Search

The detection of ship fires is a critical aspect of maritime safety and surveillance, demanding high accuracy in both identification and response mechanisms. However, the scarcity of ship fire images poses a significant challenge to the development and training of effective machine learning models. This research paper addresses this challenge by exploring advanced data augmentation techniques aimed at enhancing the training datasets for ship and ship fire detection. We have curated a dataset comprising ship images (both fire and non-fire) and various oceanic images, which serve as target and source images. By employing diverse image blending methods, we randomly integrate target images of ships with source images of oceanic environments under various conditions, such as windy, rainy, hazy, cloudy, or open-sky scenarios. This approach not only increases the quantity but also the diversity of the training data, thus improving the robustness and performance of machine learning models in detecting ship fires across different contexts. Furthermore, we developed a Gradio web interface application that facilitates selective augmentation of images. The key contribution of this work is related to object extraction-based blending. We propose basic and advanced data augmentation techniques while applying blending and selective randomness. Overall, we cover eight critical steps for dataset creation. We collected 9200 ship fire and 4100 ship non-fire images. From the images, we augmented 90 ship fire images with 13 background images and achieved 11,440 augmented images. To test the augmented dataset performance, we trained Yolo-v8 and Yolo-v10 models with "Fire" and "No-fire" augmented ship images. In the Yolo-v8 case, the precision-recall curve achieved 96.6% (Fire), 98.2% (No-fire), and 97.4% mAP score achievement in all classes at a 0.5 rate. In Yolo-v10 model training achievement, we got 90.3% (Fire), 93.7 (No-fire), and 92% mAP score achievement in all classes at 0.5 rate. In comparison, both trained models' performance is outperforming other Yolo-based SOTA ship fire detection models in overall and mAP scores. [ABSTRACT FROM AUTHOR]

The operation and maintenance of futuristic electric vehicles need accurate estimation of the state of health (SOH) of lithium-ion batteries (LIBs). To address this issue, a robust neural network framework is proposed to estimate the SOH. This article developed a novel approach that combines improved particle swarm optimization (IPSO) with bidirectional long short-term memory (Bi-LSTM) to effectively address the issue of precisely estimating SOH. The proposed IPSO-Bi-LSTM model is more effective than the other models for SOH estimation. This is because Bi-LSTM can capture both past and future appropriate information, making it more suitable for modeling complicated temporal sequences. The IPSO main objective is to optimize the model hyperparameters. To increase the model's accuracy, the IPSO improves the parameters. The PSO-Bi-LSTM model performed better than the other approaches, according to experimental findings based on the NASA-PCOE battery dataset, and all of the SOH estimated outcomes, such as root mean square errors, were less than 0.50%. This result suggests that the proposed PSO-Bi-LSTM model has the ability to robustly estimate the SOH with a high accuracy. [ABSTRACT FROM AUTHOR]

It is known that artificial intelligence algorithms are based on calculations performed using various mathematical operations. In order for these calculation processes to be carried out correctly, some types of data cannot be fed directly into the algorithms. In other words, numerical data should be input to these algorithms, but not all data in datasets collected for artificial intelligence algorithms are always numerical. These data may not be quantitative but may be important for the study under consideration. That is, these data cannot be thrown away. In such a case, it is necessary to transfer categorical data to numeric type. In this research work, 14 encoding methods of transforming of categorical data were considered. At the same time, conclusions are given about the general conditions of using these methods. During the research, categorical data in the dataset that were collected in order to assess whether it is possible to give credit to customers will be transformed based on 14 methods. After applying each encoding method, experimental tests are conducted based on the classification algorithm, and they are evaluated. At the end of the study, the results of the experimental tests are discussed and research conclusions are presented. [ABSTRACT FROM AUTHOR]

Poplar (Populus) trees play a vital role in various industries and in environmental sustainability. They are widely used for paper production, timber, and as windbreaks, in addition to their significant contributions to carbon sequestration. Given their economic and ecological importance, effective disease management is essential. Convolutional Neural Networks (CNNs), particularly adept at processing visual information, are crucial for the accurate detection and classification of plant diseases. This study introduces a novel dataset of manually collected images of diseased poplar leaves from Uzbekistan and South Korea, enhancing the geographic diversity and application of the dataset. The disease classes consist of "Parsha (Scab)", "Brown-spotting", "White-Gray spotting", and "Rust", reflecting common afflictions in these regions. This dataset will be made publicly available to support ongoing research efforts. Employing the advanced YOLOv8 model, a state-of-the-art CNN architecture, we applied a Contrast Stretching technique prior to model training in order to enhance disease detection accuracy. This approach not only improves the model's diagnostic capabilities but also offers a scalable tool for monitoring and treating poplar diseases, thereby supporting the health and sustainability of these critical resources. This dataset, to our knowledge, will be the first of its kind to be publicly available, offering a valuable resource for researchers and practitioners worldwide. [ABSTRACT FROM AUTHOR]

Genetic disorders affect over 6% of the global population and pose substantial obstacles to healthcare systems. Early identification of these rare facial genetic disorders is essential for managing related medical complexities and health issues. Many people consider the existing screening techniques inadequate, often leading to a diagnosis several years after birth. This study evaluated the efficacy of deep learning-based classifier models for accurately recognizing dysmorphic characteristics using facial photos. This study proposes a multi-class facial syndrome classification framework that encompasses a unique combination of diseases not previously examined together. The study focused on distinguishing between individuals with four specific genetic disorders (Down syndrome, Noonan syndrome, Turner syndrome, and Williams syndrome) and healthy controls. We investigated how well fine-tuning a few well-known convolutional neural network (CNN)-based pre-trained models—including VGG16, ResNet-50, ResNet152, and VGG-Face—worked for the multi-class facial syndrome classification task. We obtained the most encouraging results by adjusting the VGG-Face model. The proposed fine-tuned VGG-Face model not only demonstrated the best performance in this study, but it also performed better than other state-of-the-art pre-trained CNN models for the multi-class facial syndrome classification task. The fine-tuned model achieved both accuracy and an F1-Score of 90%, indicating significant progress in accurately detecting the specified genetic disorders. [ABSTRACT FROM AUTHOR]

