Devinder Thapa

Automatic segmentation and diagnosis of breast lesions using morphology method based on ultrasound

The main objective of this paper is to use the auto segmentation with morphological technique to find out predictable region of interest (ROI), especially the center and margin area of the tumor. The proposed method has employed moving average method for detecting edge of tumor after estimating the corresponding center using the aid of medical domain knowledge. In our re-search, after computing distance between center and edge of tumor we get factual and numerical data of tumor to calculate multi-deviation and circularity test. It is useful to construct tumor profiling by splitting up the lesion into 4 divisions with the mean of multi-standard deviation (benign: 13.7, malignancies: 38.32) and 8 divisions with the mean of multi-standard deviation (benign: 3.36, malignancies: 15.29) with equal segments. We used K-means algorithm to make classification between benign and malignance tumor. This technique has been fully validated by using more than 100 ultrasound images of the patients and found to be accurate with 90% degree of confidence. This study will help the physicians and radiologist to improve the efficiency in accurate detection of the image and appropriate diagnosis of the cancer tumor.

Speech authentication system using digital watermarking and pattern recovery

The objective of this paper is to detect speech forgery using digital audio watermarking and pattern recovery techniques. A digital watermark pattern has been attached with the speech signal to detect three kinds of alterations or forgeries such as substitution, insertion, and removal. The watermark pattern will be modified if some changes have been made to the speech contents. Modification and forgery can be measured and detected by pattern recovery. The proposed method uses the cyclic pattern embedding to overcome synchronizing problems of previous detection techniques. In addition, pattern recovery enhances the robustness to compression. This method has been tested and verified using six recording devices, which was used for collecting verbal data. The speech signals were sampled at the rate of 8kHz and digitized at 16bits resolution. Randomly chosen regions were substituted, removed, and compressed in MP3 at the rate of 16kbps as well as in CELP at the rate of 11.5kbps. The experiment shows the perfect detection for three kinds of forgeries and it proved the validity of the proposed method.

Transformation from Petri Nets Model to Programmable Logic Controller using One-to-One Mapping Technique

Agile and flexible manufacturing system makes it mandatory that a control program should have features such as agility, flexibility, and reusability in order to meet fast changing customer demands. Proper modeling and fast formation of the control logics using graphical and mathematical tools is one of the most peculiar ways to make the control logic more feasible for rapid product prototyping, concurrent engineering, flexible, and agile manufacturing. This paper illustrates efficient conversion of Petri nets model into programmable logic controller like LLD (ladder logic diagram) in a very convenient way using one-to-one mapping technique. Furthermore, property analysis has been briefly explained to generate flawless control code for better operational performance. An example of painting robots has been demonstrated to prove the proposed method

III-Phase Verification and Validation of IEC Standard Programmable Logic Controller

The objective of this paper is to define an integrated approach for offline verification and validation of the control logics to provide absolute solution by implementing the Ill-phase V&V method in a manufacturing industry. The control logic plays vital role in an agile manufacturing system for proper functioning of the FMS. The effort to integrate the formal verification techniques with virtual commissioning is emerging, which is still not in a full fledged industrial usage, due to the isolated thinking of the user about formal verification techniques. Existing techniques like simulation has not been able to detect the hidden errors, which may propagate from one workcell to another workcell in a long run and create a complete breakdown in the manufacturing unit. These errors required to be carefully tested before the real time implementation. Control logics play a vital role to reduce the down-time and ramp-up time in a manufacturing industry. We need an integrated approach and techniques to support the consistent running of the production cycle. This paper explained about the positive aspects of manual and software based automated and virtual commissioning techniques to provide an applicable solution to the fast paced manufacturing industries.

Agent based decision support system using reinforcement learning under emergency circumstances

This paper deals with agent based decision support system for patients right diagnosis and treatment under emergency circumstance. The well known reinforcement learning is utilized for modeling emergency healthcare system. Also designed is a novel interpretation of Markov decision process providing clear mathematical formulation to connect reinforcement learning as well as to express integrated agent system. Computational issues are also discussed with the corresponding solution procedure.

