Efficient Control Research Articles

A deep learning approach to detect diseases in pomegranate fruits via hybrid optimal attention capsule network

In 2022, the production rate of pomegranate is estimated at approximately 4.8 million metric tons. Unfortunately, these fruits are susceptible to many different kinds of diseases caused by bacterial, viral, and fungal infections. Such diseases can have a major negative impact on fruit quality, production, and the profitability of pomegranate cultivation. Nowadays, several machine learning and deep learning methods are used to identify pomegranate fruit diseases automatically and effectively. In post-harvest pomegranate fruit disease detection, deep learning has great potential to extract complex patterns and features from large datasets. This can improve disease identification accuracy, enabling more efficient disease control, lower crop losses, and better resource management. The proposed work introduces an intelligent deep learning-based approach for accurately detecting pomegranate diseases, begins with Improved Guided Image Filtering (Improved GIF) and resizing to pre-process fruit images, followed by feature extraction (shape, color, texture) using GLCM and GLRLM to streamline classification. Extracted features are then fed into a novel Hybrid Optimal Attention Capsule Network (Hybrid OACapsNet), which classifies the images as normal or diseased, conditions such as bacterial blight, heart rot, and scab. Our analysis indicates that the proposed classifier has a classification accuracy of 99.19 %, precision of 98.45 %, recall of 98.41 %, F1-score of 98.43 %, and specificity of 99.45 % compared to other techniques. So this approach offers a, which is a feasible solution for automated detection of diseases in fruits, thereby benefiting farmers and supporting their farming operations.

Design and Performance Analysis of A Linear Switched Reluctance Motor Considering End Effects

Introduction: In recent years, linear actuators have gained significant attention due to their ability to provide direct linear movement without the need for motion transformation devices. One significant challenge in the design and modeling of linear actuators is the occurrence of longitudinal end-effects. The finite length of the translator stack in linear actuators causes an unbalanced phase force, leading to discrepancies between the phases at the end and center of the actuator. Neglecting these end-effects can lead to inaccuracies in the actuator's performance and control. Methods: The objective of this study is to develop a comprehensive approach for the design, sizing, and modeling of the actuator to ensure optimal performance. An energy conversion procedure calculates the thrust force and determines the actuator's geometrical parameters. A numerical model based on the finite element method is developed to analyze the actuator's magnetic behavior and establish its characteristics. Furthermore, a thorough analysis of the end effect is conducted using two-dimensional finite element analysis. Results: To accurately capture the actuator's dynamic response and enable precise control, a mathematical model is formulated, incorporating the nonlinear behavior of inductance and incorporating the end effect factor. The proposed model demonstrates high accuracy and provides a solid foundation for the control of the linear switched reluctance actuator. Conclusion: Overall, this study contributes to the advancement of direct drive systems for industrial applications by providing a detailed design procedure and an accurate modeling approach for the linear actuator, enabling more efficient and precise control strategies.

Aerodynamic investigation of an S-shaped intake employing sweeping jet actuators based on proper orthogonal decomposition

The central curvature change of the S-shaped intake exacerbates the three-dimensional flow separation, resulting in total pressure and swirl distortions at the outlet. In this paper, an efficient active flow control technique, the sweeping jet actuator, was applied to control flow separation. The instantaneous characteristics of the flow field inside and outside the actuator were revealed by using validated numerical simulation methods. In addition, the effect of the sweeping jet on the aerodynamic performance of the S-shaped intake was investigated. Proper orthogonal decomposition (POD), an analysis method used to extract the main feature components of data, was applied to decompose the flow field structure at the S-shaped intake outlet in this study. The results highlight the external flow field characteristics of the actuator, with a jet sweeping range of up to ±40° and a sweeping frequency of 1 500 Hz, corresponding to a Strouhal number of 0.018. When the jet momentum coefficient is only 0.116%, the total pressure loss coefficient and pressure distortion index are reduced by 5.6% and 24.76%, respectively. This study demonstrates the critical role of momentum injection and discretization in inhibiting flow separation in the channel. The POD-based analysis indicates that a sweeping jet with high momentum can significantly enhance the energy in the flow passage and reduce the vorticity intensity of the first three modes. The stable mode structures exist near the outlet, exhibiting excitation frequency and frequency-doubling properties. The findings of this research provide essential input conditions for subsequent distortion studies.

