We propose a face synthesis approach to augment the training data of a face recognition model for performance improvement. Our approach consists of two major modules, the Source Face Generator (SFG) and the Style-Transfer Diffusion (STD) module. The SFG, composed of a prompt maker and a Multi-Modal Diffusion Transformer (DiT) model, aims to generate diversified and unique frontal faces, each tailored to a specific ethnicity, gender, age, and country group. The STD is designed to duplicate styles from a given set of reference faces onto the source faces generated by SFG while meticulously preserving the source facial identity. Our approach not only preserves the source facial identity within specific demographic groups but also enhances the diversity of the generated faces, effectively mitigating the attribute imbalance issue associated with real-world data. Experiments show that the training data augmented by the synthetic data made by our approach leads to clear performance improvement on state-of-the-art face recognition models.

We propose the Style-Preserving Generator (SPG) to generate synthetic license plate data to train License Plate Recognition (LPR) models, and compare the performance with the same models trained on real-world data. The proposed SPG can edit the characters on real-world license plates while maintaining their original styles, allowing synthetic license plate data to be generated with user-specified characters. We can therefore synthesize license plates with desired characters to effectively alleviate the data attribute imbalance and privacy issues associated with real-world license plates. To the best of our knowledge, this work is the first study to present the making of synthetic LP data by proposing a novel text-editing approach tailor-made for LP data, that is the proposed SPG. The SPG consists of a transformer, a source encoder, a source style encoder, a character mask decoder, a target generator, and a target discriminator. Given a source license plate image and a specified text as input, these components collaborate to compute the self- and cross-attention embeddings, predict character masks, and generate a synthetic license plate in the source style but with source characters replaced by the specified characters. We adopt a two-phase training scheme. Phase 1 training uses synthetic data only, but Phase 2 training uses synthetic and real-life data. To showcase the effectiveness of the SPG, we introduce a new benchmark dataset, the LP-2025 (License Plate 2025), which alleviates the limitations of existing datasets and presents new challenges for license plate recognition and generative models. We validate SPG performance on the LP-2025 dataset and other benchmark datasets and compare it against state-of-the-art text-editing approaches.

Verification of dispensed pharmaceutical packages is of paramount importance to prescription dispensing. Due to lack of identification peripherals like bar codes or RFID tags on blister packages, image-based solutions have been utilized. Earlier two-stage solutions require more resources for implementation and training, in addition to more computational time. In contrast, this paper presents an end-to-end trained solution, called Fast Rotated Occluded Rectangular (Fast ROR) pattern recognition architecture, composed of modules of: rotational rectangular detection, affine transformation, and image recognition. In particular, the features used to localize the package and the features used for identification are the same and extracted by a common feature extractor. As a result, the overall architecture is more compact with only one training set needed and more efficient computation time. Comparison experiments have been conducted on the proposed end-to-end FOR and on a representative two-stage HBIN [1] solution: Targeting a pool of 230 types of pharmaceutical packages, 30 paired front and back handheld images for each type were taken and randomly partitioned with 4:1 for training and testing, FOR (vs. HBIN) uses 41.79M (120.32M) network parameters, with a training time of 17 hours (119 hours), and a testing speed of 22.2 fps (10fps). The identification results in terms of F1-score by FOR (vs. HBIN) is 100% (98.67%) in familiar environment, whereas 94.30% (91.27%) when the identification is conducted in new environment.

Medical dispensing refers to the in-office preparation and delivery of prescription drugs, which is mostly dispensed by the units of blister packages. The objective of the study is to design an image-based blister package identification solution, which is capable of identifying a fetched drug based on a pair of the two opposite camera images of the hand-held drug. To this aim, this paper proposes a deep learning based Hand-held Blister Identification network (HBIN) to identify partially occluded blister packages present in arbitrary positions and orientation with possibly cluttered backgrounds. The proposed HBIN is a two-stage network that contains Blister cropping network (BCN) followed by RTT identification network (RIN). The BCN subnetwork, an image to image translation deep learning network, is to crop both side contours of the hand-held drug, before the pair of cropped contours can be juxtaposed as a fixed sized and fixed orientation RTT (rectified two-sides template) for final identification in the RIN sub-network. A blister package dataset containing a total of 30,394 images based on 230 types, typically found in hospital dispensing stations, have been collected and labeled. With extensive test, the accuracy of the primitive primitive HBIN attains an F-score of more than 94.33% for testing data from similar backgrounds and an F-score of 79.80% for dissimilar backgrounds. Although still a prototype, the preliminary results show the feasibility of identifying blister packages during retrieval process without resorting to bar codes nor RFID tags.

