International Journal of Advances in Applied Sciences
Not a member yet
668 research outputs found
Sort by
Improved customer churn prediction model using word order contextualized semantics on customers’ social opinion
Get PDFThrough the hype in digital marketing and the continuous increase in volume and velocity of opinions about an organization’s brands, churn prediction now requires advanced analytics in opinion mining for effective customer behavioral management beyond keywords sentiment analysis (SA). Earlier, by analyzing customers’ opinions using SA models, the extracted positive-negative polarity is used to classify customers as churners or non-churner. In those methods, the impact of word order, context, and the inherent semantics of the clustered opinion set were oftentimes overlooked. However, with the consistent creation of new words with new meanings mapped to existing words on the web, the research extended the fuzzy support vector model (FSVM) to show that the dependency distance between the headword, its dependent, and tail word can be weighted by using information content derived from a corpus to generate four-classed social opinion categories as a strongly positive, positive, negative, and strong negative. These opinion classes formed the basis for the churn category as a premium customer, Inertia customer potential churner, and churner in customer behavioral management. In performance evaluation, aside from engendering quadrupled churn class against the existing churn binary pattern, better accuracy, precision, and recall values were obtained when compared with existing SA works in support vector machine and fuzzy support vector machine (FSVM), respectively.
A new approach to hide texts into images and audio files using steganography and cryptography techniques
Get PDFThese days there are many security issues facing users while they are using the internet for exchanging information among them. And, users use technology devices, such as mobiles and computers, and they connect them to the network and internet. Therefore, users always looking for a safe way to exchange information locally and globally, when they are connecting to a network. Also, these problems lead them to many further issues such as losing privacy, hacking, and detecting personal information. Although, many security techniques have been used to solve these issues by creating many different software utilities; some of them worked perfectly to some extent, while some others still did not comply with the security environment. This research paper finds a new methodology to secure text information while exchanging among permitted users over the internet. This method is a combination of cryptography and steganography with audio and imaging multimedia, which works on hiding and encrypting information before sending it over a network. As result, this technique will add additional security processes to the data exchange, and it will provide a more reliable environment for the user to connect to the network. In addition, the quality of the data will not be altered or noticed during the encryption and decryption process
Cloud computing and 5G challenges and open issues
Get PDFThe obtainable fourth-generation technology (4G) networks have been extensively used in the cloud application and are constantly evolving to match the needs of the future cloud applications. The fifth-generation (5G) networks are probable to immense expand today's cloud that can boost communication operations, cloud security, and network challenges and drive the cloud future to the edge and internet of things (IoT) applications. The existing cloud solutions are facing a number of challenges such as large number of connection of nodes, security, and new standards. This paper reviews the current research state-of-the-art of 5G cloud, key-enabling technologies, and current research trends and challenges in 5G along with cloud application
Interior topology: a new approach in topology
Get PDFThis paper defined a new type of topology known as Interior topology. This work falls among the types of topology (such as general topology, supra topology, generalized topology, and filter) that are motivated by real-world concepts such as the orbits of planets around the sun, electron orbits around the nucleus, and so on. This form of topology is self-contained. The primary objective of this study is to respond to the question “Is general topology capable of producing Interior topology?”. Finally, we define the base for Interior topology which is called i-base
Reducing the cost of energy used for adaptation by using different exterior wall covering materials in Iraq
Get PDFThis paper aimed to study how to reduce the amounts of heat transfer from or to the internal space of the building by covering its external walls with many locally available materials, thus reducing the rate of consumption of electrical energy used in adaptation, which leads to reducing energy consumption costs. The researcher built a model room with dimensions (1 x 1 x 2) m on the third floor of a building in Baghdad (L = 33.2 N), the dimensions of its walls (1 x 2 m) east for the installation of the sample, and the other surfaces are insulated with 200 mm polystyrene sheets. Use a 0.5 ton air conditioner to provide the room thermal comfort. The researcher found that the metal sheet with a thickness of 10 mm and covered with an insulating layer of thermoplastics is considered the best among the materials used in construction, as it saves 57% of the electrical energy consumed in air conditioning. While the use of marble, porcelain, helen stone, and fiberglass slabs with a thickness of 10 mm, comes last because it saves less than 30% of electrical energy