Breast cancer detection at an early stage is crucial for improving patient survival rates. This work introduces an innovative thermal imaging prototype that incorporates compression techniques inspired by mammography equipment. The prototype offers a radiation-free and precise cancer diagnosis. By integrating compression and illumination methods, thermal picture quality has increased, and the accuracy of classification has improved. Essential components of the suggested thermography device include an equipment body, plates, motors, pressure sensors, light sources, and a thermal camera. We created a 3D model of the gadget using the SolidWorks software 2020 package. Furthermore, the classification research employed both cancer and normal images from the experimental results to validate the efficacy of the suggested system. We employed preprocessing and segmentation methods on the obtained dataset. We successfully categorized the thermal pictures using various classifiers and examined their performance. The logistic regression model showed excellent performance, achieving an accuracy of 0.976, F1 score of 0.977, precision of 1.000, and recall of 0.995. This indicates a high level of accuracy in correctly classifying thermal abnormalities associated with breast cancer. The proposed prototype serves as a highly effective tool for conducting initial investigations into breast cancer detection, offering potential advancements in early-stage diagnosis, and improving patient survival rates. [ABSTRACT FROM AUTHOR]

Face swapping or face replacement is a challenging task that involves transferring a source face to a target face while maintaining the target's facial motion and expression. Although many studies have made a lot of encouraging progress, we have noticed that most of the current solutions have the problem of blurred images, abnormal features, and unnatural pictures after face swapping. To solve these problems, in this paper, we proposed a composite face-swapping generation network, which includes a face extraction module and a feature fusion generation module. This model retains the original facial expression features, as well as the background and lighting of the image while performing face swapping, making the image more realistic and natural. Compared with other excellent models, our model is more robust in terms of face identity, posture verification, and image quality. [ABSTRACT FROM AUTHOR]

In the contemporary environment, mobile ad hoc networks (MANETs) have become necessary. They are absolutely vital in a variety of situations, where setting up a network quickly is required; however, this is infeasible due to low resources. Ad hoc networks have many applications: education, on the front lines of battle, rescue missions, etc. These networks are distinguished by high mobility and constrained computing, storage, and energy capabilities. The main aim of this research is to create a method for identifying blackhole attacks through anomaly detection techniques utilizing Support Vector Machines (SVM). Our detection system looks at node activity to scan network traffic for irregularities. In blackhole scenarios, the attackers exhibit distinct behavioral characteristics that distinguish them from other nodes. This can be efficiently detected by the proposed SVM-based detection system. The proposed detection system is designed to analyze network traffic and identify anomalies by examining node behaviors. Specifically, in the context of blackhole threats, it distinguishes the attackers from normal nodes based on behavioral characteristics. Using this approach, the system effectively detects blackhole attacks. The results demonstrate a very high level of accuracy in detecting blackhole attacks, confirming its efficacy in ensuring the security of mobile ad hoc networks (MANETs) by identifying and isolating malicious nodes. This solution is particularly valuable in scenarios like military operations and disaster management where a reliable communication system is crucial. Furthermore, the proposed detection method, ADS-SVM, was compared to two other methods (J48 classifier and NB classifier) from different researchers. The results indicate that ADS-SVM outperforms the other methods with a detection accuracy of 99.96%, surpassing the 99.2% achieved by J48 classifier and the 96.5% achieved by NB classifier. The results indicate that ADS-SVM is a highly efficient approach for identifying blackhole attacks in MANETs, potentially offering superior accuracy compared to other related methods. [ABSTRACT FROM AUTHOR]

The importance of early detection in the management of skin lesions, such as skin cancer, cannot be overstated due to its critical role in enhancing treatment outcomes. This study presents an innovative multi-input model that fuses image and tabular data to improve the accuracy of diagnoses. The model incorporates a dual-input architecture, combining a ResNet-152 for image processing with a multilayer perceptron (MLP) for tabular data analysis. To optimize the handling of tabular data, Principal Component Analysis (PCA) is employed to reduce dimensionality, facilitating more focused and efficient model training. The model's effectiveness is confirmed through rigorous testing, yielding impressive metrics with an F1 score of 98.91%, a recall of 99.19%, and a precision of 98.76%. These results underscore the potential of combining multiple data inputs to provide a nuanced analysis that outperforms single-modality approaches in skin lesion diagnostics. [ABSTRACT FROM AUTHOR]

Medical imaging and deep learning models are essential to the early identification and diagnosis of brain cancers, facilitating timely intervention and improving patient outcomes. This research paper investigates the integration of YOLOv5, a state-of-the-art object detection framework, with non-local neural networks (NLNNs) to improve brain tumor detection's robustness and accuracy. This study begins by curating a comprehensive dataset comprising brain MRI scans from various sources. To facilitate effective fusion, the YOLOv5 and NLNNs, K-means+, and spatial pyramid pooling fast+ (SPPF+) modules are integrated within a unified framework. The brain tumor dataset is used to refine the YOLOv5 model through the application of transfer learning techniques, adapting it specifically to the task of tumor detection. The results indicate that the combination of YOLOv5 and other modules results in enhanced detection capabilities in comparison to the utilization of YOLOv5 exclusively, proving recall rates of 86% and 83% respectively. Moreover, the research explores the interpretability aspect of the combined model. By visualizing the attention maps generated by the NLNNs module, the regions of interest associated with tumor presence are highlighted, aiding in the understanding and validation of the decision-making procedure of the methodology. Additionally, the impact of hyperparameters, such as NLNNs kernel size, fusion strategy, and training data augmentation, is investigated to optimize the performance of the combined model. [ABSTRACT FROM AUTHOR]

