Search

The prediction of the health status of critical components is an important influence in making accurate maintenance decisions for rotating equipment. Since vibration signals contain a large amount of fault information, they can more accurately describe the health status of critical components. Therefore, it is widely used in the field of rotating equipment health state prediction. However, there are two major problems in predicting the health status of key components based on vibration signals: (1) The working environment of rotating equipment is harsh, and if only one feature in the time or frequency domain is selected for fault analysis, it will be susceptible to harsh operating environments and cannot completely reflect the fault information. (2) The vibration signals are unlabeled time series data, which are difficult to accurately convert into the health status of key components. In order to solve the above problems, this paper proposes a combined prediction model combining a bidirectional long- and short-term memory network (BiLSTM), a self-organizing neural network (SOM) and particle swarm optimization (PSO). Firstly, the SOM is utilized to fuse the fault characteristics of multiple vibration signals of key components to obtain an indicator (HI) that can reflect the health status of rotating equipment and to also compensate for the vulnerability of single signal characteristics in the time or frequency domain to environmental influences. Secondly, the K-means clustering method is employed to cluster the health indicators and determine the health state, which solves the problem of determining the health of a component from unsupervised vibration signal data which is quite difficult. Finally, the particle swarm optimized BiLSTM model is used to predict the health state of key components and the bearing dataset from the IEEE PHM 2012 Data Challenge verifies the method's effectiveness and validity. [ABSTRACT FROM AUTHOR]

In view of the complex multi-scale target detection environment of ultrasonic atlas of weld defect and the poor detection performance of existing algorithms for the multiple small target defects, the Faster RCNN convolution neural network is applied to weld defect detection, and a Fast RCNN deep learning network is proposed in combination with an improved ResNet 50. Based on the coexistence of multiple small targets and multi-scale target detection, this paper proposes to combine deformable network, FPN network and ResNet50 to improve the detection performance of the algorithm for multi-scale targets, especially small targets. Based on the efficiency and accuracy of candidate frame selection, K-means clustering algorithm and ROI Align algorithm are proposed, and the anchors points and candidate frames suitable for weld defect data sets are customized for accurate positioning. Through the self-made ultrasonic atlas data set of weld defects and experimental verification of the improved algorithm in this paper, the overall mean average precision has reaches 93.72%, and the average precision of small target defects such as "stoma" and "crack" has reaches 92.5% and 88.9% respectively, which is 4.8% higher than the original Faster RCNN algorithm. At the same time, through the ablation experiments and comparison experiments with other mainstream target detection algorithms, it is proved that the improved method proposed in this paper improves the detection performance and is superior to other algorithms. The actual industrial detection scene proves that it basically meets the requirements of weld defect detection, and can provide a reference for the intelligent detection method of weld defects. [ABSTRACT FROM AUTHOR]

The rapid expansion of metro networks, e.g., in many cities of China, continuously introduces the operation of new stations every year. Due to the lack of historical data and complicate variations of short-term passenger flow in the early stage of operation, it is difficult to accurately predict inbound and outbound passenger flows of new metro stations in the short term, which would be the database for train scheduling for new stations before operation, dynamic capacity optimization for new stations under operation, short-term prediction of cycle sharing demands near new stations, and so on. Traditional methods usually failed to exactly reflect the complicate rules or were unusable without the new station's historical data. In order to solve the above problems, this paper proposes a short-term inbound and outbound passenger flow prediction model for new metro stations at the early stage of operation by combining the K-means clustering algorithm, an improved spatiotemporal long short-term memory model (Sp-LSTM), and a real-time feedback error model (mean absolute error, MAE), where passenger flows' spatial-temporal characteristics and land-use relevance are considered. The application in Guangzhou Metro, China, where Line 21 is regarded as a new line, shows that the proposed K-Sp-LSTM model has the best prediction accuracy compared with traditional methods. [ABSTRACT FROM AUTHOR]

Solar cells are playing a significant role in aerospace equipment. In view of the surface defect characteristics in the manufacturing process of solar cells, the common surface defects are divided into three categories, which include difficult-detecting defects (mismatch), general defects (bubble, glass-crack and cell-crack) and easy-detecting defects (glass-upside-down). Corresponding to different types of defects, the deep learning model with different optimization methods and a classification detection method based on multi-models fusion are proposed in the paper. In the proposed model, in order to solve the mismatch problem between the default anchor boxes size of YOLOv5s model and the extreme scale of the battery mismatch defect label boxes, the K-means algorithm was adopted to re-cluster the dedicated anchor boxes for the mismatch defect label boxes. In order to improve the comprehensive detection accuracy of YOLOv5s model for the general defects, the YOLOv5s model was also improved by the methods of image preprocessing, anchor box improving and detection head replacing. In order to ensure the recognition accuracy and improve the detection speed for easy-detecting defects, the lightweight classification network MobileNetV2 was also used to classify the cells with glass-upside-down defects. The experimental results show that the proposed optimization model and classification detection method can significantly improve the defect detection precision. Respectively, the detection precision for mismatch, bubble, glass-crack and cell-crack defects are up to 95.64%, 91.8%, 93.1% and 98.0%. By using lightweight model to train the glass-upside-down defect dataset, the average classification accuracy reaches 100% and the detection speed reaches 13.29 frames per second. The comparison experiments show that the proposed model has a great improvement in detection accuracy compared with the original model, and the defect detection speed of lightweight classification network is improved more obviously, which confirms the effectiveness of the proposed optimization model and the multi-defect classification detection method for solar cells defect detection. [ABSTRACT FROM AUTHOR]

In the intelligent engine room, the visual perception of ship engine room equipment is the premise of defect identification and the replacement of manual operation. This paper improves YOLOv5 for the problems of mutual occlusion of cabin equipment, an unbalanced number of different categories, and a large proportion of small targets. First, a coordinate attention (CA) mechanism is introduced into the backbone-extraction network to improve the ability of the network to extract main features. Secondly, this paper improves the neck network so that the network can learn a relatively important resolution for feature-fusion and enrich the semantic information between different layers. At the same time, this paper uses the Swin transformer as the prediction head (SPH). This enables the network to establish global connections in complex environments, which can improve detection accuracy. In order to solve the problem of cabin equipment covering each other, this paper replaces the original non-maxima suppression (NMS) with Soft-NMS. Finally, this paper uses the K-means algorithm based on the genetic algorithm to cluster new anchor boxes to match the dataset better. This paper is evaluated on the laboratory's engine room equipment dataset (EMER) and the public dataset PASCAL VOC. Compared with YOLOv5m, the mAP of CBS-YOLOv5m increased by 3.34% and 1.8%, respectively. [ABSTRACT FROM AUTHOR]

Instructors face significant time and effort constraints when grading students' assessments on a large scale. Clustering similar assessments is a unique and effective technique that has the potential to significantly reduce the workload of instructors in online and large-scale learning environments. By grouping together similar assessments, marking one assessment in a cluster can be scaled to other similar assessments, allowing for a more efficient and streamlined grading process. To address this issue, this paper focuses on text assessments and proposes a method for reducing the workload of instructors by clustering similar assessments. The proposed method involves the use of distributed representation to transform texts into vectors, and contrastive learning to improve the representation that distinguishes the differences among similar texts. The paper presents a general framework for clustering similar texts that includes label representation, K-means, and self-organization map algorithms, with the objective of improving clustering performance using Accuracy (ACC) and Normalized Mutual Information (NMI) metrics. The proposed framework is evaluated experimentally using two real datasets. The results show that self-organization maps and K-means algorithms with Pre-trained language models outperform label representation algorithms for different datasets. [ABSTRACT FROM AUTHOR]