Cost-Effectiveness Analysis of Nearly Zero-Carbon Office Buildings in Taiwan

The formulation of an affordable and economically-feasible policy for nearly zero-carbon building design is a challenge that countries encounter in promoting net-zero building. In 2022, Taiwan promulgated Building Energy Rating System (BERS), the world's first building energy efficiency assessment system tailored for subtropical climates, as a basis for evaluating its goal of achieving nearly zero-carbon buildings by 2050. However, whether this nearly zero-carbon building policy is financially feasible has remained unknown to the government and the industry. To address the issue, the objective of the paper is to conduct a cost-benefit and payback period analysis of newly constructed nearly zero-carbon office buildings in accordance with the Building Energy-efficiency Rating System for New Buildings (BERSn) assessment framework, and thereby examines the financial affordability and feasibility of Taiwan's net-zero building policies.Firstly, this study introduces existing building energy performance evaluation methods in Europe, America, and Japan, and explains the methodology of Taiwan's Building Energy Rating System (BERS). The paper then reviews international Cost-Benefit Analyses of Nearly Zero Energy Office Buildings and parallelly conducts a Cost-Benefit Analysis of Nearly Zero-Carbon Office Buildings in Taiwan. Following the BERS methodology, this paper identifies the baseline efficiency level and the Nearly Zero-Carbon Building (NZCB) efficiency level, along with their associated solutions and investment costs, for air conditioning and lighting systems. In this study, a questionnaire survey of 28 experts identifies the air conditioning unit costs of Basic Mechanical Equipment Efficiency (BME) and energy-saving control technologies (R) for energy-efficient design of Fan Coil Unit (FCU), Air Handling Unit (AHU), and Variable Refrigerant Flow (VRF) system. Accordingly, 33 air conditioning design solutions and their corresponding construction costs complying with the BERSn requirements of EAC≦0.5 for nearly-zero carbon office buildings are identified. Regarding the nearly zero-carbon lighting design, the simulations reveal that the use of LED panel luminaires or T8 LED luminaires (including those with energy-saving labels) can achieve an average operational lighting illuminance of 500 LUX and the BERSn requirements of EL ≤ 0.5 for lighting. Finally, the study further analyzes the payback period and premium cost ratio of NZCB by employing the budget data of seven building projects. The analysis shows that the premium cost ratio and the payback period of NZCB range from 1.33%-1.50% and 6.4-7.7 years, respectively. The results demonstrate that while a higher budget is commonly associated with NZCB by the public, it is in fact economically and technologically feasible to realize NZCB with prevailing energy-efficient measures.

Microchannels-enabled Vertical Alignment of Hexagonal Boron Nitride in Silicone Rubber Composites to Achieve High Through-plane Thermal Conductivity

Hexagonal boron nitride (h-BN) with high vertical alignment in polymer composites is necessary to improve through-plane thermal conductivity (TC) for thermal management applications. However, how to achieve simple, efficient and precise control of h-BN vertical alignment in polymer composites remains a challenge. Herein, a novel concept of inducing vertical alignment of h-BN in silicone rubber (SR) composites via controlling flow patterns in specially designed microchannels was proposed. The extremely strong elongational and shear stresses provided by the narrow section of the microchannels induced h-BN to align perpendicular to the flow direction. In the subsequent channel, the weak shear stress manipulated h-BN to form a ladder structure in the SR composites, including the vertical core layer and horizontal skin layer. Such ladder structure not only improved the through-plane TC of SR composite but also prevented overheating in the face of local heat sources. Moreover, the obtained SR composites exhibit a through-plane TC of 5.08 W/mK at 34.3 vol % h-BN loading when the horizontal skin layer was removed, indicating excellent heat transfer efficiency for thermal management application. We believe that this work would strengthen both scientific and technological cognition of the filler alignment during polymer composites processing.

