Search Results

This paper presents a solution that automates Abaca fiber grading which would help the time-consuming baling of Abaca fiber produce. The study introduces an objective instrument paired with a system to automate the grade classification of Abaca fiber using Convolutional Neural Network (CNN). In this study, 140 sample images of abaca fibers were used, which…

Increasing the telecommunications products that allow Vector Network Analyzer is becoming more common tools to measure the S-Parameter. It will be an absolute number from the S-Parameter measurements produced in real and imaginary, other words it is also known as the product of the calculation. The calculation findings do not include the systematic and random…

As many digital documents are required in various environments, paper documents are digitized by scanner, fax, digital camera and specific software. In the case of a scanned document, we need to check whether the document is right sided or upside down because the orientation of the scanned document is determined by the orientation in which…

Fraud, as regards means of payment, means the behavior of any legal or natural one that makes an abnormal or irregular use of a way of payment, elements of it or information contained therein, to improperly obtain an honest, service or enrichment, and or causing financial damage to the one that has distributed the means…

Time-series is a sequence of observations that are taken sequentially over time. Modelling a system that generates a future value from past observations is considered as time-series forecasting system. Recurrent neural network is a machine learning method that is widely used in the prediction of future values. Due to variant improvements on recurrent neural networks,…

Blurred small objects produced by cropping, warping, or intrinsically so, are challenging to detect and classify. Therefore, much recent research is focused on feature extraction built on Faster R-CNN and follow-up systems. In particular, RPN, SPP, FPN, SSD, and DSSD are the layered feature extraction methods for multiple object detections and small objects. However, super-resolution…

Bull service is the natural copulation by a purebred male carabao with a female counterpart. This is part of the bull loan agenda of the Philippine Carabao Center-Visayas State University (PCC-VSU), one of the 12 regional centers of PCC. For the past years, PCC-VSU used averaging of bull services count of previous years and sometimes…

In this article, a new form of UWB (ultra-wide-band) antenna operating to the desired specifications, obtained from a base antenna to which some modifications are made. The proximity of the antennas causes a mutual coupling phenomenon thus generating an apparent modification of their characteristics. It is therefore crucial to have the minimum level of insulation…

Middleboxes like load balancers are being used by all the corporations to manage and support their infrastructures. These devices see a large amount of bandwidth every day. This might include a range of protocols which might be varying from network layer to the application layer. This traffic can be corrupt or malicious thus causing these…

Recurrent Neural Networks has been widely used by researchers in the domain of weather prediction. Weather Prediction is forecasting the atmosphere for the future. In this proposed paper, Deep LSTM networks has been implemented which is the variant of RNNs having additional memory block and gates making them capable of remembering long term dependencies. Fifteen…

Many real-life applications based on the wireless sensor networks are equipped with data aggregation mechanisms for suppressing or even overcoming negative environmental effects and data redundancy. In this paper, we present an extended analysis of the linear average consensus algorithm for distributed summing with bounded execution over wireless sensor networks. We compare a centralized and…

As an emergent technology in Internet of Things (IoT), the ultimate target of fog computing is to provide a widely distributed computational resources and data repository closer to the network edge providing heterogeneous systems both in terms of software and hardware. The fog system must have the capability to deal with huge number of resources…

An emerging trend has been observed in the Trust and Reputation (T & R) systems in field of decision-making support for a majority of the provisions propagated by the Internet. It is the extreme importance that peers (users) are able to trust each other and rely on them for file sharing and for services. This…

This article develops the design and implementation of an industrial network for the control and supervision of the process of dispatching acetic acid, which aims to reduce the presence of this chemical in the environment, since the process is activated manually by the operators; what generates a lack of precision in several stages of the…

Recently, opportunistic networks are considered as one of the most attractive developments of ad hoc mobile networks (MANETs) that have emerged thanks to the development of intelligent devices. Due to the mobility-related instability of the paths between nodes and due to the limited buffer and energy resources, the ultimate objective of routing protocols in opportunistic…

In more recent times, researchers have turned their attention to link prediction and the role link inference can play in better understanding the evolutionary nature of social networking sites. The objective of this paper is to present an in-depth review, analysis, and discussion of the cutting-edge link prediction methods that can be applied to better…

This paper proposes a new classification model distinguishing four classes of attacks in Wireless Sensor Networks (WSNs) namely: attacks based on the protocol stack, on the capability of the attacker, on the attack impacts and on the attack target. Then, it presents and classifies the most known attacks in WSNs based the proposed model. Simulations…

This paper presents the setup of eye tracking calibration methodology and the preliminary test results of the training model from the eye tracking data. Eye tracking requires good accuracy from the calibration process of the human eyes feature extraction from facial region. Viola-Jones algorithm is applied for this purpose by using Haar Basic feature filters…

This paper addresses the generation of stylized texts in a multilingual setup. A long short-term memory (LSTM) language model with extended phonetic and semantic embeddings is shown to capture poetic style when trained end-to-end without any expert knowledge. Phonetics seems to have a comparable contribution to the overall model performance as the information on the…

In an enterprise Wifi network, indoor and dense, co-channel interference is a major issue. Wifi controllers help tackle this problem thanks to radio resource management (RRM). RRM is a fundamental building block of any controller functional architecture. One aim of RRM is to process the radio plan such as to maximize the overall network transmit…

Wireless sensor networks (WSNs) are considered to be the currently flourishing scientific domain, thereby found to be applicable in numerous industrial and domestic applications. As per the mathematical results in Pulse-coupled oscillator (PCO), it has been predicted that, numerous iterations are needed for convergence, leading to increased power consumption. Biologically inspired solutions are greatly applicable…

TransJakarta is one of the methods to reduce congestion in Jakarta. However, the number of TransJakarta users compared to number of private vehicle users is very small, only 24% of the total population in Jakarta. The purpose of this research is to know public opinions about TransJakarta whether positive or negative by doing sentiment analysis…

We present findings on classifying the class of executable code using convolutional, re- current neural networks by creating images from only the .text section of executables and dividing them into standard-size windows, using minimal preprocessing. We achieve up to 98.24% testing accuracy on classifying 9 types of malware, and 99.50% testing accuracy on classifying malicious…

Spatial and temporal isolation is a crucial issue in embedded systems executing multiple tasks with several levels of criticality. This is considerably significant in the context of multi-processor (or multi-core) embedded systems running multiple mixed-criticality applications in parallel. This work deals with the issue of isolation of different application classes on Network on Chip (NoC)…

An artificial neural network (ANN) computing system can be significantly influenced by its implementation type. The software implemented ANN can produce high accuracy output with slow computation time performance compared to hardware implemented ANN which runs at a faster computation time but with low accuracy. Normally, software implementation reduces the proficiency and efficiency of the…