Search

Emotional blackmail is a way of communication that forces people around them to listen to their requirements by emotional pressure. It can easily lead to negative emotions and even psychological problems of the other side, then affect the communication effect. In order to detect emotional blackmail utterance in daily communication scenarios and improve the communication effect, this paper developed an emotional blackmail utterance detection system based on Chinese text similarity evaluation. Firstly, this paper labelled the collected data based on Susan Forward's emotional blackmail theory, and construeted an emotional blackmail corpus and a test set. Secondly, this paper analyzed the expression modes of emotional blackmail, and designed text similarity evaluation methods based on part of speech and semantic words respectively, then formed an emotional blackmail utterance detection algorithm based on Chinese text similarity evaluation. Thirdly, this paper carried out experiments on the constructed datasets. The average recall and F1-score of the proposed algorithm are 95.21% and 79.95% respectively, which are better than the compared algorithms. Finally, this paper integrated an emotional blackmail utterance detection prototype system based on the proposed algorithm. Under different testing conditions, system test results show that the average recall is 87.24%, which shows good robustness and detection performance. [ABSTRACT FROM AUTHOR]

The quality of medical images is crucial for accurately diagnosing and treating various diseases. However, current automated methods for assessing image quality are based on neural networks, which often focus solely on pixel distortion and overlook the significance of complex structures within the images. This study introduces a novel neural network model designed explicitly for automated image quality assessment that addresses pixel and semantic distortion. The model introduces an adaptive ranking mechanism enhanced with contrast sensitivity weighting to refine the detection of minor variances in similar images for pixel distortion assessment. More significantly, the model integrates a structure-aware learning module employing graph neural networks. This module is adept at deciphering the intricate relationships between an image's semantic structure and quality. When evaluated on two ultrasound imaging datasets, the proposed method outshines existing leading models in performance. Additionally, it boasts seamless integration into clinical workflows, enabling real-time image quality assessment, crucial for precise disease diagnosis and treatment. [ABSTRACT FROM AUTHOR]

Prostate cancer is awidespread and global disease which affects adultmales - it is said that key causes of the cancer include age, family history, and ethnicity. In this study, the Kaggle prostate cancer dataset, comprising of data from 100 patients with a mixture that both had cancer and did not have cancer, was used alongsidemachine learning predictionmodels for the design of unsupervised and automated intelligent systems for the prediction of prostate cancer. Two intelligent systems were designed and underpinned by unsupervised learning algorithms, namely fuzzy c-means and agglomerative hierarchical clustering, where the various intelligent systems were able to make a prostate cancer prediction with accuracies of over 80% for the various classification metrics, alongside being able to predict an associated stage of the prostate cancer. Both designed intelligent systems offer a complimentary alternative to each other, and their relative merits are discussed in the paper. [ABSTRACT FROM AUTHOR]

With the increasing awareness of environmental protection, the rotary hearth furnace system has emerged as a key technology that facilitates a win-win situation for both environmental protection and enterprise economic benefits. This is attributed to its high flexibility in raw material utilization, capability of directly supplying blast furnaces, low energy consumption, and high zinc removal rate. However, the complexity of the raw material proportioning process coupled with the rotary hearth furnace system's reliance on human labor results in a time-consuming and inefficient process. This paper innovatively introduces an intelligent formula method for proportioning raw materials based on online clustering algorithms and develops an intelligent batching system for rotary hearth furnaces. Firstly, the ingredients of raw materials undergo data preprocessing, which involves using the local outlier factor (LOF) method to detect any abnormal values, using Kalman filtering to smooth the data, and performing one-hot encoding to represent the different kinds of raw materials. Afterwards, the affinity propagation (AP) clustering method is used to evaluate past data on the ingredients of raw materials and their ratios. This analysis aims to extract information based on human experience with ratios and create a library of machine learning formulas. The incremental AP clustering algorithm is utilized to learn new ratio data and continuously update the machine learning formula library. To ensure that the formula meets the actual production performance requirements of the rotary hearth furnace, the machine learning formula is fine-tuned based on expert experience. The integration of machine learning and expert experience demonstrates good flexibility and satisfactory performance in the practical application of intelligent formulas for rotary hearth furnaces. An intelligent batching system is developed and executed at a steel plant in China. It shows an excellent user interface and significantly enhances batching efficiency and product quality. [ABSTRACT FROM AUTHOR]

Designing intelligent diagnosis of prostate diseases in intelligent medical assistance systems has gradually become a research hotspot. However, rectal ultrasound (TRUS) as the main diagnostic tool for prostate diseases remains a challenging issue. (1) Due to limited prostate TRUS imaging data, it is difficult to train a robust deep learning model. (2) In terms of visual features, ultrasound images of prostate cancer are similar to TRUS images of other tissues and organs, so it is difficult for a single neural network model to accurately learn the feature representation of the disease. To address the above problems, we first establish a high-quality dataset for prostate TRUS imaging, and then design multi teacher knowledge distillation to achieve accurate disease recognition. The experimental results show that, compared with knowledge distillation without a teacher model and a single teacher model, knowledge distillation using multiple teacher models can significantly improve the accuracy of prostate TRUS image cancer prediction. As the number of teacher models increases, the accuracy rate is further improved, which verifies the effectiveness of this method in intelligent systems. [ABSTRACT FROM AUTHOR]