Reflective phenomena often occur in the detecting process of pointer meters by inspection robots in complex environments, which can cause the failure of pointer meter readings. In this paper, an improved k-means clustering method for adaptive detection of pointer meter reflective areas and a robot pose control strategy to remove reflective areas are proposed based on deep learning. It mainly includes three steps: (1) YOLOv5s (You Only Look Once v5-small) deep learning network is used for real-time detection of pointer meters. The detected reflective pointer meters are preprocessed by using a perspective transformation. Then, the detection results and deep learning algorithm are combined with the perspective transformation. (2) Based on YUV (luminance-bandwidth-chrominance) color spatial information of collected pointer meter images, the fitting curve of the brightness component histogram and its peak and valley information is obtained. Then, the k-means algorithm is improved based on this information to adaptively determine its optimal clustering number and its initial clustering center. In addition, the reflection detection of pointer meter images is carried out based on the improved k-means clustering algorithm. (3) The robot pose control strategy, including its moving direction and distance, can be determined to eliminate the reflective areas. Finally, an inspection robot detection platform is built for experimental study on the performance of the proposed detection method. Experimental results show that the proposed method not only has good detection accuracy that achieves 0.809 but also has the shortest detection time, which is only 0.6392 s compared with other methods available in the literature. The main contribution of this paper is to provide a theoretical and technical reference to avoid circumferential reflection for inspection robots. It can adaptively and accurately detect reflective areas of pointer meters and can quickly remove them by controlling the movement of inspection robots. The proposed detection method has the potential application to realize real-time reflection detection and recognition of pointer meters for inspection robots in complex environments. [ABSTRACT FROM AUTHOR]

Crabs and lobsters are valuable crustaceans that contribute enormously to the seafood needs of the growing human population. This paper presents a comprehensive analysis of single- and multi-stage object detectors for the detection of crabs and lobsters using images captured onboard fishing boats. We investigate the speed and accuracy of multiple object detection techniques using a novel dataset, multiple backbone networks, various input sizes, and fine-tuned parameters. We extend our work to train lightweight models to accommodate the fishing boats equipped with low-power hardware systems. Firstly, we train Faster R-CNN, SSD, and YOLO with different backbones and tuning parameters. The models trained with higher input sizes resulted in lower frames per second (FPS) and vice versa. The base models were highly accurate but were compromised in computational and run-time costs. The lightweight models were adaptable to low-power hardware compared to the base models. Secondly, we improved the performance of YOLO (v3, v4, and tiny versions) using custom anchors generated by the k-means clustering approach using our novel dataset. The YOLO (v4 and it's tiny version) achieved mean average precision (mAP) of 99.2% and 95.2%, respectively. The YOLOv4-tiny trained on the custom anchor-based dataset is capable of precisely detecting crabs and lobsters onboard fishing boats at 64 frames per second (FPS) on an NVidia GeForce RTX 3070 GPU. The Results obtained identified the strengths and weaknesses of each method towards a trade-off between speed and accuracy for detecting objects in input images. [ABSTRACT FROM AUTHOR]

In the evolving landscape of targeted marketing, integrating deep learning (DL) and explainable AI (XAI) offers a promising avenue for enhanced customer segmentation. This paper introduces a groundbreaking approach, DeepLimeSeg, which synergizes DL methodologies with Lime-based Explainability to segment customers effectively. The approach employs a comprehensive mathematical model to harness demographic data, behavioral patterns, and purchase histories, categorizing customers into distinct clusters aligned with their preferences and needs. A pivotal component of this research is the mathematical underpinning of the DeepLimeSeg approach. The Lime-based Explainability module ensures that the segmentation results are accurate and interpretable. The mathematical rigor facilitates businesses tailoring their marketing strategies with precision, optimizing sales outcomes. To validate the efficacy of DeepLimeSeg, we employed two real-world datasets: Mall-Customer Segmentation Data and an E-Commerce dataset. A comparative analysis between DeepLimeSeg and the traditional Recency, Frequency, and Monetary (RFM) analysis is presented. The RFM analysis, grounded in its mathematical modeling, segments customers based on purchase recency, frequency, and monetary value. Our preprocessing involved computing RFM scores for each customer, followed by K-means clustering to delineate customer segments. Empirical results underscored the superiority of DeepLimeSeg over other models in terms of MSE, MAE, and R 2 metrics. Specifically, the model registered an MSE of 0.9412, indicative of its robust predictive accuracy concerning the spending score. The MAE value stood at 0.9874, signifying minimal deviation from actual values. This paper accentuates the importance of mathematical modeling in enhancing customer segmentation. The DeepLimeSeg approach, with its mathematical foundation and explainable AI integration, paves the way for businesses to make informed, data-driven marketing decisions. [ABSTRACT FROM AUTHOR]

This paper combines the artificial intelligence (AI) and deep leaning technologies to classify the spread of national culture. First, we use the Python language to build a crawler technology in order to obtain the sample data of national culture from authoritative websites. Then, we use the natural language processing (NLP) expertise to analyze and preprocess the text of national diversity. In this way, we realize vectorization and the feature word extraction of the text related to national cultural resources based on the doc2vec technology. The vectorized texts of national cultural resources are clustered based on the K-means clustering technique. Moreover, the elbow rule process is implemented to determine the optimal number of clustering clusters. Finally, the text association relationship of the national cultural resources is obtained. Moreover, this paper adopts the unsupervised training method, which can reveal the semantic information contained in the text of national cultural resources. This can also help us during the identification process of the category connection amongst the texts of national cultural resources and provide us with methodological support for the gathering, storing, and other smart services of enormous national cultural resources. The outcomes demonstrate that the correctness rate of the suggested algorithm is greater than the accuracy of the linear regression and can reach up to 80%. [ABSTRACT FROM AUTHOR]

INTRODUCTION: As the essential part of intelligent learning, innovative learning model construction is conducive to improving the quality of intelligent new teaching models, thus leading the deep integration of teaching and artificial intelligence and accelerating the change and development of teaching supported by artificial intelligence. OBJECTIVES: Aiming at the current intelligent teaching evaluation design method, there are problems such as more objectivity, poor precision, and a single method of evaluation indexes. METHODS: his paper proposes an intelligent learning construction method based on cluster analysis and deep learning algorithms. First of all, the intelligent learning model construction process is sorted out by clarifying the idea of clever learning model construction and extracting model elements; then, the intelligent learning model is constructed through a K-means clustering algorithm and deep compression sparse self-encoder; finally, the effectiveness and high efficiency of the proposed method is verified through simulation experiment analysis. RESULTS: Solved the problem that the intelligent learning model construction method is not objective enough, has poor accuracy and is not efficient enough. CONCLUSION: The results show that the proposed method improves the model's accuracy. [ABSTRACT FROM AUTHOR]