Person Re-IDentification (Re-ID) is to recognize a person who has been seen before by different cameras from possibly scenes. Re-ID poses as one of the most difficult computer vision problems owing to the enormous amount of identities involved in a large-scale image pool, with much similar appearance constrained by low resolution image, in a possibly occluded scene, etc. Global features geared for general object recognition and face recognition are far less adequate to re-identify a same person across cameras. As such, more discriminating features are needed to identify people. In particular, part-based feature extraction methods that extract by learning local fine- grained features of different human body parts from detected persons have been proved effective for person Re-ID. To further improve the part-aligned spatial feature approach, this paper proposes an improved part-aligned feature (IPAF) deep learning framework to better characterize a person's complete information with the following threes highlights: part alignment, finer part segmentation, and better learning network backbone. Our proposed solution has been trained and tested on the two most comprehensive Re-ID datasets with comparable performance of reported state-of-the-art solutions: for the dataset of Market1501 (DukeMTMC-reID), our proposed solution both achieves competitive results with mAP of 85.96% (84.70%) and CMC 1 of 94.30% (89.84%), respectively.

Nursing shift handover involves conversations between nurses during duty handover. Handover contents have been recorded manually, and it is desirable to have an automatic speech recognition solution that transcribes audio speeches into texts. Even though there are excellent commercial Speech recognition solutions available, they are mainly designed for general contexts, which may not be most efficient for special contexts. This pilot study is to investigate speech recognition for the special contexts of nursing handover. To be more precise, we are to transcribe audios of 500 Chinese sentences conversed during nursing handover at the Taipei Hospital. A deep learning based network, Deep Speech 2 [1] working in conjunction with Beam Search Decoder with Language Model [2], is adopted for the intended automatic speech transcription. Special adaptation is considered for the audios is in Chinese: the recognition unit in DS2 is Chinese characters instead of letters as in English; the N-gram language model is also on Chinese characters rather than words as in English. Performance of the trained model has been conducted on two experiments: One is to transcribe audios made by people other than the people made the training audios. The other is to transcribe audios whose contents deviated from the recorded 500 sentences. For the former, the character error rate (CER) is 2.33%, as compared to that of 7.94% by Google Speech API [3]. For the latter, when the testing sentences are deviated from the training ones by 21% in word counts, the CER by the trained system is 13%. The results show promising foundation for more complicate sentences patterns.

Precise identification of blister packages carries utmost importance at dispensing stations, where numerous prescriptions are to be efficiently dispensed by pharmacists. However, the usual presence of several hundreds of similarly looking, but completely different types of blister packages, in a crowded dispensing station makes it prone to human error, posing serious safety and health concerns for a patients life. In this work, we propose a highlighted deep learning (HDL) based approach for accurate identification of blister packages. HDL allows smart manipulation on raw data in order to better segment the identified targets and to expose inherent descriptive features, thus facilitating an accurate deep learning based classification process. Specifically, HDL uses automatic detection and then segments and processes the raw blister pack images irrespective of position, lighting variations, etc., making them suitable for CNN to classify the correct blister pack types. A ResNet CNN classifier has been trained using the processed images, and the resultant CNN model is finally deployed for classification. We have conducted an extensive experiment at the adult lozenge dispensing station of MacKay Memorial Hospital. The database that will be released along with this paper, consists of 272 types of blister packages, with 65 images belonging to each type for training and additional 7 images for validation. On real testing scenario, the proposed approach yielded almost 100% accuracy, consistently over the entire testing set. The proposed solution can also be extended to any dispensing station for automatic detection and classification of blister packages, thereby offering an highly effective and efficient delivery system.