Fatigued driving is a problem that every driver will face, and traffic accidents caused by drowsy driving often occur involuntarily. If there is a fatigue detection and warning system, it is generally believed that the occurrence of some incidents can be reduced. However, everyone's driving habits and methods may differ, so it is not easy to establish a suitable general detection system. If a customized intelligent fatigue detection system can be established, it may reduce unfortunate accidents. With its potential to mitigate unfortunate accidents, this study offers hope for a safer driving environment. Thus, on the one hand, this research hopes to integrate the information obtained from three different sensing devices (eye movement, finger pressure, and plantar pressure), which are chosen for their ability to provide comprehensive and reliable data on a driver's physical and mental state. On the other hand, it uses an autonomous learning architecture to integrate these three data types to build a customized fatigued driving detection system. This study used a system that simulated a car driving environment and then invited subjects to conduct tests on fixed driving routes. First, we demonstrated that the system established in this study could be used to learn and classify different driving clips. Then, we showed that it was possible to judge whether the driver was fatigued through a series of driving behaviors, such as lane drifting, sudden braking, and irregular acceleration, rather than a single momentary behavior. Finally, we tested the hypothesized situation in which drivers were experiencing three cases of different distractions. The results show that the entire system can establish a personal driving system through autonomous learning behavior and further detect whether fatigued driving abnormalities occur. [ABSTRACT FROM AUTHOR]

Existing control strategies, such as Real-time Optimization (RTO), Dynamic Real-time Optimization (DRTO), and Economic Model Predictive Control (EMPC) cannot enable optimal operation and control behavior in an optimal fashion. This work proposes a novel control strategy, named the efficiency-oriented model predictive control (MPC), which can fully realize the potential of the optimization margin to improve the global process performance of the whole system. The ideas of optimization margin and optimization efficiency are first proposed to measure the superiority of the control strategy. Our new efficiency-oriented MPC innovatively uses a nested optimization structure to optimize the optimization margin directly online. To realize the computation, a Periodic Approximation technique is proposed, and an Efficiency-Oriented MPC Type I is constructed based on the Periodic Approximation. In order to alleviate the strict constraint of Efficiency-Oriented MPC Type I, the zone-control-based optimization concept is used to construct an Efficiency-Oriented MPC Type II. These two well-designed efficiency-oriented controllers were compared with other control strategies over a Continuous Stirred Tank Reactor (CSTR) application. The simulation results show that the proposed control strategy can generate superior closed-loop process performance, for example, and the Efficiency-Oriented MPC Type I can obtain 7.11% higher profits than those of other control strategies; the effectiveness of the efficiency-oriented MPC was, thereby, demonstrated. [ABSTRACT FROM AUTHOR]

Complex practical problems are distinguished by their subjective and dynamic character. Such problems never repeat exactly; therefore, the method for their solution must be built each time. In view of this, development of intelligent systems that are dedicated and have the capability of acquiring, reproducing, and using the knowledge, whose functions are estimated from the point of view of ensuring stability, openness, and real-time operation is urgent. In this work, understanding of intelligent systems and their openness is considered, as well as approaches to their design. [ABSTRACT FROM AUTHOR]

The problem of improving the efficiency of decision making based on cases (case-based reasoning) in real-time intelligent systems is considered. Methods for preprocessing and storing temporal data are discussed. A method and algorithms for structuring the case base are proposed. The main stages of the method are the generalization of properties of dynamic parameters, the formation of classes of similar situations associated with cases from the case base, and the construction of decision trees to enable efficient search for solutions in each class. The results of a machine experiment are presented. To implement the proposed approach, a temporal database created using the Neo4j NoSQL graph database management system is used. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Xihua University (Natural Science Edition) is the property of Xihua University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of GeSec: Revista de Gestao e Secretariado is the property of Sindicato das Secretarias e Secretarios do Estado de Sao Paulo (SINSESP) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Multi-sensor management and control technology generally constructs a reasonable objective function to solve the optimal control command set to control a limited number of sensors to obtain higher quality measurement information, thus obtaining better target tracking performance. In the process of multi-sensor information fusion, there is not only the problem of information redundancy but also obvious time delay. A sensor fusion algorithm combined with global optimization algorithm is innovatively proposed. According to the key frames saved in the previous steps, feature points in local maps, sensor information, and loop information, a global optimization algorithm based on graph optimization model is constructed to optimize the position and pose of intelligent hardware system and the position of spatial feature points. Moreover, this work studies and experiments on multi-sensor fusion simultaneous localization and mapping (SLAM) comprehensively and systematically, and the experimental results show that the algorithm proposed in this work is superior to common open-source SLAM algorithm in positioning accuracy and mapping effect under special circumstances. Therefore, the method proposed in this work can be applied to intelligent driving of vehicles, vision-assisted movement of robots and intelligent control of unmanned aerial vehicles, thus effectively improving the hardware control accuracy of intelligent systems.

Proximity sensing technology, which can obtain information without physical contact, has become an ideal choice in scenarios where physical contact is not feasible. Despite substantial advancements in tactile sensing, proximity sensing technology still holds great potential and has yet to be fully developed. Among numerous proximity sensing technologies, the fringing‐effect‐based capacitive proximity sensor (FE‐CPS) has garnered considerable attention due to its low cost, low power consumption, wide sensing range, and flexible and versatile structural design. However, research on FE‐CPS has not yet formed a complete system, and its development and intellectualization are still in their infancy, urgently requiring a systematic review to advance its development. This paper systematically summarizes the recent advances in FE‐CPS, from basic theory to practical applications. The working principle and typical structure of FE‐CPS are first introduced, followed by a discussion of methods for optimizing device performance. Furthermore, the application scenarios of FE‐CPS in intelligent pre‐alarm systems, intelligent control systems, and intelligent material perception systems are reviewed. Finally, the future development and challenges faced by FE‐CPS are prospected. [ABSTRACT FROM AUTHOR]