In the paper, we proposed a deep learning-based industrial equipment detection algorithm ROMS R-CNN (Rotation Occlusion Multi-Scale Region-CNN). It can solve the problem of inaccurate detection of industrial equipment under complex working conditions such as multi-scale ratio, rotation tilt, occlusion and overlap. The method proposed in this paper first is to construct the MobileNetV2 as the feature pyramid network, and then to combine high semantic information with high resolution information solved industrial equipment detection of different scales. Secondly, a specific rotation anchor scheme is proposed, and the data set is clustered through the k-means algorithm to obtain a specific aspect ratio. Combined with the rotation angle, a rotation anchor of any direction and size is generated to solve the problem of easy tilting of industrial equipment. Finally, a Non-Maximum Suppression algorithm with penalty factors is introduced to solve the overlapping in industrial equipment detection. The experimental results in common industrial equipment detection show that this method is better than other algorithms, significantly improves the missed detection and false detection, and the mAP reaches 0.939. [ABSTRACT FROM AUTHOR]

Road intelligence monitoring is an inevitable trend of urban intelligence, and clothing information is the main factor to identify pedestrians. Therefore, this paper establishes a multi-information clothing recognition model and proposes a data augmentation method based on road monitoring. First, we use Mask R-CNN to detect the clothing category information in the monitoring; then, we transfer the mask to the k-means cluster to obtain the color and finally obtain the clothing color and category. However, the monitoring scene and dataset are quite different, so a data augmentation method suitable for road monitoring is designed to improve the recognition ability of small targets and occluded targets. The small target mAP (mean average precision) recognition ability is improved by 12.37% (from 30.37%). The method of this study can help find relevant passers-by in the actual monitoring scene, which is conducive to the intelligent development of the city. [ABSTRACT FROM AUTHOR]

A massive amount of textual data now exists in digital repositories in the form of research articles, news articles, reviews, Wikipedia articles, and books, etc. Text clustering is a fundamental data mining technique to perform categorization, topic extraction, and information retrieval. Textual datasets, especially which contain a large number of documents are sparse and have high dimensionality. Hence, traditional clustering techniques such as K-means, Agglomerative clustering, and DBSCAN cannot perform well. In this paper, a clustering technique especially suitable to large text datasets is proposed that overcome these limitations. The proposed technique is based on word embeddings derived from a recent deep learning model named "Bidirectional Encoders Representations using Transformers". The proposed technique is named as WEClustering. The proposed technique deals with the problem of high dimensionality in an effective manner, hence, more accurate clusters are formed. The technique is validated on several datasets of varying sizes and its performance is compared with other widely used and state of the art clustering techniques. The experimental comparison shows that the proposed clustering technique gives a significant improvement over other techniques as measured by metrics such Purity and Adjusted Rand Index. [ABSTRACT FROM AUTHOR]

The Internet of Things (IoT) constitutes the foundation of a deeply interconnected society in which objects communicate through the Internet. This innovation, coupled with 5G and artificial intelligence (AI), finds application in diverse sectors like smart cities and advanced manufacturing. With increasing IoT adoption comes heightened vulnerabilities, prompting research into identifying IoT malware. While existing models excel at spotting known malicious code, detecting new and modified malware presents challenges. This paper presents a novel six-step framework. It begins with eight malware attack datasets as input, followed by insights from Exploratory Data Analysis (EDA). Feature engineering includes scaling, One-Hot Encoding, target variable analysis, feature importance using MDI and XGBoost, and clustering with K-Means and PCA. Our GhostNet ensemble, combined with the Gated Recurrent Unit Ensembler (GNGRUE), is trained on these datasets and fine-tuned using the Jaya Algorithm (JA) to identify and categorize malware. The tuned GNGRUE-JA is tested on malware datasets. A comprehensive comparison with existing models encompasses performance, evaluation criteria, time complexity, and statistical analysis. Our proposed model demonstrates superior performance through extensive simulations, outperforming existing methods by around 15% across metrics like AUC, accuracy, recall, and hamming loss, with a 10% reduction in time complexity. These results emphasize the significance of our study's outcomes, particularly in achieving cost-effective solutions for detecting eight malware strains. [ABSTRACT FROM AUTHOR]

Background: The social media revolution has offered new facilities and opportunities to the online community to communicate their intentions, opinions, and views regarding products, services, policies, and events. The identification of intent focuses on the detection of intents from user reviews, that is, whether the specific review of the user includes intention or not. Intent mining is also named intent identification which helps business organizations to identify the purchase intentions of users. However, detecting user intentions encoded in text queries is a complicated task in several Natural Language Processing (NLP) applications such as robots, smart agents, personal assistants, and search engines. The existing research works have discovered the utilization of several machine learning techniques to detect the intents from queries of users. Most works consider intent detection as a classification problem, with utterances as predefined intents. Research question: Whether the researcher resolves the detection of user intentions encoded in text queries? How the researcher solves the existing challenges based on intent mining? Purpose: The main contribution of the research is to design and implement intent detection using topic clustering and deep learning. Methodology: Initially, the dataset related to diverse queries is gathered. Then, the label creation is performed by clustering. The clustering is performed by a k-means clustering model with a cosine similarity function. Once the clustering is performed for different queries, the label is created, which is used to train the network under the detection process. For the detection, this paper uses a Heuristic-based Capsule Network (H-CapNet) that could perform the intention for a new query. The hybrid meta-heuristic algorithm with Escaping Energy searched Grey–Harris Hawks Algorithm (EEG-HHA) is used for improving the capsule network. Validation: Experimental analysis shows that the developed method has superior performance in evaluating standard datasets with other approaches. Results: From the simulation results, the accuracy of the developed EEG-HHA-CapNet for dataset 1 is secured at 3%, 1.6%, 2%, and 1.1% increased than PSO-CapNet, WOA-CapNet, HHO-CapNet, and GWO-CapNet. Conclusion: Thus, the designed user intent detection models reveal their more advanced performance based on the diverse performance and error metrics for datasets 1 and 2. [ABSTRACT FROM AUTHOR]

The driving cycle is a series of driving behaviours, such as acceleration, braking, and cruising, that occur over a set length of time. Predicting the driving cycle can help to improve vehicle performance or anticipate the range of an electric car. Based on prior data, long short-term memory (LSTM) networks can be used to forecast a vehicle's driving cycle. This paper studies a driving cycle prediction based on LSTM by recurrent neural network (RNN) using developed driving cycle data. The objectives of this paper are; to develop an Ipoh driving cycle (IDC), to develop a prediction of future IDC and to analyze the prediction of IDC. Firstly, the driving data is collected in three different routes in Ipoh city at back-from-work times. Then the data is divided into micro-trips and the driving features are extracted. The features are used to develop a driving cycle using k-means clustering approach. The prediction is developed after the training of neural networks by using LSTM network approach with root mean square error (RSME) of 6.2252%. [ABSTRACT FROM AUTHOR]