Human action recognition from video sequences is one of the most challenging computer vision applications, primarily owing to intrinsic variations in lighting, pose, occlusions, and other factors. The human skeleton joints extracted by the depth camera Kinect have the advantages of simplified structures and rich contents, and are therefore widely used for capturing human actions. However, at present, most of the skeletal joint and Deep learning based action recognition methods treat all skeletal joints equally in both spatial and temporal dimensions. Logically, this is not in accordance with the fact that for different human actions the contributions from skeletal joints could significantly vary spatially and temporally. Incorporating information pertaining to such natural variations will certainly aid in designing a robust human action recognitions system. Hence, in this work, we endeavor to propose a global spatial attention (GSA) model to suitably express the different skeletal joints with different weights so as to provide precise spatial information for human action recognition. Further, we will introduce the notion of accumulative learning curve (ALC) model that can highlight which frames contribute most to the final decision by giving varying temporal weights to each intermediate accumulated learning results provided by an LSTM upon input frames. The proposed GSA (for spatial information) and ALC (for temporal processing) models are integrated into the LSTM framework to construct a robust action recognition framework that takes the human skeletal joints as input and predicts the human action using the enhanced spatial-temporal attention model. Rigorous experiments on NTU datasets (by-far the largest benchmark RGB-D dataset) show that the proposed framework offers the best performance accuracy, least algorithmic complexity and training overheads, when compared with other state-of-the-art human action recognition models.

Good action recognition relies on correct interpretation of two critical attributes related to action: the spatial attribute on the detected person's posture, and the temporal attribute on the detected person's body movement. Whereas deep learning has greatly improved image recognition, we have not found a similar progress for action recognition. One of the main reasons is due to the complexity caused by the additional temporal dimension; another, to the fact that there are less annotated training data samples for action recognition than that for image recognition. In this regard, this paper proposes a handcrafted cued LSTM model for human action recognition based on RGB-D data, as a collection of 25 skeleton joints in 3D coordinates, found in NTU-RGB-D, currently the most comprehensive dataset for action recognition. As opposed to the raw data of skeleton joints, handcrafted cues, pre-processed results geared to facilitate focused learning, are proposed as input to the LSTM structure. In particular, pertaining to the spatial cue, the SVIT cue derived by Skeleton View-invariant Transformation is adopted; pertaining to the temporal cue, the Diff cue computed by taking the displacements of all joint across down-sampled raw data is utilized. Based on the train/test protocol, the experiment we conducted on NTU-RGB-D shows that the recognition result based on either of the proposed handcrafted cues is better than that based on the raw data. In addition, by our proposed techniques of feature fusion and/or decision fusion of these two handcrafted cues, the recognition performance is better than that of the state-of-the-art approaches conducting on the same dataset by same train/test protocol.

License Plate Detection (LPD) is the pivotal step for License Plate Recognition. In this work, we explore and customize state-of-the-art detection approaches for exclusively handling the LPD in the wild. In-the-wild LPD considers license plates captured in challenging conditions caused by bad weathers, lighting, traffics, and other factors. As conventional methods failed to handle these inevitable conditions, we explore the latest deep learning based detectors, namely YOLO (You-Only-Look-Once) and its variant YOLO-9000 (referred here as YOLO-2), and customize them for effectively handling the LPD. The prime customizations include modification of the grid size and of the bounding box parameter estimation, and the composition of a more challenging AOLPE (Application-Oriented License Plate Extended) database for performance evaluation. The AOLPE database is an extended version of the AOLP database [1] with additional images taken under extreme but frequently-encountered conditions. As the original YOLO and YOLO-2 are not designed for the LPD, they failed to handle the LPD on the AOLPE without the customizations. This study can be one of the pioneering works that revise state-of-the-art real-time deep networks for handling the LPD. It also serves as a case study for those who wish to customize existing deep networks for detecting specific objects. In addition to a pioneering explorations of deep networks for handling the in-the-wild LPD, our contribution also includes the release of the AOLPE database and evaluation protocol for a novel benchmark for the LPD.

