• ETRI Journal
• /
• v.41 no.4
• /
• pp.494-505
• /
• 2019

In this paper, we propose a new framework for detecting the unauthorized dumping of garbage in real-world surveillance camera. Although several action/behavior recognition methods have been investigated, these studies are hardly applicable to real-world scenarios because they are mainly focused on well-refined datasets. Because the dumping actions in the real-world take a variety of forms, building a new method to disclose the actions instead of exploiting previous approaches is a better strategy. We detected the dumping action by the change in relation between a person and the object being held by them. To find the person-held object of indefinite form, we used a background subtraction algorithm and human joint estimation. The person-held object was then tracked and the relation model between the joints and objects was built. Finally, the dumping action was detected through the voting-based decision module. In the experiments, we show the effectiveness of the proposed method by testing on real-world videos containing various dumping actions. In addition, the proposed framework is implemented in a real-time monitoring system through a fast online algorithm.

• Structural Engineering and Mechanics
• /
• v.64 no.4
• /
• pp.427-436
• /
• 2017

Concrete technologists have used ultrasonic pulse velocity test for decades to evaluate the properties of concrete. However, the presented research work focuses on the use of ultrasonic pulse velocity test to study the degradation in steel-concrete bond subjected to increasing loading. A detailed experimental investigation was conducted by testing five identical beam specimens under increasing loading. The loading was increased from zero till failure in equal increments. From the experimentation, it was found that as the reinforced concrete beams were stressed from control unloaded condition till complete failure, the propagating ultrasonic wave velocity reduced. This reduction in wave velocity is attributed to the initiation, development, and propagation of internal cracking in the concrete surrounding the steel reinforcement. Using both direct and semidirect methods of testing, results of reduction in wave velocity with evidence of internal cracking at steel-concrete interface are presented. From the presented results and discussion, it can be concluded that the UPV test method can be successfully employed to identify zones of poor bonding along the length of reinforced concrete beam. The information gathered by such testing can be used by engineers for localizing repairs thereby leading to saving of time, labor and cost of repairs. Furthermore, the implementation strategy along with real-world challenges associated with the application of the proposed technique and area of future development have also been presented.

• Structural Engineering and Mechanics
• /
• v.74 no.3
• /
• pp.313-323
• /
• 2020

Non-destructive tests are commonly used in construction industry to access the quality and strength of concrete. However, till date there is no non-destructive testing method that can be adopted to evaluate the bond condition of reinforced concrete beams. In this regard, the presented research work details the use of ultra-sonic pulse velocity test method to evaluate the bond condition of reinforced concrete beam. A detailed experimental research was conducted by testing four identical reinforced concrete beam samples. The samples were loaded in equal increments till failure and ultra-sonic pulse velocity readings were recorded along the length of the beam element. It was observed from experimentation that as the cracks developed in the sample, the ultra-sonic wave velocity reduced for the same path length. This reduction in wave velocity was used to identify the initiation, development and propagation of internal micro-cracks along the length of reinforcement. Using the developed experimental methodology, researchers were able to identify weak spots in bond along the length of the specimen. The proposed method can be adopted by engineers to access the quality of bond for steel reinforcement in beam members. This allows engineers to carryout localized repairs thereby resulting in reduction of time, cost and labor needed for strengthening. Furthermore, the methodology to apply the proposed technique in real-world along with various challenges associated with its application have also been highlighted.

• Membrane and Water Treatment
• /
• v.2 no.2
• /
• pp.121-136
• /
• 2011

A bench-scale test has recently been proposed as a predictive tool to minimize the scope of pilot-scale testing or to optimize the operation of full-scale membrane filtration systems. Consequently, a bench-scale testing unit was developed for this purpose and systematically evaluated in this study. This unit was capable of accommodating commercially available, low pressure, hollow fiber (LPHF) membranes with various configurations for testing under conditions comparable to real-world applications. Reproducibility of this unit in assessing membrane fouling and microbial removal efficiency of LPHF membranes was tested and statistically comparable results were obtained. This unit serves as a useful apparatus for academic researchers and utilities to evaluate the performance of LPHF membranes used for water treatment.

• Journal of Information Processing Systems
• /
• v.6 no.1
• /
• pp.21-32
• /
• 2010

Software maintenance is one of the major activities of the software development life cycle. Due to the time and cost constraint it is not possible to perform exhaustive regression testing. Thus, there is a need for a technique that selects and prioritizes the effective and important test cases so that the testing effort is reduced. In an analogous study we have proposed a new variable based algorithm that works on variables using the hybrid technique. However, in the real world the programs consist of multiple modules. Hence, in this work we propose a regression testing algorithm that works on interprocedural programs. In order to validate and analyze this technique we have used various programs. The result shows that the performance and accuracy of this technique is very high.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2015.10a
• /
• pp.227-229
• /
• 2015

Training students to use a Marine VHF presents challenges because materials are either out of date or cost prohibitive. It is also difficult to teach in a "real world" setting. This presentation gives a few ideas of how to give practical training and a fair testing method.

