Computer Science and Information Technologies (E-Journal)
Not a member yet
149 research outputs found
Sort by
Remote-control of multi appliances based latching circuit and DTMF
Get PDFThere are multiple technologies used to remotely control electric appliances like Wi-Fi, Bluetooth, global system for mobile (GSM), and dual-tone multi-frequency (DTMF), but these technologies contain limitations, whether by coverage distance or by the number of devices that are controlled remotely. In this paper, these restrictions were overcome with the use of DTMF and digital latching devices, which doubles the number of remote-controlled electrical appliances compared to other research using the same intended technology DTMF. Using the proposed mechanism in this paper enables the users to effectively control several electric remote devices equal to the standard number of mobile keypad buttons, so in this way, can control 12 devices. This is via the mobile phone by sending commands in the form of analog tones through calling to auto-answer remote control panel phone (RCPP). An interesting feature of this research, each keypad key of the owner mobile (OM) using to control one remote electric device to switch it ON or OFF, so that the first pressing will cause to switch it ON and the second pressing caused to switching it OFF. This method is used instead of using two keypad keys, one for ON and the other for OFF. The proposed idea working is the same as manually switching but here remotely and electronically. This feature is achieved by using a D-latch digital circuit. The work is implemented and tested by using Proteus simulation program
AdMap: a framework for advertising using MapReduce pipeline
Get PDFThere is a vast collection of data for consumers due to tremendous development in digital marketing. For their ads or for consumers to validate nearby services which already are upgraded to the dataset systems, consumers are more concerned with the amount of data. Hence there is a void formed between the producer and the client. To fill that void, there is the need for a framework which can facilitate all the needs for query updating of the data. The present systems have some shortcomings by a vast number of information that each time lead to decision tree-based approach. A systematic solution to the automated incorporation of data into a Hadoop distributed file system (HDFS) warehouse (Hadoop file system) includes a data hub server, a generic data charging mechanism and a metadata model. In our model framework, the database would be able to govern the data processing schema. In the future, as a variety of data is archived, the datalake will play a critical role in managing that data. To order to carry out a planned loading function, the setup files immense catalogue move the datahub server together to attach the miscellaneous details dynamically to its schemas
Exploring and comparing various machine and deep learning technique algorithms to detect domain generation algorithms of malicious variants
Get PDFDomain generation algorithm (DGA) is used as the main source of script in different groups of malwares, which generates the domain names of points and will further be used for command-and-control servers. The security measures usually identify the malware but the domain name algorithms will be updating themselves in order to avoid the less efficient older security detection methods. The reason being the older detection methods does not use either the machine learning or deep learning algorithms to detect the DGAs. Thus, the impact of incorporating the machine learning and deep learning techniques to detect the DGA is well discussed. As a result, they can create a huge number of domains to avoid debar and henceforth, block the hackers and zombie systems with the older methods itself. The main purpose of this research work is to compare and analyse by implementing various machine learning algorithms that suits the respective dataset yielding better results. In this research paper, the obtained dataset is pre-processed and the respective data is processed by different machine learning algorithms such as random forest (RF), support vector machine (SVM), Naive Bayes classifier, H20 AutoML, convolutional neural network (CNN), long short-term memory neural network (LSTM) for the classification. It is observed and understood that the LSTM provides a better classification efficiency of 98% and the H20 AutoML method giving the least efficiency of 75%
Enhancing the fuzzy inference system using genetic algorithm for predicting the optimum production of a scientific publishing house
Get PDFAs a scientific publishing house, Indonesian Institute of Sciences (LIPI) Press' encountered some problems in publication planning, mainly predicting the optimum production of publications. This study aimed to enhance a fuzzy inference system (FIS) parameters using the genetic algorithm (GA). The enhancements led to optimally predict the number of LIPI Press publications for the following year. The predictors used were the number of work units, the number of workers, and the publishing process duration. The dataset covered a five years range of total production of LIPI Press. Firstly, an expert set up the parameters of the fuzzy inference system denoted as a FIS expert. Next, we performed a FIS GA by applying the genetic algorithm and K-fold validation in splitting the training data and testing data. The FIS GA revealed optimum prediction with parameters that were composed of both population size (30), the probability of crossover (0.75), the probability of mutation (0.01), and the number of generations (150). The experiment results show that our enhanced FIS GA outperformed FIS expert approach
Hancitor malware recognition using swarm intelligent technique
Get PDFMalware is a global risk rife designed to destroy computer systems without the owner's knowledge. It is still regarded as the most popular threat that attacks computer systems. Early recognition of unknown malware remains a problem. swarm intelligence (SI), usually customer societies, communicate locally with their domain and with each other. Clients use very simple rules of behavior and the interactions between them lead to smart appearance, noticeable, individual behavior and optimized solution of problem and SI has been successfully applied in many fields, especially for malware ion tasks. SI also saves a considerable amount of time and enhances the precision of the malware recognition system. This paper introduces a malware recognition system for Hancitor malware using the gray wolf optimization (GWO) algorithm and artificial bee colony (ABC) algorithm, which can effectively recognize Hancitor in networks
