Search

Accurate shelf-life estimation of food products has the potential to improve the safety, reliability, and sustainability of food supply chains. Here, a scalable system for accurately indicating the freshness-related information of salmon for consumers was developed and characterized. The system comprises two parts, an optically changeable colorimetric sensor by dye incorporated with sol-gel functionalized paper sensor and a deep convolutional neural network (DCNN)-based freshness estimation system based on images. The paper sensor was produced based on paper and immersed, coated, or printed with (3-aminopropyl) triethoxysilane (APTMS) and tetraethyl orthosilicate (TEOS) sol-gel particles and indicators (e.g., pH indicator, ammonia gas indicator, oxidation indicator, and other volatile organic compounds indicators). After being augmented by machine learning, the limit of detection reaches as low as 17.1 ppm for ammonia detection and the accuracy achieved up to 99.2% for salmon freshness estimation, which satisfied the application in food supply chains. The system balanced the trade-off between detection sensitivity, stability, and cost with the ability for scalable batch production. [ABSTRACT FROM AUTHOR]

The widely used pesticide thiram is found in various environments and foodstuffs, posing a risk to human health and contaminating the environment. In this work, the novel SERS flexible sensor (FP/AgNWs@ZIF-8) consisting of silver nanowires and zeolite imidazole frameworks combined with filter paper was prepared for the sensitive and rapid detection of thiram on fruit peel surfaces. The effect that different coating cycles of ZIF-8 films exert on the Raman signal enhancement of the sensor was investigated. The results show that optimal Raman response to 4-Aminothiophenol (4-ATP) was demonstrated in the FP/AgNWs@ZIF-8(5) sensor, with a low LOD of 1.6 × 10−15 M due to a coating period of 5. Furthermore, a novel SERS FP/AgNWs@ZIF-8 sensor with a porous and flexible structure on low-cost and eco-friendly paper was obtained, as to be immersed in a solution of thiram or wiped on a nectarine skin surface, and the highly sensitive LODs of 1.4 × 10−12 M and 7.4 fg/cm2 were achieved, respectively. Therefore, this facile, rapid, and sensitive flexible sensor at low-cost has excellent potential for pesticide residue detection and environmental toxicity analysis. [Display omitted] • In situ zeolitic imidazolate framework (ZIF-8) growth on silver nanowires (AgNWs). • Multi-layer flexible film detects hazardous organic pesticides in peel and aqueous solutions. • Adsorbs dyes and pesticides smaller than the size of ZIF-8. • Synergistic enhancement of Raman response by AgNWs and ZIF-8. [ABSTRACT FROM AUTHOR]

In advanced missions, handling thin and soft membranes is difficult for robots. This task is composed of several sub-tasks, including turning and removing a sheet from a pile of papers on a table, folding paper, and sticking two pieces of paper together. In this study, a hand robot turns and removes a sheet from a pile of papers, and ensures that only one sheet is grasped. To perform this task, two robotic fingers compress the piled papers in the normal direction of the table with a specific force as they close. We therefore incorporated position-based force control into our system; for the force controller, we adopted stiffness control that calculates position modification proportionally to the difference between the target force and an external force measured by the tactile sensor. With this controller, the robot was able to remove a sheet from a pile of papers and ensure that only one sheet was removed. Using this discrimination, the maximum-minimum shearing forces are better classified than with normal force distribution deviation. [ABSTRACT FROM AUTHOR]

Fabriano paper was aged by irradiation with ultraviolet light (λ=310) in a veterometer for 300 hours. At fixed time intervals, samples of the paper under test were analysed by titanium dioxide photosensor to determine electrochemically the ‘environmental persistence’ index, by a suitable conductimeter method, to determine the specific conductivity variation and by thermogravimetry to determine the moisture content, the onset temperature of the cellulose degradation process and the value of the activation energy of the same process. The behaviour of these different types of indicators displayed approximately monotonous trends as a function of time. [ABSTRACT FROM AUTHOR]

The article discusses the study on how far optical paper quality characterization can reach on its own merits. The study involves the use of a combination of digital image acquisition, followed by the angle measurement technique (AMT). Fourteen selected paper quality parameters were evaluated using new image analytical techniques for characterization and monitoring of paper quality. The results show that the new remote sensing image technique shows promising application potential for online product monitoring of the specified physical qualities.

The proposal of Industry 5.0 has made sustainability, human-centric and resilience the core of digital manufacturing, which also puts forward new requirements for the human-machine interaction (HMI) paradigm in human-centric smart manufacturing (HCSM). In the manufacturing scenario, the process of HMI can be divided into four parts: 1) Sensors and hardware, where the environment information and input signals are collected, 2) Data processing, where the signals are converted into data, 3) Transmission mechanism, where the data is transmitted to the processing centre, and 4) Interaction and collaboration. Among them, sensors and data are expected to become breakthrough points in optimising HMI. This is not only due to the emergence of new research, innovation and technologies but also because they are closely influenced by the new design concepts brought about by Industry 5.0. This paper analyses the latest studies and technologies in the sensor field and their possible applications in HCSM scenarios. Then, opportunities and challenges of data analysis in the HMI in Industry 5.0 are discussed. Finally, based on the design concepts and requirements of Industry 5.0, this paper demonstrates how they will become the key points for future HMI development. [ABSTRACT FROM AUTHOR]

This paper is concerned with the translational guidance of multirotor aerial vehicles with uncertain dynamics and equipped with short-range detection sensors in a scenario containing disturbances/uncertainties, multiple accelerated obstacles, and velocity constraints. To address this problem, we propose a robust guidance strategy based on the continuous control obstacles method. To handle disturbances and uncertainties, the proposed method tightens the position and velocity admissible sets according to the respective tracking errors. Moreover, a hybrid prescribed-time arbitrary-order differentiator is employed to robustly estimate the obstacles' velocities and accelerations within a prescribed time interval using measurements from a short-range sensor. As a result, the proposed method can fit into the available time for executing an avoidance maneuver upon the detection and tracking of obstacles. Then, we build a set of possible future positions for the obstacles according to their observed velocities and accelerations, and use this set to calculate a position command for the guided vehicle. The proposed method is experimentally evaluated using an augmented-reality setup composed of a Crazyflie quadcopter, motion capture cameras, and virtual obstacles. The results show that the proposed method is viable for real-time implementation and effective in providing collision avoidance and satisfying velocity constraints. [ABSTRACT FROM AUTHOR]