Background: Effective management of cancer pain critically depends on timely medication administration and adherence to precise medication guidelines. In the context of limited time and a busy healthcare environment, tailoring the optimal medication schedule for each patient with cancer pain presents a significant challenge for physicians and clinical pharmacists. Methods: To address this challenge, we conducted a comprehensive analysis of healthcare professionals’ needs in guiding cancer pain medication. By developing core features based on key user needs and continuously updating them, we have created the Universal Medication Schedule System (UMSS). We invited 20 physicians and pharmacists specializing in oncology or cancer pain to trial the system and assessed UMSS usage through distributed questionnaires. Results: We identified five key needs of healthcare professionals in cancer pain medication guidance. Based on these needs, we (1) constructed a comprehensive drug information database, including basic information for 1135 drugs, 130,590 drug interaction data entries, and 1409 individual medication timing constraints, and (2) developed a web-based system that provides essential reference information such as drug interactions and dietary restrictions. It can create medication schedules and provide medication education tailored to the patient’s daily routine. Participating evaluators unanimously agreed (100%) that the system aids in accurately assessing the risks of polypharmacy and quickly scheduling medication regimens. Conclusion: UMSS, by offering personalized medication schedule support, assists healthcare professionals in better managing patients’ medication treatment plans. However, further improvements are needed in the automation of database updates and maintenance, as well as in integrating it with electronic health records. [ABSTRACT FROM AUTHOR]

Coal is the cheapest source of energy. It is much cheaper than nuclear and petroleum. However, spontaneous combustion is inherent in coal seams that lead to fires at their place of storage. Therefore, early detection is required to ensure safety. This article aims to develop an intelligent system for the classification of coal seams based on their spontaneous heating on the Internet of Things (IoT) paradigm. It utilizes an artificial intelligence (AI) approach by utilizing a two-stage neural network architecture to render an accurate and robust categorization of coal samples. Three commonly available proximate analysis parameters of the coal samples have been used as input to this system. These inherent parameters are found to be sufficient to classify coal samples into different categories according to their combustion susceptibility. Three publicly available datasets are involved in the assessment purpose. Our proposed method has outperformed previous approaches. The coal seams classification results agree with the real field experiences. [ABSTRACT FROM AUTHOR]

Due to the absence of more efficient diagnostic tools, the spread of mpox continues to be unchecked. Although related studies have demonstrated the high efficiency of deep learning models in diagnosing mpox, key aspects such as model inference speed and parameter size have always been overlooked. Herein, an ultrafast and ultralight network named Fast‐MpoxNet is proposed. Fast‐MpoxNet, with only 0.27 m parameters, can process input images at 68 frames per second (FPS) on the CPU. To detect subtle image differences and optimize model parameters better, Fast‐MpoxNet incorporates an attention‐based feature fusion module and a multiple auxiliary losses enhancement strategy. Experimental results indicate that Fast‐MpoxNet, utilizing transfer learning and data augmentation, produces 98.40% classification accuracy for four classes on the mpox dataset. Furthermore, its Recall for early‐stage mpox is 93.65%. Most importantly, an application system named Mpox‐AISM V2 is developed, suitable for both personal computers and smartphones. Mpox‐AISM V2 can rapidly and accurately diagnose mpox and can be easily deployed in various scenarios to offer the public real‐time mpox diagnosis services. This work has the potential to mitigate future mpox outbreaks and pave the way for developing real‐time diagnostic tools in the healthcare field. [ABSTRACT FROM AUTHOR]

Hand gesture recognition using a camera provides an intuitive and promising means of human-computer interaction and allows operators to execute commands and control machines with simple gestures. Research in hand gesture recognition-based control systems has garnered significant attention, yet the deploying of microcontrollers into this domain remains relatively insignificant. In this study, we propose a novel approach utilizing micro-hand gesture recognition built on micro-bottleneck Residual and micro-bottleneck Conv blocks. Our proposed model, comprises only 42K parameters, is optimized for size to facilitate seamless operation on resource-constrained hardware. Benchmarking conducted on STM32 microcontrollers showcases remarkable efficiency, with the model achieving an average prediction time of just 269ms, marking a 7× faster over the state-of-art model. Notably, despite its compact size and enhanced speed, our model maintains competitive performance result, achieving an accuracy of 99.6% on the ASL dataset and 92% on OUHANDS dataset. These findings underscore the potential for deploying advanced control methods on compact, costeffective devices, presenting promising avenues for future research and industrial applications. [ABSTRACT FROM AUTHOR]

One of the most challenging scenarios for drivers of open-pit mines is driving in dense fog. As a result, drivers cannot see the road, which causes significant vehicle colloidal accidents. To overcome the problem, an intelligent vision enhancement system has been developed by real-time processing and integrating data from the vehicle-to-everything (V2X) module, global navigation satellite system (GNSS), radar, and infrared cameras to enhance the visibility range of the operative road to the driver and mitigate the chances of accidents. Final images after image processing and object detection are displayed using a dashboard screen in front of the driver for adaptive control and safe operation. Performance analysis of the visual computing algorithm has been carried out in a mine based on image quality parameters. Field-tested images' average contrast value, peak signal-to-noise ratio, structural similarity index, visual information fidelity, and universal quality index were 0.87, 19.36, 0.39, 0.82, and 0.56, respectively, and the calculated accurateness of the convolution neural network (CNN)-based object detection model was 90%. These values indicate the output of the image processing algorithm provided better-enhanced images in the foggy condition. With the help of image processing algorithms, the camera view is able to provide a clear vision of more than 30 m in dense fog. Further, using V2X technology, the augmented visibility range has been increased up to 200 m. The 3D augmented reality (AR) view and 2D navigation view provide other surrounding vehicle locations. Untagged objects like rocks or bunds are also detected and displayed using radar. HIGHLIGHTS: The system fuses IR cameras, V2X, GNSS, radar, & visual computing for safe driving Image processing algorithm fuses CLAHE and DCP methods for clear image output CNN-based object detection algorithm integrated with image processing software Provides multi-stage safety using camera, 2D navigation, & 3D virtual reality views Intelligent system inbuilt with software and advanced analytics for fleet management [ABSTRACT FROM AUTHOR]

