JICE Digital

JICE digital products

Showing 1–8 of 39 results

  • Detection of Black Hole Attack and Performance Analysis of AODV Protocol in MANET (Mobile Ad Hoc Network)


    Abstract: A Mobile Ad hoc Network is an aggregation of mobile terminal that form a volatile network with wireless interfaces. Mobile Ad Hoc Network has no central administration. MANET is more vulnerable to attacks than wired network, as there is no central management and no clear defense mechanism. Black Hole Attack is one of the attacks against network integrity in MANET.  In this type of attack all data packets are absorbed by Black Hole node. There are lot of techniques to eliminate the black hole attack on AODV protocol in MANET. In this paper a solution named Black Hole Detection System is used for the detection of Black Hole attack on AODV protocol in MANET. The Black Hole Detection System considers the first route reply as the response from malicious node and deletes it, then the second one is chosen using the route reply saving mechanism as it comes from the destination node. We use NS-2.35 for the simulation and compare the result of AODV and BDS solution under Black Hole attack.  The BDS solution against Black hole node has high packet delivery ratio as compared to the AODV protocol under Black hole attack and it’s about 46.7%.The solution  minimize data loss, reduces the average Jitter by 5% and increases the Throughput.

    Keywords: MANET, AODV, blackholeAODV, bdsAODV

  • Accuracy Evaluation for Mental Health Indicator Based on Vocal Analysis in Noisy Environments


    Abstract: Mental health care is one of the important challenges in our modern stressful society. The authors proposed a method for measuring mental health based on the quality of the patient’s voice, and implemented a system that monitors the state of mental health based on voice during a phone conversation via smartphone. However, there has been little consideration of the analysis of mental health using voices in a noisy environment thus far. Therefore, this study investigated the impact of noise on the mental health indicator based on vocal analysis. The results showed that the mental health level was judged to be low when the analyzed voice included noise. The study also revealed that a decreased precision in the detection of utterances had a significant impact on mental health analysis.

    Keywords: Mental health care; noisy environment; vocal analysis

  • Visualization of Individual Feature Amount Appearing in Daily Performance Based on Electrostatic Induction


    Abstract: In this paper, a new technique to measure daily human body motion without using cameras and video images is presented. The change in the electric potential of the human body that is caused by the daily performance induces an electrostatic induction current in the electrode placed at a distance of a few meters from the human body. Using this technology, I have developed an effective non-contact technique for the detection of human daily performance by detecting the change in this human-generated body charge. This technique based on the detection of an electrostatic induction current of the order of approximately sub-picoamperes flowing through an electrode that is placed at a distance of 5 m from the subject. It is shown that the characteristics of the individual are included in walking motion, sitting on a chair and retiring motion. This technique effectively explains the behavior of the waveform of the electrostatic induction current flowing through a given measurement electrode through a capacitance model of the human body.

    Keywords: Daily performance, Electrostatic induction current, Non-contact measurement, Wavelet transform

  • Regional Distance-based k-NN Classification


    Abstract: The k-Nearest Neighbor (k-NN) is very simple and powerful approach to conceptually approximate real-valued or discrete-valued target function. Many researchers have recently approved that K-NN is a high-prediction accuracy algorithm for a variety of real-world systems using many different types of datasets. However, as we know, k-NN is a type of lazy learning algorithms as it has to compare to each of stored training examples for each observed instance. Besides, the prediction accuracy of k-NN is under the influence of K values. Mostly, the higher K values make the algorithm yield lower prediction accuracy according to our experiments. For these issues, this paper focuses on two properties that are to upgrade the classification accuracy by introducing Regional Distance-based k-NN (RD-kNN) and to speed up the processing time performance of k-NN by applying multi-threading approach. For the experiments, we used the real data sets (wine, iris, heart stalog, breast cancer, and breast tissue) from UCI machine learning repository. According to our test cases and simulations carried out, it was also experimentally confirmed that the new approach, RD-kNN, has a better performance than classical kNN.
    Keywords: k-NN, RD-kNN