Machining is extensively used for producing functional parts in various industries such as aerospace, automotive, energy, etc. There is a growing demand for improved part quality and performance at lower costs from increasingly difficult-to-machine materials. Whilst modern machine tools are equipped with sensors for closed loop control of their axes' movements and position, they provide minimal information regarding the cutting performance and tool condition. The integration of additional sensors into cutting tools, machine tools and/or their components can provide an insight into the machining performance. It also provides an opportunity to improve the machining process and reduce the need for post-process inspection and rework. This paper presents a comprehensive analysis of various sensors utilised for in-process and on-machine measurement and monitoring of machining performance parameters such as cutting forces, vibrations, tool wear, surface integrity, etc. Data transfer and communication methods, as well as power supply options for sensor-integrated systems are also investigated. Sensor integrated machining systems can potentially improve machining performance and part quality by early detection of errors and damages, maximising tool usage and preventing machining and tool wear induced damages. A combination of sensor data collection and intelligent sensor signal processing can further increase the capabilities of sensor integrated systems from process monitoring to active process control. [ABSTRACT FROM AUTHOR]

Network security technology is capable of mitigating attack signals launched by malicious attackers, thereby safeguarding and bolstering system security. Secure state estimation is a type of network defense technology that involves reconstructing the system state by measuring potential attacks. The relevant research has also been expanded to distributed systems to enable collaborative secure state estimation among different agents facing homogeneous attacks; however, such research significantly enhance the communication load of the system. On the other hand, if the homogeneous attack is non-existent or consistent, excessive network communication is definitely inefficient. An event-triggered approach is a potent technique that can alleviate communication overhead while having minimal impact on system performance. This paper proposes a mechanism for event-triggered transmission in the context of distributed secure state estimation. While communication latency and data transmission disorder may be present within the communication network, the estimation error of the proposed observer is constrained and bounded. The simulation results indicate that for stable malicious attack signals, system communication can be divided into high-frequency and low-frequency communication periods. The simulation results also shows that the maximum estimation error is proportional to the trigger threshold, allowing the observer's performance to be finely tuned to the required precision. • In this paper, the observer presented implements an event-triggered communication strategy, which effectively decreases the frequency of data transmission and reduces the communication load on the network. • Network latency and data disorder are also taken into consideration. • The maximum estimation error is proportional to the trigger threshold, allowing the observer's performance to be finely tuned to the required precision. [ABSTRACT FROM AUTHOR]

This paper presents the realization and assessment of a compact metamaterial (MTM)-integrated wireless information and power transfer (WIPT) system. Developed WIPT is tailored to facilitate numerous Internet of Things (IoT) sensors operating at the low-power regime. Generally, WIPT is accomplished with a system possessing two operating bands. Therefore, the dual-band system working at frequencies of 405 MHz and 900 MHz was proposed. WIPT is achieved by coupling two defected ground structure-based resonators that are designed by cascading two single-band resonating structures. Then, MTM with the double negative characteristics at WIPT's operating frequencies was incorporated, which led to the performance enhancement. The power transfer efficiency of WIPT was increased by 14% and 7% at 405 MHz and 900 MHz, respectively, when the resonators were coupled at 20 mm. It is worth mentioning that WIPT and MTM share the same area of 25 × 25 mm2 to keep the compactness of the overall system. The WIPT system was evaluated in terms of charging time for two low-power IoT sensors. The powering time was approximated considering two scenarios: using only one band and two bands simultaneously. The provided analysis in both cases reveals that MTM-integrated WIPT aids in the significant reduction of a charging cycle. [ABSTRACT FROM AUTHOR]

Cutting and abrasive processes affect the surface layer state of the components treated. This determines their performance in service. An adjustment of the surface layer properties would allow for enhanced performance. This paper introduces the influences of named processes on the surface layer state and their systematics. Models and sensor concepts for surface conditioning are described and combined to soft sensors which are the basis for active control within the processes. A validation study and actual applications of the conditioning concept are shown, allowing for further technological and scientific understanding of surface conditioning and its contribution to material and energy efficiency. [ABSTRACT FROM AUTHOR]

Refiners are used in the pulp and paper industry to separate wood chips into individual fibres and to develop the morphology of fibres to be suitable for the type and grade of paper to be produced. Within a refiner are discs, at least one of which rotates at high speed and all of which are lined with radial patterns of bars on their opposed surfaces. A mixture of chips and water is accelerated radially through the space between the discs. Compressive and shear forces are applied to chips and fibres as the bars on the opposed discs cross each other. Experiments have shown that certain process variables can greatly affect the forces applied to chips or fibres when bars cross. These findings suggest that the contact mechanics of bar-crossings are a significant factor in the development of fibre properties. To investigate these contact mechanics in operating refiners, a piezoelectric-based sensor has been developed to measure the forces applied to the chips and fibres by the bars. The sensor replaces a small section of a refiner bar and is sensitive to both axial and tangential forces. The current paper describes the evolution of the design of this sensor from a proof-of-concept prototype for a laboratory-scale refiner to the latest generation sensor for a mill-scale refiner. Performance during the most recent mill trials is presented. [ABSTRACT FROM AUTHOR]

Online learning and real-time data processing are becoming increasingly vital across various domains such as sensor networks, banking, and telecommunications. A significant challenge in this context is concept drift, wherein the statistical properties of the data change over time. Traditional drift detectors often grapple with high memory usage, extended delay in detection, prolonged runtime, and accuracy inconsistencies. This paper introduces a novel Online Drift Detector that meticulously balances these four aspects. By processing data instance-by-instance, our proposed detector optimizes the trade-offs between delay detection, runtime, memory consumption, and accuracy. We incorporate a unique diversity calculation tailored for multi-label problems, ensuring swift drift detection with minimized memory usage and enhanced runtime efficiency. Comparative analyses reveal the dominance of our approach over contemporary drift detection techniques, particularly in the realms of memory efficiency, detection speed, and accuracy. This work substantially augments the field of online data stream processing by offering a refined strategy for timely and efficient concept drift detection across a myriad of applications. [ABSTRACT FROM AUTHOR]

Copyright of Industria Textila is the property of Institutul National de Cercetare-Dezvoltare pentru Textile si Pielarie 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.)