Sono-hydrolysis of banana stem midrib using HY-zeolite from natural sand-based silica as a catalyst
Get PDFBanana stem midrib has the potential as a glucose source through catalytic hydrolysis assisted by ultrasonic (sono-hydrolysis). Besides, natural sand-based silica is the potential as raw material for zeolite synthesis. The purpose of the study was to do two things: i) characterize HY-zeolite made from natural sand-based silica and ii) determine whether HY-zeolite is effective for sono-hydrolysis of banana stem midrib. There was a total of four processes that were carried out, including i) the extraction of silica, ii) the synthesis of HY zeolite, iii) the hydrolysis process, and iv) the glucose content test. The results of the study were gained two things: i) The findings of X-ray fluorescence (XRF), X-ray diffraction (XRD), scanning electron microscopy (SEM), and Fourier transform infrared (FTIR) on HY-zeolite are 2.3 Si/Al, obtained 2 theta and d-spacing data similarities for HY-zeolite, and formed T-O-T, O-T-O (T=Si/Al), and Si-OH groups respectively; and ii) HY-zeolite with ultrasonic was effective for hydrolyzing cellulose into glucose at maximum temperature and time, 55 °C and 6 hours
Determination of microscopic optical properties of agar and Zerdine phantoms at 635 nm using Kubelka-Munk function approach: a numerical study
Get PDFSince the precise and accurate determination of the optical properties of materials is very important for the development and application of optical technology, the investigation of the optical properties of biological tissues with tissue-like phantoms is an important research field in the applications of lasers in medicine. In this study, after directly determining the macroscopic optical properties of the agar and Zerdine phantoms at 635 nm, including the absorbance, transmittance, reflectance, refractive index, and total attenuation coefficient with the single integrating sphere test apparatus; the microscopic optical characterization of these two different soft tissue phantoms were realized at 635 nm by using the Kubelka-Munk function approach. For this, the microscopic optical parameters, which are the absorption coefficient, scattering coefficient, reduced scattering coefficient, and penetration depth, were calculated over these determined macroscopic optical properties
Tri-modal technique for medical images enhancement
Get PDFOwing to methods of acquisition, medical images often require enhancement for them to serve the intended purpose of computer-aided diagnosis. Most medical image enhancement techniques are application specific, leading to the introduction of different enhancement methods for different medical images. In addition, the execution time of most of the previous enhancement methods is longer than necessary. Hence, there is a need for a method that produces fast and satisfactory results when deployed for the enhancement of several medical images. This paper proposes a tri-modal technique, involving a hybrid combination of unsharp masking, logarithmic transformation, and histogram equalization approaches, for medical image enhancement. Three classes of medical images: X-ray, magnetic resonance, and computer tomographic images are used for the evaluations of the proposed tri-modal method, where absolute mean brightness error, peak signal-to-noise ratio, and entropy are utilized as performance metrics. Both qualitative and quantitative evaluations reveal that the proposed tri-modal method performed better than the four previous methods in the literature for the three classes of medical images used in the evaluation. Also, the execution time of the tri-modal technique compares well with those of mono-mode methods. Thus, the tri-modal technique produces better enhanced medical images from different medical image inputs
Chaotic dynamics model based on field-programmable analog array technology
Get PDFEngineering applications in secure communications and encryption based on chaotic signals have attracted a lot of attention in the past decade. This paper presents an extensive study of the chaotic dynamics model of the van der pol oscillator via MATLAB/Simulink simulation and its practical implementation using field-programmable analog matrix techniques. The obtained results show the ease of changing the frequency of the oscillator signal once it is retrieved, creating the required changes, and loading it again according to the required changes. An unlimited number of signals can be generated, allowing them to be used as a chaotic signal oscillator used in many transceiver systems, which require the generation of an unlimited number of such a signal. These research results confirmed that the AN231E04 field-programmable analog array (FPAA) device could be an interesting choice for analog circuit designers, it has the advantage of the ease of use in introducing design changes and testing many critical design solutions
Pedestrian detection system based on deep learning
Get PDFPedestrian detection is a rapidly growing field of computer vision with applications in smart cars, surveillance, automotive safety, and advanced robotics. Most of the success of the last few years has been driven by the rapid growth of deep learning, more efficient tools capable of learning semantic, high-level, deeper features of images are proposed. In this article, we investigated the task of pedestrian detection on roads using models based on convolutional neural networks. We compared the performance of standard state-of-the-art object detectors like Faster region-based convolutional network (R-CNN), single shot detector (SSD), and you only look once, version 3 (YOLOv3). Results show that YOLOv3 is the best object detection model than others for pedestrians in terms of detection and time prediction