In coastal areas, due to their special geological conditions, soft soil foundation has become a common form of foundation in engineering construction. Soft soil foundation has low bearing capacity and large settlement deformation, posing a serious threat to surrounding building facilities and human life and property. Therefore, monitoring it is crucial. However, the inherent characteristics of soft soil foundation make it difficult to monitor, and traditional monitoring methods have shortcomings such as poor timeliness, low manual efficiency, and difficulty in sharing monitoring data. Therefore, in practical engineering, a combination of manual and automated methods is often used for monitoring. With the advancement of technology and the development of new technologies such as artificial intelligence, applying intelligent systems to soft soil foundation monitoring, real-time monitoring and early warning have become a new research direction. This article took a coastal soft soil foundation project as an example to introduce the application of intelligent systems in this project. [ABSTRACT FROM AUTHOR]

Infants are exceptionally fragile and physically vulnerable. Continuous monitoring of their vital characteristics and physiological parameters is vital for assessing their exact health status. The progressive achievements of bioelectrical, biophysical, biochemical and hybrid soft monitoring technologies in infant are discussed. We offer insights into the remaining challenges and translational hurdles of soft electronics for clinical-grade infant monitoring from the benchtop to the bedside. [Display omitted] Infants are exceptionally fragile and physically vulnerable who need special healthcare. Continuous monitoring of vital information of infants is essential for understanding their health status. Whereas modern infant health monitoring is carried out with dedicated facilities in controlled hospital settings, they are associated with several issues such as potential iatrogenic injuries, barriers for skin-to-skin parental bonding, and even complications during basic clinical tasks. Recently, soft electronics have become an accessory and mobile infant monitoring platform with remarkable advantages over existing technologies. This review comprehensively summarizes the research advances on soft electronics for advanced infant monitoring. We first introduce the physiological characteristics from anatomy, diseases, and treatments of infants. In accordance with these characteristics, we discuss the progressive achievements of soft bioelectrical, biophysical, biochemical, and hybrid monitoring technologies for infants. In addition, we offer insights into the remaining challenges and future directions of a soft electronics based intelligent system for clinical-grade infant monitoring from sensor design, data processing, power supply, and digital interactions in the era of Internet of Things. Finally, we highlight the translational challenges to be considered in bringing soft electronics for infant monitoring from the benchtop to the bedside. [ABSTRACT FROM AUTHOR]

Copyright of Machine Tool & Hydraulics is the property of Guangzhou Mechanical Engineering Research Institute (GMERI) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Vibration analysis identifies emerging vibration problems before they become unmanageable and cause unforeseen delays. This can be accomplished by monitoring engine vibration continuously or at specific intervals. Unbalance is a common vibration issue caused by the center of mass shifting from the center of rotation, leading to misalignment and excessive vibration between shafts. To prevent this, manual monitoring is required, but it is time-consuming. Therefore, intelligent system monitoring is necessary to save time. Using a large amount of vibration, spectrum, and phase data as input, this project aims to develop a diagnostic application for motor problems based on vibration signals. Fuzzy logic is implemented in MATLAB software to process a considerable amount of input data for all vibrations, spectrums, and phases using the fuzzy logic method. A vibration meter is used to collect vibration data from the demonstration machine. All input data will be processed by the fuzzy system based on predefined fuzzy rules that must provide accurate results for the actual operating conditions of the demonstration machine. Conducting experiments will help the intelligent system correctly detect damage from misalignment and imbalance. The intelligent fuzzy logic system can accurately diagnose damage caused by misalignment and unbalance on the demonstration machine.

The main methodological problems and strategic goals of work on creating the theory and technology of intelligent computer systems of a new generation are considered. The problems of the current state of work in the field of artificial intelligence and their causes are studied, and the need for a transition to a new generation of intelligent computer systems is substantiated. The basic principles underlying such systems, as well as the corresponding complex technology, are presented. The transition from local automation when solving particular problems to complex automation of various areas of human activity is justified. The concept of an ecosystem of interoperable intelligent computer systems is proposed, which is the basis for complex automation. The architecture of the ecosystem, the directions of its evolution, and the classes of systems included in the ecosystem are considered.

The object of research is the process of automating systems for structuring data from several sources. The subject of the research is methods and algorithms for implementing a complete system for automated and parallel processing, validation and structuring of data. One of the most problematic areas is the merging of databases with different structures and several common fields into a generalized structure. The research was aimed at developing a system to increase the efficiency of automation of big data processing. As a result of the work, optimization methods were studied, the influence of their internal parameters on the operation of algorithms was analyzed, their main advantages and disadvantages were determined, and software was developed in which the corresponding methods were implemented. An algorithm for structuring data before processing has been obtained. Data structuring is achieved by performing the «mapping» operation. Mapping can take place by indexes of already cleaned data or using a defined dictionary with a given set of keys, which allows not to care about the sequence of storing values and their possible shift. The practical significance of the developed system lies in the improvement of methods of collecting and processing information for the purpose of its further validation, cleaning and accumulation in the following categories: geographic addresses and geo-coordinates, validation and automated addition of a mobile phone number to the international format, processing of car numbers (in modern and outdated format), VIN code of the engine and car brand, validation of urls of social networks, passport data and processing of personal data. Compared to similar methods for processing large volumes of data, the possibility of splitting the input file or stream into separate parts was used, the cleaned data from which is combined at the end of the system operation. Thanks to this, it is possible to process data whose size exceeds the available volume of the device’s RAM, and the method of working with loosely structured text files in CSV format has been improved. [ABSTRACT FROM AUTHOR]