This paper focuses on the trajectory tracking problem of nth-order uncertain nonlinear systems with sensor faults. The proposed approach utilizes a fuzzy observer to estimate the unmeasurable states in the systems. Moreover, the finite-time control strategy and the command filtered technique are added in the controller design. The former aims to enhance the systems' response speed, and the latter is to mitigate the "differential explosion" problem. Meanwhile, the adaptive technique is incorporated to compensate for sensor faults. The boundedness of all the signals within the closed-loop systems is confirmed through stability analysis. Finally, the effectiveness of the proposed approach is verified through two simulation examples. [ABSTRACT FROM AUTHOR]

This paper presents the development of an innovative, tunable star-shaped microwave sensor operating at two distinct frequency bands C and X band, optimized for high-sensitivity sensing of both solid and liquid mediums. The sensor's innovative star-shaped geometry augments the surface interaction with the target substances, significantly enhancing the sensor's response and sensitivity. Furthermore, tunability allows the sensor to adapt to different sensing environments, maximizing the detection potential at both frequencies. This research delves into the sensor's performance when using four different substrates for solid sensing containing FR-4, RO-3035, RO-5880, and RO-6202. Each substrate, characterized by unique electromagnetic properties, contributes differently to the sensor's sensitivity and resolution. The extensive experimental results highlight the sensor's proficiency in detecting and differentiating between these substrates, revealing the impact of material selection on sensor performance. The sensor's ability to distinguish between various liquids, including water, milk, oil, and energy drinks, is evaluated in the liquid sensing scenario. The sensor successfully detects the subtle variances in the electromagnetic properties of these liquids, suggesting its capability for high-resolution liquid sensing. The proposed MTM-based sensor resonates at 4.46 GHz and 11.48 GHz, respectively. Numerical software CST was used to analyze all the parameters. A 3 × 3 array was used in the prototype design, and it was used to measure the C-band resonance frequency. On the other hand, a compact unit cell was used to measure the X-band resonance frequency. The outcomes suggest a substantial potential for this sensor design in various industries and scientific fields, including food quality control, the oil industry, biomedical applications, and environmental monitoring. The unique combination of star-shaped design, tunable frequencies, and various substrates offers unprecedented flexibility and sensitivity in solid and liquid sensing on microwave frequency ranges. [ABSTRACT FROM AUTHOR]

The manufacture of precise metal components by cold forging poses serious challenges to the process reliability under unstable process conditions. The detection of geometrical imperfections, such as concentricity deviations, is necessary for the operator to adjust the forging tool rack properly. In this paper, a novel piezoelectric thin-film sensor disc is introduced to detect such concentricity deviations based on the measurement of eccentric load, that is arising from elastic punch deformation. Experimental results showed, that the concentricity deviation of the produced parts efficiently can be predicted by processing measured force data using a support vector regression algorithm. [ABSTRACT FROM AUTHOR]

The Dynamic Principal Component Analysis is an adequate tool for the monitoring of large scale systems based on the model of multivariate historical data under the assumption of stationarity, however, false alarms occur for non-stationary new observations during the monitoring phase. In order to reduce the false alarms rate, this paper extends the DPCA based monitoring for non-stationary data of linear dynamic systems, including an on-line means estimator to standardize new observations according to the estimated means. The effectiveness of the proposed methodology is evaluated for fault detection in a interconnected tanks system. [ABSTRACT FROM AUTHOR]

• The probe enabled naked-eye detection of NO 2 − in the range of 0.005–9.2 mg L−1. • Primary mechanism of the sensing process was a diazotization reaction. • Low-cost (0.01$/ strip) paper-based strips showed high selectivity for NO 2 −. • The strips retained the structural integrity after interaction with NO 2 −. • Recovery of NO 2 − in real samples was found be satisfactory (>85%). An economically feasible, readily accessible colorimetric probe based on basic fuchsin (BF) was developed to detect NO 2 − in water and wastewater systems. The study is divided into two phases; liquid phase and solid phase (colorimetric strip). Initially, the parameter optimization was carried out in the liquid phase, followed by sensing via colorimetric strips. Naked eye-colorimetric detection of NO 2 − in liquid phase was in the range of 0.92–9.2 mg L−1 whereas for strips detection range was observed as 0.005–9.2 mg L−1. Proper diffusion of BF on the Whatmann filter paper (W) enhanced the sensitivity of colorimetric strip. The investigation also showed high selectivity towards NO 2 − in the presence of several anions and cations. The colorimetric strips prior to and after interaction with NO 2 − were characterized using FT-IR, Raman, UV-DRS, and XRD. Results confirmed that diazotization reaction between secondary amine portion of the BF and NO 2 − was responsible for the specific color change (pink to colorless). The leaching test reported no leachable fraction from the coating, and this was accompanied by the use of Tween-80 as a surface coating agent. The solid colorimetric probe was showed potential selectivity towards NO 2 − over several interfering ions. Furthermore, the applicability of the prepared strip for detecting NO 2 − in real water samples indicated satisfactory performance. Cost analysis confirmed that the synthesized BF@W strip is a low-cost (0.01$/strip) and a portable colorimetric sensor for the detection of aqueous NO 2 −. [ABSTRACT FROM AUTHOR]