One main difficulty in applying action recognition to practical applications is the need to segment beginnings and ends of actions in a continuous online monitoring process. This paper proposed a finite state machine (FSM) model for automatic action segmentation and recognition solution, based on pose streams in the form of skeleton joint data provided by Kinect. With the action recognition problem reframed as a state identification problem, the key solution to state identification hinges on detection of changing events, which signify the start of new action and the recognition of the underlying action. In that regard, a decision tree is constructed to detect these events based on the spatial positions and the changes of the skeleton data. In addition, to identify the current state or equivalently the action of a detected person, a fault observer is derived from the modeled action FSM. The fault observer does not only identify the initial state of action when the recognition process starts, but also serve the purpose of error recovery when the system loses track of ongoing events at times of intermittent sensor faults. Additionally, an AutoCorrect mechanism is presented to further enhance the accuracy of action recognition. To evaluate the proposed approach, an experiment with 300 participating subjects has been conducted for a total of 900 test sequences. The 98.63% correct identification result ensures the proposed approach a promising solution to constant action monitoring solution.

Although the Tree Structured Model (TSM) is proven effective for face detection, pose estimation and landmark localization, its sluggish runtime makes it unfavorable in practical applications. We propose the Bilayer Tree Structure Model (BTSM) to improve the run-time speed while keeping the performance unchanged or slightly better. The BTSM is composed of two component TSMs, the coarse c-TSM and the refined r-TSM. The c-TSM is trained on low-resolution samples so that it can provide coarse but fast detection, The r-TSM is trained on mid-resolution samples so that it can locate precise part locations. The performance of the BTSM is validated on three benchmark databases, the Multi-PIE, LFPW and AFW, and compared with the latest TSM to demonstrate its efficacy.

Kinect have been used as a revolutionary sensor for recent human activity recognition research, mainly due to its ready skeletal joint information that facilitates activity analysis. However, the sensor's unstable and imprecise measurement may impair the analysis results. To alleviate this impact due to the unavoidable noisy measurement, this paper presents a recognition approach based on the relative positional relationship among measured joints data. Relative positional relationship between two joints refers to the relation either one joint's position in the x, y, z coordinates is to the left or right, above or below, in front or behind the other. Capturing these relative positional relationship among all measured joints data as a {-1, 0, 1} sequence throughout the time span of an activity, or more succinctly represented by a summary of the change frequency of these relationship, proves to be an effective feature for comparison and classification. In doing so, measured joint data are first pre-processed by SVIT (skeleton-based viewpoint invariant transformation) to eliminate viewpoint variation. Then, as the first feature, change frequencies of relative positional relationship among joints are constructed. As a complimentary feature, a HOG3D-like feature that summarizes the joints spatial distribution throughout an activity is also constructed. Classification credibility of feature is then applied to fuse the two features with ELM as machine learning for activity classification. The proposed approach with its efficient implementation has been applied to MSRDailyActivity3D and demonstrated favorable performance than results from literature.

Most RGB-D based research focuses on gesture analysis, scene reconstruction and SLAM, but only few study its impacts on face recognition. A common yet challenging scenario considered in face recognition across pose takes a single 2D face of frontal pose as the galley and other poses as the probe set. We consider a similar scenario but with a RGB-D image pair taken at frontal pose in the gallery, only 2D images with a large scope of poses in the probe set, and study the advantage of the additional depth map on top of the regular RGB image. We formulate the 3D face reconstruction using the RGB-D image as a constrained optimization, and compare the results with different reconstruction settings. The reconstructed 3D face allows the generation of 2D face with specific poses, which can be matched with the probes. Experiments on the Biwi Kinect Head Pose Database and Eurecom Database show that the additional depth map substantially improves the cross-pose recognition performance, and the depth-based component selection also improves the recognition under occlusion and expression variation.

