This paper describes a method for learning anomaly behavior in the video by finding an attention region from spatiotemporal information, in contrast to the full-frame learning. In our proposed method, a robust background subtraction (BG) for extracting motion, indicating the location of attention regions is employed. The resulting regions are finally fed into a three-dimensional Convolutional Neural Network (3D CNN). Specifically, by taking advantage of C3D (Convolution 3-dimensional), to completely exploit spatiotemporal relation, a deep convolution network is developed to distinguish normal and anomalous events. Our system is trained and tested against a large-scale UCF-Crime anomaly dataset for validating its effectiveness. This dataset contains 1900 long and untrimmed real-world surveillance videos and splits into 950 anomaly events and 950 normal events, respectively. In total, there are approximately ~ 13 million frames are learned during the training and testing phase. As shown in the experiments section, in terms of accuracy, the proposed visual attention model can obtain 99.25 accuracies. From the industrial application point of view, the extraction of this attention region can assist the security officer on focusing on the corresponding anomaly region, instead of a wider, full-framed inspection.
The convolutional neural network (CNN) has shown excellent benefits in the classification of objects in the latest years. An important job in the context of intelligent transportation is to properly identify and classify vehicles from videos into various kinds (e.g., car, truck, bus, etc.). For monitoring, tracking and counting purposes, the classified vehicles can be further evaluated. At least two major difficulties stay, however; excluding the uninteresting area (e.g., swinging movement, noise, etc.) and designing an effective and precise system. In order to obviously differentiate the interesting region (moving car) from the uninteresting region (the rest of the area), we introduce a novel attention-based approach. Finally, to significantly increase the classification efficiency, we feed the deep CNN with the respective interesting region. We use several challenging outdoor sequences from the CDNET 2014 (baseline, bad weather and camera jitter classes), and our own dataset to assess the proposed approach. Experimental results show that it costs around ∼85 fps in GPU (and ∼50 fps in CPU) to classify moving vehicles and maintaining a highly accurate rate. Compared with other state-of-the-art object detection approaches, our method obtains a competitive detection accuracy. In addition, we also verify the result of the proposed approach by comparing with recent 3D CNN method, called saliency tubes. INDEX TERMS Attention approach, convolutional neural network (CNN), smart transportation, vehicle type classification.
ABSTRAKPenelitian ini bertujuan untuk menganalisis pengaruh Pendidikan, Pendapatan dan Jumlah Anggota Keluarga terhadap Pengeluaran Keluarga. Data yang digunakan dalam penelitian ini adalah data primer yang diperoleh dari hasil wawancara dengan panduan kuesioner atau angket. Jumlah sampel yang dipakai adalah 99 KK, diambil menggunakan metodeproporsional random sampling. Teknik analisis yang digunakan dalam penelitian ini adalah uji statistik dengan metode regresi linear berganda dan uji hipotesis menggunakan uji F dan uji t, namun sebelum melakukan uji hipotesis dilakukan uji asumsi klasik terlebih dahulu. Hasil penelitian menunjukkan bahwa variabel pendidikan dan pendapatan berpengaruh positif dan signifikan terhadap pengeluaran keluarga. Serta variabel jumlah anggota keluarga berpengaruh positif dan tidak signifikan terhadap pengeluaran keluarga. Variabel yang memiliki pengaruh paling dominan terhadap pengeluaran adalah variabel pendapatan. Dari penelitian ini diperoleh nilai R 2 sebesar 0.398, hal tersebut berarti bahwa 39.8% variabel pengeluaran keluarga dapat dijelaskan oleh variabel independen nya yaitu pendidikan, pendapatan dan jumlah anggota keluarga. Sisanya yaitu 60.9% dijelaskan oleh variabel-variabel yang lain diluar model atau di luar variabel. ABSTRACT This study aims to analyze the effect of Education, Income and Number of FamilyMembers on Family Expenditures. The data used in this study are primary data obtained from interviews with questionnaire or questionnaire guidelines. The number of samples used was 99 households, taken using the proportional random sampling method. The analysis technique used in this study is a statistical test with multiple linear regression methods and hypothesis testing using the F test and t test, but before conducting the hypothesis test the classical assumption test is done first. The results showed that education and income variables had a positive and significant effect on family expenses. And the variable number of family members has a positive and not significant effect on family expenses. The variable that has the most dominant influence on expenditure is the income variable. From this study an R2 value of 0.398 was obtained, which means that 39.8% of the family expenditure variable can be explained by the independent variables namely education, income and the number of family members. The remaining 60.9% is explained by other variables outside the model or outside the variables.
Marble, one of natural stone, has been widely produced since the last decade. In South Aceh, Marble stone is fabricated at Marble Production Unit that is located around Polytechnic of Aceh Selatan. The using of large-scale stone-cutting machines in Marble Production process tends to be a major noise source in Polytechnic of Aceh Selatan environment. The aim of this study is to analyze the noise level generated by Marble Cutting Machine in Marble Production Unit. The noise levels were analyzed by measuring Background Noise Level (BNL) and Sound Pressure Level (SPL). Sound Level Meter Type SL-814 was employed in the measurement. The results show that Background Noise Level measured is 53.03 dB on average. The highest Sound Pressure Level measured when the marble cutting machine was operated without workpiece is 94dB. In addition, the highest sound pressure level measured when marble cutting machine was operated with the workpiece is 96 dB. The values have generally exceeded the Threshold Noise Level allowed for education area, 55 dB. The noisy condition in campus environment would have an impact on teaching and learning processes within the Polytechnic of South Aceh.
Bar straightness is one of several factors that can affect the quality of the strain wave signal in a Split Hopkinson Pressure Bar (SHPB). Recently, it was found that the bar components of the SHPB at the Lightweight Structures Laboratory displayed a deviation in straightness because of manufacturing limitations. An evaluation was needed to determine whether the strain wave signals produced from this SHPB are acceptable or not. A numerical model was developed to investigate this effect. In this paper, experimental work was performed to evaluate the quality of the signal in the SHPB and to validate the numerical model. Good agreement between the experimental results and the numerical results was obtained for the strain rates and stress-strain relationship for mild steel ST37 and aluminum 6061 specimen materials. The recommended bar straightness tolerance is proposed as 0.36 mm per 100 mm.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.