In order to improve the reliability of Tibetan Thangka sales channels, this paper combines blockchain technology to construct an intelligent model that can be used for Tibetan Thangka sales. This paper uses cryptographic encryption technology to encrypt the uploaded data to prevent Thangka producers or logistics turnover parties from tampering with Thangka‐related information, and uses the timestamp in blockchain technology to realize the traceability of Thangka‐related information. In addition, this paper uses the timestamp technology in the blockchain system to generate a traceable, query and supervised blockchain, which runs through the whole process of thangka from planting to selling. Finally, a sales model of Tibet Thangka based on blockchain technology is designed, and system performance analysis is carried out through simulation experiments. The experimental research results verify that the designed sales model has a certain effect. [ABSTRACT FROM AUTHOR]

With the growth of open areas comes an ever-increasing risk of fire. However, there is a problem with the present approaches to fire detection, which rely on smoke sensors for wide regions. The advent of video surveillance systems has greatly improved our ability to detect smoke and flames coming from a distance and reduced this risk. Point sensors are slower at detecting fires than cameras when image processing is used. Moreover, using this video and image data presents processing challenges due to the enormous volume of data involved. Several approaches have recently been put forth to address this issue and distinguish between fire and smoke. Earlier methods included image processing algorithms for flame and smoke detection as well as motion-based estimation of smoke. Recently, a variety of techniques have been put forth using deep learning and convolutional neural networks (CNNs) to predict and automatically identify fire and smoke in videos and images. In this study, we review previous studies of fire/smoke detection systems based on machine vision and deep learning. The foundations of image processing techniques, CNN, and their applicability to video smoke and fire detection are explained. A discussion of current data sets and an overview of recent methods applied in this field The difficulties and potential solutions for advancing the application of CNN in this field are discussed. Then a comparison for researchers in the last years based on the dataset, year, technique, limitation, and accuracy they got The CNNs have been found to have a high potential for detecting open areas, and improved development can help create a system that would significantly reduce the loss of human life and property. Remarks for future work were concluded. [ABSTRACT FROM AUTHOR]

Flexible sensors for food quality control are experiencing rapid development. The purpose of this study is to address the time‐consuming issues associated with traditional fruit grading methods by utilizing a homemade flexible impedance sensing system (FISS). A customized spiral slide system was innovatively designed in the study to simulate the grading process on a fruit assembly line with multimodal features for low power consumption and non‐destructive evaluation. FISS integrated components such as a camera, spiral slider, 3D printed slider, latex ball, flexible impedance electrodes, and back‐end measurement circuits and successfully achieved accurate food quality assessment by using a visual classification model for primary grading based on YOLOv5s‐CBAM and an impedance feature classification model for secondary grading of mangoes based on the coefficient of variation method and threshold coefficient method. With an impressive assessment accuracy of 97.07% and a classification speed of up to 3 s/piece, the system successfully classified mangoes into seven grades covering overripe, fully ripe, ripe, unevenly ripe, unripe, underripe, and rotten states. By eliminating the reliance on complex instruments and expensive equipment, FISS provides a cost‐effective alternative for food quality control, significantly reducing operational costs. Practical applications: The purpose of this study is to address the time‐consuming issues associated with traditional fruit grading methods by utilizing a homemade flexible impedance sensing system (FISS). A customized spiral slide system was innovatively designed in the study to simulate the grading process on a fruit assembly line with multimodal features for low power consumption and non‐destructive evaluation. FISS integrated components such as a camera, spiral slider, 3D printed slider, latex ball, flexible impedance electrodes, and back‐end measurement circuits and successfully achieved accurate food quality assessment by using a visual classification model for primary grading based on YOLOv5s‐CBAM and an impedance feature classification model for secondary grading of mangoes based on the coefficient of variation method and threshold coefficient method. With an impressive assessment accuracy of 97.07% and a classification speed of up to 3 s/piece, the system successfully classified mangoes into seven grades covering overripe, fully ripe, ripe, unevenly ripe, unripe, underripe, and rotten states. By eliminating the reliance on complex instruments and expensive equipment, FISS provides a cost‐effective alternative for food quality control, significantly reducing operational costs. [ABSTRACT FROM AUTHOR]

The supply chain functions as a complex web, interconnecting various stakeholders such as suppliers, manufacturers, wholesalers, retailers, and ultimately, end consumers. Central to effective supply chain management is the meticulous handling of inventory, a critical factor influencing both cost efficiency and service excellence throughout the entire network. The management of inventory within this context extends beyond the confines of individual enterprises, bearing significance across the entirety of the supply chain. Consequently, achieving optimal performance necessitates a cohesive, holistic approach to management, aligning with the overarching objectives of the system. Through dynamic data analysis of multiple types of power materials, a dynamic inventory control model for power materials is constructed to achieve optimal adjustment of inventory management. Ultimately, a multi-granularity inventory control method based on big data analysis of power warehousing is constructed, which effectively improves inventory management efficiency and reduces logistics management costs for enterprises. Through big data analysis of power material warehousing, the characteristics of power material demand are excavated, and a classification method for power material demand is constructed to achieve an overall inventory control strategy for power materials. The implementation results show that the controlled inventory can better meet the changing demand, thereby improving inventory management efficiency. The multi-granularity inventory control method based on big data mining of warehousing combines inventory and multiobjective optimization theories, proves the applicability and feasibility of the proposed method, effectively improves inventory management efficiency, reduces logistics management costs for enterprises, and provides practical guidance and decision-making reference for improving the intensive management level of power production and maintenance materials. [ABSTRACT FROM AUTHOR]

