This poster presents a novel system for inventory automation in large outdoor warehouses using a lightweight drone-mounted UHF RFID reader. The system leverages autonomous aerial platforms equipped with custom-developed RFID readers operating in the 865–868 MHz band, combined with intelligent software modules for tag readability evaluation. The proposed solution addresses major limitations of traditional stationary or handheld readers by enabling efficient scanning from a distance, including hard-to-reach areas. Two prototypes of RFID readers were developed, tested and optimized for use on commercial drones, and validated in real-world environments in both Czech and Korean warehouse facilities. The results confirm the reader’s ability to reliably detect tags at distances up to 28 meters and demonstrate its applicability for regular inventory processes. In addition to the hardware, two supporting methodologies and a software tool were developed for integration into existing information systems. The project was carried out within an international research consortium, where the Korean partners focused on AI-based image processing for drone navigation and risk avoidance. The presented solution contributes to the development of autonomous inventory systems, improves safety, and significantly reduces human effort and inventory time in logistics operations.

This poster presents the Smart_Safe system, a modular platform for real-time safety management in indoor industrial environments. The system integrates wearable sensors, Auto-ID technologies (such as RFID and Bluetooth), and AI-based analytics to detect, evaluate, and prevent occupational safety risks. Its core functionality includes real-time tracking of workers, detection of critical events (such as falls or zone violations), and prevention of collisions between people and mobile robots or forklifts. The system is designed to be scalable, interoperable with existing infrastructure, and privacy-respecting through the use of anonymized tracking and local processing. Integration with edge computing and digital twins enables context-aware decision-making and dynamic response to incidents. Smart_Safe supports applications in warehouses, smart factories, and production halls with a focus on high-risk or high-traffic areas. Initial testing demonstrates the feasibility of using hybrid sensor networks and lightweight AI models to ensure workplace safety and optimize movement flows. The poster also outlines the international collaboration between Czech and Korean partners, highlighting the hardware-software co-design process and the future roadmap for deployment.

This article presents an efficient burst mode control algorithm (BMCA) designed to reduce the turn-onswitch current spike in the power control of a single-ended induction heater (SE-IH). Modern SE-IH uses two control modes: square wave control at heavy loads and burst mode control at light loads to effectively control power flow to the induction heating load. First, the former achieves soft switching, i.e., zero voltage switching, at higher load conditions by properly controlling the switching frequency or duty ratio. Second, the latter often encounters inefficiencies and potential hazards due to current spikes at the switch turn-oninstant, caused by the sudden discharge of the dc-link capacitor through the resonant capacitor at lower load conditions. These current spikes result in significant power loss and thermal stress, which can ultimately cause the power switch to burn out. This article proposes a novel BMCA that optimizes burst mode operation to significantly reduce current spikes and enhance system reliability and overall power efficiency. The proposed algorithm, thoroughly tested, demonstrates superior performance compared to conventional commercial SE-IHs. Experimental results from a 2.6 kW SE-IH prototype using a TMS320F28377D control board validate the proposed solution’s efficacy under various load conditions.

Fuel cell electric vehicles (FCEVs) offer a promising solution for environment-friendly and sustainable future transportation, thanks to their remarkable features (e.g., zero-carbon emission, high-power capacity, long driving range, etc.). This article extensively reviews all power electronic systems in FCEVs with special emphasis on current implementation status, recent breakthroughs, existing industrial practices, challenges, and prospects. Different from conventional studies, this article provides a more comprehensive, systematic, and organized review of all FCEV systems that can be categorized into three systems: first, fuel cell systems, including fuel cell stack and its nonisolated high-voltage (HV) dc/dc power converter; second, power backup systems, including HV battery and ultracapacitor along with their bidirectional dc/dc power converter and energy management system; and finally, driving systems, including dc/ac inverter, traction motor, regenerative braking system, and low-voltage dc/dc power converter. Finally, future challenging issues, development trends, and prospects are comprehensively discussed.

