Clustered Routing Using Chaotic Genetic Algorithm with Grey Wolf Optimization to Enhance Energy Efficiency in Sensor Networks.

As an alternative to flat architectures, clustering architectures are designed to minimize the total energy consumption of sensor networks. Nonetheless, sensor nodes experience increased energy consumption during data transmission, leading to a rapid depletion of energy levels as data are routed towards the base station. Although numerous strategies have been developed to address these challenges and enhance the energy efficiency of networks, the formulation of a clustering-based routing algorithm that achieves both high energy efficiency and increased packet transmission rate for large-scale sensor networks remains an NP-hard problem. Accordingly, the proposed work formulated an energy-efficient clustering mechanism using a chaotic genetic algorithm, and subsequently developed an energy-saving routing system using a bio-inspired grey wolf optimizer algorithm. The proposed chaotic genetic algorithm-grey wolf optimization (CGA-GWO) method is designed to minimize overall energy consumption by selecting energy-aware cluster heads and creating an optimal routing path to reach the base station. The simulation results demonstrate the enhanced functionality of the proposed system when associated with three more relevant systems, considering metrics such as the number of live nodes, average remaining energy level, packet delivery ratio, and overhead associated with cluster formation and routing.

Masked Face Emotion Recognition Based on Facial Landmarks and Deep Learning Approaches for Visually Impaired People.

Current artificial intelligence systems for determining a person's emotions rely heavily on lip and mouth movement and other facial features such as eyebrows, eyes, and the forehead. Furthermore, low-light images are typically classified incorrectly because of the dark region around the eyes and eyebrows. In this work, we propose a facial emotion recognition method for masked facial images using low-light image enhancement and feature analysis of the upper features of the face with a convolutional neural network. The proposed approach employs the AffectNet image dataset, which includes eight types of facial expressions and 420,299 images. Initially, the facial input image's lower parts are covered behind a synthetic mask. Boundary and regional representation methods are used to indicate the head and upper features of the face. Secondly, we effectively adopt a facial landmark detection method-based feature extraction strategy using the partially covered masked face's features. Finally, the features, the coordinates of the landmarks that have been identified, and the histograms of the oriented gradients are then incorporated into the classification procedure using a convolutional neural network. An experimental evaluation shows that the proposed method surpasses others by achieving an accuracy of 69.3% on the AffectNet dataset.

Development of Language Models for Continuous Uzbek Speech Recognition System.

Automatic speech recognition systems with a large vocabulary and other natural language processing applications cannot operate without a language model. Most studies on pre-trained language models have focused on more popular languages such as English, Chinese, and various European languages, but there is no publicly available Uzbek speech dataset. Therefore, language models of low-resource languages need to be studied and created. The objective of this study is to address this limitation by developing a low-resource language model for the Uzbek language and understanding linguistic occurrences. We proposed the Uzbek language model named UzLM by examining the performance of statistical and neural-network-based language models that account for the unique features of the Uzbek language. Our Uzbek-specific linguistic representation allows us to construct more robust UzLM, utilizing 80 million words from various sources while using the same or fewer training words, as applied in previous studies. Roughly sixty-eight thousand different words and 15 million sentences were collected for the creation of this corpus. The experimental results of our tests on the continuous recognition of Uzbek speech show that, compared with manual encoding, the use of neural-network-based language models reduced the character error rate to 5.26%.

Parking Lot Occupancy Detection with Improved MobileNetV3.

