Computer vision based decision support tool for hydro-dams surface deterioration assessment and visualization using fuzzy sets and pseudo-coloring

Clinical Decision Support Tools

It has been established that varicose veins are better visualized with infrared photography. As near-infrared films are nowadays hard to get and to develop in the digital world, we investigated the use of digital photography of varicose veins. Topics that are discussed are illumination setup, photography and digital image enhancement and analysis.

Gentle remediation options (GRO) are risk management strategies/technologies that result in a net gain (or at least no gross reduction) in soil function as well as risk management. They encompass a number of technologies, including the use of plant (phyto‐), fungi (myco‐), and/or bacteria‐based methods, with or without chemical soil additives or amendments, for reducing contaminant transfer to local receptors by in situ stabilization, or extraction, transformation, or degradation of contaminants. Despite offering strong benefits in terms of risk management, deployment costs, and sustainability for a range of site problems, the application of GRO as practical on‐site remedial solutions is still in its relative infancy, particularly for metal(loid)‐contaminated sites. A key barrier to wider adoption of GRO relates to general uncertainties and lack of stakeholder confidence in (and indeed knowledge of) the feasibility or reliability of GRO as practical risk management solutions. The GREENLAND project has therefore developed a simple and transparent decision support framework for promoting the appropriate use of gentle remediation options and encouraging participation of stakeholders, supplemented by a set of specific design aids for use when GRO appear to be a viable option. The framework is presented as a three phased model or Decision Support Tool (DST), in the form of a Microsoft Excel‐based workbook, designed to inform decision‐making and options appraisal during the selection of remedial approaches for contaminated sites. The DST acts as a simple decision support and stakeholder engagement tool for the application of GRO, providing a context for GRO application (particularly where soft end‐use of remediated land is envisaged), quick reference tables (including an economic cost calculator), and supporting information and technical guidance drawing on practical examples of effective GRO application at trace metal(loid) contaminated sites across Europe. This article introduces the decision support framework. ©2015 Wiley Periodicals, Inc.

In this paper, we systematically review recent advances in surface inspection using computer vision andimage processing techniques, particularly those based on texture analysis methods. The aim is to reviewthe state-of-the-art techniques for the purposes of visual inspection and decision making schemes that areable to discriminate the features extracted from normal and defective regions. This field is so vast that itis impossible to cover all the aspects of visual inspection. This paper focuses on a particular but importantsubset which generally treats visual surface inspection as texture analysis problems. Other topics related tovisual inspection such as imaging system and data acquisition are out of the scope of this survey.The surface defects are loosely separated into two types. One is local textural irregularities which is themain concern for most visual surface inspection applications. The other is global deviation of colour and/ortexture, where local pattern or texture does not exhibit abnormalities. We refer this type of defects as shadeor tonality problem. The second type of defects have been largely neglected until recently, particularly whencolour imaging system has been widely used in visual inspection and where chromatic consistency plays animportant role in quality control. The emphasis of this survey though is still on detecting local abnormalities,given the fact that majority of the reported works are dealing with the first type of defects.The techniques used to inspect textural abnormalities are discussed in four categories, statistical approaches,structural approaches, filter based methods, and model based approaches, with a comprehensivelist of references to some recent works. Due to rising demand and practice of colour texture analysis inapplication to visual inspection, those works that are dealing with colour texture analysis are discussedseparately. It is also worth noting that processing vector-valued data has its unique challenges, which conventionalsurface inspection methods have often ignored or do not encounter.We also compare classification approaches with novelty detection approaches at the decision makingstage. Classification approaches often require supervised training and usually provide better performancethan novelty detection based approaches where training is only carried out on defect-free samples. However,novelty detection is relatively easier to adapt and is particularly desirable when training samples areincomplete

This paper discussed the external environmental conditions and humans’ internal cognition relating to the visual inspection process of actual mass productions. In visual inspection, human perception and recognition are indispensable to the detection and pass-fail discrimination of the defects, because only those form the discipline of the inspection. First, the effects of the external environment on the defect detection rate were evaluated based on the experimental results. Both defects’ features and environmental factors such as the display luminance and defects’ contrast and size are significant for the peripheral visual inspection. Some of the main effects reported in previous studies were verified again, and new interaction effects and whole factors became clear by quantitative analysis. The second was experiments and analyses of human perception and cognition of actual visual inspection targets. A wearable eye-tracker was used to observe experts and a beginner. The visual inspections by the experts were highly efficient because of their skilled perception at first glance and discrimination based on various industrial knowledge in addition to the defect’s appearance. The experts could stably detect a tiny and low-contrast defect on product images including much disturbing stimulus, and it is thought that their sensitivity and resolution were improved based on “attention” because they answered with high confidence. On the other hand, under the same situation, the number of the beginner’s focal points much increases, and processing speed deteriorates remarkably. Finally, some suggestions were summarized based on the results of the first and second topics about the environment of the visual inspection to raise the efficiency of defect detection and pass-fail judgement.