Emotion detection holds significant importance in facilitating human–computer interaction, enhancing the depth of engagement. By integrating this capability, we pave the way for forthcoming AI technologies to possess a blend of cognitive and emotional understanding, bridging the divide between machine functionality and human emotional complexity. This progress has the potential to reshape how machines perceive and respond to human emotions, ushering in an era of empathetic and intuitive artificial systems. The primary research challenge involves developing models that can accurately interpret and analyze emotions from both auditory and textual data, whereby auditory data require optimizing CNNs to detect subtle and intense emotional fluctuations in speech, and textual data necessitate access to large, diverse datasets to effectively capture nuanced emotional cues in written language. This paper introduces a novel approach to multimodal emotion recognition, seamlessly integrating speech and text modalities to accurately infer emotional states. Employing CNNs, we meticulously analyze speech using Mel spectrograms, while a BERT-based model processes the textual component, leveraging its bidirectional layers to enable profound semantic comprehension. The outputs from both modalities are combined using an attention-based fusion mechanism that optimally weighs their contributions. The proposed method here undergoes meticulous testing on two distinct datasets: Carnegie Mellon University's Multimodal Opinion Sentiment and Emotion Intensity (CMU-MOSEI) dataset and the Multimodal Emotion Lines Dataset (MELD). The results demonstrate superior efficacy compared to existing frameworks, achieving an accuracy of 88.4% and an F1-score of 87.9% on the CMU-MOSEI dataset, and a notable weighted accuracy (WA) of 67.81% and a weighted F1 (WF1) score of 66.32% on the MELD dataset. This comprehensive system offers precise emotion detection and introduces several significant advancements in the field. [ABSTRACT FROM AUTHOR]

The Nth-degree Truncated polynomial Ring Unit (NTRU) is one of the famous post-quantum cryptographic algorithms. Researchers consider NTRU to be the most important parameterized family of lattice-based public key cryptosystems that has been established to the IEEE P1363 standards. Lattice-based protocols necessitate operations on large vectors, which makes parallel computing one of the appropriate solutions to speed it up. NTRUEncrypt operations contain a large amount of data that requires many repetitive arithmetic operations. These operations make it a strong candidate to take advantage of the high degree of parallelism. The main costly operation that is repeated in all NTRU algorithm steps is polynomial multiplication. In this work, a Parallel Post-Quantum NTRUEncrypt algorithm called PPQNTRUEncrypt is proposed. This algorithm exploits the capabilities of parallel computing to accelerate the NTRUEncrypt algorithm. Both analytical and Apache Spark simulation models are used. The proposed algorithm enhanced the NTRUEncrypt algorithm by approximately 49.5%, 74.5%, 87.6%, 92.5%, 93.4%, and 94.5%, assuming that the number of processing elements is 2, 4, 8, 12, 16, and 20 respectively. [ABSTRACT FROM AUTHOR]

The realm of medical imaging is a critical frontier in precision diagnostics, where the clarity of the image is paramount. Despite advancements in imaging technology, noise remains a pervasive challenge that can obscure crucial details and impede accurate diagnoses. Addressing this, we introduce a novel teacher–student network model that leverages the potency of our bespoke NoiseContextNet Block to discern and mitigate noise with unprecedented precision. This innovation is coupled with an iterative pruning technique aimed at refining the model for heightened computational efficiency without compromising the fidelity of denoising. We substantiate the superiority and effectiveness of our approach through a comprehensive suite of experiments, showcasing significant qualitative enhancements across a multitude of medical imaging modalities. The visual results from a vast array of tests firmly establish our method's dominance in producing clearer, more reliable images for diagnostic purposes, thereby setting a new benchmark in medical image denoising. [ABSTRACT FROM AUTHOR]

Forest fires rank among the costliest and deadliest natural disasters globally. Identifying the smoke generated by forest fires is pivotal in facilitating the prompt suppression of developing fires. Nevertheless, succeeding techniques for detecting forest fire smoke encounter persistent issues, including a slow identification rate, suboptimal accuracy in detection, and challenges in distinguishing smoke originating from small sources. This study presents an enhanced YOLOv8 model customized to the context of unmanned aerial vehicle (UAV) images to address the challenges above and attain heightened precision in detection accuracy. Firstly, the research incorporates Wise-IoU (WIoU) v3 as a regression loss for bounding boxes, supplemented by a reasonable gradient allocation strategy that prioritizes samples of common quality. This strategic approach enhances the model's capacity for precise localization. Secondly, the conventional convolutional process within the intermediate neck layer is substituted with the Ghost Shuffle Convolution mechanism. This strategic substitution reduces model parameters and expedites the convergence rate. Thirdly, recognizing the challenge of inadequately capturing salient features of forest fire smoke within intricate wooded settings, this study introduces the BiFormer attention mechanism. This mechanism strategically directs the model's attention towards the feature intricacies of forest fire smoke, simultaneously suppressing the influence of irrelevant, non-target background information. The obtained experimental findings highlight the enhanced YOLOv8 model's effectiveness in smoke detection, proving an average precision (AP) of 79.4%, signifying a notable 3.3% enhancement over the baseline. The model's performance extends to average precision small (APS) and average precision large (APL), registering robust values of 71.3% and 92.6%, respectively. [ABSTRACT FROM AUTHOR]