In recent years, parking lot management systems have garnered significant research attention, particularly concerning the application of deep learning techniques. Numerous approaches have emerged for tackling parking lot occupancy challenges using deep learning models. This study contributes to the field by addressing a critical aspect of parking lot management systems: accurate vehicle occupancy determination in specific parking spaces. We propose an advanced solution by harnessing an optimized MobileNetV3 model with custom architectural enhancements, trained on the CNRPark-EXT and PKLOT datasets. The model processes individual parking space patches from real-time video feeds, providing occupancy classification for each patch, identifying occupied or available spaces. Our architectural modifications include the integration of a convolutional block attention mechanism in place of the native attention module and the adoption of blueprint separable convolutions instead of the traditional depth-wise separable convolutions. In terms of performance, our proposed model exhibits superior results when benchmarked against state-of-the-art methods. Achieving an exceptional area under the ROC curve (AUC) value of 0.99 for most experiments with the PKLot dataset, our enhanced MobileNetV3 showcases its exceptional discriminatory power in binary classification. Benchmarked against the CarNet and mAlexNet models, representative of previous state-of-the-art solutions, our proposed model showcases exceptional performance. During evaluations using the combined CNRPark-EXT and PKLot datasets, the proposed model attains an impressive average accuracy of 98.01%, while CarNet achieves 97.03%. Beyond achieving high accuracy and precision comparable to previous models, the proposed model exhibits promise for real-time applications. This work contributes to the advancement of parking lot occupancy detection by offering a robust and efficient solution with implications for urban mobility enhancement and resource optimization.

Automatic Object Detection Algorithm-Based Braille Image Generation System for the Recognition of Real-Life Obstacles for Visually Impaired People.

The global prevalence of visual impairment due to diseases and accidents continues to increase. Visually impaired individuals rely on their auditory and tactile senses to recognize surrounding objects. However, accessible public facilities such as tactile pavements and tactile signs are installed only in limited areas globally, and visually impaired individuals use assistive devices such as canes or guide dogs, which have limitations. In particular, the visually impaired are not equipped to face unexpected situations by themselves while walking. Therefore, these situations are becoming a great threat to the safety of the visually impaired. To solve this problem, this study proposes a living assistance system, which integrates object recognition, object extraction, outline generation, and braille conversion algorithms, that is applicable both indoors and outdoors. The smart glasses guide objects in real photos, and the user can detect the shape of the object through a braille pad. Moreover, we built a database containing 100 objects on the basis of a survey to select objects frequently used by visually impaired people in real life to construct the system. A performance evaluation, consisting of accuracy and usefulness evaluations, was conducted to assess the system. The former involved comparing the tactile image generated on the basis of braille data with the expected tactile image, while the latter confirmed the object extraction accuracy and conversion rate on the basis of the images of real-life situations. As a result, the living assistance system proposed in this study was found to be efficient and useful with an average accuracy of 85% a detection accuracy of 90% and higher, and an average braille conversion time of 6.6 s. Ten visually impaired individuals used the assistance system and were satisfied with its performance. Participants preferred tactile graphics that contained only the outline of the objects, over tactile graphics containing the full texture details.

Automatic Speech Recognition Method Based on Deep Learning Approaches for Uzbek Language.

Communication has been an important aspect of human life, civilization, and globalization for thousands of years. Biometric analysis, education, security, healthcare, and smart cities are only a few examples of speech recognition applications. Most studies have mainly concentrated on English, Spanish, Japanese, or Chinese, disregarding other low-resource languages, such as Uzbek, leaving their analysis open. In this paper, we propose an End-To-End Deep Neural Network-Hidden Markov Model speech recognition model and a hybrid Connectionist Temporal Classification (CTC)-attention network for the Uzbek language and its dialects. The proposed approach reduces training time and improves speech recognition accuracy by effectively using CTC objective function in attention model training. We evaluated the linguistic and lay-native speaker performances on the Uzbek language dataset, which was collected as a part of this study. Experimental results show that the proposed model achieved a word error rate of 14.3% using 207 h of recordings as an Uzbek language training dataset.

Automatic Fire Detection and Notification System Based on Improved YOLOv4 for the Blind and Visually Impaired.