Classification of mammograms based on features extraction techniques using support vector machine
Get PDFNow mammography can be defined as the most reliable method for early breast cancer detection. The main goal of this study is to design a classifier model to help radiologists to provide a second view to diagnose mammograms. In the proposed system medium filter and binary image with a global threshold have been applied for removing the noise and small artifacts in the pre-processing stage. Secondly, in the segmentation phase, a hybrid bounding box and region growing (HBBRG) algorithm are utilizing to remove pectoral muscles, and then a geometric method has been applied to cut the largest possible square that can be obtained from a mammogram which represents the region of interest (ROI). In the features extraction phase three method was used to prepare texture features to be a suitable introduction to the classification process are first Order (statistical features), local binary patterns (LBP), and gray-level co-occurrence matrix (GLCM), Finally, support vector machine (SVM) has been applied in two-level to classify mammogram images in the first level to normal or abnormal, and then the classification of abnormal once in the second level to the benign or malignant image. The system was tested on the MAIS the mammogram image analysis society (MIAS) database, in addition to the image from the Teaching Oncology Hospital, Medical City in Baghdad, where the results showed achieving an accuracy of 95.454% for the first level and 97.260% for the second level, also, the results of applying the proposed system to the MIAS database alone were achieving an accuracy of 93.105% for the first level and 94.59 for the second level
MLGrafViz: multilingual ontology visualization plug-in for Protégé
Get PDFNatural language processing (NLP) is rapidly increasing in all domains of knowledge acquisition to facilitate different language user. It is required to develop knowledge-based NLP systems to provide better results. Knowledge based systems can be implemented using ontologies where ontology is a collection of terms and concepts arranged taxonomically. The concepts that are visualized graphically are more understandable than in the text form. In this research paper, new multilingual ontology visualization plug-in MLGrafViz is developed to visualize ontologies in different natural languages. This plug-in is developed for Protégé ontology editor. This plug-in allows the user to translate and visualize the core ontology into 135 languages
Virtual assistant upper respiratory tract infection education based natural language
Get PDFThe high incidence of upper respiratory tract infection (URTI) in Indonesia requires an efficient healthcare solution to maintain human wellbeing. The e-health education model proposed in this paper is a virtual assistant in the form of an interactive question and answer system assistant virtual interactive question answering (AVIQA) with a natural language approach. AVIQA is a form of problem-solving approach to design some aspects of education and consultation in helping parents to recognize symptoms and dealing with several preventive ac tions for toddlers when exposed to Upper Respiratory Tract Infection. The technologies proposed for the development of AVIQA include (i) Representation of sentence meanings to build an URTI knowledge base; (ii) Design of dialogue models for interactive consultation using a combination between information state and frame base model and (iii) development of IQA based on casebase reasoning and semantic role labelling. The purpose of developing this technology is to achieve a system that is capable of assisting the users especially mothers in searching for information, reducing user time compared to reading a document, and providing a good advice for finding the right answers, which then can be constructed from a management model prototype information for the education and independent consultation for users. The final result of this study is e-health education system based Indonesian natural language that has an ability in terms of health consultations especially health of children under five in Acute Respiratory Infection disease. This system is expected to have a significant impact on the ability of a mother to recognize symptoms and deal with children attacked by URTI
Numerical approach for extraction of photovoltaic generator single-diode model parameters
Get PDFIn this work, a numerical approach has been proposed to estimate the five single-diode circuit model physical parameters of photovoltaic generators from their experimental current-voltage characteristics. Linear least square method has been used to solve the system of three linear equations to express the shunt resistance, the saturation current and the photocurrent as a function of the series resistance and the ideality factor. Two key points have been used to solve the system of two nonlinear equations to extract values of series resistance and ideality factor. The advantage of the proposed method with respect of existing numerical techniques is that use only two key points of the experimental characteristic and need only two initial guesses and does not use any approximation. To evaluate the proposed method, three PV generators data have been used to compare the experimental and the theoretical curves. The application of the proposed method provides a good agreement with the experimental
Less computational approach to detect QRS complexes in ECG rhythms
Get PDFElectrocardiogram (ECG) signals are normally affected by artifacts that require manual assessment or use of other reference signals. Currently, Cardiographs are used to achieve basic necessary heart rate monitoring in real conditions. This work aims to study and identify main ECG features, QRS complexes, as one of the steps of a comprehensive ECG signal analysis. The proposed algorithm suggested an automatic recognition of QRS complexes in ECG rhythm. This method is designed based on several filter structure composes low pass, difference and summation filters. The filtered signal is fed to an adaptive threshold function to detect QRS complexes. The algorithm was validated and results were checked with experimental data based on sensitivity test