Hygrothermal performance of hybrid multi-storey buildings under future climate scenarios

Climate change, energy efficiency, and carbon footprint objectives pose significant challenges to the hygrothermal performance of building structures in climates with extreme temperature variations. To meet long term sustainability targets, buildings designed for a lifespan of up to 100 years must exhibit resilience not only to current climate conditions but also to projected future scenarios. This study evaluated the hygrothermal performance of a hybrid log-concrete multi-storey building, combining the structural strength of concrete with the sustainable, moisture-regulating properties of wood, to address energy efficiency and moisture control challenges in subarctic climates. Onsite measurements were validated using numerical simulations to assess hygrothermal performance of log wall structure under climate change scenarios. Results showed minimal mould growth risk under present conditions, while future climate projections (RCP8.5 for 2080) indicated a maximum mould index of 1.32 near the exterior log surface. These findings highlight the resilience of log-based structures in cold climates and underscore the need for proactive moisture management under warmer, more humid future scenarios. Stable ideal indoor temperatures (averaging 21.56 °C to 22.09 °C) and effective moisture control (with a maximum average moisture excess of 0.89 g/m3) over the measurement period further demonstrate the suitability of hybrid log-concrete buildings for energy-efficient, moisture-regulating construction in cold climates. The study recommends surface treatments that allow vapour diffusion while preserving wood’s hygroscopic qualities to enhance durability in changing climates.

Mechanistic Model Advancements for Optimal Calcium Removal in Water Treatment: Integral Operation Improvements and Reactor Design Strategies

Drinking water softening has primarily prioritized public health, environmental benefits, social costs and enhanced client comfort. Annually, over 35 Gm3 of water is softened worldwide, often utilizing three main techniques: nanofiltration, ion exchange and seeded crystallization by pellet softening. However, recent modifications in pellet softening, including changes in seeding materials and acid conditioning used post-softening, have not fully achieved desired flexibility and optimization. This highlights the need of an integral approach, as drinking water softening is just one step in the drinking water treatment chain, which includes ozonation, softening, biological active carbon filtration (BACF) and sand filtration among others. In addition, pellet softening is often practiced based on operator knowledge, lacking practical key reactor performance indicators (KPIs) for efficient control. For that reason, we propose a newly and improved integral mechanistic model designed to accurately predict (1) calcite removal rates in drinking water through seeded crystallization in pellet softening reactors, (2) the saturation of the filter bed in the subsequent treatment step, (3) values for the KPIs steering the softening efficiency. Our new mechanistic model integrates insights from hydrodynamics, thermodynamics, mass transfer kinetics, nucleation and reactor engineering, focussing on critical variables such as temperature, linear velocity, pellet particle size and saturation index with respect to calcite. Our model was validated with data from the Waternet Weesperkarspel drinking water treatment plant in Amsterdam, The Netherlands, but implies universal applicability for addressing industrial challenges beyond drinking water softening. The implementation of our model proposes five effective KPIs to optimize the softening process, chemical usage, and reactor design. The advantage of this model is that it eliminates the application of numerical methods and fills a significant gap in the field by providing predictions of the carry-over (i.e., the produced CaCO3 fines leaving the fluidized bed) from water softening practices. With our model, the calcium removal rate is predicted with an average standard deviation (SD) of 40% and the consequential clogging prediction of the BACF bed with an average SD of 130%. Ultimately, our model provides crucial insights for operational management and decision-making in drinking water treatment plants, steering towards a more circular and environmentally sustainable process.