The growing aging population suffers from high levels of vision and cognitive impairment, often resulting in a loss of independence. Such individuals must perform crucial everyday tasks such as cooking and heating with systems and devices designed for visually unimpaired individuals, which do not take into account the needs of persons with visual and cognitive impairment. Thus, the visually impaired persons using them run risks related to smoke and fire. In this paper, we propose a vision-based fire detection and notification system using smart glasses and deep learning models for blind and visually impaired (BVI) people. The system enables early detection of fires in indoor environments. To perform real-time fire detection and notification, the proposed system uses image brightness and a new convolutional neural network employing an improved YOLOv4 model with a convolutional block attention module. The h-swish activation function is used to reduce the running time and increase the robustness of YOLOv4. We adapt our previously developed smart glasses system to capture images and inform BVI people about fires and other surrounding objects through auditory messages. We create a large fire image dataset with indoor fire scenes to accurately detect fires. Furthermore, we develop an object mapping approach to provide BVI people with complete information about surrounding objects and to differentiate between hazardous and nonhazardous fires. The proposed system shows an improvement over other well-known approaches in all fire detection metrics such as precision, recall, and average precision.

Improved Classification Approach for Fruits and Vegetables Freshness Based on Deep Learning.

Classification of fruit and vegetable freshness plays an essential role in the food industry. Freshness is a fundamental measure of fruit and vegetable quality that directly affects the physical health and purchasing motivation of consumers. In addition, it is a significant determinant of market price; thus, it is imperative to study the freshness of fruits and vegetables. Owing to similarities in color, texture, and external environmental changes, such as shadows, lighting, and complex backgrounds, the automatic recognition and classification of fruits and vegetables using machine vision is challenging. This study presents a deep-learning system for multiclass fruit and vegetable categorization based on an improved YOLOv4 model that first recognizes the object type in an image before classifying it into one of two categories: fresh or rotten. The proposed system involves the development of an optimized YOLOv4 model, creating an image dataset of fruits and vegetables, data argumentation, and performance evaluation. Furthermore, the backbone of the proposed model was enhanced using the Mish activation function for more precise and rapid detection. Compared with the previous YOLO series, a complete experimental evaluation of the proposed method can obtain a higher average precision than the original YOLOv4 and YOLOv3 with 50.4%, 49.3%, and 41.7%, respectively. The proposed system has outstanding prospects for the construction of an autonomous and real-time fruit and vegetable classification system for the food industry and marketplaces and can also help visually impaired people to choose fresh food and avoid food poisoning.

Design and Implementation of Embedded-Based Vein Image Processing System with Enhanced Denoising Capabilities.

In general, it is very difficult to visually locate blood vessels for intravenous injection or surgery. In addition, if vein detection fails, physical and mental pain occurs to the patient and leads to financial loss in the hospital. In order to prevent this problem, NIR-based vein detection technology is developing. The proposed study combines vein detection and digital hair removal to eliminate body hair, a noise that hinders the accuracy of detection, improving the performance of the entire algorithm by about 10.38% over existing systems. In addition, as a result of performing venous detection of patients without body hair, 5.04% higher performance than the existing system was detected, and the proposed study results were verified. It is expected that the use of devices to which the proposed study is applied will provide more accurate vascular maps in general situations.

A Wildfire Smoke Detection System Using Unmanned Aerial Vehicle Images Based on the Optimized YOLOv5.

Wildfire is one of the most significant dangers and the most serious natural catastrophe, endangering forest resources, animal life, and the human economy. Recent years have witnessed a rise in wildfire incidents. The two main factors are persistent human interference with the natural environment and global warming. Early detection of fire ignition from initial smoke can help firefighters react to such blazes before they become difficult to handle. Previous deep-learning approaches for wildfire smoke detection have been hampered by small or untrustworthy datasets, making it challenging to extrapolate the performances to real-world scenarios. In this study, we propose an early wildfire smoke detection system using unmanned aerial vehicle (UAV) images based on an improved YOLOv5. First, we curated a 6000-wildfire image dataset using existing UAV images. Second, we optimized the anchor box clustering using the K-mean++ technique to reduce classification errors. Then, we improved the network's backbone using a spatial pyramid pooling fast-plus layer to concentrate small-sized wildfire smoke regions. Third, a bidirectional feature pyramid network was applied to obtain a more accessible and faster multi-scale feature fusion. Finally, network pruning and transfer learning approaches were implemented to refine the network architecture and detection speed, and correctly identify small-scale wildfire smoke areas. The experimental results proved that the proposed method achieved an average precision of 73.6% and outperformed other one- and two-stage object detectors on a custom image dataset.

