components with similar intensity values and assigns them to their relevant labeled components (binary masks). These binary masks are then used in the active contours method for further segmentation by highlighting the boundaries/edges of ROIs. Finally, a deep learning recurrent neural network (RNN) model automatically detects and extracts cancerous lesions and their edges from the histology images via the blob detection method. This proposed approach utilizes the capabilities of both the connected components method and the active contours method to resolve the limitations of blob detection. This detection method is evaluated on 27,249 unsupervised, augmented human breast cancer histology dataset images, and it shows a significant evaluation result in the form of a $98.82\%$ F1 accuracy score. Full article

Among the several usages of unmanned aerial vehicles (UAVs), a wireless relay system is one of the most promising applications. Specifically, a small fixed-wing UAV is suitable to establish the system promptly. In the system, an antenna pointing control system directs an onboard antenna to a ground station in order to form and maintain a communication link between the UAV and the ground station. In this paper, we propose a sensor system to detect the direction of the ground station from the UAV by using color marker patterns for the antenna pointing control system. The sensor detects the difference between the antenna pointing direction and the ground station direction. The sensor is characterized by the usage of both the color information of multiple color markers and color marker pattern matching. These enable the detection of distant, low-resolution markers, a high accuracy of marker detection, and robust marker detection against motion blur. In this paper, we describe the detailed algorithm of the sensor, and its performance is evaluated by using the prototype sensor system. Experimental performance evaluation results showed that the proposed method had a minimum detectable drawing size of 10.2 pixels, a motion blur tolerance of 0.0175, and a detection accuracy error of less than 0.12 deg. This performance indicates that the method has a minimum detectable draw size that is half that of the ArUco marker (a common AR marker), is 15.9 times more tolerant of motion blur than the ArUco marker, and has a detection accuracy error twice that of the ArUco marker. The color markers in the proposed method can be placed farther away or be smaller in size than ArUco markers, and they can be detected by the onboard camera even if the aircraft’s attitude changes significantly. The proposed method using color marker patterns has the potential to improve the operational flexibility of radio relay systems utilizing UAVs and is expected to be further developed in the future. Full article

Background: Prostate cancer management optimally requires non-invasive, objective, quantitative, accurate evaluation of prostate tumors. The current research applies visual inspection and quantitative approaches, such as artificial intelligence (AI) based on deep learning (DL), to evaluate MRI. Recently, a different spectral/statistical approach has been used to successfully evaluate spatially registered biparametric MRIs for prostate cancer. This study aimed to further assess and improve the spectral/statistical approach through benchmarking and combination with AI. Methods: A zonal-aware self-supervised mesh network (Z-SSMNet) was applied to the same 42-patient cohort from previous spectral/statistical studies. Using the probability of clinical significance of prostate cancer (PCsPCa) and a detection map, the affiliated tumor volume, eccentricity was computed for each patient. Linear and logistic regression were applied to the International Society of Urological Pathology (ISUP) grade and PCsPCa, respectively. The R, p-value, and area under the curve (AUROC) from the Z-SSMNet output were computed. The Z-SSMNet output was combined with the spectral/statistical output for multiple-variate regression. Results: The R (p-value)–AUROC [95% confidence interval] from the Z-SSMNet algorithm relating ISUP to PCsPCa is 0.298 (0.06), 0.50 [0.08–1.0]; relating it to the average blob volume, it is 0.51 (0.0005), 0.37 [0.0–0.91]; relating it to total tumor volume, it is 0.36 (0.02), 0.50 [0.0–1.0]. The R (p-value)–AUROC computations showed a much poorer correlation for eccentricity derived from the Z-SSMNet detection map. Overall, DL/AI showed poorer performance relative to the spectral/statistical approaches from previous studies. Multi-variable regression fitted AI average blob size and SCR results at a level of R = 0.70 (0.000003), significantly higher than the results for the univariate regression fits for AI and spectral/statistical approaches alone. Conclusions: The spectral/statistical approaches performed well relative to Z-SSMNet. Combining Z-SSMNet with spectral/statistical approaches significantly enhanced tumor grade prediction, possibly providing an alternative to current prostate tumor assessment. Full article