Clustering algorithms with deep neural network has attracted wide attention to scholars. A deep fuzzy K-means clustering algorithm model on adaptive loss function and entropy regularization (DFKM) is proposed by combining automatic encoder and clustering algorithm. Although it introduces adaptive loss function and entropy regularization to improve the robustness of the model, its segmentation effect is not ideal for high noise. The research purpose of this paper is to focus on the anti-noise performance of image segmentation. Therefore, on the basis of DFKM, this paper focus on image segmentation, combine neighborhood median and mean information of current pixel, introduce neighborhood information of membership degree, and extend Euclidean distance to kernel space by using kernel function, propose a dual-neighborhood information constrained deep fuzzy clustering based on kernel function (KDFKMS). A large number of experimental results show that compared with DFKM and classical image segmentation algorithms, this algorithm has stronger anti-noise robustness. [ABSTRACT FROM AUTHOR]

Traditional geophysical inversion methods rely on an assumption of prior knowledge, starting from the establishment of the initial model and ending with the model being modified many times. This iterative process makes the forward modelling results move increasingly closer to the observed data. However, each inversion step requires multiple forward calculations, which consumes considerable time and computing resources. This is the greatest obstacle to real-time inversion at present. Airborne transient electromagnetic (ATEM) response data are collected in a time-channel manner. The different stratigraphic structures reveal different time-varying electromagnetic response laws. In this paper, deep learning technology is used to advance the 'model correction-forward iteration' step in the geophysical inversion process to the data preprocessing stage, to better adapt to the specialty of ATEM, improve the efficiency of the inversion and shorten the inversion time. In this method, a sample set composed of a 'stratigraphic texture model—ATEM response' is established, the K-Means clustering technique of unsupervised learning is used to complete the sample tag attachment, and the multilayer perceptron (MLP) deep learning network with supervised learning is used to complete the multiclassification tasks. Then, the sample sets are input into the deep learning network for training to build the inversion from the input response data to the output of the stratigraphic model. Finally, the inversion flow is verified with test set samples. The prediction results are consistent with the simulated data, and the inversion, from the test data to the prediction model, is implemented efficiently. [ABSTRACT FROM AUTHOR]

This main intention of this paper is to adopt a new disease detection model for plant leaves. The proposed model involves several steps such as pre‐processing, leaf segmentation, abnormality segmentation, feature extraction and detection. Image scaling and contrast enhancement are performed during the pre‐processing phase. Once the pre‐processing is done, the segmentation phase starts with leaf segmentation by binary thresholding method and abnormality segmentation by K‐means clustering. Further, the local binary pattern and grey‐level co‐occurrence matrix features are extracted and a dimensionality reduced technique called principle component analysis is determined. As the main novelty, the weighted feature extraction is performed, in which the weight functions are optimized by the self‐adaptive deer hunting optimization (SA‐DHOA). Another contribution of this paper is to implement a hybrid classifier for disease detection. Here, the extracted weighted features are subjected to a support vector machine, and the abnormality segmented image is subjected to convolutional neural network (CNN), which is a deep learning algorithm that can learn the features automatically. Here, the same SA‐DHOA is used to improve the performance of CNN, which is termed as SA‐DHOA‐SCNN. Finally, the performance analysis confirms the maximum success rate of the proposed model over other conventional methods. [ABSTRACT FROM AUTHOR]

Naturalistic driving data (NDD) are valuable for testing autonomous driving systems under various driving conditions. Automatically identifying scenes from high-dimensional and unlabeled NDD remains a challenging task. This paper presents a novel approach for automatically identifying test scenarios for autonomous driving through deep unsupervised learning. Firstly, US DAS2 NDD are leveraged, and the selection of data variables representing the vehicle state and surrounding environment is conducted to formulate the segmentation criterion. The isolation forest (IF) algorithm is then employed to segment the data, yielding two distinct types of datasets: typical scenarios and extreme scenarios. Secondly, a one-dimensional residual convolutional autoencoder (1D-RCAE) is developed to extract scenario features from the two datasets. Compared to four other autoencoders, the 1D-RCAE can effectively extract crucial information from high-dimensional data with optimal feature extraction capability. Next, considering the varying importance of different features, an information entropy (IE)-optimized K-means algorithm is employed to cluster the features extracted using 1D-RCAE. Finally, statistical analysis is performed on the parameters of each cluster of scenarios to explore their distribution characteristics within each class, and four typical scenarios are identified along with five extreme scenarios. The proposed unsupervised framework, combining IF, 1D-RCAE, and IE-improved K-means algorithms, can automatically identify typical and extreme scenarios from NDD. These identified scenarios can then be applied to test the performance of autonomous driving systems, enriching the library of automated driving test scenarios. [ABSTRACT FROM AUTHOR]

This paper proposes a recommendation system based on a hybrid learning approach for a personal deep sleep service, called the Customized Deep Sleep Recommender System (CDSRS). Sleep is one of the most important factors for human life in modern society. Optimal sleep contributes to increasing work efficiency and controlling overall well-being. Therefore, a sleep recommendation service is considered a necessary service for modern individuals. Accurate sleep analysis and data are required to provide such a personalized sleep service. However, given the variations in sleep patterns between individuals, there is currently no international standard for sleep. Additionally, service platforms face a cold start problem when dealing with new users. To address these challenges, this study utilizes K-means clustering analysis to define sleep patterns and employs a hybrid learning algorithm to evaluate recommendations by combining user-based and collaborative filtering methods. It also incorporates feedback top-N classification processing for user profile learning and recommendations. The behavior of the study model is as follows. Using personal information received through mobile devices and data, such as snoring, sleep time, movement, and noise collected through AI motion beds, we recommend sleep and receive user evaluations of recommended sleep. This assessment reconstructs the profile and, finally, makes recommendations using top-N classification. The experimental results were evaluated using two absolute error measurement methods: mean squared error (MSE) and mean absolute percentage error (MAPE). The research results regarding the hybrid learning methods show 13.2% fewer errors than collaborative filtering (CF) and 10.2% fewer errors than content-based filtering (CBF) on an MSE basis. According to the MAPE, the methods are 14.7% more accurate than the CF model and 9.2% better than the CBF model. These results demonstrate that CDSRS systems can provide more accurate recommendations and customized sleep services to users than CF, CBF, and combination models. As a result, CDSRS, a hybrid learning method, can better reflect a user's evaluation than traditional methods and can increase the accuracy of recommendations as the number of users increases. [ABSTRACT FROM AUTHOR]

Plant diseases have been one of the most threatening scenarios to farmers. Although most plant diseases can be identified by observing leaves, it often requires human expertise. The recent improvements in computer vision have led to introduce disease classification systems through observing leaf images. Nevertheless, most disease classification systems are specific to diseases and plants, limiting method's usability. The methods are also costly as they require vast labeled data, which can only be done by experts. This paper introduces a self-supervised leaf disease clustering system that can be used for classifying plant diseases. As self-supervision does not require labeled data, the proposed method can be inexpensive and can be implemented for most types of plants. The method implements a siamese deep convolutional neural network (DCNN) for generating clusterable embeddings from leaf images. The training strategy of the embedding network is conducted using AutoEmbedder approach with randomly augmented image pairs. The self-supervised embedding model training involves three different data pair linkage scenarios: can-link, cannot-link, and may-link pairs. The embeddings are further clustered using k-means algorithm in the final classification stage. The experiment is conducted to individually classify diseases of eight different fruit leaves. The results indicate that the proposed leaf disease identification method performs better than the existing self-supervised clustering systems. The paper indicates that end-to-end siamese networks can outperform well-designed sequentially trained self-supervised methods. [ABSTRACT FROM AUTHOR]