Enhanced Classification of Dog Activities with Quaternion-Based Fusion Approach on High-Dimensional Raw Data from Wearable Sensors.

The employment of machine learning algorithms to the data provided by wearable movement sensors is one of the most common methods to detect pets' behaviors and monitor their well-being. However, defining features that lead to highly accurate behavior classification is quite challenging. To address this problem, in this study we aim to classify six main dog activities (standing, walking, running, sitting, lying down, and resting) using high-dimensional sensor raw data. Data were received from the accelerometer and gyroscope sensors that are designed to be attached to the dog's smart costume. Once data are received, the module computes a quaternion value for each data point that provides handful features for classification. Next, to perform the classification, we used several supervised machine learning algorithms, such as the Gaussian naïve Bayes (GNB), Decision Tree (DT), K-nearest neighbor (KNN), and support vector machine (SVM). In order to evaluate the performance, we finally compared the proposed approach's F-score accuracies with the accuracy of classic approach performance, where sensors' data are collected without computing the quaternion value and directly utilized by the model. Overall, 18 dogs equipped with harnesses participated in the experiment. The results of the experiment show a significantly enhanced classification with the proposed approach. Among all the classifiers, the GNB classification model achieved the highest accuracy for dog behavior. The behaviors are classified with F-score accuracies of 0.94, 0.86, 0.94, 0.89, 0.95, and 1, respectively. Moreover, it has been observed that the GNB classifier achieved 93% accuracy on average with the dataset consisting of quaternion values. In contrast, it was only 88% when the model used the dataset from sensors' data.

Design and Implementation of a Video/Voice Process System for Recognizing Vehicle Parts Based on Artificial Intelligence.

With the recent development of artificial intelligence along with information and communications infrastructure, a new paradigm of online services is being developed. Whereas in the past a service system could only exchange information of the service provider at the request of the user, information can now be provided by automatically analyzing a particular need, even without a direct user request. This also holds for online platforms of used-vehicle sales. In the past, consumers needed to inconveniently determine and classify the quality of information through static data provided by service and information providers. As a result, this service field has been harmful to consumers owing to such problems as false sales, fraud, and exaggerated advertising. Despite significant efforts of platform providers, there are limited human resources for censoring the vast amounts of data uploaded by sellers. Therefore, in this study, an algorithm called YOLOv3+MSSIM Type 2 for automatically censoring the data of used-vehicle sales on an online platform was developed. To this end, an artificial intelligence system that can automatically analyze an object in a vehicle video uploaded by a seller, and an artificial intelligence system that can filter the vehicle-specific terms and profanity from the seller's video presentation, were also developed. As a result of evaluating the developed system, the average execution speed of the proposed YOLOv3+MSSIM Type 2 algorithm was 78.6 ms faster than that of the pure YOLOv3 algorithm, and the average frame rate per second was improved by 40.22 fps. In addition, the average GPU utilization rate was improved by 23.05%, proving the efficiency.

Towards Tangible Vision for the Visually Impaired through 2D Multiarray Braille Display.

This paper presents two methodologies for delivering multimedia content to visually impaired people with the use of a haptic device and braille display. Based on our previous research, the research using Kinect v2 and haptic device with 2D+ (RGB frame with depth) data has the limitations of slower operational speed while reconstructing object details. Thus, this study focuses on the development of 2D multiarray braille display using an electronic book translator application because of its accuracy and high speed. This approach provides mobility and uses 2D multiarray braille display to represent media content contour more efficiently. In conclusion, this study achieves the representation of considerably massive text content compared to previous 1D braille displays. Besides, it also represents illustrations and figures to braille displays through quantization and binarization.