BackgroundDuring the COVID-19 pandemic, medical laypersons with symptoms indicative of a COVID-19 infection commonly sought guidance on whether and where to find medical care. Numerous web-based decision support tools (DSTs) have been developed, both by public and commercial stakeholders, to assist their decision making. Though most of the DSTs’ underlying algorithms are similar and simple decision trees, their mode of presentation differs: some DSTs present a static flowchart, while others are designed as a conversational agent, guiding the user through the decision tree’s nodes step-by-step in an interactive manner.ObjectiveThis study aims to investigate whether interactive DSTs provide greater decision support than noninteractive (ie, static) flowcharts.MethodsWe developed mock interfaces for 2 DSTs (1 static, 1 interactive), mimicking patient-facing, freely available DSTs for COVID-19-related self-assessment. Their underlying algorithm was identical and based on the Centers for Disease Control and Prevention’s guidelines. We recruited adult US residents online in November 2020. Participants appraised the appropriate social and care-seeking behavior for 7 fictitious descriptions of patients (case vignettes). Participants in the experimental groups received either the static or the interactive mock DST as support, while the control group appraised the case vignettes unsupported. We determined participants’ accuracy, decision certainty (after deciding), and mental effort to measure the quality of decision support. Participants’ ratings of the DSTs’ usefulness, ease of use, trust, and future intention to use the tools served as measures to analyze differences in participants’ perception of the tools. We used ANOVAs and t tests to assess statistical significance.ResultsOur survey yielded 196 responses. The mean number of correct assessments was higher in the intervention groups (interactive DST group: mean 11.71, SD 2.37; static DST group: mean 11.45, SD 2.48) than in the control group (mean 10.17, SD 2.00). Decisional certainty was significantly higher in the experimental groups (interactive DST group: mean 80.7%, SD 14.1%; static DST group: mean 80.5%, SD 15.8%) compared to the control group (mean 65.8%, SD 20.8%). The differences in these measures proved statistically significant in t tests comparing each intervention group with the control group (P<.001 for all 4 t tests). ANOVA detected no significant differences regarding mental effort between the 3 study groups. Differences between the 2 intervention groups were of small effect sizes and nonsignificant for all 3 measures of the quality of decision support and most measures of participants’ perception of the DSTs.ConclusionsWhen the decision space is limited, as is the case in common COVID-19 self-assessment DSTs, static flowcharts might prove as beneficial in enhancing decision quality as interactive tools. Given that static flowcharts reveal the underlying decision algorithm more transparently and require less effort to develop, they might prove more efficient in providing guidance to the public. Further research should validate our findings on different use cases, elaborate on the trade-off between transparency and convenience in DSTs, and investigate whether subgroups of users benefit more with 1 type of user interface than the other.Trial RegistrationDeutsches Register Klinischer Studien DRKS00028136; https://tinyurl.com/4bcfausx (retrospectively registered)

Computer vision is a multidisciplinary field that cannot be separated with image processing techniques and Neuro-Computing specifically Deep Learning (DL) algorithms, in recent time DL techniques enable computer vision to understand the content of an image, moreover, it is working hand in hand with image processing techniques because image preprocessing are essential components in digital image analysis. Therefore, the remarkable advancement recorded by computer vision today such as in remote sensing, security, medical imaging and robotics etc. The aim of this research work was to explored the technical and theoretical contributions of image processing techniques and DL algorithms to computer vision. A systematic method of literature review was adapted. Basic image processing techniques such as standardization, denoising, filtering, and segmentation are clearly explored, concept of DL algorithms are briefly discussed, recent reviewed articles (from 2018 to date) are obtained from top journals in computer vision thus; IEEE, Elsevier and ISPR and tabulated as a major source of information for this work. We have shown some of the software’s used for the implementation of deep learning researches in computer vision. Finally we concludes and give recommendations based on our findings.