  • A Stress Analysis Method using Poincaré Plot and Complex Correlation Measures for Wearable Health Devices


    Abstract: This paper attempts to develop a stress analysis method using short-term heart rate (HR) data obtained with wearable health devices. Evaluation method for stress analysis is very important for disease prevention and health promotion. Wearable health devices, such as smart phones and wristband fitness watches, are capable of measuring HR data using photoplethysmography technologies. In recent years, many new commodity devices have been issued and been used to obtain healthcare information, including HR data, in people’s everyday life. However, since HR data of wearable devices are recorded with uneven and relatively long sampling intervals, which are constrained by their hardware issues, it is difficult to apply traditional spectral analysis methods for the HR data. The proposed method evaluates HR data using a non-linear technique, Poincaré plot. As the number of points in a plot is restricted by the limited sampling features of wearable devices, this paper applies two stress analysis indices that are based on complex correlation measures of time-varying characteristics in Poincaré plots. On the other hand, the proposed method can investigate dynamic changes in stress levels of short-term (e.g., one minute) analysis duration. Mental stress induction experiments were conducted with nine subjects to validate the proposed method.

    Keywords: Stress analysis; Wearable health devices; Heart rate variability (HRV); Poincaré plot; Complex correlation measure (CCM)

  • Detection of Genes Patterns with an Enhanced Partitioning-Based DBSCAN Algorithm


    Abstract: Microarray datasets are enriched with numerous unknown gene expression patterns  that may have significant biological meaning. Detecting well-separated gene expression patterns is a critical task in microarray data analysis. The density-based spatial clustering DBSCAN  algorithm has been used to detect patterns with different shapes and sizes in many applications. However, the DBSCAN algorithm is time-consuming when used on big datasets, and microarray datasets are considered as big and complex datasets. Therefore, in this study, we modified the DBSCAN algorithm by combining it with a partitioning around medoids algorithm based on normalized and weighted Mahalanobis distance (NWM). The developed algorithm (NWM_PDBSCAN) was tested on selected microarray expression datasets, which were pre-processed prior to analysis. The results revealed an optimal cluster solution with different shapes and sizes. We further reduced the dataset sizes using a random sampling technique to enhance the performance of the DBSCAN algorithm. The proposed NWM_PDBSCAN algorithm performed ideally, and was evaluated using Dunn’s validity index.

    Keywords: Microarray data; Partitioning around medoids; DBSCAN; Normalized weighted Mahalanobis distance; Validity index; Pre-processing; Sampling; Number of clusters

  • Deep Learning based Handwritten Digit Recognition


    Abstract: Neural network and depth learning have been widely used in the field of image processing. Good recognition results are often required for complex network models. But the complex network model makes training difficult and takes a long time. In order to obtain a higher recognition rate with a simple model, the BP neural network and the convolutional neural network are studied separately and verified on the MNIST data set. In order to improve the recognition results further, a combined depth network is proposed and validated on the MNIST dataset. The experimental results show that the recognition effect of the combined depth network is obviously better than that of a single network. A more accurate recognition result is achieved by the combined network.

  • Water Bloom Warning Model Based on Random Forest


    Abstract: Based on the random forest classification algorithm, a warning model of water bloom is proposed. Using the collected data, Select the water quality, meteorological factors which like Chlorophyll a (Chl-a), water temperature (T), PH, nitrogen and phosphorus ratio (TN:TP), chemical oxygen demand (COD), total nitrogen (TN), total phosphorus (TP), dissolved oxygen Light (E) and so on as the impact factor and use them establish a warning model for Water bloom. And compared with the prediction accuracy of neural network model and SVM model. The results show that the water bloom warning model is established by using stochastic forest classification algorithm, the prediction accuracy is slightly higher than other algorithms. And the random forest algorithm has the characteristics of high robustness, China good performance, strong practicability can effectively carry out water bloom early warning.