This article proposes an improved duty control-based resonant bidirectional dc–dc converter (BDC) to remarkably minimize input-current ripple for battery energy storage systems. The proposed converter offers a resonant-boost operation using a pulsewidth-modulation (PWM) full-bridge circuit with a push-pull transformer under the forward mode. Whereas, in the backward mode, a resonant-buck operation is implemented with a PWM neutral-point-clamped (NPC)-type. Unlike conventional current-fed BDCs, the most appealing characteristic of the proposed converter is the NPC-type structure with a push-pull transformer, which can significantly mitigate the input-current ripple without using extra input-inductors. Moreover, the proposed BDC minimizes the conduction loss of the low-voltage side bottom switches by alleviating unbalanced dc offset-currents via proposed duty-compensation control under mismatched magnetizing inductances of the transformer's primary windings. The designed circuit operation is analyzed in detail and its practicability has been fully confirmed with the proportional-integral and spider-monkey-optimization control techniques-based experimental verifications using a prototype 1-kW test bed.

Inventory management is very important in any industry. In the past, people were directly involved in inventory management. However, this method is time consuming and requires a lot of labor. Therefore, in recent years, inventory management methods using drones are increasing. In this paper, we introduce an inventory management system using RFID and QR code, and a method of estimating the relative position of a drone based on the QR code, which is essential in the system. As a result of the experiment, when the center point of the QR code and the center point of the camera coincide, the error rate was very small, 0-1%. When the center points do not coincide, an error rate of up to 4% occurred.

This article presents an improved iterative learning direct torque control (IL-DTC) to remarkably minimize the torque ripples for a surface-mounted permanent magnet synchronous motor (SPMSM) drive. Unlike the conventional IL-DTC, the proposed IL-DTC significantly attenuates the torque ripples by effectively suppressing the repetitive disturbances using the speed and load torque compensating terms in the improved error dynamics via the improved feedback control terms and iterative learning control terms. Further, it has a simple structure and fast dynamic response due to the direct control of the torque and flux. The stability is verified through the convergence of speed errors to zero as the iteration index goes to infinity. The comparative results via MATLAB/Simulink and a prototype SPMSM test-bed with TI-TMS320F28335-DSP demonstrate the improved control performance (e.g., less torque ripples, faster transient response, smaller overshoot/undershoot, and smaller steady-state error) over the conventional IL-DTC under critical load/speed conditions with severe model parameter uncertainties.

Due to the continuously increasing demand on switched-mode power converters (i.e., dc-dc, dc-ac, ac-dc, and ac-ac) that can achieve high efficiency at high switching frequency, soft-switching techniques have received much attention in the area of power converter applications over recent years. This article provides a comprehensive review of the state-of-the-art soft-switching techniques used to achieve the zero-voltage switching and zero-current switching supplied by power switching devices. First, the auxiliary-circuit-based and nonauxiliary-circuit-based techniques that perform soft switching are systematically classified according to power converter. Next, soft-switching techniques for each power converter are comprehensively classified and reviewed in detail. Unlike the existing review papers that only categorize the soft-switching techniques used in dc choppers and inverters, this article offers further helpful categorization for all types of power converters. Further, it provides the merits, demerits, and suitable applications for each soft-switching technique. Finally, it suggests future research issues for soft-switching techniques in power converters.

This article investigates an observer-based optimal direct torque control (DTC) strategy for improving the transient and steady-state performance of surface-mounted permanent magnet synchronous motor (SPMSM) drives. Unlike conventional DTC techniques, the proposed method simultaneously controls speed, torque, and flux variables by employing the optimal control theory in the stationary reference frame. This helps achieving a simple structure along with good low-speed operation as the stator flux angle need not be estimated. Further, the feedforward control terms are designed to compensate for system uncertainties. Additionally, an in-depth stability analysis is presented through the Lyapunov theory. Comparative results via a real-time prototype SPMSM test-bed with TI-TMS320F28335 DSP indicate improved performance of the proposed optimal DTC compared to conventional PI DTC, nonlinear optimal DTC, and adaptive DTC, including less computational burden, less torque and flux ripples, more robustness to parameter uncertainty, and improved transient response under very low speed/load step-changes and speed reversal.