The multi-objective economic statistical design of the p-chart: NSGA II approach

A control chart is a crucially important tool in statistical process control that is essentially used to differentiate between assignable and chance causes of variation. With the advent of Six Sigma in the parlance of quality management, the control chart assumes more significance to hold the gain in the control phase after attaining process improvement in the improve phase. The sample size, sampling interval, and control limits’ multiplier are three important parameters required to design an effective as well as efficient control chart. Many approaches like economic design, statistical design, and economic statistical design of control charts have been studied by several researchers. All these approaches consider a single objective function. In this paper, we have proposed a multi-objective design of the p-chart, where we are minimizing both out-of-control Average Run Length ( ARL δ ) and the expected cost per cycle ( C E ). Non-dominated Sorting Genetic Algorithm II (NSGA II) is used to solve the proposed multi-objective model. The proposed approach is demonstrated with the help of two numerical examples and the corresponding results are found to be quite encouraging for minimizing both objectives in comparison to another pertinent model given in the literature. Sensitivity analysis has been carried out to give credence to the worth of the proposed approach.

Fixed-time adaptive sliding mode-based trajectory tracking control for Wheeled Mobile Robot: Theoretical development and real-time implementation

Wheeled mobile robots (WMR) are common autonomous systems requiring efficient control methods. This work investigates fixed-time adaptive sliding mode control (FxT-ASMC) for the trajectory tracking task of a WMR subject to disturbances/uncertainties. The developed control strategy seeks to avoid the chattering problem, cope with disturbances when the upper limit is undefined, and enhance the convergence of the system states. Indeed, a new adaptive technique has been developed to effectively handle disturbances, even in the absence of prior knowledge regarding their upper bound. This technique consists in estimating the switching gain for each channel separately. On the other hand, an appropriate design of the reaching law ensures the fixed-time convergence of the sliding variables to zero. Additionally, sliding variables are designed in a way that guarantees the tracking errors will stabilize within a set amount of time. This kind of convergence was demonstrated using Lypunov stability theory. In order to realize the trajectory tracking control structure, the FxT-ASMC system is incorporated with a classical kinematic controller. The efficiency of the suggested control methodology is proven via simulations and practical implementation.

Update on Fatty Liver in Dairy Cattle with Major Emphasis on Epidemiological Patterns, Pathophysiology in Relationship to Abdominal Adiposity, and Early Diagnosis

Fatty liver is a more common than expected metabolic disease affecting dairy cattle around parturition, which generates high economic losses for the dairy industry. The disease has evolved from a low incidence of moderate cases to a greater increase of severe cases in recent years. This evolution could be explained by the higher rate of genetic selection that has been carried out for milk production, which concomitantly brings pleiotropic genes that determine greater abdominal adiposity, ketosis, and other diseases. Abdominal fat is much more reactive, pro-inflammatory, saturated, and low in adiponectin than subcutaneous fat. In this review, we will mainly address the epidemiological aspects, the pathophysiology concerning the different types of fat depots (subcutaneous and abdominal), and the early diagnosis of the disease to carry out efficient control and preventive strategies.

The Simulation of Mode Control for a Photonic Lantern Adaptive Amplifier

A photonic lantern is a low-loss device that connects a single multimode waveguide to multiple single-mode waveguides and can enhance the beam quality of a fiber laser by adaptively controlling the optical parameters (amplitude, phase, polarization) at the input. In this work, we combined the gains and losses of individual modes within the fiber amplifier and introduced a mode content parameter at the amplifier’s output as an evaluation function to simulate mode control effects. Mode competition within the gain fiber can degrade the control effect of the fundamental mode and lead to it taking a longer time for the control to converge. Optimal parameters, such as the gain fiber length and pumping method, were identified to improve control effectiveness. Specifically, an optimal gain fiber length of 8 m was determined, and backward pumping was found to achieve higher pumping efficiency and better control results. The system demonstrated significant power amplification potential and could stabilize mode control under different pumping powers ranging from 50 W to 5 kW. In conclusion, our research demonstrates that an adaptive fiber amplifier based on a photonic lantern can achieve a stable, high-power, large-mode-field, near-fundamental-mode output from the gain fiber. Although mode competition within the gain fiber can degrade the control effect of the fundamental mode and cause the control to take a longer time to converge, these aspects should be further studied to improve the control’s effectiveness. These findings contribute to the development of advanced simulation models that guide high-power mode control experiments and deepen our understanding of physical processes in science and technology.

