Proceeding of the Electrical Engineering Computer Science and Informatics
Not a member yet
649 research outputs found
Sort by
Neural Network Controller Design for a Mobile Robot Navigation; a Case Study
Get PDFMobile robot are widely applied in various aspect of human life. The main issue of this type of robot is how to navigate safely to reach the goal or finish the assigned task when applied autonomously in dynamic and uncertain environment. The ap- plication of artificial intelligence, namely neural network, can provide a ”brain” for the robot to navigate safely in completing the assigned task. By applying neural network, the complexity of mobile robot control can be reduced by choosing the right model of the system, either from mathematical modeling or directly taken from the input of sensory data information. In this study, we compare the presented methods of previous researches that applies neural network to mobile robot navigation. The comparison is started by considering the right mathematical model for the robot, getting the Jacobian matrix for online training, and giving the achieved input model to the designed neural network layers in order to get the estimated position of the robot. From this literature study, it is concluded that the consideration of both kinematics and dynamics modeling of the robot will result in better performance since the exact parameters of the system are known
Towards Development of a Computerised System for Screening and Monitoring of Diabetic Retinopathy
Get PDFOne of the complications of diabetes can lead to vision problems when it occurs in the retina which is known as diabetic retinopathy (DR). In practice, to diagnose and monitor DR severity, ophthalmologists observe the presence of several pathologies in colour retinal fundus images. However, this approach is tedious and time consuming, especially in the case of screening for early detection. Several techniques have been developed to achieve the final goal that is an automated DR screening system. This paper presents three kinds of approach towards the development of a computerised DR screening and monitoring system. The first approach is pathology-based methods. This approach detects and analyses several pathologies such as microaneurysms, haemorrhages, exudates and changes of retinal vessels. This approach achieves the performance results of more than 90% of accuracy, sensitivity and specificity for detection of the pathologies. The second approach is retinal structure-based methods. This approach detects optic disc, macula and foveal avascular zone (FAZ). The FAZ determination successfully achieves the accuracy of around 97%. DR severity has been proven to have strong correlation up to 0.912 with the enlargement of FAZ. The third approach is deep learning-based methods. This approach has achieved promising results with accuracy of more than 95% in screening and grading the severity of the DR. The third approach offers several advantages compared to the two previous ones in which this approach does not need to specifically detect the presence of pathologies nor the retinal structure to determine DR grade. However, this approach needs huge dataset to learn. The next development is to implement the deep learning based method into a low-cost embedded system
IoT Smart Device for e-Learning Content Sharing on Hybrid Cloud Environment
Get PDFCentralized e-Learning technology has dominated the learning ecosystem that brings a lot of potential usage on media rich learning materials. However, the centralized architecture has their own constraint to support large number of users for accessing large size of learning contents. On the other hand, Content Delivery Network (CDN) solution which relies on distributed architecture provides an alternative solution to eliminate bottleneck access. Although CDN is an effective solution, the implementation of technology is expensive and has less impact for student who lives in limited or non-existence internet access in geographical area. In this paper, we introduce an IoT smart device to provide e-Learning access for content sharing on hybrid cloud environment with distributed peer-to- peer communication solution for data synchronization and updates. The IoT smart device acts as an intermediate device between user and cloud services, and provides content sharing solution without fully depending on the cloud server
Robust and Imperceptible Image Watermarking by DC Coefficients Using Singular Value Decomposition
Get PDFMain problem frequently encountered in all schemes transform domain watermarking technique is the robustness and imperceptibility. Due to achieved optimal result most algorithms of image watermarking using combination two or more transformation domain. This paper proposed Discrete Cosine Transform (DCT) and Singular Value Decomposition (SVD) to embed binary watermark to color Image. Before the message embedded in the color images, we converting RGB to YCbCr color space. Luminance component will be split into sub- block and it has been transformed by DCT to produce DC and AC coefficients. DC coefficients selected as embedding place because it is perceptually usefulness and robust against various attacks. DC coefficients will be collected from every sub-block to create a reference image. Then apply SVD on reference image and embed message in singular values. Various attacks have been implemented and tested due to achieve robustness using Normalized Cross Correlation (NCC) and imperceptibility tested using Peak Signal to Noise Ratio (PSNR). High values of the measurement results show the feasibility of the proposed method. A highest PSNR value resulted 42.3009 dB, whereas a highest NCC values 0.9993 after JPEG Compression
Recommendation System on Knowledge Management System via OAI-PMH