An Inertial Navigation System (INS) is a standalone system that provides continuous navigation information on the position, velocity, and attitude in various conditions. Gyroscopes and accelerometers are essential components of INS. However, these sensors are prone to errors that accumulate over time and degrade the accuracy of the INS. Therefore, enhancing the performance of INS is a challenging problem. This paper aims to address this problem by proposing a method to reduce errors in real-time processing. The method uses Lifting Wavelet Transform (LWT), a popular denoising technique that belongs to the wavelet family and has an advantage over the classic wavelets in terms of time and computation complexity. Moreover, the method employs an optimization technique based on the Genetic algorithm as an intelligent averaging for combining different multi-level LWTs, which significantly improves the accuracy and efficiency of INSs. Finally, a new and implementable structure is introduced for denoising inertial sensors. The results show that the proposed method achieves an 83% and 59% improvement in gyroscope and accelerometer data for dynamic data, compared with raw data. Besides, for static data, there are 71% and 36% improvements in gyroscope and accelerometer data, respectively. [ABSTRACT FROM AUTHOR]

Among the different challenges related to the improvement of wireless sensor network (WSN) performance, the optimization of energy consumption takes an important place. Basically, sensor nodes in WSN are powered by limited battery. These batteries can allow sensor nodes to be functional for a limited period of time then sensor nodes turn out to be dead. Enhancing energy consumption and finding new manners to save sensor nodes' energy is becoming essential and more challenging. Improving energy consumption for each sensor nodes leads to enhance the lifetime of WSN. Clustering is among the outstanding strategies to reach this goal. In this paper, a new scheme of routing protocol in WSN will be presented in order to minimize the energy consumption and improve WSN lifetime. The new scheme is proposed in order to find the best selection of cluster head (CH) by taking in consideration the energy at each sensor node. It has been proposed based on Firefly Algorithm. We have compared the proposed scheme with LEACH, EAMMH, SEP, E-SEP, BRE, NEAHC and WEB protocol. Experimental results show that the proposed scheme yields better performance than the compared routing protocols in terms of better energy consumption and packet delivery between sensor nodes and base station. Results obviously prove that the proposed scheme could improve the WSN lifetime. • A new scheme of routing protocol has been proposed in order to optimize the energy consumption by sensor nodes in WSN. • The proposed scheme has been proposed based on Fireflies optimization algorithm. • Results of simulation showed the effectiveness of the proposed scheme. [ABSTRACT FROM AUTHOR]

The compound eyes of insects can extract the heading by sensing multi-directional polarization information. Inspired by this, the integration with bionic eye polarization compass and low-precision MEMS inertial sensors yields a new choice for autonomous navigation in a GPS-denied environment. However, the occlusion environments, such as jungles and buildings, seriously affects the attitude estimation accuracy by destroying the polarization information. Considering the above problem, this paper proposes a reliable attitude estimation method based on vector matching measurement models for integration with bionic compound eye polarization compass and low-cost MEMS inertial sensors, including the polarization vector, solar vector, and gravity vector. To realize the matching and fusion among these vector models, the vector optimization selection algorithm is designed according to the number of visible polarization sensors in the occlusion environment. Particularly, the vector optimization selection factor is designed according to the error between the measured and theoretical polarization vectors. Furthermore, when using the solar vector estimation model, the degree of the polarization is applied to improve the calculation accuracy of the solar vector. The gravity vector measurement model is employed to enhance the autonomy of the integration. Finally, the effectiveness of the proposed method is verified by simulated and outdoor experiments under tree obscuration. [ABSTRACT FROM AUTHOR]

The distributed state and parameter estimation problem is investigated in this paper for discrete-time nonlinear systems subject to sensor nonlinearities and stochastic disturbances over a wireless sensor network. A novel architecture for distributed state estimator is introduced that incorporates adaptive coupling gains to govern the information exchange between the sensor nodes under event-triggering mechanism. The aim of this paper is to provide a scalable structure for unknown parameter identification independent of sensor networks' complexity. The boundedness of estimation error is ensured in the framework of uniformly ultimately bounded stability by developing an algebraic connectivity based criterion. The estimator gains including proposed coupling gains are then presented as solution to matrix inequalities. Finally, two simulation examples are presented to demonstrate the effectiveness of proposed estimation architecture. • A novel distributed state estimation structure is introduced. • Both unknown parameters and sensor nonlinearities have been considered. • Event-triggered observer conditions with improved feasibility are developed. • A method for determining coupling gains for complex design problem is revealed. [ABSTRACT FROM AUTHOR]

The distributed state and parameter estimation problem is investigated in this paper for discrete-time nonlinear systems subject to sensor nonlinearities and stochastic disturbances over a wireless sensor network. A novel architecture for distributed state estimator is introduced that incorporates adaptive coupling gains to govern the information exchange between the sensor nodes under event-triggering mechanism. The aim of this paper is to provide a scalable structure for unknown parameter identification independent of sensor networks' complexity. The boundedness of estimation error is ensured in the framework of uniformly ultimately bounded stability by developing an algebraic connectivity based criterion. The estimator gains including proposed coupling gains are then presented as solution to matrix inequalities. Finally, two simulation examples are presented to demonstrate the effectiveness of proposed estimation architecture. • A novel distributed state estimation structure is introduced. • Both unknown parameters and sensor nonlinearities have been considered. • Event-triggered observer conditions with improved feasibility are developed. • A method for determining coupling gains for complex design problem is revealed. [ABSTRACT FROM AUTHOR]