Copyright of Railway Construction Technology is the property of Railway Construction Technology Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Advanced sensor technology, especially those that incorporate artificial intelligence (AI), has been recognized as increasingly important in various contemporary applications, including navigation, automation, water under imaging, environmental monitoring, and robotics. Data-driven decision-making and higher efficiency have enabled more excellent infrastructure thanks to integrating AI with sensors. The agricultural sector is one such area that has seen significant promise from this technology using the Internet of Things (IoT) capabilities. This paper describes an intelligent system for monitoring and analyzing agricultural environmental conditions, including weather, soil, and crop health, that uses internet-connected sensors and equipment. This work makes two significant contributions. It first makes it possible to use sensors linked to the IoT to accurately monitor the environment remotely. Gathering and analyzing data over time may give us valuable insights into daily fluctuations and long-term patterns. The second benefit of AI integration is the remote control; it provides for essential activities like irrigation, pest management, and disease detection. The technology can optimize water usage by tracking plant development and health and adjusting watering schedules accordingly. Intelligent Control Systems (Matlab/Simulink Ver. 2022b) use a hybrid controller that combines fuzzy logic with standard PID control to get high-efficiency performance from water pumps. In addition to monitoring crops, smart cameras allow farmers to make real-time adjustments based on soil moisture and plant needs. Potentially revolutionizing contemporary agriculture, this revolutionary approach might boost production, sustainability, and efficiency. [ABSTRACT FROM AUTHOR]

Water resources are essential for human beings and nowadays polluted water jeopardizes the human health. Toxic substances come from houses, industries and farm lands, dust mix with water causes water pollution. This pollution depreciates the quality of water and affects the human life. In this paper, our objective is to evaluate and supervise the physicochemical quality of the ground water, for the safety of human beings. The sample quality of 15 sites was used for measuring important parameters like pH, EC, Ca2+, Mg2+, Na+, K+, Cl−, SO42−, Also, NH4+ and NO3−, Fe2+ and HCO3−12 were considered for performance analysis. A soft computing component fuzzy logic system is used to design an intelligent system. The fuzzy logic system-based model measures groundwater quality status along with its sustainability. The results obtained from the model help the authorities, policy makers to plan proper policies for geochemical operation (water treatment process) and a foundation for observing the physicochemical quality of water in the area. [ABSTRACT FROM AUTHOR]

Heart disease is a complex disease, and many people around the world suffer from this disease. Due to the lack of a healthy lifestyle, it is the most common cause of death worldwide. Machine learning plays an important role in medical treatment. The goal of this research is to develop a machine learning model to help diagnose heart disease quickly and accurately. In this article, an effective and improved machine learning method is proposed to diagnose heart disease. We designed a novel and robust ensemble model that combines the top three classifiers, namely Random Forest, XGBoost and Gradient Boosting Machine, to effectively diagnose heart disease. We used an ensemble voting method to combine the results of the top three classifiers to improve the prediction of heart disease. We used a combined heart disease dataset containing five different datasets (Hungary, Statlog, Switzerland, VA Long Beach and Cleveland). Feature selection algorithms (Pearson Correlation, Univariate Feature Selection, Recursive Feature Elimination, Boruta Feature Selection, Random forest, and LightGBM) are used to select highly relevant features based on rankings to improve classification accuracy. The proposed ensemble model is designed using seven highly relevant features, and a comparison of machine learning algorithms and ensemble learning techniques is applied to the selected features. Different performance evaluation methods are used to evaluate the proposed model: accuracy, sensitivity, precision, F1-score, MCC, NPV and AUC. Results analysis shows that the ensemble model achieves excellent classification accuracy, sensitivity, and precision of 96.17%, 98.37%, and 94.53%. Our proposed model performs better than existing models and individual classifiers. The results show that the proposed ensemble method can effectively predict the risk of heart disease. [ABSTRACT FROM AUTHOR]

Copyright of Bearing is the property of Bearing Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

During an epidemic, the transportation of patients to emergency departments and the monitoring of their physiological parameters pose significant challenges in this critical scenario. Swift and efficient diagnosis has the potential to rescue the lives of these patients. The objective is accomplished through the utilization of deep learning to categorize information into emergencies, prioritizing its dispatch. In this article, we present a sophisticated emergency system that employs deep learning to swiftly transmit vital information from emergency patients to the hospital that can provide the highest quality healthcare for these individuals. The fusion method integrates data obtained and refined from patients' electronic medical records with data acquired by the wireless medical sensor network during the transportation phase. Subsequently, the process of choosing the parameters is employed as inputs to the learning model. The data gathered and educational outcomes, such as emergency notifications, are transmitted through Wi-Fi and 5G devices in our sophisticated system. The proposed contribution achieves a 98% accuracy with a runtime of 1.53 seconds. This discovery demonstrates the efficacy of our system, particularly in the context of epidemic situations such as COVID-19. [ABSTRACT FROM AUTHOR]

The object of this research is the processing of synthetic aperture radar (SAR) images using artificial intelligence. The subject of the study focuses on the utilization of artificial intelligence for the object detection on SAR images. The primary goal of this thesis is to investigate the principles of SAR operation, analyze various systems for detecting anomalous objects in soil, develop an intelligent system for processing SAR images, and evaluate the potential of the developed system for the classification of explosive objects. The research methods include the analysis of existing literature and programming in Python. The findings and materials from this thesis are recommended for use in the analysis of current underground anomaly detection systems, the potential application of artificial intelligence and machine learning in demining processes, and the examination of radar image processing methods. [ABSTRACT FROM AUTHOR]

The purpose of the study is to develop an approach to planning the trajectory of the manipulator robot using an intelligent system based on neural networks. For this purpose, the work considered the processes of planning and deploying the movement of the robot. The analysis of existing methods of planning the movement of manipulator robots and the review of intelligent control systems made it possible to obtain a complete picture of the current state of this issue. A system is proposed that can perceive the environment and control the movement of the robot by generating the correct control commands. For this, 3 tasks were solved, namely: analysis of the environment in order to determine its features, determination of the trajectory in order to neutralize the collision and determination of controlled influences for the executive authorities in order to implement the movement. The functionality and structure of the neural network for solving each of the tasks are proposed. [ABSTRACT FROM AUTHOR]