Abstract IBM Watson is one of the representative tools for speech recognition system which can automatically generate not only speech-to-text information but also speaker ID and timing information, which is called as Informatized Caption. However, if there is some noise in the voice signal to the IBM Watson API, the recognition performance is significantly decreased. It can be easily found in movies with background music and special sound effects. This paper aims to improve the inaccuracy problem of current Informatized Captions in noisy environments. In this paper, a method of modifying incorrectly recognized words and a method of enhancing timing accuracy while updating database in real time are suggested based on the original caption and Informatized Caption information. Experimental results shows that the proposed method can give 81.09% timing accuracy for the case of 10 representative animation, horror and action movies.

This paper presents a robust adaptive PI voltage controller (PIVC) that effectively eliminates the impact of disturbances and distorted model parameters for a three-phase constant voltage constant frequency (CVCF) inverter with an output LC filter. The proposed controller contains an adaptive control stage to enhance its tracking performance by compensating for distorted model parameters and a feedback control stage to stabilize the error dynamics to converge to zero. Unlike a conventional PIVC, the proposed adaptive method automatically updates its gains using the adaptive control stage. The stability of the proposed controller is proven by the Lyapunov stability theory. Even without information regarding the load current, the proposed adaptive PIVC achieves a fast dynamic response, small steady-state error, and low total harmonic distortion under critical load conditions. Experimental results demonstrate the efficacy of the proposed control method on a prototype three-phase CVCF inverter using a TI TMS320F28335 DSP.

Permanent magnet synchronous motor (PMSM) drive has emerged as one of the most preferred motor drives for industrial applications owing to its distinguished advantages, such as high torque density, high efficiency, and wide speed range operation. However, accurately updated knowledge about the PMSM parameters is crucial to designing a high-performance trajectory tracking controller. This article presents a state-of-the-art comprehensive review and up-to-date progress of the offline and online parameter estimation techniques of the PMSM drives. First, the problems associated with parameter estimation of the PMSM are systematically summarized to identify the parameters having fast and accurate convergence. Second, the offline parameter estimation techniques are categorized based on the frequency and time responses. Third, the recent advances and developments of the online parameter estimation techniques for PMSMs are assessed. Finally, there is a discussion of extensive industrial applications and future research trends for the parameter estimation techniques.

This paper proposes a variable structure speed controller (VSSC) that guarantees the robust transient performance against the external disturbances and parameter uncertainties of an interior permanent magnet synchronous motor (IPMSM) drive. Unlike the conventional VSSC applied to the IPMSMs, the proposed nonlinear compensating control term not only assures the robustness against the system uncertainties, but also implements the maximum torque per ampere technique. Furthermore, the convergence and stability of the proposed VSSC are fully proven through the Lyapunov theory by introducing reasonable bounded uncertainties which determine a feasible range for the system dynamics. The effectiveness of the proposed scheme is investigated through the simulation using MATLAB/Simulink and experiment using a prototype IPMSM drive system with a TI TMS320F28335 DSP. Finally, the proposed VSSC can ensure faster and more robust transient response than the conventional proportional-integral speed controller under the dynamic load conditions including the uncertainties.

This paper investigates a high-performance finite-set model predictive control (FS-MPC) based on an optimal switching voltage vector technique for voltage-source inverter (VSI)-fed interior permanent magnet synchronous motor (IPMSM) drives. The proposed algorithm clamps one switch that supplies the largest phase current at each sampling interval while allowing the other two pole switches to remain active. Unlike the conventional FS-MPC scheme, the proposed scheme involves only two voltage vectors to obtain an optimal switching state with reduced switching losses and low computational cost without incorporating any additional parameters or constraints in the cost function. Thus, the proposed FS-MPC implemented on a DSP-based prototype exhibits high performance features (low switching losses and low harmonic distortion above rated speed) in constant torque and power regions. The experimental results on prototype VSI-fed IPMSM with TMS320F28335 are presented under various conditions to demonstrate the efficacy of the proposed scheme compared with the conventional FS-MPC.