Combining depth information and color image, RGB-D cameras provide ready detection of humans and the associated 3D skeleton joints data, facilitating if not revolutionizing conventional image centric researches in, among others, computer vision, surveillance, and human activity analysis. Applicability of a D-RBG camera, however, is restricted by its limited range of frustum of depth in the range of 0.8 to 4 meters. Although a RGB-D camera network, constructed by deployment of several RGB-D cameras at various locations, could extend the range of coverage, it requires precise localization of the camera network: relative location and orientation of neighboring cameras. By introducing a skeleton-based viewpoint invariant transformation (SVIT) that derives relative location and orientation of a detected human's upper torso to a RGB-D camera, this paper presents a reliable automatic localization technique without the need for additional instrument or human intervention. By respectively applying SVIT to two neighboring RGB-D cameras on a commonly observed skeleton, the respective relative position and orientation of the detected human's skeleton to these two respective cameras can be obtained before being combined to yield the relative position and orientation of these two cameras, thus solving the localization problem. Experiments have been conducted where two Kinects are situated with bearing differences of about 45 degrees and 90 degrees when coverage extended by up to 70% with the installment of an additional Kinect. The same localization technique can be applied repeatedly to a larger number of RGB-D cameras, thus extending the applicability of RGB-D cameras to camera networks in making human behavior analysis and context-aware service in a lager surveillance area.

Deadlock prevention policies are used to solve the deadlock problems of flexible manufacturing systems. Theory of regions is the efficient method for obtaining optimal (i.e. maximally permissive) controllers. All legal and live maximal behavior can be preserved by using marking/transition-separation instances (MTSIs) or event-state-separation-problem (ESSP) methods. However, solving all sets of inequalities is very time-consuming. Moreover, the number of linear programming problems (LPPs) of all legal markings is also exponential with net size. In this paper, a novel methodology is proposed to reduce the number of MTSIs/ESSPs and LPPs. Preciously, one new concept called critical ones of crucial marking/transition-separation instances (COCMTSI) is developed and used in this deadlock prevention policy that allows designers to employ few MTSIs to deal with deadlocks.

Deadlock prevention policies are used to solve the deadlock problems of FMSs. The theory of regions is recognized as the unique method for obtaining maximally permissive (i.e., optimal) controllers in the existing literature. In this paper, the selective siphons and critical markings method [17] is merged in the new deadlock prevention policy. First of all, reachability graph is still needed. Second, CMTSIs are identified. Further, selective siphons and critical markings method is used to check if all dead/quasi-dead markings of CMTSIs are covered by these selective siphons. Furthermore, choose anyone CMTSI that belongs to a same selective siphon to be processed. Finally, controllers are therefore obtained. Experimental results indicate that the computational cost can be reduced again. Besides, it is the most efficient policy to obtain maximal permissive behavior of Petri net models.

A framework is proposed to generate datasets good for benchmarking face detection using database meant for benchmarking face recognition. Instead of the common way of collecting images manually, the datasets from the proposed framework are made by a synthesis process with two phases: intrinsic parameterization and extrinsic parameterization. The former parameterizes the intrinsic variables that affect the appearance of a face, while the latter parameterizes the extrinsic variables that dominate how faces appear on background images as required by a test criterion. Experiments reveal that the proposed framework can generate test samples similar to those available from a popular face detection database, and also samples unavailable from existing face databases.

A sequence-based visual navigation system for autonomous robots is proposed. A sequence of reference images representing a transportation route is taken as the navigation clues. When a robot navigates in a route, two navigation modes, with better reduction in total transportation time required, are switched according to the difference of scales between the robot's current view and the targeted reference image. When the scale is large, log-polar transform is applied to match regions in two images. A less accurate moving direction is inferred from the matching result. After the difference of scale is reduced when the robot approaches the targeted waypoint, SIFT features are matched between two images. An accurate moving direction is decided from the epipolar geometry which is computed from matched SIFT features. The robot's moving velocity is adjusted accordingly, thus reducing the overall transportation time. While other sequence-based navigation methods moves the robot at a maximal velocity of 10 cm/sec, the proposed method moves the robot in an average velocity of 26.5 cm/sec during a 117.3 m long route with 11 reference images. Comparing to a similar sequence-based navigation research, the proposed method does not only reduce transportation time by at least half, but also requires less number of reference images in route transportation applications.