Long COVID is a condition that affects a significant proportion of patients who have had COVID-19. It is characterised by the persistence of associated symptoms after the acute phase of the illness has subsided. Although several studies have investigated the risk factors associated with long COVID, identifying which patients will experience long-term symptoms remains a complex task. Among the various symptoms, dyspnea is one of the most prominent due to its close association with the respiratory nature of COVID-19 and its disabling consequences. This work proposes a new intelligent clinical decision support system to predict dyspnea 12 months after a severe episode of COVID-19 based on the SeguiCovid database from the Álvaro Cunqueiro Hospital in Vigo (Galicia, Spain). The database is initially processed using a CART-type decision tree to identify the variables with the highest predictive power. Based on these variables, a cascade of expert systems has been defined with Mamdani-type fuzzy-inference engines. The rules for each system were generated using the Wang-Mendel automatic rule generation algorithm. At the output of the cascade, a risk indicator is obtained, which allows for the categorisation of patients into two groups: those with dyspnea and those without dyspnea at 12 months. This simplifies follow-up and the performance of studies aimed at those patients at risk. The system has produced satisfactory results in initial tests, supported by an AUC of 0.75, demonstrating the potential and usefulness of this tool in clinical practice. [ABSTRACT FROM AUTHOR]

In recent years, with the rapid development of China's technological level, internet business has also increased, resulting in a shortage of wireless spectrum resources. Therefore, relevant scholars have introduced device direct communication technology into communication networks. Traditional cellular networks improve utilization efficiency and system capacity by introducing device through technology, and can also reduce the transmission pressure of base stations. However, this solution allows cellular users and device through users to share resources simultaneously, and each user may cause interference before. When the interference is severe, users cannot use the communication system. Therefore, this article proposes a communication resource allocation algorithm based on a proportional algorithm, which can enable users to experience better usage effects and leverage the performance advantages of device direct communication technology. Intelligent manufacturing can reflect the industrial competitiveness of every country, and China also attaches great importance to the development of intelligent manufacturing and increases efforts to support intelligent manufacturing. The manufacturing industry of intelligent systems is carried out through the industrialization of computers, promoting system optimization and upgrading. This article studies and explores the clustering of industrial IoT and digital intelligent manufacturing, applying these technologies to wireless resource allocation, thereby promoting the development and improvement of intelligent systems. [ABSTRACT FROM AUTHOR]

The objective of this paper is to introduce a module that works with smart glasses that to detect and recognize traffic signs on the road. The developed module encompasses the detection and classification of traffic signs, thereby enhancing safety and convenience for users during their travels. Employing innovative recognition algorithms, the software distinguishes between various types of signs, including speed limits, hazard warnings, and directional indicators. Furthermore, the system prioritizes user convenience by providing an intuitive and easily com-prehensible interface. This facilitates quick and precise access to information about traffic signs for both drivers and pedestrians, irrespective of their technological experience. Our endeavor not only illustrates the functionality of the system but also underscores its significance in augmenting road user safety. This innovative approach reflects our commitment to advancing technologies that not only offer intelligent solutions but also simplify everyday tasks for individuals. The paper establishes the sustainability and efficacy of this prototype, thereby laying the groundwork for future development and potential large-scale implementation of the system. This presents an exciting opportunity to enhance the mobility and safety for road users through innovative technologies and intelligent solutions. [ABSTRACT FROM AUTHOR]

Due to the absence of more efficient diagnostic tools, the spread of mpox continues to be unchecked. Although related studies have demonstrated the high efficiency of deep learning models in diagnosing mpox, key aspects such as model inference speed and parameter size have always been overlooked. Herein, an ultrafast and ultralight network named Fast‐MpoxNet is proposed. Fast‐MpoxNet, with only 0.27 m parameters, can process input images at 68 frames per second (FPS) on the CPU. To detect subtle image differences and optimize model parameters better, Fast‐MpoxNet incorporates an attention‐based feature fusion module and a multiple auxiliary losses enhancement strategy. Experimental results indicate that Fast‐MpoxNet, utilizing transfer learning and data augmentation, produces 98.40% classification accuracy for four classes on the mpox dataset. Furthermore, its Recall for early‐stage mpox is 93.65%. Most importantly, an application system named Mpox‐AISM V2 is developed, suitable for both personal computers and smartphones. Mpox‐AISM V2 can rapidly and accurately diagnose mpox and can be easily deployed in various scenarios to offer the public real‐time mpox diagnosis services. This work has the potential to mitigate future mpox outbreaks and pave the way for developing real‐time diagnostic tools in the healthcare field.

The increase in uncertain weather affects agriculture, impacting crop yield and quality, mainly due to the interaction of climatic variables such as temperature, wind speed, and humidity. In addition, soil erosion and nutrient loss are regional problems aggravated by inadequate agricultural practices in developing sugarcane agriculture. The present research proposes an Intelligent System based on a detection algorithm and a fuzzy model to estimate the quality of the sugarcane crop and the probability of the presence of pests and diseases through the prediction of uncertain variables. Wind speed, cloudiness, humidity, and thermal amplitude were considered variables of interest because parameters out of control of these variables generate a state of thermal stress, triggering pests and diseases that reduce crop quality and sugar production. This research uses geospatial information to simplify the exchange of information through a detection algorithm using real-time satellite images and a fuzzy model to estimate crop quality and prevent climate change-related problems. The variables humidity and cloudiness determine sugarcane quality as they are related to crop phenology and the probability that the crop will develop pests and diseases. In contrast, the intelligent system showed a correlation of over 93% for predicting the variables of interest.