Smart Zone-Based Vehicle Speed Retarding System Utilizing Radio Frequency (RF) in Electronic Vehicles

The proposed system aims in designing an efficient automatic wireless vehicle speed control in low-speed zones using RF communication. The advent of new high-speed technology and the growing computer capacity provided realistic opportunity for new robot controls and realization of new methods of control theory. This technical improvement together with the need for high performance robots created faster, more accurate and more intelligent robots using new robots control devices, new drivers and advanced control algorithms. The proposed method uses RF transmitter and receiver modules for establishing wireless communication, DC motors for the vehicle movement controller. The status of the project will display on LCD display. The controlling device of the whole system is a Microcontroller to which RF receiver module, DC motors are interfaced through a motor driver. Whenever the vehicle enters into a low-speed zone, the data from RF transmitter of low-speed zone will be received by the vehicle system. The microcontroller in the vehicle system automatically slows down the speed to the speed limit of that zone. The microcontroller checks the data with the program embedded in it and performs appropriate actions on the electric motors. The microcontroller is programmed using Embedded C language.

Automation of agricultural machinery: Development and validation of a portable automation module for oil palm plantation machinery

The primary objective of this project is to create a portable automation module that should be suitable for various heavy machines in agriculture. To begin, the OREC Bull Mower machine was chosen as the initial pilot study. Five major machine components were identified through meticulous analysis, laying the groundwork for the automation process. Several functions, including gear shifting, clutch operation, and other critical tasks, were successfully automated. Extensive testing and measurements were performed to identify the best actuators for precise and efficient control. The actuators and controllers were thoughtfully integrated into the enclosure, resulting in a versatile automation module that can be programmed for remote or autonomous operation. Lab and on-site testing proved the module's efficacy in real-world scenarios, validating its successful implementation. While the project has produced promising results, future improvements are required, particularly in mechanical fitting, design for assembly, and the use of reliable electronic components.

Cloud migration and microservices optimization framework for large-scale enterprises

As large-scale enterprises increasingly adopt cloud computing, the need for a structured framework to guide seamless cloud migration and optimize microservices architecture becomes critical. This review presents a comprehensive designed to address the challenges and opportunities associated with transitioning to cloud environments and optimizing microservices for performance, scalability, and security. The review begins with an assessment of the enterprise’s current infrastructure, emphasizing a phased approach to cloud migration. It outlines key strategies such as lift-and-shift, re-platforming, and re-architecting, each tailored to specific organizational needs. The selection of the appropriate cloud model (public, private, or hybrid) and the use of multi-cloud strategies are discussed to ensure flexibility and risk mitigation during migration. For microservices optimization, focuses on designing services that are loosely coupled and highly scalable. Key elements include the use of service discovery, load balancing, API gateways, and database management strategies to improve the efficiency and reliability of microservices. Additionally, this introduces security best practices, including identity and access management (IAM), encryption protocols, and microservices-specific security measures such as Zero Trust Architecture. The review also highlights optimization strategies involving containerization (Docker) and orchestration (Kubernetes), alongside the integration of Continuous Integration/Continuous Delivery (CI/CD) pipelines for streamlined development and deployment. Performance monitoring, real-time logging, and proactive maintenance are emphasized for sustained efficiency and cost control in cloud environments. Case studies demonstrate the successful implementation of cloud migration and microservices optimization in large enterprises, showcasing both the benefits and common challenges. The review concludes by exploring future trends, such as serverless computing and AI-driven optimization, that will continue to shape cloud migration and microservices architecture.

Quaqc: efficient and quick ATAC-seq quality control and filtering.

"quaqc" allows for ATAC-seq-specific quality control and read filtering of NGS data with minimal processing time and extremely low memory overhead. An efficient scaling implementation allows for a wide range of use cases, from processing individual samples processed on personal laptops to handling thousands of samples processed in parallel on compute clusters. The helper R package "quaqcr" allows for interactive program execution and exploration of results. Source code and documentation are freely available for download from https://github.com/bjmt/quaqc and https://github.com/bjmt/quaqcr under the GPLv3 license. "quaqc" is implemented in C and has been tested on both macOS and Linux. The "quaqcr" helper package only requires the R programming language. Fixed versions of the programs and code associated with this manuscript can be found at https://zenodo.org/records/13833437.

