International Journal of Computer (IJC)

An Adaptation of DSRC Protocol for V2V Communications in Developing Countries: End-to-End Delay Evaluation

Zongo Meyo, Nlong II Jean Michel, Ndoundam Réné — Sun, 16 Aug 2020 08:02:20 +0000

Vehicular Ad hoc NETworks (VANETs) help in improving road traffic safety and efficiency. In V2V communications, vehicles exchange kinematic information over a suitable protocol in order, either to warn other vehicles of a dangerous situation or inform them about the current status of the traffic flow. When using Wireless Access in Vehicular Environments (WAVE), also referred to as Dedicated Short Range Communication (DSRC) protocol, kinematic information is called Wave Short Messages (WSM), based on Basic Safety Message (BSM) defined by the SAE J2735 dictionary set. BSM is used for safety advertisement, either in one hop or multi-hop broadcasts. However, DSRC evaluations in many urban and sub-urban environments have shown that this protocol is highly sensitive to transmission conditions such as the density and speed of vehicles, antenna position, interference, etc., which makes it difficult to predict its performance. In this paper, we are interested in evaluating, based on various scenarios, the end-to-end delays when a particular emergency vehicle broadcasts BSM to all its nearby vehicles. The results are obtained by modeling and simulating a modified version of the DSRC protocol to fit the Cameroonian environment. Our results reveal that our adapted version of DSRC protocol performs very well and outperform others proposed protocols.

Human Resource Information System with Digital Archiving

Elwin S. Argana, Romy Jun A. Sunico, Virnille C. Francisco — Fri, 21 Aug 2020 06:03:12 +0000

This study aimed to develop an automated tool for Human Resource Information System (HRIS) with security code and verifier integrated module. Rapid Application Development (RAD) Model was used in the planning, creating, deploying, and testing the system. VisualBasic.net, Navicat, and Dezign were utilized in the system development and MySQL as database. The system helps manages employees’ records, in particular, information for leave credits, service records, and training development programs. It also tracks employees' performance and skills and manage the office resources. Using the system evaluation based on the ISO 9126 standard, the system has a high rate of usability (4.27), functionality (4.35), maintainability (4.23), and efficiency (4.30). Thus, the system is believed to provide a significant contribution to the productivity of the Human Resource employees; thereby, generating a due and timely feedback to the administration.

Stationary Wavelet Transform(SWT) Based MRI Images Enhancement and Brain Tumor Segmentation

Aye Min, Nu War — Thu, 27 Aug 2020 06:40:51 +0000

Brain tumor is the anomalous growing of Brain cancer cells. Because of its complex structure, brain tumor segmentation and identification are very difficult tasks in medical field. As with MR image processing, MR images are particularly sensitive to noise, resulting in errors in image acquisition and transmission such as Gaussian noise and impulse noise, etc. MRI image is filtered with Median filter and Wiener filter simultaneously to improve the MR image The Stationary Wavelet Transform (SWT) is then used to combine both Median and Wiener filter results. After preprocessing, Adaptive K-means clustering is used for image segmentation. In the post processing step, morphological operation and Median filter are used to get better segmentation results. This method is applied to the BRATS-2015 dataset, which consists of multi-sequence MRI data available to the public from patients with brain tumors. The well-known, based line methods are compared for comparing the proposed system. Mean Square Error (MSE) and Peak Signal Noise Ratio (PSNR) are used in evaluation of the enhancement. For testing tumor segmentation measures, True Positive Rate (TPR), True Negative Rate (TNR), Accuracy, and Jaccard Similarity Index are used. Compared with dependent line methods and state of the art, this system performs well, especially for the entire tumor area.

SEN-Iot: A Smart Emergency Notification System Suitable for Developing Countries using Internet of Things

Sun, 06 Sep 2020 06:35:23 +0000

Research has shown that disaster effects on properties and lives can be drastically reduced through wide dissemination of information on the impending danger to people at the appropriate time. Generally, the emergency alert systems are usually proactive systems; they are meant to gather data in surrounding using the necessary tools, alert the specified listeners about an impending danger and gives suggestion on the necessary actions to be taken in each situation. In addition, some emergency alert systems also activate automatic responses. Furthermore, the integration of Internet of things (IoT) technology with emergency notification systems is rapidly attracting new discovery in this domain. In this paper, an effective smart emergency notification system named SEN-IoT was design using IOT technology. SEN-IoT was modeled to manage domestic hazard with a scope of water, fire and gas leaks; by creating an emergence notification and immediate response systems. The SEN- IOT was implemented using arduino, sensors and the GSM module. The system was tested for maintainability, functionality, efficiency, usability and reliability, and results revealed that SEN-IoT can effectively handle domestic hazard.

