International Journal of Engineering Research and Advanced Technology
Not a member yet
478 research outputs found
Sort by
The Web of Things
No full textThe Web of Things may be regarded as an extension of the Internet of Things that leverage Web-based standards and protocols to access and control real-world objects. While the Internet of Things (IoT) empowers communication between heterogeneous devices at the network layer, the web of things (WoT) enables interoperability at the application layer.
This paper provides a brief introduction to the web of things
Multilingual Text Summarization using Deep Learning
No full textAlong with the extreme expansion of big data and the vast development of the internet, making documentation of the huge internet information is the first interest for people. These online textual data led to information overload and redundancy. Multi-document summarization is one of the solutions to such an issue, used to extract the main ideas of the documents and put them into a short summary. Summarizing documents should not affect the major concepts and the meaning of the original text. This paper proposes a new method for multi-document summarization. The basic idea of the proposed method relied on six different features to be extracted of each sentence in the studied collection, these features must be language. A set of the feature vectors is introduced to Convolutional Neural Networks (CNNs) for classification as either summary or non-summary sentences. A graph of summary sentences was generated and assigned scores by the TextRank algorithm. The implemented system was evaluated on both English and Arabic versions of the dataset of the TAC-2011 MultiLing Pilot by using ROUGE metrics. The proposed method achieved an average F-measure 0.46079, 0.20664 using ROUGE-1 and ROUGE-2 respectively, for English documents, and achieved an average F-measure 0.45624, 0.30725 for Arabic documents
Encrypting Image based on Chaotic Map algorithm
No full textDue to the network and multimedia application developments, information security become important since information can be attacked over the transmission channels, and the combination of cryptography and chaotic become an important field of information security, where many encryption algorithms are based on chaotic mapping due to the inherent features of Image like high redundancy and bulk data capacity. In this paper, three chaotic maps are used to achieve a good diffused Image by setting the initial conditions to generate the shuffling sequence randomly by 2D Zaslevskii map and employ them in 2D cat map for shuffling the image pixels positions; also baker map is used to decomposed Image into four rectangles and shuffle them.
For increasing the levels of security related to the encryption algorithm, the Gaffe random key generator is used to generate 128 bits keys and employ it with an exclusive-OR equation to the diffused Image. The results indicated that the combination of chaotic and cryptography proved to be good for the high-security level. The experimental results have shown that the suggested algorithm is secure due to the large key space and the high sensitivity to the secret key. This paper applies a chaotic map algorithm by Mat lab a program
An Approach for Multi-Document Text Summarization Using Extreme Learning Machine and LexRank
No full textDue to the exponential growth of online textual data and the variety of its sources, there is a need to produce an accurate text summary with the least time and effort. Extractive multi-document text summarization methods are intended to automatically generate summaries from a document collection, covering the main content and avoiding redundant information. In this study, a new method for extractive multi-document summarization has been proposed based on the combination of supervised and unsupervised learning. Throughout the supervised learning, a set of seven features was extracted from each sentence in the document collection and introduces to the Extreme Learning Machine (ELM), to distinguish between important and unimportant sentences. A graph of important sentences was generated and assigned scores by the LexRank algorithm during the unsupervised learning. The performance of the proposed method on the DUC-2002 dataset was calculated using ROUGE evaluation metrics. The proposed method achieved a 0.47472 ROUGE for 200-word summaries and 0.54641 ROUGE for 400-word summaries
Planning of Heavy Equipment Fabrication Plant Layout using CORELAP Software: A case study of Indonesia