Modern management model for KAREB Bojonegoro cooperative: Integration of ABM, lean six sigma, and RBV and TPB approaches

In global business competition, ABM helps cooperatives such as KAREB Bojonegoro Cooperative achieve cost efficiency without sacrificing quality. KAREB Cooperative's expenditure is very high, reaching IDR158.82 billion in five years, with the main costs on fuel, labor, and maintenance. Optimizing expenditure and cost management is important to reduce waste, increase efficiency, and profitability. Various studies have shown that Lean Six Sigma and ABM methods increase efficiency, reduce waste, and improve financial performance in various industries with proper implementation and intensive training. However, external factors, recent data, and regional variations, with deficiencies in data and methodology, and challenges in lean sigma implementation have not contributed simultaneously. This study offers the Integration of ABM, RBV, and TPB in Lean Sigma at KAREB Bojonegoro Cooperative because it is suspected that the condition of tobacco processing is not optimal and this approach needs to improve sustainable production efficiency. This study will analyze the implementation of ABM and Lean Sigma for cost control and waste reduction in tobacco drying at Kareb Cooperative with the contribution of Resource-Based View (RBV) and Theory of Planned Behavior (TPB) to improve process quality and optimal resource monitoring. This study uses a qualitative model with a case study method to assess the implementation of Activity-Based Management (ABM) in production cost efficiency, linking it with Lean Six Sigma, Resource-Based View (RBV), and Theory of Planned Behavior (TPB). Key informants from Kareb Cooperative Bojonegoro, including the Head of Production, Accounting, and HR, provided insights into the impact of ABM and internal factors on efficiency. The research instruments included in-depth interviews, observation, and documentation, while the research procedure followed a systematic flow to ensure the validity and relevance of the data. This study states that the implementation of ABM at Kareb Cooperative Bojonegoro allocates costs based on actual activities, improving efficiency and cost control. Costs include procurement of materials (Rp24,375,300,000), production (Rp9,216,862,000), and distribution (Rp6,000,000,000). Lean Sigma focuses on reducing waste such as overproduction, defects, and waiting by improving processes and training. The ability is quite large in identifying production inputs and related costs such as fuel (Rp14,375,300,000), raw materials (Rp10,000,000,000), and production and distribution processes. Waste management such as overproduction and waiting, as well as the implementation of ABM and Lean Sigma, aims to increase efficiency and reduce costs. Evaluation and training are carried out to optimize processes and reduce waste. Setting costs based on activities, while Lean Sigma uses the Just-In-Time (JIT) system. Variable costs are optimized, production is controlled to reduce defects,and distribution and storage are improved for cost efficiency. The keys to success are open communication, management support, and intensive training. The implementation of ABM and Lean Sigma in Kareb Bojonegoro Cooperative effectively reduces costs and waste through training, JIT, and process control. These findings are expected to increase productivity, reduce costs, and improve the competitiveness of cooperatives and provide a model for implementing modern management.

Pulse current stabilizer with digital control for the power supply system of the plasmatron