In the current era of advanced IoT technology, human occupancy monitoring and positioning technology is widely used in various scenarios. For example, it can optimize passenger flow in public transportation systems, enhance safety in large shopping malls, and adjust smart home devices based on the location and number of occupants for energy savings. Additionally, in homes requiring special care, it can provide timely assistance. However, this technology faces limitations such as privacy concerns, environmental factors, and costs. Traditional cameras may not effectively address these issues, but infrared thermal sensors can offer similar applications while overcoming these challenges. Infrared thermal sensors detect the infrared heat emitted by the human body, protecting privacy and functioning effectively day and night with low power consumption, making them ideal for continuous monitoring scenarios like security systems or elderly care. In this study, we propose a system using the AMG8833, an 8 × 8 Infrared Thermal Array Sensor. The sensor data are processed through interpolation, adaptive thresholding, and blob detection, and the merged human heat signatures are separated. To enhance stability in human position estimation, a dynamic sliding window adjusts its size based on movement speed, effectively handling environmental changes and uncertainties. Full article

Augmented reality applications involving human interaction with virtual objects often rely on segmentation-based hand detection techniques. Semantic segmentation can then be enhanced with instance-specific information to model complex interactions between objects, but extracting such information typically increases the computational load significantly. This study proposes a training strategy that enables conventional semantic segmentation networks to preserve some instance information during inference. This is accomplished by introducing pixel weight maps into the loss calculation, increasing the importance of boundary pixels between instances. We compare two common fully convolutional network (FCN) architectures, U-Net and ResNet, and fine-tune the fittest to improve segmentation results. Although the resulting model does not reach state-of-the-art segmentation performance on the EgoHands dataset, it preserves some instance information with no computational overhead. As expected, degraded segmentations are a necessary trade-off to preserve boundaries when instances are close together. This strategy allows approximating instance segmentation in real-time using non-specialized hardware, obtaining a unique blob for an instance with an intersection over union greater than 50% in 79% of the instances in our test set. A simple FCN, typically used for semantic segmentation, has shown promising instance segmentation results by introducing per-pixel weight maps during training for light-weight applications. Full article

Waterborne illnesses lead to millions of fatalities worldwide each year, particularly in developing nations. In this paper, we introduce a comprehensive system designed for the autonomous early detection of viral outbreaks transmitted through water to ensure sustainable access to healthy water resources, especially in remote areas. The system utilizes an autonomous water quality monitoring setup consisting of an airborne water sample collector, an autonomous sample processor, and an artificial intelligence-aided microscopic detector for risk assessment. The proposed system replaces the time-consuming conventional monitoring protocol by automating sample collection, sample processing, and pathogen detection. Furthermore, it provides a safer processing method against the spillage of contaminated liquids and potential resultant aerosols during the heat fixation of specimens. A morphological image processing technique of light microscopic images is used to segment images, assisting in selecting a unified appropriate input segment size based on individual blob areas of different bacterial cultures. The dataset included harmful pathogenic bacteria (A. baumanii, E. coli, and P. aeruginosa) and harmless ones found in drinking water and wastewater (E. faecium, L. paracasei, and Micrococcus spp.). The segmented labeled dataset was used to train deep convolutional neural networks to automatically detect pathogens in microscopic images. To minimize prediction error, Bayesian optimization was applied to tune the hyperparameters of the networks’ architecture and training settings. Different convolutional networks were tested in accordance with different required output labels. The neural network used to classify bacterial cultures as harmful or harmless achieved an accuracy of 99.7%. The neural network used to identify the specific types of bacteria achieved a cumulative accuracy of 93.65%. Full article