Amid the swift evolution of advanced technologies such as autonomous robotics, edge computing, and the Internet of Things, Intelligent Agriculture Management Systems (IAMS) have become increasingly pivotal in contemporary smart agriculture. One vital task, crop disease monitoring, significantly contributes to ensuring agricultural production quality and food supply security. However, IAMS encounters a particular challenge: due to the limited computational capacity of agricultural equipment and the scarcity of available training datasets, general detection models struggle to achieve anticipated performance in agricultural environments, especially when dealing with small-scaled targets. In this paper, we propose a diffusion learning detector named CropDetdiff, designed for disease detection in agricultural environments where training samples are limited. We have developed a backbone network based on dynamic convolutional kernels, which also embeds a graph attention network in its final stage, enhancing feature extraction capabilities for small targets. Additionally, we employ a fuzzy label assignment strategy to balance positive and negative samples and devise a new loss function, HIoU, to supervise the detection of small targets. A series of experiments on two crop disease datasets validate that CropDetDiff achieves an optimal balance between detection performance and operational efficiency. Specifically, the proposed model has achieved a mean Average Precision (mAP) of 73.2% and 40.1% on the two datasets, improving by at least 3.7% and 2.9% over other detectors, respectively, and there is a significant improvement in small targets particularly, thus achieving optimal performance. Additionally, the proposed model exhibits commendable performance in terms of parameter quantity and execution velocity. These results substantiate the efficacy and stability of CropDetDiff, underscoring its suitability for real-world applications within IAMS. • This paper builds the graph-embedded lightweight backbone network with learnable convolutional kernels (LCSPNet) to mine small targets and their potential graph connections with the background, so that the model can better cope with the detection of multi-scale features under crop dense distribution, especially small targets. • One-to few label assignment strategy is proposed to optimize the imbalance of positive and negative samples in the training process, and add it to the detection head to detect the target region more accurately. Furthermore, we use the new detection head to achieve efficient redundant box suppression in the diffusion learning process of the detection frame. • This study used two small crop diseases datasets to validate the model. Abundant experiments prove that the proposed model achieves good performance results, which can be better adapted to practical applications in different scenarios. [ABSTRACT FROM AUTHOR]

Deep learning techniques have outstanding performance in feature extraction and model fitting. In the field of aero-engine fault diagnosis, the introduction of deep learning technology is of great significance. The aero-engine is the heart of the aircraft, and its stable operation is the primary guarantee of the aircraft. In order to ensure the normal operation of the aircraft, it is necessary to study and diagnose the faults of the aero-engine. Among the many engine failures, the one that occurs more frequently and is more hazardous is the wheeze, which often poses a great threat to flight safety. On the basis of analyzing the mechanism of aero-engine surge, an aero-engine surge fault diagnosis method based on deep learning technology is proposed. In this paper, key sensor data are obtained by analyzing different engine sensor data. An aero-engine surge dataset acquisition algorithm (ASDA) is proposed to sample the fault and normal points to generate the training set, validation set and test set. Based on neural network models such as one-dimensional convolutional neural network (1D-CNN), convolutional neural network (RNN), and long-short memory neural network (LSTM), different neural network optimization algorithms are selected to achieve fault diagnosis and classification. The experimental results show that the deep learning technique has good effect in aero-engine surge fault diagnosis. The aero-engine surge fault diagnosis network (ASFDN) proposed in this paper achieves better results. Through training, the network achieves more than 99% classification accuracy for the test set. [ABSTRACT FROM AUTHOR]

In this paper, a novel nonlinear observer-based approach is established to cast light on the problem of isolating sensor faults from un-stealthy attacks for Lipschitz affine nonlinear systems subjected to unknown uncertainties and disturbances. A structure consisting of a multi-line transmission mechanism, a random number generator (RNG), and Dedicated Observer Scheme is developed to make the abnormal behaviors distinguishable. A group of two interlinked nonlinear Luenberger-Like observers is designed in nonlinear coordinates to detect abnormal behaviors. Two banks of detection observers and an incidence matrix are introduced to make the final decisions. Adaptive threshold techniques are exploited to guarantee the robustness against the model uncertainties and disturbances. Compared with the existing results, the proposed approach isolates the abnormal behaviors without the need for any redundant hardware components. Finally, the performance of the proposed approach is evaluated on a continuous stirred tank reactor (CSTR). [ABSTRACT FROM AUTHOR]

The multiple-attribute decision-making (MADM) problem is resolved through the q -rung complex diophantine neutrosophic normal set (q -rung CDNNS). An important way to express uncertain information is using q -rung orthopair fuzzy sets (q -ROFs). Yager introduced q -ROFs as a generalization of intuitionistic fuzzy sets in which the sum of membership and non-membership degrees is one. In addition, they have superiority over intuitionistic fuzzy sets and Pythagorean fuzzy sets. Complex diophantine fuzzy sets are generalizations of neutrosophic and diophantine fuzzy sets, respectively. Several aggregating operations (AOs) are discussed here, as well as their respective interpretations. The paper discusses q -rung CDNN weighted averaging (q -rung CDNNWA), q -rung CDNN weighted geometric (q -rung CDNNWG), q -rung generalized CDNN weighted averaging (q -rung GCDNNWA) and q -rung generalized CDNN weighted geometric (q -rung GCDNNWG). We will review several of these sets with important properties in greater detail using algebraic operations. Additionally, we develop an algorithm for solving MADM problems using these operators. Several real-world examples illustrate how enhanced score values can be applied. Sensor robots are said to rely heavily on computer science and machine tool technology. Four factors are to evaluate when determining a sensor robotics system's quality: resolution, sensitivity, error, and environment. It is possible to compare expert opinions with the criteria and determine the best alternative. Therefore, the value of q significantly impacts the model's results. To prove that the models considered are valid and useful, we will compare the current and proposed models. Thus, q has a significant impact on the results of the model. [ABSTRACT FROM AUTHOR]