Hand gesture recognition using a camera provides an intuitive and promising means of human-computer interaction and allows operators to execute commands and control machines with simple gestures. Research in hand gesture recognition-based control systems has garnered significant attention, yet the deploying of microcontrollers into this domain remains relatively insignificant. In this study, we propose a novel approach utilizing micro-hand gesture recognition built on micro-bottleneck Residual and micro-bottleneck Conv blocks. Our proposed model, comprises only 42K parameters, is optimized for size to facilitate seamless operation on resource-constrained hardware. Benchmarking conducted on STM32 microcontrollers showcases remarkable efficiency, with the model achieving an average prediction time of just 269ms, marking a 7× faster over the state-of-art model. Notably, despite its compact size and enhanced speed, our model maintains competitive performance result, achieving an accuracy of 99.6% on the ASL dataset and 92% on OUHANDS dataset. These findings underscore the potential for deploying advanced control methods on compact, cost-effective devices, presenting promising avenues for future research and industrial applications.

Subject of the Research: The creation of an intelligent assistance system for people with visual impairments. Nowadays, the task of developing effective intelligent assistance systems that allow people with vision problems to achieve maximum independence is important and relevant, as existing systems have a number of drawbacks, such as limited autonomy, limited integration with other devices and systems, limited analysis of dynamic obstacles, and limited user feedback capabilities, which in most cases are restricted to voice guidance. Objective: The objective of this work is to create a generalized functional model of an intelligent assistance system for people with visual impairments, which has enhanced autonomy, integration with other devices and systems, the ability to analyze dynamic objects and predict their movement trajectory, and provide diverse feedback to the user. Tasks: To achieve the set objective, the following tasks were accomplished: a generalized functional model of the proposed intelligent assistance system for people with visual impairments was created; the functional dependencies of the components of the developed model were substantiated; a review of the basic modules of the proposed system model was conducted. Methods: The methods used include functional modeling methods and system analysis methods. Results: The following results were obtained: a functional model of an intelligent assistance system for people with visual impairments was proposed. This system surpasses existing analogs in a number of functional capabilities: detection of static and dynamic obstacles with prediction of dynamic obstacles’ movement trajectory, the ability to operate in various conditions (indoors, outdoors, in light or dark, in different weather conditions), support for integration with other systems and devices, and a high level of autonomy. Conclusions: The developed system model has enhanced autonomy, integration with other devices and systems, the ability to analyze dynamic objects and predict their movement trajectory, and provides diverse feedback to the user.

Using a single hidden layer neural network in estimating orientation angles for solar photovoltaics lacks the complexity required to model nonlinear relationships between input variables and the optimal orientation angles for solar photovoltaics. It struggles to generalize well to new and unseen data. More sophisticated neural network architectures such as deep learning with multi-hidden perceptron (MLP) can solve these issues by changing the architecture by deepening the network. Deepening the network will increase complexity, energy consumption, and time complexity. The study uses a novel approach to outperform traditional MLP models with two, three, four, and five hidden layers. An innovative approach was proposed by enhancing a single hidden layer MLP with a quadratic polynomial function, utilizing two robust methodologies, Least Absolute Residuals (LAR) and Bisquare methods. The results demonstrate that these approaches yield significant improvements in Root Mean Square Error (RMSE) and coefficient of determination (R squared). LAR-based MLP showed superiority over both bisquare-based and conventional MLPs methods in R2 and RMSE, ranging from 1.13 to 1.18 and 2.53 to 3.06, respectively. The study outperformed conventional MLP architectures with five hidden layers regarding accuracy and efficiency. The proposed model offers a more effective and less complex solution for data prediction tasks.

A secure and reliable intelligent multi-cloud resource scheduling system in cyberspace is especially important in some industry applications. However, this task has become exceedingly challenging due to the intricate nature of information, the variety of knowledge representations, the compatibility of diverse knowledge reasoning engines, and the numerous security threats found in cloud networks. In this paper, we applied the endogenous security theory to the multi-cloud resource scheduling intelligent system and presented a novel model of the system. The proposed model incorporates various knowledge representations and inference engines, resulting in a multi-cloud resource scheduling intelligent system that ensures endogenous security. In addition, we have devised a scheme for an intelligent system that schedules multi-cloud resources using dual-channels and has an endogenous security mechanism, which we have named Dynamic, Heterogeneous, and Redundant (DHR). Finally, we have used the multi-cloud resource scheduling intelligent run log database to carry out numerous experiments to validate the efficiency of the dual-channel redundant reasoning system with the endogenous security mechanism's DHR property. The results of the experiment demonstrated that the multi-cloud resource intelligent scheduling system model with an endogenous security mechanism was superior to the current single-channel inference system scheme in regards to security and reliability.

进入大数据时代后，互联网应用和信息服务全面普及，大量的个人敏感生物信息被收集整理，导致隐私泄露风险增加；事件相机作为新型的生物启发式传感器，具有低延迟、高动态、无纹理等特性，可为解决数据端隐私保护问题提供全新的技术途径，也因其光敏工作原理而适用于家庭监控等私人场景。本文从大数据时代的隐私泄露问题、事件相机在隐私保护中的优势两方面，深入分析了事件相机用于隐私保护的研究背景；系统梳理了基于人脸模板的隐私保护、基于去识别的隐私保护、基于点云混沌加密的隐私保护等传统的敏感生物信息隐私保护方法，包括行人重识别、手势识别、面部分析在内的面向隐私保护的事件感知方法以及两大类方法的研究进展。进一步总结了强度图像重建、图像修复、视频重建等基于事件流的图像重建与修复新进展，完成了基于6 种算法的图像重建及其结果分析，证明已有重建算法对纹理信息的恢复能力有限，反向验证了基于事件相机的隐私保护技术可行性。针对事件相机未来的规模化应用，提出了降低硬件成本、改进算法网络、从市场角度推动等发展建议，以期为事件相机的隐私保护深化应用提供基础参考。