• Asian Pacific Journal of Cancer Prevention
• /
• v.17 no.7
• /
• pp.3385-3390
• /
• 2016

Background: Sequential use of circulating prostate cell (CPC) detection has been reported to potentially decrease the number of unnecessary prostate biopsies in men suspected of prostate cancer. In order to determine the real world effectiveness of the test, we present a prospective study of men referred to two hospitals from primary care physicians, one using CPC detection to determine the necessity of prostate biopsy the other not doing so. Materials and Methods: Men with a suspicion of prostate cancer because of elevated PSA >4.0ng/ml or abnormal DRE were referred to Hospitals A or B. In Hospital A all underwent 12 core TRUS biopsy, in Hospital B only men CPC (+), with mononuclear cells obtained by differential gel centrifugation identified using double immunomarking with anti-PSA and anti-P504S, were recommended to undergo TRUS biopsy. Biopsies were classifed as cancer or no-cancer. Diagnostic yields were calculated, including the number of posible biopsies that could be avoided and the number of clinically significant cancers that would be missed. Results: Totals of 649 men attended Hospital A, and 552 men attended Hospital B; there were no significant differences in age or serum PSA levels. In Hospital A, 228 (35.1%) men had prostate cancer detected, CPC detection had a sensitivity of 80.7%, a specificity of 88.6%, and a negative predictive value of 89.5%. Some 39/44 men CPC negative with a positive biopsy had low grade small volume tumors. In Hospital B, 316 (57.2%) underwent biopsy. There were no significant differences between populations in terms of CPC and biopsy results. The reduction in the number of biopsies was 40%. Conclusions: The use of sequential CPC testing in the real world gives a clear decision structure for patient management and can reduce the number of biopsies considerably.

• Korean Journal of Radiology
• /
• v.22 no.3
• /
• pp.442-453
• /
• 2021

Artificial intelligence (AI) will likely affect various fields of medicine. This article aims to explain the fundamental principles of clinical validation, device approval, and insurance coverage decisions of AI algorithms for medical diagnosis and prediction. Discrimination accuracy of AI algorithms is often evaluated with the Dice similarity coefficient, sensitivity, specificity, and traditional or free-response receiver operating characteristic curves. Calibration accuracy should also be assessed, especially for algorithms that provide probabilities to users. As current AI algorithms have limited generalizability to real-world practice, clinical validation of AI should put it to proper external testing and assisting roles. External testing could adopt diagnostic case-control or diagnostic cohort designs. A diagnostic case-control study evaluates the technical validity/accuracy of AI while the latter tests the clinical validity/accuracy of AI in samples representing target patients in real-world clinical scenarios. Ultimate clinical validation of AI requires evaluations of its impact on patient outcomes, referred to as clinical utility, and for which randomized clinical trials are ideal. Device approval of AI is typically granted with proof of technical validity/accuracy and thus does not intend to directly indicate if AI is beneficial for patient care or if it improves patient outcomes. Neither can it categorically address the issue of limited generalizability of AI. After achieving device approval, it is up to medical professionals to determine if the approved AI algorithms are beneficial for real-world patient care. Insurance coverage decisions generally require a demonstration of clinical utility that the use of AI has improved patient outcomes.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.26 no.2
• /
• pp.533-540
• /
• 2016

It is important to establish the environment for cyber warrior training, testing support and effectiveness analysis in order to cope with sharply increasing cyber threat. However, those practices cannot be easily performed in real world and are followed with many constraints. In this paper, we propose a live/virtual M&S-based system for training/testing and constructive M&S-based system for effectiveness analysis to provide an environment similar to real world. These can be utilized to strengthen the capability to carry out cyber war and analyze the impact of cyber threat under the large-scale networks.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.9
• /
• pp.3885-3906
• /
• 2020

Hybrid fuzzing which combines fuzzing and concolic execution, has proved its ability to achieve higher code coverage and therefore find more bugs. However, current hybrid fuzzers usually suffer from inefficiency and poor scalability when applied to complex, real-world program testing. We observed that the performance bottleneck is the inefficient cooperation between the fuzzer and concolic executor and the slow symbolic emulation. In this paper, we propose a novel solution named EPfuzzer to improve hybrid fuzzing. EPfuzzer implements two key ideas: 1) only the hardest-to-reach branch will be prioritized for concolic execution to avoid generating uninteresting inputs; and 2) only input bytes relevant to the target branch to be flipped will be symbolized to reduce the overhead of the symbolic emulation. With these optimizations, EPfuzzer can be efficiently targeted to the hardest-to-reach branch. We evaluated EPfuzzer with three sets of programs: five real-world applications and two popular benchmarks (LAVA-M and the Google Fuzzer Test Suite). The evaluation results showed that EPfuzzer was much more efficient and scalable than the state-of-the-art concolic execution engine (QSYM). EPfuzzer was able to find more bugs and achieve better code coverage. In addition, we discovered seven previously unknown security bugs in five real-world programs and reported them to the vendors.