Hasil Pencarian  ::  Simpan CSV :: Kembali

"Facial detection is a crucial stage in the facial recognition process. Misclassification during the facial detection process will impact recognitionresults. In this research, windowing system facial detection using the Gaborkernel filter and the fast Fourier transform was proposed. The training setimages, for both facial and non-facial images, were processed to obtain thelocal features by using the Gabor kernel filter and the fast Fourier transform.The local features were measured using probabilistic learning vectorquantization. In this process, facial and non-facial features were classifiedusing label 1 and -1. The proposed method was evaluated using facial and non-facial image testing sets, whichwere taken from the MIT+CMU image database. Thetesting images were enhanced first before the detection process using fourdifferent enhancement methods: histogram equalization, adaptive histogram equalization,contrast limited adaptive histogram equalization, and the single-scale retinexmethod. The detection results demonstrated that the highest average accuracywas 83.44%."

"Facial detection is a crucial stage in the facial recognition process. Misclassification during the facial detection process will impact recognition results. In this research, windowing system facial detection using the Gabor kernel filter and the fast Fourier transform was proposed. The training set images, for both facial and non-facial images, were processed to obtain the local features by using the Gabor kernel filter and the fast Fourier transform. The local features were measured using probabilistic learning vector quantization. In this process, facial and non-facial features were classified using label 1 and -1. The proposed method was evaluated using facial and non-facial image testing sets, which were taken from the MIT+CMU image database. The testing images were enhanced first before the detection process using four different enhancement methods: histogram equalization, adaptive histogram equalization, contrast limited adaptive histogram equalization, and the single-scale retinex method. The detection results demonstrated that the highest average accuracy was 83.44%."

"Assessing trustworthiness of social media posts is increasingly important, as the number of online users and activities grows. Current deploying assessment systems measure post trustworthiness as credibility. However, they measure the credibility of all posts, indiscriminately. The credibility concept was intended for news types of posts. Labeling other types of posts with credibility scores may confuse the users. Previous notable works envisioned filtering out non-newsworthy posts before credibility assessment as a key factor towards a more efficient credibility system. Thus, we propose to implement a topic-based supervised learning approach that uses Term Frequency-Interim Document Frequency (TF-IDF) and cosine similarity for filtering out the posts that do not need credibility assessment. Our experimental results show that about 70% of the proposed filtering suggestions are agreed by the users. Such results support the notion of newsworthiness, introduced in the pioneering work of credibility assessment. The topic-based supervised learning approach is shown to provide a viable social network filter."

"In any heterogeneous system, porting reconfigurable computing is often a highperformance platform for a broad range of computationally challenging issues.However, efficiently utilizing the maximum potential of these reconfigurablesystems is a difficult job without understanding their performancecharacteristics. This work proposes an analytic performance model using PetriNets (PN) for a Reconfigurable OR1200 (ROR1200) soft-core processor with modelvalidation and verifications. By modeling the ROR1200 system using Petri Nets,both behavioral and structural properties existing in parallel systems wereanalyzed. The Bound Level Analysis with respect to the dependency level of datais also performed on Soft Core Processors (SCP) like the ROR1200, the OR1200and the MicroBlaze."

"Jurnal ini mengusulkan sebuah model aturan dalam memprediksi prestasi akademik jurusan teknik informatika politeknik poliprofesi medan. Hingga saat ini memprediksi praestasi akademik mahasiwa masih menjadi perdebatan yang hangat di institusi-institusi pendidikan tinggi. Untuk itu sangat penting dibuat sebuah model aturan untuk memprediksi prestasi akademik mahasiswa yang dapat digunakan pihak manajemen sebagai system pendukung dalam pengambilan keputusan. Dalam hal ini algoritma kernel k-means clustering telah digunakan untuk mendapatkan suatu model aturan prediksi prestasi akademik mahasiswa teknik informatika politeknik poliprofesi medan."

"Diabetes is one of themost serious health challenges in both developed and developing countries. Early detection and accurate diagnosis ofdiabetes can reduce the risk of complications. In recent years, the use of machine learning in predicting disease hasgradually increased. A promising classification technique in machinelearning is the use of support vector machines in combination with radial basisfunction kernels (SVM-RBF). In this study, we used SVM-RBF to predict diabetes.The study used a Pima Indian diabetes dataset from the University ofCalifornia, Irvine (UCI) Machine Learning Repository. The subjects were female and ≥ 21 yearsof age at the time of the index examination. Our experiment design used 10-foldcross-validation. Confusion matrix and ROC were used to calculate performanceevaluation. Based on the experimental results, the study demonstrated that SVM-RBFshows promise in aiding diagnosis of Pima Indian diabetes disease in the earlystage."

"In this paper, two highlysensitive photonic crystal fiber (PCF) structures with microstructure core and claddinghave been demonstrated for Ethanol sensing. Themicrostructure core of both proposedPCFs is designed with supplementary holes in an octagonal formation. We have investigated therelative sensitivity and the confinement loss of the proposed PCF structuresemploying a fullvectorial finite element method (FEM). The proposed PCFs work at a widetransmission band covering 0.8 µm to 2 µm and exhibit high sensitivity and lowconfinement loss simultaneously. The numerical analysis shows that the circular shape of air holes in the first ring is a moresalient attribute forincreasing sensitivity and the presence of the square shape of air holes in the first ring showsbetter performance to reduce confinement loss."

"Telecommunication technology is very fast developing.One of them is mobile phone technology.The question is how to detect mobile phone position when it is used,especially in emergency....."

"An efficient Region-Based Image Retrieval (RBIR) system must consider query region determination techniques and target regions in the retrieval process. A query region is a region that must contain a Region of Interest (ROI) or saliency region. A query region determination can be specified manually or automatically. However, manual determination is considered less efficient and tedious for users. The selected query region must determine specific target regions in the image collection to reduce the retrieval time. This study proposes a strategy of query region determination based on the Region Importance Index (RII) value and relative position of the Saliency Region Overlapping Block (SROB) to produce a more efficient RBIR. The entire region is formed by using the mean shift segmentation method. The RII value is calculated based on a percentage of the region area and region distance to the center of the image. Whereas the target regions are determined by considering the relative position of SROB, the performance of the proposed method is tested on a CorelDB dataset. Experimental results show that the proposed method can reduce the Average of Retrieval Time to 0.054 seconds with a 5x5 block size configuration."

"The routine dailyactivities that tend to be sedentary and repetitive may cause severe healthproblems. This issue has encouraged researchers to design a system to detectand record people activities in real time and thus encourage them to do morephysical exercise. By utilizing sensors embedded in a smartphone, many researchstudies have been conducted to try to recognize user activity. The most commonsensors used for this purpose are accelerometers and gyroscopes; however, wefound out that a gravity sensor has significant potential to be utilized aswell. In this paper, we propose a novel method to recognize activities usingthe combination of an accelerometer and gravity sensor. We design a simplehierarchical system with the purpose of developing a more energy efficientapplication to be implemented in smartphones. We achieved an average of 95% forthe activity recognition accuracy, and we also succeed at proving that our workis more energy efficient compared to other works."