This paper introduces MyHome, a framework of smart home by which household information is all at a finger tip. Through adopting Message oriented middleware (MOM) and open service gateway initiative (OSGi) technologies, MyHome offers reliable automatic operations, fault tolerant and configurable home automation, high extensibility and large scalability. In its design, MyHome system is composed of a residential gateway MyServer and Internet accessible GUI MyIcon and MyMobile. MyServer is used to provide services regarding home security, inventory tracking, facility management, GPS location recording and family care. Inherently an interactive and multitasking system driven by peripherals connected through wireless sensor networks, the overall MyServer architecture is designed with six core service modules operating on a MOM. Each of these modules is designed as an OSGi bundles and is implemented by a programming template utilizing event publish/subscribe messaging mechanism. To facilitate program demonstration, simulator and scenario editor are also developed. A successful implementation of the proposed MyServer is also demonstrated in an emulated home environment where peripherals are connected through ZigBee wireless sensor network with data integrated into a database. With these clearly defined service modules and pertinent infrastructure to integrate household peripherals, this paper presents a practical approach to the implementation of a smart home.

This paper addresses the design and implementation of a residential gateway: MyServer, which is to provide services regarding home security, inventory tracking, facility management, and family care in a smart home system. Inherently an interactive and multitasking system driven by peripherals connected through wireless sensor networks, the overall MyServer architecture is designed with six clearly defined core service modules operating on a message oriented middleware (MOM) framework. Each of these modules is implemented with a programming template utilizing event publish/subscribe messaging mechanism. This paper also demonstrates a successful implementation of the proposed MyServer system in an emulated home environment, where peripherals are connected through ZigBee wireless sensor network.

This paper addresses the problem of designing robust static output-feedback controllers for nonlinear discrete-time interval systems with time delays both in states and in control input. In the approach, we do not directly employ the Lyapunov approach, as do in most of traditional fuzzy control design approaches. Instead, sufficient conditions for guaranteeing the robust stability for the considered systems are derived in terms of the matrix spectral norm of the closed-loop fuzzy system. The stability conditions are further formulated into linear matrix inequalities so that the desired controller can be easily obtained by using the Matlab linear matrix inequality (LMI) toolbox. Finally, an example is provided to illustrate the effectiveness of the proposed approach.

This paper presents a new class of "well-behaved" Petri nets called extended resource control net (ERCN*) merged nets that generalize the class of ERCN merged nets proposed in a previous paper by Xie and Jeng. ERCN merged nets can model parallel and synchronized processes in semiconductor manufacturing such as lot split and lot merging, which occurs frequently in a research and development (R&D) semiconductor fab (semiconductor plant) for engineering purposes. However, processing cycles for each resource type must include the initial state of the resource type. In other words, no local processing cycles are allowed. This makes the modeling of degraded behavior in semiconductor manufacturing such as rework, failure, and maintenance difficult. In the current work, this constraint is relaxed under the "extended free-choice (EFC)" or "asymmetric choice (AC)" condition. Specifically, for each operation place with degrading outgoing arcs, the FC or AC condition is satisfied. In addition, degraded behavior is modeled as blocks within ERCNs. We show that conditions for liveness and reversibility of an ERCN* merged net correspond to the absence of unmarked siphons. The "well-behaved" conditions can be transformed into inequalities of the initial marking. Examples are shown to illustrate the proposed methodology.

A typical semiconductor wafer fabrication involves hundreds of complex manufacturing steps on capital-intensive equipment. In the persistent pursuit of near perfect hundred percents of production yield and equipment utilization, automation systems have been designed implemented to provide the functions of: direct equipment control, automated material transportation, and real-time lot dispatching. This paper presents an overview of typical semiconductor fab automation systems, of which two key systems are presented: (1) manufacturing executions systems (MES) that formulates manufacturing methods and procedures, and (2) cell controller that serves as the automation link between the upper MES and the lower equipment. At the end of the paper, lot operation of the lower equipment. At the end of the paper, lot operation of one manufacturing step is detailed to highlight the interaction between MES and cell controller within a fully automated semiconductor fab.