Get PDFKnowledge Management System (KMS) might be a transformation from Library Management System (LMS). This transformation is possible when we add several knowledge processes from KMS not available in LMS. When a KMS is a transformation from a LMS, functionalities derived from librarian system will be also available in KMS. One of this functionality is recommendation system, where patron may receive related and recommended reading, usually based on subject similarity between knowledge documents. However, recommendation is delivered from system directly to patron. There is no recommendation from one system directly to another. This research proposes a communication model to provide recommendation from one KMS to another using LMS interoperability language, OAI-PMH. Although there is no real implementation, authors hope that this model may become a basic reference for a better one. The novelty of this research is how to accommodate recommendation system between KMSs if the interaction is via knowledge sharing protocol, which in this research is OAI-PMH
Development and Evaluation of Android Based Notification System to Determine Patient's Medicine for Pharmaceutical Clinic
Get PDFThe development of science in the field of health clinical pharmacy grows rapidly in recent years. Based on the data from information was obtained that needs to be done a reparation a learning process in clinical pharmacy to produce them who as requested by users pharmaceutical graduates. According to the results of the information there is a problem that in conducting the process of determining the pharmacys drug it can be made a mistake, especially in patients who have complications disease. The process of checking conducted repeatedly to make sure a medicine that is concocted in accordance with a list of the acts of treat a patient, while patient data not yet integrated into a system that could help them in analysis and determine a drug that in accordance. Notification system that developed using android platform this, the hope can become the tools in the form of a system that can give notification to the farmasis easily accessible at any time through gadgets. Based on the results of testing with the methods alpha test can be concluded the number of feasibility this system reached 88.75%. Thus notification system in the determination of medicine patients rule based as a medium learn students pharmaceutical clinic worthy to used
Spoken Word Recognition Using MFCC and Learning Vector Quantization
Get PDFIdentification of spoken word(s) can be used to control external device. This research was result word identification in speech using Mel-Frequency Cepstrum Coefficients (MFCC) and Learning Vector Quantization (LVQ). The output of system operated the computer in certain genre song appropriate with the identified word. Identification was divided into three classes contain words such as "Klasik", "Dangdut" and "Pop", which are used to playing three types of accordingly songs. The voice signal is extracted by using MFCC and then identified using LVQ. The training and test set were obtained from six subjects and 10 times trial of the words "Klasik", "Dangdut" and "Pop" separately. Then the recorded sound signal is pre-processed using Histogram Equalization, DC Removal and Pre-emphasize to reduce noise from the sound signal, and then extracted using MFCC. The frequency spectrum generated from MFCC was identified using LVQ after passing through the training process first. Accuracy of the testing results is 92% for identification of training sets while testing new data recorded using different SNR obtained an accuracy of 46%. However, the test results of new data recorded using the same SNR with training data has an accuracy of 75.5%
Odor Localization using Gas Sensor for Mobile Robot
Get PDFThis paper discusses the odor localization using Fuzzy logic algorithm. The concentrations of the source that is sensed by the gas sensors are used as the inputs of the fuzzy. The output of the Fuzzy logic is used to determine the PWM (Pulse Width Modulation) of driver motors of the robot. The path that the robot should track depends on the PWM of the right and left motors of the robot. When the concentration in the right side of the robot is higher than the middle and the left side, the fuzzy logic will give decision to the robot to move to the right. In that condition, the left motor is in the high speed condition and the right motor is in slow speed condition. Therefore, the robot will move to the right. The experiment was done in a conditioned room using a robot that is equipped with 3 gas sensors. Although the robot is still needed some improvements in accomplishing its task, the result shows that fuzzy algorithms are effective enough in performing odor localization task in mobile robot
Compact Fractal Patch Microstrip Antenna Fed by Coplanar Waveguide for Long Term Evolution Communications
Get PDFThis paper proposes a new design of compact fractal patch microstrip antenna fed by coplanar waveguide to reduce the antenna dimension and to increase its bandwidth for Long Term Evolution application purposes. The results shown return loss of -23.45 dB and VSWR 1.144 can be achieved by controlling the height and the width of the fractal patch dimension. Bandwidth of the proposed antenna is 375 MHz which is equal to an increase of 200% compared to the conventional rectangular patch antenna and also the dimension of fractal patch antenna can be reduced until 66%
Nonlinear Programming Approach of Wireless Pricing Models
Get PDFThe pricing for wireless networks is developed to obtain surplus from subscribers. The linearity factors, elasticity price, price factors are discussed. the new approach of wireless pricing model proposed by previous research are approached by considering the model as the nonlinear programming problem that can be solved optimally using LINGO 13.0. The problem is considered to be nonlinear programming that can be solved using optimization tools. The solutions are expected to give some information about the connections between the acceptance factor and the price. The models attempt to maximize the total price for a connection based on QoS parameter. The maximum goal to maximum price is achieved when the provider set the increment of price change due to QoS change and amount of QoS value. The linearity parameter set up for most cases is obtained in ceiling value. Linear price factor ranges between the prescribed value especially cases when we increase the price change due to QoS change and increase the amount of QoS values