Affordable and reliable energy is not only central to prosperity, but also to poverty reduction, local development, environmental integrity, quality of life, growth, and progress. Given the importance and wide scale of energy generation all around the world, its ever growing economic, social and environmental aspects need to be taken into better consideration. The sustainability performance of energy operations shall be assessed on a project basis, as energy generation projects may significantly vary, depending on the needs and circumstances. This chapter introduces a novel approach for evaluating energy projects from a sustainability point of view and estimates their sustainability performance as a decision-making support tool. Decision environments can sometimes be complicated for an individual decision maker (DM) to consider every aspect of the problem. Group decision making (GDM) can be advantageous to reduce the impact of biased and personal opinions on the decision process. Moreover, DMs’ judgments are mostly far from being completely certain, making it more difficult to put their ratings into numerical forms. In such circumstances, the fuzzy set theory can be applied to better represent DMs’ preferences. This chapter applies GDM together with the fuzzy set theory to find the importance of the selected evaluation criteria. Then, GDM and the fuzzy set theory are combined with VIKOR (Vlse Kriterijumska Optimizacija Kompromisno Resenje) technique to rank the energy project alternatives. This approach is particularly useful for its strength in dealing with actual energy projects so that it can support both researchers and business managers to compare the sustainability performance of planned or realized power plants in a balanced manner. The usability of the proposed approach is shown in a case study from Turkey, where different energy projects are evaluated for their overall sustainability performance.

Characteristics of the lesions in digital mammography images will be more clear after image enhancement, which can increase the detection rate of early breast cancer. This paper proposes a modified unsharp masking approach based on an improved high-pass filter. Experimental result of digital mammography image enhancement proves that the proposed method can effectively extrude the edges of lesions and at the same time can suppress the noises in uniform background areas.

Fuzzy description of ball-bearing wear

This paper seeks to identify the most environmental friendly way of conducting a refurbishment of Broendby Strand, with focus on PCB remediation. The actual identification is conducted by comparing four remediation techniques using urban metabolism fused with life cycle assessment (UM-LCA) in combination with information relating to cost and efficiency of the compared techniques. The methodological goal of our paper is to test UM-LCA as a decision support tool and discuss application of the method in relation to large refurbishment projects. To assess the environmental performance of PCB-remediation techniques, the UM-LCA method was applied. By combining UM and LCA methodologies, the total environmental impact potentials of the remediation techniques were calculated. To build an inventory for each technique, we contacted and interviewed experts and studied existing literature, cases, and projects in order to compile information on practical details of the techniques. To process the collected inventory data, we used the simplified product system modeling software Quantis Suite 2.0 (QS2.0). In order to validate the results from the simplified software, we carried out the exact same analysis using a more complex tool—OpenLCA 1.5. Based on the assessment results, we compared the remediation techniques and identified the techniques with the smallest and largest environmental impact potentials. The results obtained are presented, and the technique with the smallest impact identified. A comparison between the two software tools applied is made, and differences between the two are discussed in detail. Further discussed is how possible inventory errors affect the results and if any assumptions should be considered as critical for the final results. Furthermore, are the remediation efficiencies of each technique and the cost of each method considered and compared. Finally, UM-LCA’s ability to work as a tool for decision support is discussed and possible ways of implementing the method in sustainable decision-making is considered. In this study, it is found that the most environmental friendly PCB-remediation technique is thermal desorption, whereas the technique with the largest environmental impact potential is sand blasting, due to the environmental impacts induced in relation to disposal of the building waste. It is concluded that the UM-LCA method can be applied as a tool for decision support, and if economic aspects are incorporated, the UM-LCA approach could be an essential approach for designing sustainable buildings.

The selection of suitable sanitation options is a complex issue. There are many factors that influence the performance of each system. Sanitation suitable for use in low-income housing areas in developing countries is normally based on a combination of options specific to the local context. That makes it really difficult to develop an effective tool for decision-making. To date, decision support tools have failed to make a long-term impact on the choice for sanitation services in rural as well as urban and peri-urban settlements in developing countries. Most relate the choice of a sanitation option to one element (i.e. septic tank or pit latrine) rather than considering the sanitation system as a whole. Some lack transparency or are guided by personal choices and assumptions, which can include as well as exclude relevant aspects for the selection of sanitation systems. Decision-models are generally complex to understand and use and sometimes seem inconsistent. WASTE in collaboration with international experts is developing a practical support instrument to facilitate informed choice of sanitation systems. The tool is a knowledge sharing or awareness mechanism intended to provide a more comprehensive view of a settlement's limitations on the one hand and available sanitation options on the other. It intends to assist a wide range of stakeholders from city officials, planners, CBO's, users, service providers to financial and political authorities. Furthermore WASTE wants to present a practitioner's tool that uses a three-step approach providing a simple interface, flexible framework and transparent outcome. This support tool can be used independently, integrated in strategic sanitation planning as well as provide the base-ground for the selection of sanitation options in a multi-stakeholder participatory process.