The lack of medical databases is currently the main barrier to the development of artificial intelligence-based algorithms in medicine. This issue can be partially resolved by developing a reliable high-quality synthetic database. In this study, an easy and reliable method for developing a synthetic medical database based only on statistical data is proposed. This method changes the primary database developed based on statistical data using a special shuffle algorithm to achieve a satisfactory result and evaluates the resulting dataset using a neural network. Using the proposed method, a database was developed to predict the risk of developing type 2 diabetes 5 years in advance. This dataset consisted of data from 172,290 patients. The prediction accuracy reached 94.45% during neural network training of the dataset. [ABSTRACT FROM AUTHOR]

In the rapidly evolving landscape of internet usage, ensuring robust cybersecurity measures has become a paramount concern across diverse fields. Among the numerous cyber threats, denial of service (DoS) and distributed denial of service (DDoS) attacks pose significant risks, as they can render websites and servers inaccessible to their intended users. Conventional intrusion detection methods encounter substantial challenges in effectively identifying and mitigating these attacks due to their widespread nature, intricate patterns, and computational complexities. However, by harnessing the power of deep learning-based techniques, our proposed dense channel-spatial attention model exhibits exceptional accuracy in detecting and classifying DoS and DDoS attacks. The successful implementation of our proposed framework addresses the challenges posed by imbalanced data and exhibits its potential for real-world applications. By leveraging the dense channel-spatial attention mechanism, our model can precisely identify and classify DoS and DDoS attacks, bolstering the cybersecurity defenses of websites and servers. The high accuracy rates achieved across different datasets reinforce the robustness of our approach, underscoring its efficacy in enhancing intrusion detection capabilities. As a result, our framework holds promise in bolstering cybersecurity measures in real-world scenarios, contributing to the ongoing efforts to safeguard against cyber threats in an increasingly interconnected digital landscape. Comparative analysis with current intrusion detection methods reveals the superior performance of our model. We achieved accuracy rates of 99.38%, 99.26%, and 99.43% for Bot-IoT, CICIDS2017, and UNSW_NB15 datasets, respectively. These remarkable results demonstrate the capability of our approach to accurately detect and classify various types of DoS and DDoS assaults. By leveraging the inherent strengths of deep learning, such as pattern recognition and feature extraction, our model effectively overcomes the limitations of traditional methods, enhancing the accuracy and efficiency of intrusion detection systems. [ABSTRACT FROM AUTHOR]

Fire incidents occurring onboard ships cause significant consequences that result in substantial effects. Fires on ships can have extensive and severe wide-ranging impacts on matters such as the safety of the crew, cargo, the environment, finances, reputation, etc. Therefore, timely detection of fires is essential for quick responses and powerful mitigation. The study in this research paper presents a fire detection technique based on YOLOv7 (You Only Look Once version 7), incorporating improved deep learning algorithms. The YOLOv7 architecture, with an improved E-ELAN (extended efficient layer aggregation network) as its backbone, serves as the basis of our fire detection system. Its enhanced feature fusion technique makes it superior to all its predecessors. To train the model, we collected 4622 images of various ship scenarios and performed data augmentation techniques such as rotation, horizontal and vertical flips, and scaling. Our model, through rigorous evaluation, showcases enhanced capabilities of fire recognition to improve maritime safety. The proposed strategy successfully achieves an accuracy of 93% in detecting fires to minimize catastrophic incidents. Objects having visual similarities to fire may lead to false prediction and detection by the model, but this can be controlled by expanding the dataset. However, our model can be utilized as a real-time fire detector in challenging environments and for small-object detection. Advancements in deep learning models hold the potential to enhance safety measures, and our proposed model in this paper exhibits this potential. Experimental results proved that the proposed method can be used successfully for the protection of ships and in monitoring fires in ship port areas. Finally, we compared the performance of our method with those of recently reported fire-detection approaches employing widely used performance matrices to test the fire classification results achieved. [ABSTRACT FROM AUTHOR]

Over the past several years, many children have died from suffocation due to being left inside a closed vehicle on a sunny day. Various vehicle manufacturers have proposed a variety of technologies to locate an unattended child in a vehicle, including pressure sensors, passive infrared motion sensors, temperature sensors, and microwave sensors. However, these methods have not yet reliably located forgotten children in the vehicle. Recently, visual-based methods have taken the attention of manufacturers after the emergence of deep learning technology. However, the existing methods focus only on the forgotten child and neglect a forgotten pet. Furthermore, their systems only detect the presence of a child in the car with or without their parents. Therefore, this research introduces a visual-based framework to reduce hyperthermia deaths in enclosed vehicles. This visual-based system detects objects inside a vehicle; if the child or pet are without an adult, a notification is sent to the parents. First, a dataset is constructed for vehicle interiors containing children, pets, and adults. The proposed dataset is collected from different online sources, considering varying illumination, skin color, pet type, clothes, and car brands for guaranteed model robustness. Second, blurring, sharpening, brightness, contrast, noise, perspective transform, and fog effect augmentation algorithms are applied to these images to increase the training data. The augmented images are annotated with three classes: child, pet, and adult. This research concentrates on fine-tuning different state-of-the-art real-time detection models to detect objects inside the vehicle: NanoDet, YOLOv6_1, YOLOv6_3, and YOLO7. The simulation results demonstrate that YOLOv6_1 presents significant values with 96% recall, 95% precision, and 95% F1. [ABSTRACT FROM AUTHOR]

