SKSinchai Kamolphiwong

Sinchai Kamolphiwong

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Sinchai Kamolphiwong has a total of 63 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    ZleepNet: A Deep Convolutional Neural Network Model for Predicting Sleep Apnea Using SpO2 Signal

    by Hnin Thiri Chaw, Thossaporn Kamolphiwong, Sinchai Kamolphiwong, Krongthong Tawaranurak, Rattachai Wongtanawijit

    Sleep apnea is one of the most common sleep disorders in the world. It is a common problem for patients to suffer from sleep disturbances. In this paper, we propose a deep convolutional neural network (CNN) model based on the oxygen saturation (SpO2) signal from a smart sensor. This is the reason why we called ZleepNet a network for sleep apnea detection. The proposed model includes three convolutional layers, which include ReLu activation function, 2 dense layers, and one dropout layer for predicting sleep apnea. In this proposed model, the use of signals for detecting the sleep apnea can be reduced from 25 sensors to 1 sensor. We conducted experiments to evaluate the performance of the proposed CNN using real patient data and compared them with traditional machine learning methods such as least discriminant analysis (LDA) and support vector machine (SVM), baggy representation tree, and artificial neural network (ANN) on publicly available sleep datasets using the same parameter setting. The results show that the proposed model outperformed the other methods with the accuracy of 91.30 with the split rate of 0.2 in which the training data are 20 and testing data are 80. The accuracy of the proposed CNN is 90.33 when compared with the LDA which achieved 86.5 accuracy with the split rate of 0.5 in which training data are 50 and testing data are 50. It achieved 91.56 accuracy when compared with the support vector machine (SVM) in which training data are 70 and testing data are 30. The achieved accuracy of the proposed CNN is 91.89 when compared with bagging representation tree in which training data are 90 and testing data are 10. The accuracy of the proposed CNN is 91.30 in which training data are 83 and testing data are 17 when compared with artificial neural networks (ANN).


  • Open Access

    Detecting Anomalous LAN Activities under Differential Privacy

    by Norrathep Rattanavipanon, Donlapark Ponnoprat, Hideya Ochiai, Kuljaree Tantayakul, Touchai Angchuan, Sinchai Kamolphiwong

    Anomaly detection has emerged as a popular technique for detecting malicious activities in local area networks (LANs). Various aspects of LAN anomaly detection have been widely studied. Nonetheless, the privacy concern about individual users or their relationship in LAN has not been thoroughly explored in the prior work. In some realistic cases, the anomaly detection analysis needs to be carried out by an external party, located outside the LAN. Thus, it is important for the LAN admin to release LAN data to this party in a private way in order to protect privacy of LAN users; at the same time, the released data must also preserve the utility of being able to detect anomalies. This paper investigates the possibility of privately releasing ARP data that can later be used to identify anomalies in LAN. We present four approaches, namely, naïve, histogram-based, naïve-, and histogram-based- and show that they satisfy different levels of differential privacy—a rigorous and provable notion for quantifying privacy loss in a system. Our real-world experimental results confirm practical feasibility of our approaches. With a proper privacy budget, all of our approaches preserve more than 75% utility of detecting anomalies in the released data.


  • The Design of SDN Based Detection for Distributed Denial of Service (DDoS) Attack

    by Myo Myint Oo, Sinchai Kamolphiwong, Thossaporn Kamolphiwong

    Software Defined Networking (SDN) is the network architecture where the network control is decoupled and separated from forwarding mechanism. It is more popular in enterprise network for simplicity, scalability and traffic flow optimization. SDN can give an attractive solution for network security. However, Distributed Denial of Service (DDoS) attacks are the challenges in SDN environments. Despite a large number of DDoS detection and mitigation techniques exist in today, DDoS attacks continue to grow in attacks frequency, attacks volume and they are threatening the network security. There are two kinds of DDoS detection techniques; signature based and anomaly based detection. When the signature based detection technique uses network behaviors, the anomaly based detection uses machine learning techniques. In this paper, we propose the design of SDN based detection for DDoS attack. In this propose system design, we use Advanced Support Vector Machine (ASVM) algorithm in order to detect DDoS attack. With the advantage of ASVM, it can significantly reduce the testing time as well as training time compared with SVM algorithm. We validate the propose system by using Hierarchical Task Analysis (HTA) technique in order to validate the human errors to achieve certain goal.