Разработано программное обеспечение ImgOpinion, которое позволяет выполнять оптико-структурный анализ цифрового изображения объекта методами компьютерного зрения. Оно предназначено для использования в экспертных лабораториях в составе аппаратно-программного комплекса компьютерного зрения MS-Unit, который включает специализированный осветитель “Фотобокс 3138” с цифровой регистрирующей камерой. Выходные данные строятся в виде цифрового паспорта огнестрельного повреждения, в котором приводятся криминалистически значимые характеристики объекта исследования, а также выявленных на нем следов выстрела. The ImgOpinion software, capable to perform the optical and structural analysis of a digital image of the object by computer vision methods, was developed. It can be employed in expert laboratories as a part of the computer vision hardware-software complex MS-Unit together with specialized illuminator “Photobox 3138” with a digital recording camera. The output data is constructed in the form of a digital passport of the gunshot residue, which contains forensically significant characteristics of the object under investigation, as well as a gunshot residue detected on it. Purpose. The research has solved the problem of creating a specialised hardware and software complex for forensic examination, the use of which partially automates the processes of identification and quantitative characterisation of gunshot traces and products. Methodology. Non-destructive research methods are implemented in computer vision systems, which include two main stages: a digital image acquisition and its mathematical processing. The hardware and software complex of a computer vision usually consists of an illuminator, a digital recording video camera and a specialised program for processing the raw data. Findings. ImgOpinion software has been developed, which allows performing the optical-structural analyses of digital images using the computer vision methods and is intended for use in expert laboratories as part of the MS-Unit computer vision hardware and software complex, which includes a specialized illuminator “Photobox 3138” with a digital recording camera. Autonomous and portable device has a mobile design and provides white light with colour temperature 5000 K (CIE D50) and colour rendering index CRI = 97+. Six independently switched LED monochrome illuminators with narrow spectral bands from 365 to 880 nm (UV to IR spectral bands) provide the uniform illumination without extraneous stray light on the working field (light intensity drop below 2 % at the edges of the working field). Value. The ImgOpinion output is constructed in the form of a digital passport of a gunshot injury, which contains forensically relevant characteristics of the object of investigation. The digital passport is an adaptation of the forensically significant information on the firearm traces for the integration into specialized databases for further development of the automation of expert evaluation processes, conducting the automated trace comparison and the determination of incident circumstances by it.

Coherent and digital image enhancement, their basic differences and constraints

Aerial application of dispersants are an effective means of responding to oil spills in coastal waters and the deeper waters of the Outer Continental Shelf or Gulf of Mexico. To ensure the safety of responders and nearby wildlife, a buffer area is put in place around the spilled oil to be treated, within which spraying operations are conducted. In 2015, a research project was initiated to develop a prototype Decision Support Tool (DST) designed specifically for estimating the spray drift during the aerial application of dispersants on an oil spill. In 2019, an initiative was undertaken to further develop the DST and address known data gaps in the modeling used in the prototype, expand on the aircraft included in the tool, and include a contour plot output of dispersant deposition. The DST has been designed specifically for estimating the spray drift during the aerial application of dispersants on an oil spill through the use of complex Computational Fluid Dynamics (CFD) modeling. The DST program operational space was developed based on direct input from Oil Spill Response Operators (OSROs) for ten airframes currently used in the United States for aerial response operations, including both turbo propeller and turbo fan engine types. The DST employs a database of results generated using the latest in CFD modeling technology to examine flow structures and drift effects created by various operating conditions, coupled with specific configurations of different oil spill response aircraft and their spray systems (boom and nozzle configurations). The DST uses a Response Surface Curve (RSC) for each airframe to predict the drift extent of dispersant particles and mass deposition concentration, the RSC for each airframe was derived from a database of results generated using the latest CFD modeling technology. The studies conducted to generate data for the DST RSCs provided considerable insight into the relationships between the particle dispersant behavior for different airframe types. Trends were identified in particle dispersion behavior when airframes were flown with a heavy payload (full weight) compared to lighter payload (empty weight). These trends change depending on the airframe used and, more specifically, the location and arrangement of the boom used to release the droplets relative to the location of the main wing. Change in Particle Size Distribution (PSD) was also investigated for flight operations of one airframe and the impact on the drift extent reported. The DST will provide oil spill responders with information related to the extent of any areas potentially impacted by dispersant drift. This will assist the operational control personnel in establishing setback distances, information which becomes increasingly important as a spill escalates beyond a Tier 1 response where the size of the spill, and the resources committed, become significant. In addition, the DST generates a contour plot of mass deposition at ground level based on the operational and environmental parameters input to the program, providing the user with a graphical display of where the majority of the aerial dispersant is predicted to land. While the analysis and tool development are complete, a formal peer review has not been completed at the time of the paper publication.