In complex maritime scenarios where the grayscale polarity of ships is unknown, existing infrared ship detection methods may struggle to accurately detect ships among significant interference. To address this issue, this paper first proposes an infrared image smoothing method composed of Grayscale Morphological Reconstruction (GMR) and a Relative Total Variation (RTV). Additionally, a detection method considering the grayscale uniformity of ships and integrating shape and spatiotemporal features is established for detecting bright and dark ships in complex maritime scenarios. Initially, the input infrared images undergo opening (closing)-based GMR to preserve dark (bright) blobs with the opposite suppressed, followed by smoothing the image with the relative total variation model to reduce clutter and enhance the contrast of the ship. Subsequently, Maximally Stable Extremal Regions (MSER) are extracted from the smoothed image as candidate targets, and the results from the bright and dark channels are merged. Shape features are then utilized to eliminate clutter interference, yielding single-frame detection results. Finally, leveraging the stability of ships and the fluctuation of clutter, true targets are preserved through a multi-frame matching strategy. Experimental results demonstrate that the proposed method outperforms ITDBE, MRMF, and TFMSER in seven image sequences, achieving accurate and effective detection of both bright and dark polarity ship targets. Full article

The condition and hazard monitoring of bridges play important roles in ensuring their service continuity not only throughout their entire lifespan but also under extreme conditions such as those of earthquakes. Advanced structural health monitoring (SHM) systems using vision-based technology, such as surveillance, traffic, or drone cameras, may assist in preventing future impacts due to structural deficiency and are critical to the emergence of sustainable and smart transportation infrastructure. This study evaluates several feature detection and tracking algorithms and implements them in the vision-based SHM of bridges along with their systematic procedures. The proposed procedures are implemented via a two-span accelerated bridge construction (ABC) system undergoing a large-scale shake-table test. The research objectives are to explore the effect of refined matching algorithms on blob-based features in improving their accuracies and to implement the proposed algorithms on large-scale bridges tested under seismic loads using vision-based SHM. The procedure begins by adopting blob-based feature detectors, i.e., the scale-invariant feature transform (SIFT), speeded-up robust features (SURF), and KAZE algorithms, and their stability is compared. The least medium square (LMEDS), least trimmed square (LTS), random sample consensus (RANSAC), and its generalization maximum sample consensus (MSAC) algorithms are applied for model fitting, and their sensitivity for removing outliers is analyzed. The raw data are corrected using mathematical models and scaled to generate displacement data. Finally, seismic vibrations of the bridge are generated, and the seismic responses are compared. The data are validated using target-tracking methods and mechanical sensors, i.e., string potentiometers. The results show a good agreement between the proposed blob feature detection and matching algorithms and target-tracking data and reference data obtained using mechanical sensors. Full article

The work presented in this paper makes multiple scientific contributions related to the investigation of the global fear associated with COVID-19 by performing a comprehensive analysis of a dataset comprising survey responses of participants from 40 countries. First, the results of subjectivity analysis performed using TextBlob, showed that in the responses where participants indicated their biggest concern related to COVID-19, the average subjectivity by the age group of 41–50 decreased from April 2020 to June 2020, the average subjectivity by the age group of 71–80 drastically increased from May 2020, and the age group of 11–20 indicated the least level of subjectivity between June 2020 to August 2020. Second, subjectivity analysis also revealed the percentage of highly opinionated, neutral opinionated, and least opinionated responses per age-group where the analyzed age groups were 11–20, 21–30, 31–40, 41–50, 51–60, 61–70, 71–80, and 81–90. For instance, the percentage of highly opinionated, neutral opinionated, and least opinionated responses by the age group of 11–20 were 17.92%, 16.24%, and 65.84%, respectively. Third, data analysis of responses from different age groups showed that the highest percentage of responses indicating that they were very worried about COVID-19 came from individuals in the age group of 21–30. Fourth, data analysis of the survey responses also revealed that in the context of taking precautions to prevent contracting COVID-19, the percentage of individuals in the age group of 31–40 taking precautions was higher as compared to the percentages of individuals from the age groups of 41–50, 51–60, 61–70, 71–80, and 81–90. Fifth, a deep learning model was developed to detect if the survey respondents were seeing or planning to see a psychologist or psychiatrist for any mental health issues related to COVID-19. The design of the deep learning model comprised 8 neurons for the input layer with the ReLU activation function, the ReLU activation function for all the hidden layers with 12 neurons each, and the sigmoid activation function for the output layer with 1 neuron. The model utilized the responses to multiple questions in the context of fear and preparedness related to COVID-19 from the dataset and achieved an accuracy of 91.62% after 500 epochs. Finally, two comparative studies with prior works in this field are presented to highlight the novelty and scientific contributions of this research work. Full article