Understanding and identifying emotional cues in human speech is a crucial aspect of human–computer communication. The application of computer technology in dissecting and deciphering emotions, along with the extraction of relevant emotional characteristics from speech, forms a significant part of this process. The objective of this study was to architect an innovative framework for speech emotion recognition predicated on spectrograms and semantic feature transcribers, aiming to bolster performance precision by acknowledging the conspicuous inadequacies in extant methodologies and rectifying them. To procure invaluable attributes for speech detection, this investigation leveraged two divergent strategies. Primarily, a wholly convolutional neural network model was engaged to transcribe speech spectrograms. Subsequently, a cutting-edge Mel-frequency cepstral coefficient feature abstraction approach was adopted and integrated with Speech2Vec for semantic feature encoding. These dual forms of attributes underwent individual processing before they were channeled into a long short-term memory network and a comprehensive connected layer for supplementary representation. By doing so, we aimed to bolster the sophistication and efficacy of our speech emotion detection model, thereby enhancing its potential to accurately recognize and interpret emotion from human speech. The proposed mechanism underwent a rigorous evaluation process employing two distinct databases: RAVDESS and EMO-DB. The outcome displayed a predominant performance when juxtaposed with established models, registering an impressive accuracy of 94.8% on the RAVDESS dataset and a commendable 94.0% on the EMO-DB dataset. This superior performance underscores the efficacy of our innovative system in the realm of speech emotion recognition, as it outperforms current frameworks in accuracy metrics. [ABSTRACT FROM AUTHOR]

Drowsy driving can significantly affect driving performance and overall road safety. Statistically, the main causes are decreased alertness and attention of the drivers. The combination of deep learning and computer-vision algorithm applications has been proven to be one of the most effective approaches for the detection of drowsiness. Robust and accurate drowsiness detection systems can be developed by leveraging deep learning to learn complex coordinate patterns using visual data. Deep learning algorithms have emerged as powerful techniques for drowsiness detection because of their ability to learn automatically from given inputs and feature extractions from raw data. Eye-blinking-based drowsiness detection was applied in this study, which utilized the analysis of eye-blink patterns. In this study, we used custom data for model training and experimental results were obtained for different candidates. The blinking of the eye and mouth region coordinates were obtained by applying landmarks. The rate of eye-blinking and changes in the shape of the mouth were analyzed using computer-vision techniques by measuring eye landmarks with real-time fluctuation representations. An experimental analysis was performed in real time and the results proved the existence of a correlation between yawning and closed eyes, classified as drowsy. The overall performance of the drowsiness detection model was 95.8% accuracy for drowsy-eye detection, 97% for open-eye detection, 0.84% for yawning detection, 0.98% for right-sided falling, and 100% for left-sided falling. Furthermore, the proposed method allowed a real-time eye rate analysis, where the threshold served as a separator of the eye into two classes, the "Open" and "Closed" states. [ABSTRACT FROM AUTHOR]

In the image restoration task, the generative adversarial network (GAN) demonstrates excellent performance. However, there remain significant challenges concerning the task of generative face region inpainting. Traditional model approaches are ineffective in maintaining global consistency among facial components and recovering fine facial details. To address this challenge, this study proposes a facial restoration generation network combined a transformer module and GAN to accurately detect the missing feature parts of the face and perform effective and fine-grained restoration generation. We validate the proposed model using different image quality evaluation methods and several open-source face datasets and experimentally demonstrate that our model outperforms other current state-of-the-art network models in terms of generated image quality and the coherent naturalness of facial features in face image restoration generation tasks. [ABSTRACT FROM AUTHOR]

Deep learning has achieved remarkably positive results and impacts on medical diagnostics in recent years. Due to its use in several proposals, deep learning has reached sufficient accuracy to implement; however, the algorithms are black boxes that are hard to understand, and model decisions are often made without reason or explanation. To reduce this gap, explainable artificial intelligence (XAI) offers a huge opportunity to receive informed decision support from deep learning models and opens the black box of the method. We conducted an explainable deep learning method based on ResNet152 combined with Grad–CAM for endoscopy image classification. We used an open-source KVASIR dataset that consisted of a total of 8000 wireless capsule images. The heat map of the classification results and an efficient augmentation method achieved a high positive result with 98.28% training and 93.46% validation accuracy in terms of medical image classification. [ABSTRACT FROM AUTHOR]

Authorities and policymakers in Korea have recently prioritized improving fire prevention and emergency response. Governments seek to enhance community safety for residents by constructing automated fire detection and identification systems. This study examined the efficacy of YOLOv6, a system for object identification running on an NVIDIA GPU platform, to identify fire-related items. Using metrics such as object identification speed, accuracy research, and time-sensitive real-world applications, we analyzed the influence of YOLOv6 on fire detection and identification efforts in Korea. We conducted trials using a fire dataset comprising 4000 photos collected through Google, YouTube, and other resources to evaluate the viability of YOLOv6 in fire recognition and detection tasks. According to the findings, YOLOv6's object identification performance was 0.98, with a typical recall of 0.96 and a precision of 0.83. The system achieved an MAE of 0.302%. These findings suggest that YOLOv6 is an effective technique for detecting and identifying fire-related items in photos in Korea. Multi-class object recognition using random forests, k-nearest neighbors, support vector, logistic regression, naive Bayes, and XGBoost was performed on the SFSC data to evaluate the system's capacity to identify fire-related objects. The results demonstrate that for fire-related objects, XGBoost achieved the highest object identification accuracy, with values of 0.717 and 0.767. This was followed by random forest, with values of 0.468 and 0.510. Finally, we tested YOLOv6 in a simulated fire evacuation scenario to gauge its practicality in emergencies. The results show that YOLOv6 can accurately identify fire-related items in real time within a response time of 0.66 s. Therefore, YOLOv6 is a viable option for fire detection and recognition in Korea. The XGBoost classifier provides the highest accuracy when attempting to identify objects, achieving remarkable results. Furthermore, the system accurately identifies fire-related objects while they are being detected in real-time. This makes YOLOv6 an effective tool to use in fire detection and identification initiatives. [ABSTRACT FROM AUTHOR]