Electromyogram (EMG) signal-based gait phase recognition for walking-assist devices warrants much attention in human-centered system design as it well exemplifies human-in-the-loop control where the system's prediction directly affects subsequent walking motion. Since walking motion poses considerable variations in electrode placement, performance reliability of such systems is contingent on a combination of electrode montage and a feature extraction method that takes into account underlying physiological factors of peripheral muscles where electrodes are placed. In many practical applications, however, proper consideration of effects of the electrode location variation on performance reliability of the system has received scant empirical attention. Here, based on a user-centered design principle, we establish a gait phase recognition system that is capable of rigidly controlling ill effects due to this covariate by carrying out a large-scale analysis that combines statistical, model-based, and empirical approaches. In doing so, we have developed a special sensing suit for the control of electrode placement and a reliable data acquisition. We then have conducted a nonparametric statistical analysis on class separability values of thirty types of EMG feature sets, followed by a model-based analysis to address the tradeoff between class separability and dimensionality. To further address the issue of how these results generalize to independent systems and data sets, we have carried out an empirical performance assessment over six classification methods. First, the two feature types, Integral of Absolute Value and Histogram, and a combination of the two are shown to be robust against electrode location variations while providing a firm performance guarantee. Second, system organization scenarios are presented on a case-by-case basis, allowing us to trade off system complexity for on-line adaptation capability. Collectively, our integrated analysis lends itself to formulating a guideline for design of highly reliable EMG signal-based walking assistant systems in a variety of smart home scenarios.

Abstract Robust statistical methods are employed to reduce the noise in Monte Carlo ray tracing. Through the use of resampling, the sample mean distribution is determined for each pixel. Because this distribution is uni‐modal and normal for a large sample size, robust estimates converge to the true mean of the pixel values. Compared to existing methods, less additional storage is required at each pixel because the sample mean distribution can be distilled down to a compact size, and fewer computations are necessary because the robust estimation process is sampling independent and needs a small input size to compute pixel values. The robust statistical pixel estimators are not only resistant to impulse noise, but they also remove general noise from fat‐tailed distributions. A substantial speedup in rendering can therefore be achieved by reducing the number of samples required for a desired image quality. The effectiveness of the proposed approach is demonstrated for path tracing simulations.

This paper investigates a disturbance observer-based fuzzy adaptive voltage controller for three-phase pulse width modulation (PWM) inverter of a standalone distributed generation (DG) unit in the existence of system uncertainties. The proposed control law includes only a voltage control loop, which has advantages such as a simple control structure and a fast transient response due to the direct control of the output voltage. Next, a disturbance observer is presented to reduce the number of the sensors and improve the control performance. Besides, the proposed strategy is insensitive to any system uncertainties, because it does not require any accurate knowledge about system parameter and load current information. Experimental results on a prototype DG unit with a TMS320F28335 DSP are demonstrated to validate the superior performance of the proposed control scheme over the conventional proportional-derivative (PD) control method and feedback linearization control (FLC) method under sudden load disturbances, system uncertainties, and nonlinear load.

Theoretically optimal performance and behavior of a routing protocol are very important because they can be used to guide the design of practical protocols. Motivated by the promising lifetime performance of an existing online cooperative transmission (CT) routing protocol for wireless sensor networks (WSNs), we formulate the lifetime optimization problem of cooperative routing using linear programming (LP), which requires considerations of CT's unique characteristics and sophisticated variable definitions. By using our LP, one can obtain the optimal lifetime of multi-hop WSNs that use cooperative routing, which can serve as a performance bound or a benchmark to compare to the lifetimes of existing routing protocols. Through the evaluations of our LP, we show the benefit of cooperative routing and usefulness of our LP formulation.

Theoretically optimal performance and behavior of a routing protocol are very important because they can be used to guide the design of practical protocols. Motivated by the promising lifetime performance of an existing suboptimal cooperative transmission (CT) routing protocol for wireless sensor networks, we formulate the lifetime-optimization problem using linear programming (LP), which requires considerations of CT's unique characteristics and sophisticated variable definitions. By evaluating LP for various cases, we show the effectiveness of cooperative routing by comparing it with the non-CT case. Also, by analyzing the LP solution, we identify some important factors and behaviors of optimal cooperative routing. More specifically, we conclude that (i) matching the rate of doing CT and matching the candidate pools of cooperators to the LP solution are important factors to achieve near-optimal lifetime performances, and, (ii) for small multi-hop networks, the design of cooperative routing can be simplified because one may use the sink node as a single VMISO receiver and rely on the existing energy-aware routing for the primary routing.