Generation of PLC Ladder Diagram Using Modular Structure

In this research work, auto-generation of PLC ladder diagram program is explained. This work is carried out in real time operation of PLCs in the plant and simulation of the models in the PlcStudioreg. Involved modelling and simulation tasks are performed in PlcStudioreg which is research product of digital manufacturing system (DMS) team in Ajou University, consists of input/output model and graphics tool for PLC based industries. Object-oriented approach DEVS (discrete event system) is employed in formalism of process structures, later, formalized model is simulated using plc-DEVS simulator, which is extended from conventional DEVS. Generated sequence of operation (SOP) from the simulation and mapping it into input/output table to generate executable ladder diagram is explained consecutively in the paper. The algorithm developed to connect plc-DEVS and graphics module of PlcStudioreg is elaborated. In the mean time, to show the applicability of methodology, pallet conveyor system is described.

Neural network based algorithms for diagnosis and classification of breast cancer tumor

This paper outlines an approach for applying acquiring numerical breast cancer image data and diagnosis using neural network algorithm in a way that is easy to classify between benign and malignance. This paper is an extended work related to our previous work [1]. In our previous work we used k-means algorithm to detect and diagnosis breast cancer tumor’s region. However, to find the better results from the algorithm we need to add more numerical parameters of the breast cancer image and this algorithm has limited usage when applied with more number of parameters. Even if the cancer tumor is abnormal it was quite difficult to distinguish among those tumors. This paper summarizes the different comparative study of neural network algorithms to get the best classification of the breast cancer and explains how to acquire more numerical parameters from the breast cancer image data, so that it can help doctors to diagnosis efficiently between benign and malignance tumors.

A Formal Model for Real-Time Automated Manufacturing System Control with Timed-MPSG

The objective of this paper is to extend the MPSC model by introducing the temporal properties to check time constraint, and do the performance analysis of the real-time shop floor controller. The MPSG (message-based part state graph) model has been developed for the execution portion of shop-floor controllers that operate in a distributed and hierarchical control environment. It is based on deterministic finite state automata and represents the execution module of shop-floor controller as a communicating finite state machine. However, there is still no consideration for handling the time in this framework. For this purpose, a formal model of Timed-MPSG processes is proposed in terms of a real-time part processing task. Furthermore, the conceptual idea, control flow algorithm and the implementation methodology of the Timed-MPSG are described with a simple example.

Architecture for modeling, simulation, and execution of PLC based manufacturing system

In this paper, we propose an integrated architecture for modeling, simulation, and execution of PLC (programmable logic controller) based manufacturing system. The main objective is to integrate the high level modeling, simulation, and device level executable code generation. This architecture can improve the fidelity between high level system model and lower level PLC controlled devices. In this paper, we model the shop floor controller system using DEVS (discrete event system specification) formalism, subsequently, simulate the model and generate SOP (sequence of operations). We added two algorithms in conventional DEVS, the first algorithm makes an interface between 3D graphic model and DEVS model, whereas, the second algorithm generates SOP. As a result, the generated SOP can be mapped with PLC I/O (input/output) address to generate an executable controller code. For the purpose of further validation and implementation, the generated program can be downloaded to software or hardware PLC.

Controller logic design and implementation using t-MPSG

The objective of this paper is to reduce the development time of PLC (programmable logic controller) by automating the task of controller logic design and implementation. For this purpose we applied the t-MPSG, an extended finite state automaton, to model the sequence of operations. It is developed for generating execution module for the real-time shop floor controller system. The t-MPSG supervises the flow of part from one state to another state considering the precondition of the system. It can be used to model the controller logic, which can be consequently translated to textual code, and finally translated into IEC standard PLC code. The generated code can be downloaded to PLC for the purpose of simulation or execution.