Commercial e-learning platforms have to overcome the challenge of resource overload and find the most suitable material for educators using a recommendation system (RS) when an exponential increase occurs in the amount of available online educational resources. Therefore, we propose a novel DNN method that combines synchronous sequences and heterogeneous features to more accurately generate candidates in e-learning platforms that face an exponential increase in the number of available online educational courses and learners. Mitigating the learners' cold-start problem was also taken into consideration during the modeling. Grouping learners in the first phase, and combining sequence and heterogeneous data as embeddings into recommendations using deep neural networks, are the main concepts of the proposed approach. Empirical results confirmed the proposed solution's potential. In particular, the precision rates were equal to 0.626 and 0.492 in the cases of Top-1 and Top-5 courses, respectively. Learners' cold-start errors were 0.618 and 0.697 for 25 and 50 new learners. [ABSTRACT FROM AUTHOR]

There is a high risk of bushfire in spring and autumn, when the air is dry. Do not bring any flammable substances, such as matches or cigarettes. Cooking or wood fires are permitted only in designated areas. These are some of the regulations that are enforced when hiking or going to a vegetated forest. However, humans tend to disobey or disregard guidelines and the law. Therefore, to preemptively stop people from accidentally starting a fire, we created a technique that will allow early fire detection and classification to ensure the utmost safety of the living things in the forest. Some relevant studies on forest fire detection have been conducted in the past few years. However, there are still insufficient studies on early fire detection and notification systems for monitoring fire disasters in real time using advanced approaches. Therefore, we came up with a solution using the convergence of the Internet of Things (IoT) and You Only Look Once Version 5 (YOLOv5). The experimental results show that IoT devices were able to validate some of the falsely detected fires or undetected fires that YOLOv5 reported. This report is recorded and sent to the fire department for further verification and validation. Finally, we compared the performance of our method with those of recently reported fire detection approaches employing widely used performance matrices to test the achieved fire classification results. [ABSTRACT FROM AUTHOR]

During the last decade, surveillance cameras have spread quickly; their spread is predicted to increase rapidly in the following years. Therefore, browsing and analyzing these vast amounts of created surveillance videos effectively is vital in surveillance applications. Recently, a video synopsis approach was proposed to reduce the surveillance video duration by rearranging the objects to present them in a portion of time. However, performing a synopsis for all the persons in the video is not efficacious for crowded videos. Different clustering and user-defined query methods are introduced to generate the video synopsis according to general descriptions such as color, size, class, and motion. This work presents a user-defined query synopsis video based on motion descriptions and specific visual appearance features such as gender, age, carrying something, having a baby buggy, and upper and lower clothing color. The proposed method assists the camera monitor in retrieving people who meet certain appearance constraints and people who enter a predefined area or move in a specific direction to generate the video, including a suspected person with specific features. After retrieving the persons, a whale optimization algorithm is applied to arrange these persons reserving chronological order, reducing collisions, and assuring a short synopsis video. The evaluation of the proposed work for the retrieval process in terms of precision, recall, and F1 score ranges from 83% to 100%, while for the video synopsis process, the synopsis video length compared to the original video is decreased by 68% to 93.2%, and the interacting tube pairs are preserved in the synopsis video by 78.6% to 100%. [ABSTRACT FROM AUTHOR]

In the discipline of hand gesture and dynamic sign language recognition, deep learning approaches with high computational complexity and a wide range of parameters have been an extremely remarkable success. However, the implementation of sign language recognition applications for mobile phones with restricted storage and computing capacities is usually greatly constrained by those limited resources. In light of this situation, we suggest lightweight deep neural networks with advanced processing for real-time dynamic sign language recognition (DSLR). This paper presents a DSLR application to minimize the gap between hearing-impaired communities and regular society. The DSLR application was developed using two robust deep learning models, the GRU and the 1D CNN, combined with the MediaPipe framework. In this paper, the authors implement advanced processes to solve most of the DSLR problems, especially in real-time detection, e.g., differences in depth and location. The solution method consists of three main parts. First, the input dataset is preprocessed with our algorithm to standardize the number of frames. Then, the MediaPipe framework extracts hands and poses landmarks (features) to detect and locate them. Finally, the features of the models are passed after processing the unification of the depth and location of the body to recognize the DSL accurately. To accomplish this, the authors built a new American video-based sign dataset and named it DSL-46. DSL-46 contains 46 daily used signs that were presented with all the needed details and properties for recording the new dataset. The results of the experiments show that the presented solution method can recognize dynamic signs extremely fast and accurately, even in real-time detection. The DSLR reaches an accuracy of 98.8%, 99.84%, and 88.40% on the DSL-46, LSA64, and LIBRAS-BSL datasets, respectively. [ABSTRACT FROM AUTHOR]

Currently, there is a growing population around the world, and this is particularly true in developing countries, where food security is becoming a major problem. Therefore, agricultural land monitoring, land use classification and analysis, and achieving high yields through efficient land use are important research topics in precision agriculture. Deep learning-based algorithms for the classification of satellite images provide more reliable and accurate results than traditional classification algorithms. In this study, we propose a transfer learning based residual UNet architecture (TL-ResUNet) model, which is a semantic segmentation deep neural network model of land cover classification and segmentation using satellite images. The proposed model combines the strengths of residual network, transfer learning, and UNet architecture. We tested the model on public datasets such as DeepGlobe, and the results showed that our proposed model outperforms the classic models initiated with random weights and pre-trained ImageNet coefficients. The TL-ResUNet model outperforms other models on several metrics commonly used as accuracy and performance measures for semantic segmentation tasks. Particularly, we obtained an IoU score of 0.81 on the validation subset of the DeepGlobe dataset for the TL-ResUNet model. [ABSTRACT FROM AUTHOR]