No full textAccording to the target, PT Heavy Equipment Ternama needs a good and smooth production system to support the fabrication process. Often the delivery time for boom components is not by the predetermined target, so it is necessary to improve to support the delivery target to the customer on time because the welding process is not optimal. The Engineering Department invests by adding one welding robot unit to support the production process to match the target. The addition of these new facilities requires re-planning the boom component processes and maximizing the distance between processes, which are currently less efficient, marked by long distances, and requiring a long time to move components between processes. The purpose of this research is to propose to improve the best factory layout with a comparison of the total distance of material movement between the initial layout and the proposed layout, which has an impact on changes in material handling costs. This study uses the CORELAP (Computerized Relationship Layout Planning) method to determine the best factory layout. The proposed new layout is the location between processes into one Production Line, which was previously on different Production Lines. This has an impact on reducing handling costs for one product which was originally Rp. 2,875,040 to Rp. 998,240 or decreased by 65% , and the handling distance, which was originally 162m, became 98m or decreased by 39.5% compared to the initial layout. PT Heavy Equipment Ternama from January to March 2020 can save handling costs of Rp. 296,534,400
The Use of Input Words Vectors to Detect Crowd Region in Images
No full textHuman crowd analysis has common utilizations from the urban engineering and traffic management to law enforcement. They all need a crowd for first being detected, and is the issue that has been dealt with in the present study. Considering an image, the algorithm that has been proposed in this paper performs a segmentation of that image to crowd and non-crowd areas. The fundamental concept is capturing two main characteristics of the crowd: (a) on a narrower scale, its main elements have to appear like humans (only weakly so, as a result of the low resolution, dressing variations, occlusion, and so on), whereas (b) on the wider scale, the crowd intrinsically includes elements of the redundant appearance. The proposed approach makes use of that through the utilization of underlying statistical framework which has been based on the quantized features of the SURF. The two previously mentioned characteristics of the crowds have been obtained through the resultant statistical model responses’ feature vector, which describe the level of crowd-like appearances around the location of an image with the increase of the spatial level around it
Subject Review: Image Encryption Based on Multi Techniques
No full textThe enormous advancements in the communication networks, particularly the internet networks, that employed to allow numerous individuals to exchange various forms of data, the Security of data has become a big issue. As a result, the usage of cipherment and decipherment ways is becoming more popular. Sundry cipherment means have been created to ensure data security, the chaos encryption system being one of the most widely employed in recent years. In this research, a review of diverse image cipherment algorithms has been reviewed, which researchers can gain insight into the most efficient techniques to employ
Artificial intelligence (A.I.) in Social Sciences: A Primer
No full textArtificial intelligence (AI) is the intelligence exhibited by machines which can do similar work with human consciousness. It refers to systems that can perform tasks that in the past had required human intelligence. AI is now being used in an ever-growing range of human activities. The proliferation of AI technologies is yielding substantial societal benefits, ranging from more efficient supply chain management to more reliable medical diagnosis. This paper is a primer on the uses of AI in social sciences
CFD Analysis of Wind-induced Pollutant Dispersion in Built Environment
No full textThe paper analyzed the wind-induced pollutant dispersion in a built environment using computational fluid dynamics simulation. SF6 was used as the tracer gas released from a roof stack. The steady-state analysis used to develop the adaptive mesh was carried out using the RNG-KE turbulence model. The computational domain and boundary condition for the wind flow on the urban area was adopted as recommended by the Cost guideline. Also, the SF6 species was modeled as a passive scalar transport convection-diffusion equation. From the result, it was observed that the funnel effect and vortex shedding effect reduces the concentration level of pollutants within a locality
Analysis Critical Success Factor for Toll Road Performance Improvement with Dynamic Model
No full textIn toll road construction, all aspects need to be considered, from planning, implementing, and meeting minimum service standards during operations. In addition, to reduce the risk of toll road project investment by reducing the risk of rework. Repetitive work (rework) has a direct and indirect impact on project performance which has an impact on costs, rework is also a very significant contributor to waste or additional time which results in the completion of the project schedule. This research answers the factors related to the increase in cost and time performance. Cost-related research discusses rework modeling using the System Dynamic and time-related research using the Line of Ballance. Rework is a problem in construction that can be caused by many interrelated aspects that are not taken into account in planning. Rework modeling using a System Dynamic can provide simulations to get the best results. The research obtained 12 outcome factors that affect cost and time performance on a toll road project, a dynamic system implementation can provide optimal solutions with the ability to reduce the proportion of the number of rework by 23.11% for 42 month