Stochastic configuration network (SCN) is an emerging incremental randomized regression modeling technology with the advantages of adaptively determining the hidden layer parameters, and has been successfully applied to industrial soft sensor modeling field. However, the traditional SCN model is intrinsically a supervised learner, which has the underlying assumption that all the training samples are labeled. In fact, most of process samples are unlabeled and the labeled samples are relatively rare in real industrial scenarios. To handle this issue, this paper presents one modified SCN model, called locality preserving SCN (LPSCN), for semi-supervised industrial soft sensor modeling. In this method, all the training samples, including the labeled and the unlabeled, are fed into the soft sensor model, where the labeled samples are used to capture the modeling error, while the unlabeled samples help construct the local adjacency graph. Based on these two kinds of samples, the supervised optimization objective in the traditional SCN is improved to be a semi-supervised version by minimizing the modeling error and preserving the local data relationship simultaneously. Furthermore, the random parameter configuration mechanism is deduced under the modified semi-supervised optimization framework. A new inequality constraint condition with considering the unlabeled samples is obtained to generate the hidden layer nodes incrementally so that the LPSCN model structure is determined automatically. Experiments on two real industrial systems demonstrate that the proposed LPSCN method outperforms the SCN method in terms of the soft sensor prediction performance. • A semi-supervised stochastic configuration network (SCN) model is presented by considering the unlabeled samples. • A new SCN optimization objective function is designed by introducing the locality preserving regularization term. • A new inequality constraint expression to configure node parameters is given for the modified SCN model training. [ABSTRACT FROM AUTHOR]

This paper proposes a zone-based three-level heterogeneous clustering protocol (ZB-TLHCP) for heterogeneous WSNs. In ZB-TLHCP, the sensor field/region is divided into zones where super, advance, and normal nodes are deployed uniformly and randomly. The performance of the proposed ZB-TLHCP system is compared with that of zonal-stable election protocol (Z-SEP), distributed energy efficient clustering (DEEC), and threshold-based DEEC (TDEEC) protocol by varying the number of super and advance nodes, their energy levels for the fixed sensor field, and the total number of nodes. Matlab simulation results revealed that the proposed ZB-TLHCP solution performed better than Z-SEP, DEEC, and TDEEC protocols, as it increased the instability period, prolonged the network's lifetime, and achieved higher throughput values. [ABSTRACT FROM AUTHOR]

In Bayesian multi-target tracking, the Poisson multi-Bernoulli mixture (PMBM) filter is a state-of-the-art filter based on the methodology of random finite set which is a conjugate prior composed of Poisson point process (PPP) and multi-Bernoulli mixture (MBM). In order to improve the random finite set-based filter utilized in multi-target tracking of sensor scanning, this paper introduces the Poisson multi-Bernoulli mixture filter into time-matching Bayesian filtering framework and derive a tractable and principled method, namely: the time-matching Poisson multi-Bernoulli mixture (TM-PMBM) filter. We also provide the Gaussian mixture implementation of the TM-PMBM filter for linear-Gaussian dynamic and measurement models. Subsequently, we compare the performance of the TM-PMBM filter with other RFS filters based on time-matching method with different birth models under directional continuous scanning and out-of-order discontinuous scanning. The results of simulation demonstrate that the proposed filter not only can effectively reduce the influence of sampling time diversity, but also improve the estimated accuracy of target state along with cardinality. [ABSTRACT FROM AUTHOR]

Fault-tolerant control (FTC) is a design methodology that ensures control systems continue to function even with component faults or failures. FTC is particularly used in Brushless DC Motors (BLDC), electric motors that use electronic commutation instead of brushes. These motors use three Hall effect sensors, placed 120 degrees apart, to accurately determine the rotor's position and control its speed and torque. This paper presents a methodology using electronic logic gates to compensate for sensor faults by analyzing the behavior of the Hall effect signals, translating them into binary language, and enabling continued control of the BLDC motor. This methodology improves the fault-tolerant capability of BLDC motors and ensures their continued functioning despite component failures. Simulation and validation results using Matlab/Simulink demonstrate the effectiveness of the proposed methodology in ensuring the continued operation of the BLDC motor despite component failures. The proposed fault-tolerant control strategy can enhance the reliability and performance of BLDC motors, making it a valuable tool for various industrial applications. [ABSTRACT FROM AUTHOR]

The article presents a new concept drift detection method based on analyzing the importance of features of instances in the data stream. The data stream contains information about distribution patterns that reflect different concepts that may be hidden in the data stream. The presented drift detector concept uses information about the fluctuation of the most informative feature inside chunks of the data stream and compares it with the change of the same feature in neighbor chunks. In the case of data streams, the meaning of features can change over time. These changes affect the quality of the classification but can also be a significant indicator of ongoing concept drift. After detecting the drift, the classifier should be trained with the new dataset. But this issue is not addressed in this article. In this work, we propose a new concept drift detector in the data stream for the first time. This goal is achieved by observing the changing importance of features in different parts of the data stream. The proposed approach uses the feature significance measure as a drift detector. The obtained results indicate that the method can be introduced in practice. Because these are only preliminary results, in this paper, we focused on presenting the advantages of our strategy without comparison with other methods. [ABSTRACT FROM AUTHOR]

Copyright of China Textile Leader is the property of China Textile Information Center 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.)

In this paper, event-triggered output feedback control of a class of high-order nonlinear strict-feedback systems with parametric uncertainties is investigated, in which both of the controller and the parameter estimator are triggered based on a set of event-triggered conditions. Firstly a new one-step control design framework is proposed for the strict-feedback nonlinear systems, therefore both expressions of the controller and the parameter estimate laws are much more simple than those of the recursive design approaches such as backstepping control. Secondly observers are designed to estimate the unknown states, and a set of event-triggering mechanism is proposed for the sensors such that the states are transmitted through the communication network only at the triggering points. The estimated parameter is obtained without real-time integration due to the event-triggered estimator. It is proved that our proposed control law guarantees the closed-loop system is globally bounded and the system output converges to zero asymptotically. It is also proved that the Zeno behavior is excluded. Simulation results demonstrate the effectiveness of the proposed control scheme. • A novel adaptive output feedback control for strict-feedback systems is designed. • A new one-step control design framework for strict-feedback systems is proposed. • An event-triggered rule is designed to be transmitted only at the triggering points. • It is guaranteed that the system output converges to zero asymptotically. [ABSTRACT FROM AUTHOR]