Meticulous learning of human emotions through speech is an indispensable function of modern speech emotion recognition (SER) models. Consequently, deriving and interpreting various crucial speech features from raw speech data are complicated responsibilities in terms of modeling to improve performance. Therefore, in this study, we developed a novel SER model via attention-oriented parallel convolutional neural network (CNN) encoders that parallelly acquire important features that are used for emotion classification. Particularly, MFCC, paralinguistic, and speech spectrogram features were derived and encoded by designing different CNN architectures individually for the features, and the encoded features were fed to attention mechanisms for further representation, and then classified. Empirical veracity executed on EMO-DB and IEMOCAP open datasets, and the results showed that the proposed model is more efficient than the baseline models. Especially, weighted accuracy (WA) and unweighted accuracy (UA) of the proposed model were equal to 71.8% and 70.9% in EMO-DB dataset scenario, respectively. Moreover, WA and UA rates were 72.4% and 71.1% with the IEMOCAP dataset. [ABSTRACT FROM AUTHOR]

Owing to the availability of a wide range of emotion recognition applications in our lives, such as for mental status calculation, the demand for high-performance emotion recognition approaches remains uncertain. Nevertheless, the wearing of facial masks has been indispensable during the COVID-19 pandemic. In this study, we propose a graph-based emotion recognition method that adopts landmarks on the upper part of the face. Based on the proposed approach, several pre-processing steps were applied. After pre-processing, facial expression features need to be extracted from facial key points. The main steps of emotion recognition on masked faces include face detection by using Haar–Cascade, landmark implementation through a media-pipe face mesh model, and model training on seven emotional classes. The FER-2013 dataset was used for model training. An emotion detection model was developed for non-masked faces. Thereafter, landmarks were applied to the upper part of the face. After the detection of faces and landmark locations were extracted, we captured coordinates of emotional class landmarks and exported to a comma-separated values (csv) file. After that, model weights were transferred to the emotional classes. Finally, a landmark-based emotion recognition model for the upper facial parts was tested both on images and in real time using a web camera application. The results showed that the proposed model achieved an overall accuracy of 91.2% for seven emotional classes in the case of an image application. Image based emotion detection of the proposed model accuracy showed relatively higher results than the real-time emotion detection. [ABSTRACT FROM AUTHOR]

This research aims to analyze the effect of feature selection on the accuracy of music popularity classification using machine learning algorithms. The data of Spotify, the most used music listening platform today, was used in the research. In the feature selection stage, features with low correlation were removed from the dataset using the filter feature selection method. Machine learning algorithms using all features produced 95.15% accuracy, while machine learning algorithms using features selected by feature selection produced 95.14% accuracy. The features selected by feature selection were sufficient for classification of popularity in established algorithms. In addition, this dataset contains fewer features, so the computation time is shorter. The reason why Big O time complexity is lower than models constructed without feature selection is that the number of features, which is the most important parameter in time complexity, is low. The statistical analysis was performed on the pre-processed data and meaningful information was produced from the data using machine learning algorithms. [ABSTRACT FROM AUTHOR]

Automatic detection of Wireless Endoscopic Images can avoid dangerous possible diseases such as cancers. Therefore, a number of articles have been published on different methods to enhance the speed of detection and accuracy. We also present a custom version of the YOLOv4-tiny for Wireless Endoscopic Image detection and localization that uses a You Only Look Once (YOLO) version to enhance the model accuracy. We modified the YOLOv4-tiny model by replacing the CSPDarknet-53-tiny backbone structure with the Inception-ResNet-A block to enhance the accuracy of the original YOLOv4-tiny. In addition, we implemented a new custom data augmentation method to enhance the data quality, even for small datasets. We focused on maintaining the color of medical images because the sensitivity of medical images can affect the efficiency of the model. Experimental results showed that our proposed method obtains 99.4% training accuracy; compared with the previous models, this is more than a 1.2% increase. An original model used for both detection and the segmentation of medical images may cause a high error rate. In contrast, our proposed model could eliminate the error rate of the detection and localization of disease areas from wireless endoscopic images. [ABSTRACT FROM AUTHOR]

Computing software plays an essential role in almost every sector of the digital age, but the process of efficient software development still faces several challenges. Effective software development methodology can be the difference between the success and failure of a software project. This research aims to evaluate the overall impact of Agile Software Development (ASD) on the individual, organizational, software development, and project management dimensions. For this purpose, we surveyed several software development professionals from a variety of backgrounds (experience, location, and job ranks) to explore the impact of ASD on the IT industry of Pakistan. Our analysis of the collected information is two folds. First, we summarized the findings from our surveys graphically clearly show the opinions of our survey respondents regarding the effectiveness of the Agile methodology for software development. Secondly, we utilized quantitative measures to analyze the same data statistically. A comparison is drawn between the graphical and statistical analysis to verify the reliability of our findings. Our findings suggest the existence of a strong relationship between effective software development and the use of Agile processes. Our analysis shows that the job fit of software development professionals and ASD are critical factors for software development project success in terms of cost, quality, stakeholders satisfaction, and time. Although the study focuses on the IT industry of Pakistan, the findings can be generalized easily to other developing IT industries worldwide. [ABSTRACT FROM AUTHOR]