High-speed trains often pass through tunnel, turnout, ramp, bridge, and other line features in the process of running. At the same time, the length of the operation time, weather conditions, changes in train running conditions, and other conditions will lead to the loss of the train. In view of the complexity of a high-speed train structure and operation environment, in order to effectively evaluate the health of the train in the operation process, this paper proposes a diagnosis method of bearing temperature anomaly of a high-speed train based on condition identification and multitask deep learning. In this paper, the important components of bogie axle box, gearbox, and traction motor are taken as the research object. Firstly, the operating condition parameters of the high-speed train are analyzed and identified, and the K-means algorithm is used to classify and identify the operating condition of the high-speed train. Then, based on the operating condition identification and multitask deep learning, the bearing temperature prediction model is constructed. In addition, according to statistical quality control theory, the difference between the value predicted by the model and the real value is used to diagnose the anomaly of the bearing temperature of the high-speed train. Finally, the accuracy and availability of the model are verified by an example. The model can judge whether the running train bearing temperature is in the normal range in real time and predict and alarm the abnormal bearing temperature. [ABSTRACT FROM AUTHOR]

Object detection models based on convolutional neural networks (CNN) have achieved state-of-the-art performance by heavily rely on large-scale training samples. They are insufficient when used in specific applications, such as the detection of military objects, as in these instances, a large number of samples is hard to obtain. In order to solve this problem, this paper proposes the use of Gabor-CNN for object detection based on a small number of samples. First of all, a feature extraction convolution kernel library composed of multi-shape Gabor and color Gabor is constructed, and the optimal Gabor convolution kernel group is obtained by means of training and screening, which is convolved with the input image to obtain feature information of objects with strong auxiliary function. Then, the k-means clustering algorithm is adopted to construct several different sizes of anchor boxes, which improves the quality of the regional proposals. We call this regional proposal process the Gabor-assisted Region Proposal Network (Gabor-assisted RPN). Finally, the Deeply-Utilized Feature Pyramid Network (DU-FPN) method is proposed to strengthen the feature expression of objects in the image. A bottom-up and a topdown feature pyramid is constructed in ResNet-50 and feature information of objects is deeply utilized through the transverse connection and integration of features at various scales. Experimental results show that the method proposed in this paper achieves better results than the state-of-art contrast models on data sets with small samples in terms of accuracy and recall rate, and thus has a strong application prospect. [ABSTRACT FROM AUTHOR]

Autism spectrum disorder (ASD), is a neurological developmental disorder. It affects how people communicate and interact with others, as well as how they behave and learn. The symptoms and signs appear when a child is very young. Derived with increased usage of machine learning procedure in the medicinal analysis investigations. In this paper, our objective is to find out the most significant attributes and automate the process using classification techniques and pattern clustering using K-means clustering. We have analyzed ASD datasets of children towards determining the best performance of classifier for these binary datasets considering recall, precision, accuracy and classification errors. For this purpose only we use classifier along with a training model with the deep learning technique. In this deep neural network the different types of patterns have been obtained, and then the entire autism dataset has been trained using this classification technique. After that, the group of patterns has been formed using K- means clustering technique. Then these grouped patterns have been sent to the stochastic gradient descent (SGD) for obtaining the classification with enhanced accuracy, and after this, the regression process is done, then by this classified output, the recommendation learning system model is given for autism affected children. The need for recommendation for ASD is due to slow functioning of the brain and change in personal characteristic of the affected children, so it is necessary for recommendation learning model in ASD. [ABSTRACT FROM AUTHOR]

Forecasting carbon prices has important implications for the formulation of environmental and energy policies as well as for the investment and management of workers in related industries. This paper proposes a novel multi-index nonlinear ensemble framework based on carbon price trading data and technical index data, which combines extreme gradient boost (XGBoost), K-means clustering algorithm based on elbow method (KCE), bidirectional long and short-term memory (BiLSTM) and bidirectional gated recurrent units (BiGRU). First, the XGBoost method is used to filter the raw data set to determine the input variables, and they were then divided into groups using the KCE method. Then, the BiLSTM method is used as the predictor for forecasting the sub model. Finally, BiGRU is applied to nonlinear integration. The developed prediction framework is used to predict China's regional carbon price to evaluate its performance. Experimental results show that the prediction performance of the framework in all target carbon markets is better than the benchmark model, and it is an effective tool for carbon market. [ABSTRACT FROM AUTHOR]

Discovering the mode of transportation is a fundamental and challenging step in the various transportation analysis problems such as travel demand analysis, transport planning, and traffic management. Supervised learning approaches have frequently been used to detect the mode of transportation. In the supervised learning approach, extracted features from the GPS data and labeled mode of each trajectory are used to detect the mode of transportation. However, the sample size of trips for training is not enough due to the scarcity of labeled data. In real-time scenario, labeling the data is a tedious and expensive task. Furthermore, a huge amount of unlabeled data remains unutilized, which in turn degrades the quality of the solution. To overcome these drawbacks, an unsupervised learning method is proposed in this paper. In the proposed work, the point level characteristics such as speed, acceleration/deceleration, jerk, and bearing angle are fused with GPS coordinates to extract the joint probability densities using a type of generative deep learning model called masked autoregressive flow (MAF). Based on the probability density of each trajectory, K-means algorithm is applied to find the modes of transportation. The proposed model can handle the long sequence of trajectories having variable lengths. In this work, we compare our methodology with traditional machine learning algorithms and most related studies. The results are in favor of incorporating the proposed unsupervised approach in transportation mode detection. [ABSTRACT FROM AUTHOR]

The presence of community structures in complex networks reveals meaningful insights about such networks and their constituent entities. Finding groups of related nodes based on mutual interests, common features, objectives, or interactions in a network is known as community detection. In this paper, we propose a novel Stacked Autoencoder-based deep learning approach augmented by the Crow Search Algorithm (CSA)-based k-means clustering algorithm to uncover community structure in complex networks. As per our approach, firstly, we generate a modularity matrix for the input graph. The modularity matrix is then passed through a series of stacked autoencoders to reduce the dimensionality of the matrix while preserving the topology of the network and improving the computational time of the proposed algorithm. The obtained matrix is then provided as an input to a modified k-means clustering algorithm augmented with the crow search optimization to detect the communities. We use Crow Search Algorithm-based optimization to generate the initial centroids for the k-means algorithm instead of generating them randomly. We perform extensive experimental analysis on several real-world and synthetic datasets and evaluate various performance metrics. We compare the results obtained by our algorithm with several traditional and contemporary community detection algorithms. The obtained results reveal that our proposed method achieves commendable results. [ABSTRACT FROM AUTHOR]