The fast segmentation of the liver in the CT images is the important but difficult procedure for subsequent image processing and analysis. We applied the pseudocolorization and connected component labeling methods to segment the upper dome area of the liver in the transverse CT slice images. Arterial phase transverse CT slice images including the upper dome area of the liver was used for segmentation by the methods. The original transverse slice CT images were pseudocolorized and the color component images including the liver were separated. And the connected component labeling algorithm was performed and the upper dome area of the liver was segmented. The segmentation of the remaining portion of the liver in the neighboring CT slice images can be done effectively with active contouring or region growing with interslice reference to the previously segmented liver CT image.

In this paper, we describe the "soft remote control system" that provides easy control of home installed appliances to improve the inhabitant's comfort. This system is feasible to control various home appliances naturally by recognizing the user's hand gestures in the "intelligent sweet home". The user selects the device that he/her wants to control by pointing it with his/her hand. Then, the user can command operation of the desired function via a predefined hand gesture. The approach complements the inconvenience of the conventional remote controllers giving additional freedom to persons with movement deficits and people without disabilities.

This paper deals with a method to recognize hand-postures in Softremocon system. The system uses multiple cameras to recognize the user's hand-posture. It is hard to recognize hand-posture since a human-hand is the object with high degree of freedom and there follows the self-occlusion problem, the well-known problem in vision-based recognition area. It can be a possible solution to use multiple cameras. However, when we use multiple images, another problem is arisen, that is, the composition methods of multiple recognition results from each camera to get the final decision. We show 2-staged recognition process. The first stage gets the results which represent each camera viewpoint. And the second one results out the final decision. This structure gives robustness to the hand-posture recognition against view-point variation.

The hand-posture-based user interface has been considered as an alternative to human-computer interaction (HCI), or for human-robot interaction, but many difficulties remain to be resolved. For natural recognition of hand posture by a vision device, we find that view-point-in variance is one of the most required characteristics. This paper presents a hand-posture recognition method that is robust against various viewpoints. Observing that when the viewing direction is changed, the same appearance feature does not necessarily match the 3D structure, and vice versa, we propose a 2-layered hand-posture database structure in which the 2D appearance-based method and the 3D-based method are complementarity combined. We have tested the approach in an experiment for 15 different viewing directions.

Many diverse methods have been developed in the field of biometric identification as a greater emphasis is placed on human friendliness in the area of intelligent systems. One emerging method is the use of footprint shape. However, in previous research, there were some limitations resulting from the spatial resolution of sensors. One possible method to overcome this limitation is through the use of additional and independent information such as gait information during walking. In this study, we suggest a new person-recognition scheme based on the center of pressure (COP) trajectory in the dynamic footprint. To make an efficient and automated footprint-based person recognition method using the COP trajectory, we use a hidden Markov model and a neural network. Finally, we demonstrate the usefulness of the suggested method, obtaining an approximately 80% recognition rate using only the COP trajectory in our experiment with 11 people. © 2004 Wiley Periodicals, Inc. Int J Int Syst 19: 1127–1141, 2004.

In this paper we present results, which have obtained by extensive simulations for mobile IP and session initiation protocol from the perspective of VoIP service in wireless Internet access. After illustrating the problem in these two protocols for diverse cases of mobility management, we propose an integrated model, to reduce the handover latency and packet loss during handover. This combination of network and application layer mobility management model reduces disruption time during handovers and provides fast handoff for ongoing conversations. Simulation results presented in this paper are based on the ns2 mobility software. However, since the current version of ns2 does not include SIP model for VoIP service, we add a suite of new features and procedures that are specific to this paper. The simulations results show that our proposed mechanisms achieve better performance than other protocols.