Purpose. Solution of theoretical and practical problems on providing digital control of a pulse converter using high-speed microprocessor tools in the output current stabilization mode with provision of a specified duration of transient processes caused by an increase in load voltage and output current astaticity, which allows to obtain significant advantages over analog versions. Methodology. Review of literary and patent sources on the subject, theory of pulse automatic control systems, mathematical modeling of processes in pulse current stabilizers in the MATLAB / Simulink software environment and physical prototyping. Findings. A simulation model of an autonomous power supply system based on a converter using soft switching technology of transistors and an arc load is presented. A control law is synthesized and a model of a pulse current stabilizer is developed. A method is proposed and ways are found to control a pulse current stabilizer that provide a given duration of transients and astatism of the output current. A model of a pulse stabilizer with digital control based on a single-crystal computing module is developed and manufactured. The results of the study confirm the achievement of a finite duration of transient processes caused by a step change in the load voltage, close to 3-4 periods of conversion and output current astaticism. It is shown that the use of a pulse stabilizer using a fully digital control circuit has undeniable advantages over analog systems. Originality. The problem of synthesizing a digital controller for a given control time by the method of desired transfer functions for a soft switching operating converter on an arc load is solved. In addition to the given control time, additional quality requirements in the steady state are provided. Practical value.The use of microprocessor technology makes it possible not only to implement complex and new highly efficient control algorithms for a converter operating in the pulse current stabilizer mode, but also to perform additional functions for overload protection, self-diagnostics and telemetry of pulse converters. The use of this same digital device simultaneously for the purpose of controlling a pulse converter will allow to abandon analog PWM controllers and thereby reduce its own energy consumption and weight and size characteristics, increase the reliability of the functioning of pulse converters in power supply systems as a whole.

Comparison of machine learning algorithms for dengue virus (DENV) classification

Dengue, transmitted by the Aedes aegypti mosquito, necessitates accurate case classification for effective management. The research focuses on leveraging machine learning algorithms to enhance diagnosis and streamline control strategies. Utilizing a dataset from a public hospital, encompassing 21,157 cases categorized by period, outcome, gender, age, symptoms, and origin (autochthonous or imported), the study conducted a comparative analysis of Support Vector Machine, Random Forest, and Artificial Neural Network algorithms. The dataset was divided into 70% (14,809 cases) for training and 30% (6,348 cases) for testing. Results unveiled the Artificial Neural Network as the frontrunner, exhibiting an impressive 86.47% accuracy and a robust 92.91% recall in the classification of dengue-related cases. This underscores the potential of machine learning in refining dengue diagnosis and facilitating more efficient control strategies, offering a promising avenue for combating this vector-borne disease.

Reconfigurable binary diffractive optical neural network based on chalcogenide phase change material Ge2Sb2Se4Te1

Diffractive optical neural networks (DONNs) possess unique advantages such as light-speed computing, low energy consumption, and parallel processing, which have obtained increasing attention in recent years. However, once conventional DONNs are fabricated, their function remains fixed, which greatly limits the applications of DONNs. Thus, we propose a reconfigurable DONN framework based on a repeatable and non-volatile phase change material Ge2Sb2Se4Te1(GSST). By utilizing phase modulation units made of GSST to form the network's neurons, we can flexibly switch the functions of the DONN. Meanwhile, we apply a binary training algorithm to train the DONN weights to binary values of 0 and π, which is beneficial for simplifying the design and fabrication of DONN while reducing errors during physical implementation. Furthermore, the reconfigurable binary DONN has been trained as a handwritten digit classifier and a fashion product classifier to validate the feasibility of the framework. This work provides an efficient and flexible control mechanism for reconfigurable DONNs, with potential applications in various complex tasks.

Electro-optically Modulated Nonlinear Metasurfaces.

Electrically reconfigurable nonlinear metasurfaces provide dynamic control over nonlinear phenomena such as second-harmonic generation (SHG), unlocking novel applications in signal processing, light switching, and sensing. Previous methods, like electric-field-induced SHG in plasmonic metasurfaces and Stark-tuned nonlinearities in quantum well metasurfaces, face limitations due to weak SHG responses from metals and mid-infrared constraints of quantum wells, respectively. Addressing the need for efficient SHG control in the visible and near-infrared ranges, we present a novel approach using the electro-optic (EO) effect to modulate SHG. By leveraging the exceptional EO and SHG properties of lithium niobate (LN), we integrate the EO effect with SHG within a metasurface framework for the first time. Our LN metasurface achieves an 11.3% modulation depth in SHG amplitude under a ±50 V alternating voltage. These results open new avenues for reconfigurable photonic applications. including tunable nonlinear light sources, quantum optics, and nonlinear information processing.