Images of molecules are often utilized in education and synthetic exploration to predict molecular characteristics. Deep learning (DL) has also had an influence on drug research, such as the interpretation of cellular images as well as the development of innovative methods for the synthesis of organic molecules. Although research in these areas has been significant, a comprehensive review of DL applications in drug development would be beyond the scope of a single Account. In this study, we will concentrate on a single major area where DL has influenced molecular design: the prediction of molecular properties of modified gedunin using machine learning (ML). AI and ML technologies are critical in drug research and development. In these other words, deep learning (DL) algorithms and artificial neural networks (ANN) have changed the field. In short, advances in AI and ML present a good potential for rational drug design and exploration, which will ultimately benefit humanity. In this paper, long short-term memory (LSTM) was used to convert a modified gedunin SMILE into a molecular image. The 2D molecular representations and their immediately visible highlights should then provide adequate data to predict the subordinate characteristics of atom design. We aim to find the properties of modified gedunin using K-means clustering; RNN-like ML tools. To support this postulation, neural network (NN) clustering based on the AI picture is used and evaluated in this study. The novel chemical developed via profound learning has long been predicted on characteristics. As a result, LSTM with RNNs allow us to predict the properties of molecules of modified gedunin. The total accuracy of the suggested model is 98.68%. The accuracy of the molecular property prediction of modified gedunin research is promising enough to evaluate extrapolation and generalization. The model suggested in this research requires just seconds or minutes to calculate, making it faster as well as more effective than existing techniques. In short, ML can be a useful tool for predicting the properties of modified gedunin molecules. [ABSTRACT FROM AUTHOR]

To quickly detect and count the number of bayberry trees, this paper improves the YOLO-v4 model and proposes an optimal YOLO-v4 method for detecting bayberry trees based on UAV images. We used the Leaky_ReLU activation function to accelerate the model extraction speed and used the DIoU NMS to retain the most accurate prediction boxes. In order to increase the recall rate of the object detection and construct the optimal YOLO-v4 model, the K-Means clustering method was embedded into DIoU NMS. We trained the model using UAV images of bayberry trees, it was determined that the optimal YOLO-v4 model threshold was 0.25, which had the best extraction effect. The optimal YOLO-v4 model had a detection accuracy of up to 97.78% and a recall rate of up to 98.16% on the dataset. The optimal YOLO-v4 model was compared with YOLO-v4, YOLO-v4 tiny, the YOLO-v3 model, and the Faster R-CNN model. With guaranteed accuracy, the recall rate was higher, up to 97.45%, and the detection of bayberry trees was better in different contexts. The result shows that the optimal YOLO-v4 model can accurately achieve the rapid detection and statistics of the number of bayberry trees in large-area orchards. [ABSTRACT FROM AUTHOR]

Achieving a real-time and accurate detection of drones in natural environments is essential for the interception of drones intruding into high-security areas. However, a rapid and accurate detection of drones is difficult because of their small size and fast speed. In this paper a drone detection method as proposed by pruning the convolutional channel and residual structures of YOLOv3-SPP3. First, the k-means algorithm was used to cluster label the boxes. Second, the channel and shortcut layer pruning algorithm was used to prune the model. Third, the model was fine tuned to achieve a real-time detection of drones. The experimental results obtained by using the Ubuntu server under the Python 3.6 environment show that the YOLOv3-SPP3 algorithm is better than YOLOV3, Tiny-YOLOv3, CenterNet, SSD300, and faster R-CNN. There is significant compression in the size, the maximum compression factor is 20.1 times, the maximum detection speed is increased by 10.2 times, the maximum map value is increased by 15.2%, and the maximum precision is increased by 16.54%. The proposed algorithm achieves the mAP score of 95.15% and the detection speed of 112 f/s, which can meet the requirements of the real-time detection of UAVs. [ABSTRACT FROM AUTHOR]

Electric vehicles have the advantages of zero emissions and high energy efficiency. They have a broad potential in today's social life, especially in China where they have been widely used. In the current situation, whereby the storage capacity of electric vehicles is continually increasing and the requirements for grid stability are getting higher and higher, V2G technology emerges to keep up with the times. Since the electric vehicle charging station is a large-scale electric vehicle cluster charging terminal, it is necessary to pay attention to the status and controllability of each charging pile. In view of the lack of attention to the actual operation of the electric vehicle charging station in the existing vehicle–network interaction mode, the charging state of the current electric vehicle charging station is fixed. In this paper, deep learning is used to establish a load perception model for electric vehicle charging stations, and K-means clustering is used to optimize the load perception model to realize random load perception and non-intrusive load monitoring stations for electric vehicle charging. The calculation example results show that the proposed method has good performance in the load perception and controllability evaluation of electric vehicle charging stations, and it provides a feasible solution for the practical realization of electric vehicle auxiliary response. [ABSTRACT FROM AUTHOR]

Agriculture is a very important economic sector in Morocco, which requires a set of tools to improve agricultural production. Among these tools, the use of geomembrane basins. The latter is of great importance in smart farming planning, management practices or even in livestock use. In this context, this study evaluates a recognition and classification of the geomembrane basin using remote sensing satellite images; based on the Yolov3 deep learning neural network. This paper first adjusts the network model to make it suitable for detecting small targets on remote sensing images, then uses the k-means algorithm to calculate the grid size of the Yolo network model suitable for geomembrane basins, then uses yolov3 to train the data that makes up the satellite remote sensing imagery. The network model for the detection of the geomembrane basins is obtained by the test phase. Finally, the geomembrane basin detection model adapted to the remote sensing image is obtained in the validation phase. Through the research and analysis of the experimental results, it can be seen that this method effectively detects the geomembrane basins in the remote sensing images and ensures the high detection accuracy of the experimental results, which gave us an accuracy of 75%. [ABSTRACT FROM AUTHOR]

Instance-wise contrastive learning (Instance-CL), which learns to map similar instances closer and different instances farther apart in the embedding space, has achieved considerable progress in self-supervised video representation learning. However, canonical Instance-CL does not handle properly the temporal similarities between different videos, limiting the representation capabilities of learned models. This paper presents a novel two-stage framework that combines Instance-CL and unsupervised clustering to progressively learn desirable temporal representations with high intra-class compactness. Specifically, (a) we first introduce a new consistency-preserving sampling strategy to generate positive/negative pairs. Compared to the traditional sampling methods, our sampling strategy focuses more on motion dynamics, resulting in more temporal-related feature representations. (b) To further explore the temporal similarities between videos so as to encourage intra-class compactness, we set temporal representations extracted from Instance-CL as an initializer, and iteratively use k-means clustering to generate pseudo-labels for training the encoder. We term our method as Improved Instance-CL with Deep Clustering (ICDC) and apply it to two downstream tasks, including action recognition and video retrieval. Extensive experimental results show that ICDC gains considerable improvements compared to the existing self-supervised methods. [ABSTRACT FROM AUTHOR]

Inventory is the basis of business activities; inventory management helps industries keep their inventories stocked with reasonable quantities, which ensures consumers demand while minimizing storage costs. The traditional manual inventory management has low efficiency and a high labor cost. In this paper, we used improved YOLOv3 to detect the cups stored on the warehouse shelves and counted their numbers to realize automated inventory management. The warehouse images are collected by the camera and transmitted to the industrial computer, which runs the YOLOv3 network. There are three feature maps in YOLOv3, the two smaller feature maps and the structure behind them are removed, and the k-means algorithm is used to optimize the default anchor size. Moreover, the detection range is limited to a specified area. Experiments show that, by eliminating those two feature maps, the network parameter is reduced from 235 MB to 212 MB, and detection FPS is improved from 48.15 to 54.88 while mAP is improved from 95.65% to 96.65% on our test dataset. The new anchors obtained by the k-means algorithm further improve the mAP to 96.82%. With those improvements, the average error rate of detection is reduced to 1.61%. Restricted detection areas eliminate irrelevant items to ensure the high accuracy of the detection result. The accurately counted number of cups and its change provide significant data for inventory management. [ABSTRACT FROM AUTHOR]