Optimization of lamp arrangement in a closed-conduit UV reactor based on a genetic algorithm.

The choice for the arrangement of the UV lamps in a closed-conduit ultraviolet (CCUV) reactor significantly affects the performance. However, a systematic methodology for the optimal lamp arrangement within the chamber of the CCUV reactor is not well established in the literature. In this research work, we propose a viable systematic methodology for the lamp arrangement based on a genetic algorithm (GA). In addition, we analyze the impacts of the diameter, angle, and symmetry of the lamp arrangement on the reduction equivalent dose (RED). The results are compared based on the simulated RED values and evaluated using the computational fluid dynamics simulations software ANSYS FLUENT. The fluence rate was calculated using commercial software UVCalc3D, and the GA-based lamp arrangement optimization was achieved using MATLAB. The simulation results provide detailed information about the GA-based methodology for the lamp arrangement, the pathogen transport, and the simulated RED values. A significant increase in the RED values was achieved by using the GA-based lamp arrangement methodology. This increase in RED value was highest for the asymmetric lamp arrangement within the chamber of the CCUV reactor. These results demonstrate that the proposed GA-based methodology for symmetric and asymmetric lamp arrangement provides a viable technical solution to the design and optimization of the CCUV reactor.

Carrier Transport Properties of MoS2 Asymmetric Gas Sensor Under Charge Transfer-Based Barrier Modulation.

Over the past few years, two-dimensional materials have gained immense attention for next-generation electric sensing devices because of their unique properties. Here, we report the carrier transport properties of MoS2 Schottky diodes under ambient as well as gas exposure conditions. MoS2 field-effect transistors (FETs) were fabricated using Pt and Al electrodes. The work function of Pt is higher than that of MoS2, while that of Al is lower than that of MoS2. The MoS2 device with Al contacts showed much higher current than that with Pt contacts because of its lower Schottky barrier height (SBH). The electrical characteristics and gas responses of the MoS2 Schottky diodes with Al and Pt contacts were measured electrically and were simulated by density functional theory calculations. The theoretically calculated SBH of the diode (under gas absorption) showed that NOx molecules had strong interaction with the diode and induced a negative charge transfer. However, an opposite trend was observed in the case of NH3 molecules. We also investigated the effect of metal contacts on the gas sensing performance of MoS2 FETs both experimentally and theoretically.

Cardiac segmentation by a velocity-aided active contour model.

Heart disease is one of the more life-threatening diseases. Accurate diagnosis and treatment are central to the survival of patients. Numerous diagnostic methods that can assess abnormalities of the heart have been developed. Among these methods, cardiac functional analysis has been widely used to derive cardiac functional parameters that describe the functionality of the heart and are frequently used in diagnosis of various heart diseases. Segmentation of the myocardial boundaries is an essential step for deriving these cardiac functional parameters, and the accuracy of parameters depends much on the correctness of the segmented boundaries. Therefore, it is essential that cardiac segmentation be accurate and reliable. However, current segmentation techniques still have difficulty both extracting accurate myocardial boundaries, especially the endocardial boundary and performing a fully automatic process because of low image quality, the complex shape and motion pattern of the heart, and lack of clear delineation between the myocardium and adjacent anatomic structures. A velocity-aided cardiac segmentation method based a modified active contour model, the tensor-based orientation gradient force (OGF) and phase contrast magnetic resonance imaging (MRI) has been developed to improve the accuracy of segmentation of the myocardial boundaries, especially the endocardial boundary. Furthermore, the initial seed contour tracking (SCT) algorithm has been also developed to improve the accuracy of automatic sequential frame segmentation in conjunction with the OGF-based segmentation method. The performance of the proposed method was assessed by experimentations on a phase contrast MRI data set of three normal human volunteer. The results of the individual frame segmentation showed that the accuracy and reproducibility of segmentation of the endocardial boundary by the use of the OGF was generally improved around the lower level of the LV and end systole. The results of the sequential frame segmentation showed that the propagation of errors caused was significantly reduced by the use of the SCT in addition to the OGF and improvements in the accuracy and reproducibility of segmentation of the endocardial boundary were much higher than the individual frame segmentation. However, improvements were generally negligible around the upper level of the LV and end diastole, and the velocity wrap-around problem and blood turbulence around the basal level of the ventricles even degraded the performance of boundary segmentation. Although this work demonstrates the potential of using the velocity information from phase contrast MRI for cardiac segmentation, the velocity wrap-around artifacts in phase contrast MRI data sets can degrade the performance. Therefore, future work must include the development of appropriate methods to cope with these artifacts.