The various data collected by urban sensor devices need a huge storage space. The cloud's powerful calculation ability provides decent performance support and reduces the overhead on local storage. There are many kinds of data collected by urban sensor devices, and the same kind of sensors often need to upload large numbers of files together, which are usually private, so secure cloud storage in group members is essential. However, the cloud may try to modify or hide data for its own benefit, which requires the detection of a third-party auditor. This paper puts forward a new public audit scheme. Some changes have been made to the way of generating the private key, the parameters of key generation come from the feature information set of the same sensor. When the two information sets are close enough, the correctness of the authenticator generated by this file can be verified. When the sensor is revoked due to damage or loss, this scheme will effectively revoke and regenerate the private key with less overhead, thus preventing the leakage of data privacy. This also avoids the huge overhead caused by re-downloading data to generate authenticators in traditional schemes. In addition, our scheme is effective in tracking malicious members and reducing the computing overhead of the group. Finally, the experimental results show the effectiveness and practicality of the proposed scheme. [ABSTRACT FROM AUTHOR]

The advances in electronics, sensors, actuators, smart materials, computers, and communication technologies led to new and improved mechatronics-based smart tooling systems. This paper reviews the sensors and actuators used in tooling systems. The sensor principles to measure force, displacement, and temperature are explained. Actuators based on piezo, magnetorheological fluid, shape memory alloy, and magnetostrictive principles are discussed. Wireless and wire-based power supply and signal transmission techniques to stationary and rotating tools are described. The integration of sensors, actuators, power supply, and microcontrollers to various tooling systems used in boring, milling, turning, and grinding operations are presented along with their process monitoring and control applications in the industry. It is shown that the sensor-actuator tooling systems improve the accuracy, robustness, and productivity of machining which adds intelligence to the machine tools. The current challenges include widening the operating bandwidth of tooling systems, wireless power and high-speed data transmission, miniaturization of actuators and sensors, and onboard processing using embedded micro-controllers. [ABSTRACT FROM AUTHOR]

Detecting and fixing vulnerabilities in software programs before production is crucial in software engineering. Manual vulnerability detection is labor-intensive, especially for large programs, leading to the proposal of machine learning-based methods for automation. However, existing approaches primarily detect vulnerabilities at the function level, providing non-specific results that require additional developer effort to locate vulnerabilities. Detection at the line-of-code level is an underexplored area. In this paper, we propose a novel deep learning method for line-of-code vulnerability detection. Our hybrid neural network combines a memory network and multi-head attention mechanism. Through comprehensive experiments, we analyze the impact of each modification, demonstrating significant improvements in performance. Our approach outperforms existing methods for comparison, showcasing its effectiveness in vulnerability detection. [ABSTRACT FROM AUTHOR]

In this paper, a robust asynchronous filter is proposed to detect faults in Markovian jump systems with sensor saturations. The proposed filter has a mode different from that of the original system, and is tolerant of external disturbances. The residual is generated to construct an evaluation function that can successfully perform fault detection. Detailed filter matrices can be computed from the existing conditions. Furthermore, practical and comparative simulations are performed to verify the efficiency of the proposed technique. • This work firstly tries to use the hidden Markov model, in order for the settlement of the asynchronous FD filter design problem for MJSs. • The designed FD filter has taken the sensor saturation into account, thus making the proposed filte have widespread application. • In addition, the proposed method can be directly applied to MJSs, of which the modes are known. [ABSTRACT FROM AUTHOR]

Safety, availability and reliability are the main concern of many industries. Thus, fault detection and isolation of industrial machines, which are in most cases switched systems, is a primary task in many companies. The presented paper proposes a new diagnostic approach for switched systems using two powerful tools: bond graph and observer. A diagnostic layer detects model errors using bond graph, and a smart algorithm identifies and locates faults using observer. Although observers serve as fault detectors, they also have their own errors caused by convergence delay of calculations; even in the case of no sensor defect, the residue does not converge to zero. In this paper, we propose a new method to solve this problem by integrating dynamic thresholds in the detection procedure, which helped to avoid false alarms and ensure a highly reliable diagnosis. [ABSTRACT FROM AUTHOR]

Based on binocular stereo vision measurement and wireless sensing theory, this paper studies the measurement and analysis methods of athletes' movement displacement parameters. The main purpose is to explore the relationship between sports biomechanical parameters. The analysis reveals the laws of athletes 'movements, and provides theoretical guidance on athletes' attitude recognition and physical training. Based on the principle of binocular stereo vision, a non-contact displacement measurement system was developed. The displacement measurement system uses template matching to extract the image coordinates of the measurement points and restore the spatial coordinates of the measurement points through European 3D reconstruction, which improves the practicality of the measurement system. In the cantilever beam vibration test, the traditional displacement sensor and binocular image displacement measurement system are used to simultaneously measure the cantilever beam displacement. The experimental results show that the integrated displacement measurement system in this paper has higher accuracy and better stability. [ABSTRACT FROM AUTHOR]

Multivariate Time series data forecasting (MTSF) is the assignment of forecasting future estimates of a particular series employing historic data. Lately, this work has enticed the focus of machine and deep learning researchers to tackle the complex and time consuming aspects of conventional forecasting techniques. Along with increasing access to historic documented data and the dire need of carrying out precise time-series feature forecasting. In this paper, we put forward a deep-learning(DL) technique proficient to tackle the setback of conventional forecasting techniques and display precise forecasting. The proposed technique is a Stacked Bidirectional long-short term memory architecture, which is an improvised version of existing Bidirectional LSTM in which multiple Bidirectional LSTM blocks are stacked, such that each layer contains multiple cells. In the direction of fair assessment, the functioning of the proposed technique is compared with existing LSTMs. Using varied evaluation measures, the obtained results show that the proposed Deep Bidirectional long-short term memory model exceeds standard approaches. [ABSTRACT FROM AUTHOR]