Traditional digital camouflage is mainly designed for a single background and state. Its camouflage performance is appealing in the specified time and place, but with the change of place, season, and time, its camouflage performance is greatly weakened. Therefore, camouflage technology, which can change with the environment in real-time, is the inevitable development direction of the military camouflage field in the future. In this paper, a fast-self-adaptive digital camouflage design method based on deep learning is proposed for the new generation of adaptive optical camouflage. Firstly, we trained a YOLOv3 model that could identify four typical military targets with mean average precision (mAP) of 91.55%. Secondly, a pre-trained deepfillv1 model was used to design the preliminary camouflage texture. Finally, the preliminary camouflage texture was standardized by the k-means algorithm. The experimental results show that the camouflage pattern designed by our proposed method is consistent with the background in texture and semantics, and has excellent camouflage performance in optical camouflage. Meanwhile, the whole pattern generation process takes a short time, less than 0.4 s, which meets the camouflage design requirements of the near-real-time camouflage in the future. [ABSTRACT FROM AUTHOR]

The deep learning diagnosis of aircraft engine-bearing faults enables cost-effective predictive maintenance while playing an important role in increasing the safety, reliability, and efficiency of aircraft operations. Because of highly dynamic and harsh operating conditions of this system, such modeling is challenging due to data complexity and drift, making it difficult to reveal failure patterns. As a result, the objective of this study is dual. To begin, a highly structured data preprocessing strategy ranging from extraction, denoising, outlier removal, scaling, and balancing is provided to solve data complexity that resides specifically in outliers, noise, and data imbalance problems. Gap statistics under k-means clustering are used to evaluate preprocessing results, providing a quantitative estimate of the ideal number of clusters and thereby enhancing data representations. This is the first time, to the best of authors' knowledge, that such a criterion has been employed for an important step in a preliminary ground truth validation in supervised learning. Furthermore, to tackle data drift issues, long-short term memory (LSTM) adaptive learning features are used and subjected to a learning parameter improvement method utilizing recursive weights initialization (RWI) across several rounds. The strength of such methodology can be seen by application to realistic, extremely new, complex, and dynamic data collected from a real test-bench. Cross validation of a single LSTM layer model with only 10 neurons shows its ability to enhance classification performance by 7.7508% over state-of-the-art results, obtaining a classification accuracy of 92.03 ± 0.0849%, which is an exceptional performance in such a benchmark. [ABSTRACT FROM AUTHOR]

Cluster computing is an essential technology in distributed environments for practical data analysis in complex datasets like tumor segmentation, disease classification etc. Today real-world applications like medicine and transport are needed for big data analytics environments. This research article considers complex image data environments like brain tumor segmentation based on advanced clustering techniques for effective tumor prediction. An a-state-of-art analysis used Hierarchical clustering to extract initial tumor segments from the image. The next segment is further refined using novel Noise detection-based levelsetting techniques. The unsupervised Fuzzy C-means and k-means clustering is used to segment the diseases affected region to enhance noise detection used in the level set. Effective features are extracted using gray level co-occurrence matrix and redundant discrete wavelet transform. Finally, classifying malignant and benign brain tumor images is done using deep probabilistic neural networks. Publicly available datasets are used to validate the proposed algorithms. Experimental results prove that proposed pipeline techniques have effective performance in tumor segmentation and classification model. [ABSTRACT FROM AUTHOR]

Water resource management represents a fundamental aspect of a modern society. Urban areas present multiple challenges requiring complex solutions, which include multidomain approaches related to the integration of advanced technologies. Water consumption monitoring applications play a significant role in increasing awareness, while machine learning has been proven for the design of intelligent solutions in this field. This paper presents an approach for monitoring and predicting water consumption from the most important water outlets in a household based on a proposed IoT solution. Data processing pipelines were defined, including K-means clustering and evaluation metrics, extracting consumption events, and training classification methods for predicting consumption sources. Continuous water consumption monitoring offers multiple benefits toward improving decision support by combining modern processing techniques, algorithms, and methods. [ABSTRACT FROM AUTHOR]

The monitoring of the daily life activities routine is beneficial, especially in old age. It can provide relevant information on the person's health state and wellbeing and can help identify deviations that signal care deterioration or incidents that require intervention. Existing approaches consider the daily routine as a rather strict sequence of activities which is not usually the case. In this paper, we propose a solution to identify flexible daily routines of older adults considering variations related to the order of activities and activities timespan. It combines the Gap-BIDE algorithm with a collaborative clustering technique. The Gap-BIDE algorithm is used to identify the most common patterns of behavior considering the elements of variations in activities sequence and the period of the day (i.e., night, morning, afternoon, and evening) for increased pattern mining flexibility. K-means and Hierarchical Clustering Agglomerative algorithms are collaboratively used to address the time-related elements of variability in daily routine like activities timespan vectors. A prototype was developed to monitor and detect the daily living activities based on smartwatch data using a deep learning architecture and the InceptionTime model, for which the highest accuracy was obtained. The results obtained are showing that the proposed solution can successfully identify the routines considering the aspects of flexibility such as activity sequences, optional and compulsory activities, timespan, and start and end time. The best results were obtained for the collaborative clustering solution that considers flexibility aspects in routine identification, providing coverage of monitored data of 89.63%. [ABSTRACT FROM AUTHOR]

Vocal fold, a significant body structure, is accountable for phonation, which regulates air motion within and out of the lungs. The disorders in the vocal fold influence the quality of life. Thus, diagnosis of vocal fold disorders has a significant need, and CT of the neck is employed for an effective imaging scheme. Accordingly, this paper proposes an advanced multi-resolution algorithm (MRA) that optimally identifies and classifies pathologies. The vocal regions are acquired using the genetic k-means algorithm. The pathology features are generated using the local directional pattern (LDP) fed to pathology classification using moth search-rider optimization-based deep convolutional neural networks (MRA-based DCNN). The hybrid optimization (MRA), integrates the standard rider optimization algorithm (ROA) and moth search algorithm (MS) that trains deep learning classifier (DCNN). The analysis using the real databases regarding the performance metrics divulge that the proposed pathology detection module obtained the accuracy, specificity, and sensitivity of 97.020%, 91.698%, and 96.624%. [ABSTRACT FROM AUTHOR]

Vector Quantization (VQ) is a clustering problem in the fields of signal processing, source coding, information theory etc. Taking advantage of recent advances in the field of deep neural networks, this paper investigates the performance between VQ clustering problems and deep neural networks. A k‐means‐based deep network architecture for VQ is presented to solve clustering problems. By applying the deep learning implementation of convergence optimization, a clustering neural network (algorithm) for the purpose of VQ is proposed. In practice, the proposed network quantifies the vectors over a set of stacked neural layers, overcoming the exponential complexity problem of VQ methods by trainable parameters. Experiments show that the work can improve the results without human intervention, and outperforms traditional clustering methods modified for VQ. [ABSTRACT FROM AUTHOR]