Numerical study of the effects of surface roughness on water disinfection UV reactor.

UV reactors are an emerging choice as a big barrier against the pathogens present in drinking water. However, the precise role of reactor's wall roughness for cross flow ultraviolet (CF-UV) and axial flow ultraviolet (AF-UV) water disinfection reactors are unknown. In this paper, the influences of reactor's wall roughness were investigated with a view to identify their role on the performance factors namely dose distribution and reduction equivalent dose (RED). Herein, the relative effects of reactor's wall roughness on the performance of CF-UV and AF-UV reactors were also highlighted. This numerical study is a first step towards the comprehensive analysis of the effects of reactor's wall roughness for UV reactor. A numerical analysis was performed using ANSYS Fluent 15 academic version. The reactor's wall roughness has a significant effect on the RED. We found that the increase in RED is Reynolds number dependent (at lower value of turbulent Reynolds number the effects are remarkable). The effects of reactor's roughness were more pronounced for AF-UV reactor. The simulation results suggest that the study of reactor's wall roughness provides valuable insight to fully understand the effects of reactor's wall roughness and its impact on the flow behavior and other features of CF-UV and AF-UV water disinfection reactors.

A Reduced Graphene Oxide Based Radio Frequency Glucose Sensing Device Using Multi-Dimensional Parameters.

A reduced graphene oxide (RGO) based glucose sensor using a radio frequency (RF) signal is demonstrated. An RGO with outstanding electrical property was employed as the interconnector material between signal electrodes in an RF electric circuit, and it was functionalized with phenylbutyric acid (PBA) as a linker molecule to bind glucoses. By adding glucose solution, the fabricated sensor with RGO and PBA showed detecting characteristics in RF signal transmission and reflection. Frequency dependent electrical parameters such as resistance, inductance, shunt conductance and shunt capacitance were extracted from the RF results under the equivalent circuit model. These parameters also provided sensing characteristics of glucose with different concentrations. Using these multi-dimensional parameters, the RF sensor device detected glucose levels in the range of 1⁻4 mM, which ordinarily covers the testing range for diabetes or medical examination. The RGO based RF sensor, which fits well to a linear curve with fine stability, holds considerable promise for biomaterials detection, including glucose.

Elastically deformable model-based motion-tracking of left ventricle.

The motion of the myocardium is a sensitive indicator of many types of heart disease. Quantitative characterization of this motion is essential for the accurate diagnosis and treatment of heart disease. Although several magnetic resonance imaging (MRI) techniques, such as tagged MRI and phase contrast MRI, provide noninvasive tools to obtain correlation of the position of points within the myocardium between images taken at subsequent time phases, the accurate tracking of the movement of these points remains a challenge due to the relatively low out-of-plane resolution of these imaging techniques. A motion tracking method based on elastic deformation estimation of a deformable model has been developed to track the three-dimensional motion of the myocardium. Elastic deformation estimation is performed on phase contrast MRI data by balancing the deformation potential energy of a deformable model and the potential energy derived from integrating velocity values of myocardial tissue points. The advantage of this method is that it can provide a physically plausible yet computationally efficient framework for cardiac motion tracking. To assess the proposed method, the motion of a normal human left ventricle (LV) was tracked throughout the entire cardiac cycle, and a quantitative strain analysis of the motion of the LV was carried out from end diastole to end systole. The results showed that the strain measurements were generally found to be consistent with previously published values.