Enhanced Wi-Fi Security of University Premises Using MAC Address and Randomly Generated Password

Tanveer Ahmed, Md. Shafiqul Islam — Tue, 22 Sep 2020 06:38:27 +0000

Many solutions are available for setting up wireless home networks to get internet connectivity working as quickly as possible. It is also quite risky as numerous security problems can result. Today’s Wi-Fi networking products do not always help the situation as configuring their security features, and they can be time-consuming. In this paper, an improved security protocol is proposed for University premises, which is a combination of the process of MAC address filtering and random password generation. If the MAC address match, then the server will send a randomly generated password to the client. As a result, the whole network will face fewer intruders, and the security will be of top-notch. The proposed security solution was compared with the existing four security methods. The proposed solution has universality as the device and software needed for it is available all over the world.

Modelling of Indoor Positioning Systems Based on Location Fingerprinting

Mrindoko R. Nicholaus, Edephonce Nfuka, Kenedy A. Aliila — Tue, 22 Sep 2020 06:48:54 +0000

In recent years, localization systems for indoor vicinity using the present wireless local area (WLAN) network infrastructure have been proposed. Such positioning systems create the usage of location fingerprinting instead of direction or time of arrival techniques for deciding the location of mobile users. However experimental study associated to such localization systems have been proposed, high attenuation and signal scattering related to greater density of wall attenuation still affecting the indoor positioning performance. This paper presents an analytical model for minimizing high signal attenuation effect for WLAN fingerprinting indoor positioning systems. The model employs the probabilistic algorithm that using signal relation method.

Human Face Detection: Manual vs. Kohonen Self Organizing Map

Payal Bose, Prof. Samir K Bandyopadhyay — Mon, 28 Sep 2020 06:08:45 +0000

In today's world it is very much important to maintain the security of information and its risks. The biometric-based techniques are very much useful in these problems. Among the several kinds of biometric-based technique, face detection is much complex and much more important. Due to the age and several other problems, a human face structure changes over time, again a human has lots of expressions. Sometimes due to the lighting condition or the variation of the angle of an input device, the pattern of a human face structure also changed. As a result, the face cannot be detected properly. In this paper, a method is proposed that can detect the human faces both automatically and manually very efficiently. In manual mode, a user can select the input faces referred by the system according to their choice. In automated mode, the system detected all possible face areas using the Kohonen Self-Organizing Feature Map technique. This method reduced the complex color image into a vector quantized image with desired colors. Then a color segmentation technique is used to detect the possible face skin areas from the vector quantized image. Then the Histogram Oriented Gradient technique used to detect the feature from the faces and K-Nearest Neighbor Classifier is used to compare both face images detected by the two modes. The automated method prosed better accuracy than the manual method.

CNN Transfer Learning for Automatic Fruit Recognition for Future Class of Fruit

Israr Hussain, Shunquan Tan, Wajid Ali, Amjad Ali — Thu, 08 Oct 2020 00:00:00 +0000

Deep fruit recognition model learned on big dataset outperform fruit recognition task on difficult unconstrained fruit dataset. But in practice, we are often lack of resources to learn such a complex model, or we only have very limited training samples for a specific fruit recognition task. In this study we address the problem of adding new classes to an existing deep convolutional neural network framework. We extended our prior work for automatic fruit recognition by applying transfer learning techniques to adding new classes to existing model which was trained for 15 different kind of fruits. Pre-trained model was previously trained on a large-scale dataset of 44406 images. To add new class of fruit in our pre-trained model, we need to train a new classifier which will be trained for scratch, on the top of pre-trained model so, that we can re- purpose the feature learned previously for the dataset. Transfer learning using our pre-trained model has been demonstrated to give the best classification accuracy of 95.00%. The experimental results demonstrate that our proposed CNN framework is superior to the previous state-of-the- art networks.

Automatic Paddy Leaf Disease Detection Based on GLCM Using Multiclass Support Vector Machine

Venuja Satgunalingam, Rajeetha Thaneeshan — Fri, 09 Oct 2020 14:45:48 +0000

The paddy leaf diseases have increased rapidly in the recent years because of globalization, environmental pollution and climate changes which reduce the production of rice and economy of the country. For healthy growth of rice plants there is a need of automatic system which can detect the paddy diseases automatically on time to give the proper treatment for the affected plants. In this paper, we proposed a methodology to develop an automatic system for detect the paddy disease which are Paddy Blast Disease, Brown Spot Disease, Narrow Brown Spot Disease using MATLAB. This paper concentrate on the image processing techniques used to enhance the quality of the image and Multiclass Support Vector Machine to classify the paddy diseases. The methodology involves image acquisition, pre-processing, segmentation, feature extraction and classification of the paddy diseases. Image segmentation technique is used to detect infected parts of leaf by using canny edge detection, multilevel thresholding and region growing techniques. We extract texture features using GLCM (grey level co- occurrence matrix) techniques, additionally we extract color and shape features to improve the accuracy of the framework and use Multiclass Support Vector Machine for classification. We achieved 87.5% accuracy for the test dataset.