Atmospheric turbulence is one of the causes of quality degradation in long-range imaging and its removal from degraded frame sequences is considered an ill-posed problem. There have been numerous attempts to address this problem. However, there is still room for improving the quality of the restored images. In contrast to the previous approaches to address this problem, in this paper, we propose a data-driven approach. First, an end-to-end deep convolutional autoencoder is trained using natural images and its encoder part is exploited to extract high-level features from all the frames in a sequence that are distorted by atmospheric turbulence. Then, the binary search algorithm and the unsupervised K-means clustering method are jointly exploited to analyze these high-level features to find the best set of frames that can help accurately reconstruct the original high-quality image. After removing the geometric distortion from the selected frames, the saliency map of the average set of the selected frames is calculated and used with the original selected frames to train an end-to-end multi-scale saliency-guided deep convolutional autoencoder network to fuse the registered frames. This network uses different scales of the input frames and their saliency maps for better fusion performance. Specifically, the fusion network learns how to fuse these sets of frames and also exploit information from their saliency map to generate an image with more details of the scene. Finally, this fused image is post-processed to boost the visual quality of the output fused image. The experimental results on both synthetically and naturally distorted sequences show the superiority of our method compared to the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

During the power grid system maintenance and overhaul, real-time detection of the insulators and drop fuses is important for the live working robots in the distribution network to plan motion. The visual system of the robot needs object detection algorithms with high detection precision, fast speed, and robustness to image brightness changes. In this paper, the improved YOLOv4 is proposed for detecting the insulators and drop fuses based on the YOLOv4. The improved YOLOv4 extracts features of power components through convolutional neural networks (CNN) and then performs feature fusion. After feature extraction and fusion, the algorithm generates prediction boxes based on anchor boxes that are clustered by fuzzy C-means algorithm (FCM) instead of K-means algorithm to detect the objects. Finally, the nonmaximum suppression algorithm (NMS) is used to obtain the final prediction results. In order to detect small targets, the improved YOLOv4 is added to a larger detection layer. For enhancing the robustness of the algorithm, data augmentation methods are carried out to enrich the data set. Combining the improvements, the test results show that the improved YOLOv4 gets higher accuracy and faster detection speed compared with the other detection algorithms based on deep learning. The mean average precision is 97.0%, and the average detection time is 0.012 s. Therefore, the improved YOLOv4 is suitable for the live working robots in the distribution network to detect the insulators and drop fuses fast and accurately. [ABSTRACT FROM AUTHOR]

A brain tumor is a collection of irregular and needless cell development in the brain region, and it is considered a life-threatening disease. Therefore, early level segmentation and brain tumor detection with Magnetic Resonance Imaging (MRI) is more important to save the patient's life. Moreover, MRI is more effective in identifying patients with brain tumors since the recognition of this modality is moderately larger than considering other imaging modalities. The classification of brain tumors is the most important, difficult task in medical imaging systems because of size, appearance and shape variations. In this paper, Competitive Poor and Rich Optimization (CPRO)-based Deep Quantum Neural Network (Deep QNN) is proposed for brain tumor classification. Additionally, the pre-processing process assists in eradicating noises and uses image intensity to eliminate the artifacts. The significant features are extracted from pre-processed image to perform a productive classification process. The Deep QNN classifier is employed for classifying the brain tumor regions. Besides, the Deep QNN classifier is trained by the developed CPRO approach, which is newly designed by integrating Poor and Rich Optimization (PRO) and Competitive Swarm Optimizer (CSO). The developed brain tumor detection model outperformed other existing models with accuracy, sensitivity and specificity of 94.44%, 97.60% and 93.78%. [ABSTRACT FROM AUTHOR]

In this paper, we investigate an unmanned aerial vehicle (UAV) communication system, where the trajectories of multi-UAVs are designed for the data collection mission of IoT nodes. We aim at minimizing the mission time with constraints of UAV’s maximum speed and acceleration, the collision avoidance, and communication interference among UAVs. We propose a three-step approach to solve this problem, which is based on the K-means algorithm, and Deep Reinforcement Learning (DRL) with a distributed manner and a centralized manner. The mutual influences like collision avoidance and interference among UAVs are explicitly expressed in our algorithm. Numerical results show the advantage of our proposed approach. [ABSTRACT FROM AUTHOR]

Although many computer vision-based object detection techniques have evolved in the past decade, it suffers from inconsistent detection accuracy, especially for multiclass classification problems. This paper proposed an approach using the Single Stage Deep Transfer Learning model (SS-DTLM) for multiclass apparel detection using a customized YoloV3 algorithm by adapting 3-level Spatial pyramid pooling (SPP), a multi-scale image feature extractor for faster and reasonable apparel detection and classification. This approach produced a reasonable Mean Average Precision (mAP), reliable object detection, and classification. Our model trained and tested on Open Images Dataset (OIDV4) with six object classes and Custom built Apparel Dataset with five object classes of apparels. Finally, experimental results compared with baseline Yolov3 and Yolov3-Tiny algorithms. Further, this paper also emphasized the detected image's various color spaces using SS-DTLM by applying the K-Means clustering algorithm for further analysis. [ABSTRACT FROM AUTHOR]

Complex labels have been widely used in various industries. The accuracy of its content is critical both in the fields of people's livelihood, such as supermarkets and shopping centers, and in the management of goods in the industrial fields, such as logistics and factories. Inaccurate label information identification can make item management difficult. Because complex labels can simultaneously contain text, icons, bar codes, QR codes, and other information with different aspect ratios. Traditional methods like feature extraction and template matching have problems, such as detection frames breaking between Chinese, English, and numeric symbols. As a result, entire lines of text on complex labels cannot be detectable, resulting in low detection accuracy. In this paper, a deep learning-based text detection algorithm was proposed. By employing the operation of inverse convolution, improved the object detection algorithm you only look once 5 (YOLOv5). In the backbone part of the original model, involution is used instead of the convolution layer to improve target classification and prediction. The original anchor frame was modified using k-means clustering to make it more applicable to text of various sizes in labels. The enhanced algorithm is called as Invo-YOLOv5. Experiments show that this model can significantly improve detection efficiency while also addresse the problems of false detection and missed detection. Finally, the detected text is verified by using CRNN and Tesseract OCR with complex labels as samples for recognition. Both methods can be effectively recognized, demonstrating the efficacy and generality of the Invo-YOLOv5 method in the process of complex labels text detection and improving the detection accuracy. [ABSTRACT FROM AUTHOR]

There are different methods available for detecting lung cancer including CT (Computed Tomography) scan, MRI(Magnetic Resonance Imaging) scan etc. Among all methods, CT scan images are preferred more because they can detect a very small nodule in the lungs. Early treatment can be given to patients if it is diagnosed at early stages, hence reducing the number of deaths. This paper shows that Median Filter outperformed the Average, Gaussian, Laplacian, and Wiener Filters in the preprocessing stage for the removal of noise from images. Additionally, a study has been conducted on several image segmentation algorithms, such as clustering, watershed, and Thresholding segmentation. This was followed by the extraction and classification of nodules. Different performance parameters have been calculated to validate the results of the model and it is discovered that proposed model has greatest performance. [ABSTRACT FROM AUTHOR]