  • SDN-based Network Mobility

    by P. Sornlertlamvanich, T. Ang-Chuan, S. Sae-Wong, T. Kamolphiwong, S. Kamolphiwong

    Software-Defined Networking (SDN) provides network operators to easily and quickly introduce new services and flexibly adapt to their requirements. In new network architectures, mobility management is an important aspect for the future of mobile networks. To offer the mobility of an entire network (e.g., vehicles), it needs the mobility protocol for a moving group of users or devices. This paper proposes a DMM solution based on SDN architecture for NEMO called SDN-NEMO. This solution offers a lot of advantages including no need to deploy any mobility-related component at the access router, independence of the underlying technologies, and per-flow mobility support. To evaluate the SDN-NEMO, we describe an analytical evaluation for signaling and packet deliver costs. The numerical results shows the SDN-NEMO can provide better costs and optimal route for the mobile network.


  • Automated Home Agent Configuration for Mobile IPv6

    by Wuttipon Noopetch, Sinchai Kamolphiwong

  • An Enhancement of IPv4-in-IPv6 Mechanism

    by N. Chuangchunsong, S. Kamolphiwong, T. Kamolphiwong, R. Elz

    From global Internet information, IPv6 traffic grows slowly. A large portion of service providers are still using IPv4 even IPv6 co-exists with IPv4 for long time. However, IPv6 traffic are gradually growing especially most of network backbone sides. This paper proposes an enhancement mechanism of IPv4-in-IPv6 which supports IPv6 natively and provides IPv4 connectivity by using IPv4-in-IPv6 tunneling, so called "Lightweight 4over6 (lw4over6)". The performance metrics used in this evaluation are: system throughput and packet dropped. Based on our computer simulation results, when the system has a mix of intra and inter-communications, we have found that, with light traffic load, the proposed method performs better than lw4over6 and 4over6 slightly. However, with more heavy traffic load the proposed method gives higher performance than lw4over6 significantly.


  • Modeling design of the distributed reasoning based on Chord

    by Sunitsa Maneechai, Sinchai Kamolphiwong

    Context aware systems are able to adapt their operation to the current context information without explicit user intervention, in order to derive high-level context information from low-level context information that may be spread over multiple domains, context reasoning method is necessary. Most existing reasoning methods in context aware systems rely on centralized approach that combines local ontology of each node into single global ontology which has some limitations such as a single point of failure, single process bottleneck and require system administration at the centralized server. However, the most important problem is when all nodes need to update context information frequently. It will have massive information flooding in the system. This paper introduces a simple model to enable reasoning with multiple ontologies interrelated via semantic mapping in P2P without combining all ontologies into a single global ontology. Our design is based on Chord mechanism. We have proposed a simple semantic mapping by measuring the similarity value of two concepts based on WordNet. We focus on the advantages of integrating semantic mapping for ontology sharing in the P2P system.


  • Personal Health Assistant on Android Mobile Device: Sleeping, Nutrition and Exercise

    by Kiatateeti Anusornpakdee, Matugorn Limpanadusadee, Sangsuree Vasupongayya, Sinchai Kamolphiwong

    Good health can be achieved by maintaining good behaviors such as a good night sleep, enough exercise and good nutrition. However, the competitive environment nowadays prevents such good behaviors. Thus, this work aims to develop an application on mobile devices that is able to (1) record the daily sleeping, exercise and nutrition information, (2) analyze the collected information in order to provide a notification or an alarm, and (3) present the analyzed results in a simple and easy to understand format. The proposed application can collect data from other application and from the users. A set of simple data analysis methods is performed on the collected data in order to provide a personal health advice based on the user pre-defined preferences.