This paper presents a new class of "well-behaved" Petrinets called ERCN merged nets that generalize the class of ERCN merged nets proposed in (X.L. Xie and M.D. Jeng, 1999). ERCN merged nets can model parallel and synchronized processes in semiconductor manufacturing such as lot split and merging. However, processing cycles for each resource type must include the initial state of the resource type. In other words, no local processing cycles are allowed. This makes the modeling of degraded behavior in semiconductor manufacturing such as rework, failure, and maintenance, difficult. In the current work, this constraint is relaxed under the "extended free-choice (EFC)" or "asymmetric choice (AC)" condition. Specifically, for each operation place with degrading outgoing arcs, the FC or AC condition is satisfied. In additions, degraded behavior is modeled as blocks within ERCNs. We show that conditions for liveness and reversibility of an unmarked siphons. The "well-behaved" conditions can be transforms into inequalities of the initial marking. Examples are shown to illustrate the proposed methodology.

Machine identification of discrete event systems (DES) addresses the issue of identifying an unknown system based on externally observed sample path of the unknown system. Online Modeling Refinement studies the continuing machine identification process in the context when the observed sample path is updated incrementally. While machine identification problem for fixed length sample path is NP-complete, the computational requirement for the proposed online modeling refinement algorithm is maintained at minimal by taking the structure similarity between successive accumulated observed sample paths. In addition to the computational advantage, the proposed algorithm also guarantees the identification results of the system models "converge" to the unknown DEDS model as the incrementally observed sequence get "long" and "rich" enough.

Failure diagnosis in the context of DES was first formulated by Sampath et al. Where the notion of diagnosability and the associated diagnoser are proposed. Ushio et al. extended Sampath's study to systems modeled by Petri nets. This paper further assumes some of the transitions in a Petri net model are observable in the sense that its occurrence can be observed. The main contribution of this study shows how diagnosers and verifiers for systems modeled by Petri net are constructed accordingly. As shown by examples, the additional information from observed transitions adds diagnosability to the system.

Statecharts have been proposed as a visual formalism for the behavioral of complex systems. The dynamical behavior of an elevation is a example to illustrate the operation of statechart systems because it shares with many other discrete event systems (DESs) the features of: simple actions, aggregating complexity of state descriptions, and great variety of possible control strategies and resulting trajectories. This paper applies the statechart terminologies to cope with the difficult situation of elevator system problems. In this paper, we present the modeling, control and implementation of an elevator system. A statechart-based for an elevator controller design and implementation is proposed. The intended advantage of the proposed controller is that using statechart terminologies, we can describe the system's behavior over time, including the dynamics of activities, and the conditions and events that cause states to change and other occurrences to take place. Moreover, A statechart-based approach is adopted to model the operation flows in the elevator system, and from the hierarchical tree of the elevator system, we can construct its statecharts model.

Generic equipment control, which allows control of multiple types of equipment simultaneously, is made possible under the premise that individual equipment operational scenario can be normalized. Scenario normalization for In-Line Steppers (ILS) in a photolithographic cell is complicated due to the necessity of integrating the track and stepper. To the best of our knowledge, scenario normalization for ILS and has not been addressed before in the literature. To establish the foundation of photolithographic cell control, this paper addresses the scenario normalization procedure for ILS and its implementation. To do so, we use the sequence diagram that highlights the operation details at the equipment level to model the operational scenarios of the stepper and track. Then, the overall operational scenarios are checked against the normalized operational flow to derive normalization rules, expressed in terms of "triggering rules" before being implemented in an event triggering programming platform as a coordinator between the equipment control system and the ILS. The design of an ILS coordinator for a real-world photolithographic cell controller is presented in detail.

We present a new deadlock prevention algorithm for a class Petri nets. A new class of net that is extended from S/sup 3/PR, called ES/sup 3/PR, where deadlocks are related to unmarked siphons. This method is an iterative approach by adding two kinds of control places, called the ordinary control place and weighted control place, to the original model to prevent siphons from being unmarked. We obtained the relation of the algorithm, liveness and reversibility of the controlled net. Finally, a flexible manufacturing example is presented for illustrating the method.