The virtual hair styling service, which now is necessary for cosmetics companies and beauty centers, requires significant improvement efforts. In the existing technologies, the result is unnatural as the hairstyle image is serviced in the form of a 'composite' on the face image, image, extracts and synthesizing simple hair images. Because of complicated interactions in illumination, geometrical, and occlusions, that generate pairing among distinct areas of an image, blending features from numerous photos is extremely difficult. To compensate for the shortcomings of the current state of the art, based on GAN-Style, we address and propose an approach to image blending, specifically for the issue of visual hairstyling to increase accuracy and reproducibility, increase user convenience, increase accessibility, and minimize unnaturalness. Based on the extracted real customer image, we provide a virtual hairstyling service (Live Try-On service) that presents a new approach for image blending with maintaining details and mixing spatial features, as well as a new embedding approach-based GAN that can gradually adjust images to fit a segmentation mask, thereby proposing optimal styling and differentiated beauty tech service to users. The visual features from many images, including precise details, can be extracted using our system representation, which also enables image blending and the creation of consistent images. The Flickr-Faces-HQ Dataset (FFHQ) and the CelebA-HQ datasets, which are highly diversified, high quality datasets of human faces images, are both used by our system. In terms of the image evaluation metrics FID, PSNR, and SSIM, our system significantly outperforms the existing state of the art. [ABSTRACT FROM AUTHOR]

Communication for hearing-impaired communities is an exceedingly challenging task, which is why dynamic sign language was developed. Hand gestures and body movements are used to represent vocabulary in dynamic sign language. However, dynamic sign language faces some challenges, such as recognizing complicated hand gestures and low recognition accuracy, in addition to each vocabulary's reliance on a series of frames. This paper used MediaPipe in conjunction with RNN models to address dynamic sign language recognition issues. MediaPipe was used to determine the location, shape, and orientation by extracting keypoints of the hands, body, and face. RNN models such as GRU, LSTM, and Bi-directional LSTM address the issue of frame dependency in sign movement. Due to the lack of video-based datasets for sign language, the DSL10-Dataset was created. DSL10-Dataset contains ten vocabularies that were repeated 75 times by five signers providing the guiding steps for creating such one. Two experiments are carried out on our dataset (DSL10-Dataset) using RNN models to compare the accuracy of dynamic sign language recognition with and without the use of face keypoints. Experiments revealed that our model had an accuracy of more than 99%. [ABSTRACT FROM AUTHOR]

Traditional GAN-based image generation networks cannot accurately and naturally fuse surrounding features in local image generation tasks, especially in hairstyle generation tasks. To this end, we propose a novel transformer-based GAN for new hairstyle generation networks. The network framework comprises two modules: Face segmentation (F) and Transformer Generative Hairstyle (TGH) modules. The F module is used for the detection of facial and hairstyle features and the extraction of global feature masks and facial feature maps. In the TGH module, we design a transformer-based GAN to generate hairstyles and fix the details of the fusion part of faces and hairstyles in the new hairstyle generation process. To verify the effectiveness of our model, CelebA-HQ (Large-scale CelebFaces Attribute) and FFHQ (Flickr-Faces-HQ) are adopted to train and test our proposed model. In the image evaluation test used, FID, PSNR, and SSIM image evaluation methods are used to test our model and compare it with other excellent image generation networks. Our proposed model is more robust in terms of test scores and real image generation. [ABSTRACT FROM AUTHOR]

It is no secret today that quality software has a higher superiority than leading technology solutions in computer vision. Remarkable advancement has been achieved in ultrasound image classification, essentially because of the availability of large-scale annotated datasets and deep convolutional neural networks (CNN). Applying CNN in the sphere of medicine is also becoming an active and attractive research area for researchers. In this paper, we introduce an efficient method for the classification of fetal ultrasound images using CNN. To classify these images, we collected four types of fetal ultrasound images from hospitals and internet sources. We first analyze and evaluate various CNN models such as AlexNet, Inception_v3, and MobileNet_v1 for training and testing. Then, the results of these CNN models are quantitatively compared with the proposed model in accuracy and speed. The results show that the proposed classification method can be recognized faster without compromising performance and adjust the ultrasound image parameters quickly and automatically. The proposed CNN model's weight size is less than 1 Mb and can be used on mobile or embedded operating systems. We also developed and tested the application on the Android operating system-based mobile device. [ABSTRACT FROM AUTHOR]

Customer reviews on the Internet reflect users' sentiments about the product, service, and social events. As sentiments can be divided into positive, negative, and neutral forms, sentiment analysis processes identify the polarity of information in the source materials toward an entity. Most studies have focused on document-level sentiment classification. In this study, we apply an unsupervised machine learning approach to discover sentiment polarity not only at the document level but also at the word level. The proposed topic document sentence (TDS) model is based on joint sentiment topic (JST) and latent Dirichlet allocation (LDA) topic modeling techniques. The IMDB dataset, comprising user reviews, was used for data analysis. First, we applied the LDA model to discover topics from the reviews; then, the TDS model was implemented to identify the polarity of the sentiment from topic to document, and from document to word levels. The LDAvis tool was used for data visualization. The experimental results show that the analysis not only obtained good topic partitioning results, but also achieved high sentiment analysis accuracy in document- and word-level sentiment classifications. [ABSTRACT FROM AUTHOR]

Methods for text detection and recognition in images of natural scenes have become an active research topic in computer vision and have obtained encouraging achievements over several benchmarks. In this paper, we introduce a robust yet simple pipeline that produces accurate and fast text detection and recognition for the Uzbek language in natural scene images using a fully convolutional network and the Tesseract OCR engine. First, the text detection step quickly predicts text in random orientations in full-color images with a single fully convolutional neural network, discarding redundant intermediate stages. Then, the text recognition step recognizes the Uzbek language, including both the Latin and Cyrillic alphabets, using a trained Tesseract OCR engine. Finally, the recognized text can be pronounced using the Uzbek language text-to-speech synthesizer. The proposed method was tested on the ICDAR 2013, ICDAR 2015 and MSRA-TD500 datasets, and it showed an advantage in efficiently detecting and recognizing text from natural scene images for assisting the visually impaired. [ABSTRACT FROM AUTHOR]