Optimized PTP (Point to Point) Navigation by customized mobile agent constitutes extensive research domain in Machine Intelligence. Distinct Literature survey confirms the proposal of SLAM (Simultaneous Localization And Mapping) mediated sensor usage for visual data collection in a particular GPS (Global Positioning System) - denied indoor environment. This has been further followed by fused data collection using multi sensor for obtaining long time and high precision localization and obstacle detection in MRN (Mobile Robot Navigation). This paper proposes an idea to incorporate machine learning module for data modeling so that the obstacle detection and identification results in relatively more precise, accurate and efficient. The comparative numerical analysis has been presented to establish the proposed methodology. Along with this, Fusion SLAM algorithm has been created and proposed which combines features of both 2D LiDAR (Light Detection And Ranging) and RGB-D (Red, Green, Blue Depth) SLAM, resulting in visual reference of combined detected periphery and reconstructed 3D depth of on-path obstacles. The aforesaid procedure is further extended with integration of Bio Intelligent path planning approach. Experimental analysis carried out with sample candidate functions with respect to concerned mobile robot and considered indoor environment has been presented which would prove to be important citation for further research in the domain of collision-free optimum MRN. [ABSTRACT FROM AUTHOR]

Digital twins are able to bridge the physical and the virtual world, which is especially useful in industrial environments. One small, but rather essential, kind of digital twin is the so called virtual sensor model. This type of model is used to enhance or replace a physical sensor in industrial settings to reduce costs or enable information retrieval from inaccessible locations within a machine or process. The virtual sensor model is usually trained once, whereat only a predefined amount of information without any adaptation possibilities on the clients side is provided. As manufacturers want to provide the possibility of custom adaptations for their clients, the virtual sensor models require to incorporate adaptive features, which also have to handle incomplete data recordings, e.g. uncensored data. Traditional offline machine learning approaches are often insufficient for such adaptive requirements, therefore the usage of online learning approaches is gaining increased attention, to avoid high computational, storage and temporal costs. This paper covers the continued training of such adaptive virtual sensor models, focusing on the handling and integration of censored online data. Different approaches to tackle the problems of catastrophic forgetting in online learning and correction of censored data are presented as well as the handling of censored data in online learning environments. The experiments sections compares various scenarios with and without censored data using an industrial dataset and demonstrates the positive influence of different online learning approaches. [ABSTRACT FROM AUTHOR]

The quality of printed electronic sensors by aerosol jet printing (AJP) process is hard to guarantee due to an insufficient reproducibility of the AJP process. This paper proposes a novel quality inspection method to identify defects on the printed sensor by AJP process using infrared imaging and machine learning. Potentially defective regions with high temperature distributions on printed lines are estimated from the infrared imaging when the current is applied. Demanded regions for the repair are identified by a machine learning algorithm. Finally, the applicability of the proposed method has been demonstrated by repair experiments. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Harbin Institute of Technology. Social Sciences Edition / Haerbin Gongye Daxue Xuebao. Shehui Kexue Ban is the property of Harbin Institute of Technology 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.)

Pose estimation of the sensor is important issue in many applications such as robotics, navigation, tracking, and Augmented Reality. This paper proposes visual-inertial integration system appropriate for dynamically moving condition of the sensor. The orientation estimated from Inertial Measurement Unit (IMU) sensor is used to calculate the essential matrix based on the intrinsic parameters of the camera. Using the epipolar geometry, the outliers of the feature point matching are eliminated in the image sequences. The pose of the sensor can be obtained from the feature point matching. The use of IMU sensor can help initially eliminate erroneous point matches in the image of dynamic scene. After the outliers are removed from the feature points, these selected feature points matching relations are used to calculate the precise fundamental matrix. Finally, with the feature point matching relation, the pose of the sensor is estimated. The proposed procedure was implemented and tested, comparing with the existing methods. Experimental results have shown the effectiveness of the technique proposed in this paper. [ABSTRACT FROM AUTHOR]

Agility is the ability of a person to change direction quickly. Measuring the basic and sport-specific physical abilities of athletes is important in sport and recreation. To assess agility, various tests are regularly included in physical abilities test batteries. This paper presents a state-of-the-art approach to measuring human movement in agility tests using infrared optical gates and kinematic sensors. The combination of precise time measurement, position detection and motion measurement enables the acquisition of previously inaccessible kinematic and spatiotemporal variables. This makes the assessment of agility more accurate and provides the athletes and coaches with additional information. With the system presented in this paper, the assessment of the athletes' agility can be recorded more objectively and with greater accuracy than would be possible with conventional equipment and methods. The athletes' performance is assessed with a combination of different sensors, all of which are synchronized with our sensor-based system. This combination provides the athletes with new information about their movement, which is not possible with traditional professional timing devices used to measure time in agility tests. The presented sensor system can be used in various sports and test types, including the frequently used T-test. We present summarized results from a pilot study conducted in cooperation with the Slovenian youth volleyball team. [ABSTRACT FROM AUTHOR]

Negative selection algorithms play an important role in anomaly detection. Interface detectors are a special negative selection algorithm that completely eliminates outer holes, but there are detection blind areas. This paper proposes a negative selection algorithm with hypercube interface detectors for anomaly detection. It uses self-sample clusters to construct self-space, and boundary self-sample clusters to describe the interface detectors. It eliminates the detection blind area and improves the detection rate. To validate the performance of the proposed method, experiments were conducted using the iris dataset, the skin segmentation dataset, the Breast Cancer of Wisconsin (BCW) dataset, and the Waveform Database Generator (Version 2) dataset. Experimental results show that the proposed method in this paper has a higher detection rate, lower false alarm rate, and fewer detectors than other anomaly detection methods for the same parameters. • HI-detector breaks away from the hyperspherical detector used by traditional negative selection algorithms. • HI-detector consists of a cluster of multiple hypercube self-samples. • HI-detector completely eliminates duplicate coverage of holes and detectors. • HI-detector has only one parameter that needs to be set. [ABSTRACT FROM AUTHOR]