Search

The implementation of a smart water network (SWN) is viewed as a strategic approach to address many challenges faced by water utilities, such as pipe leak detection and main break prevention. This paper develops a convolutional neural network (CNN)–based model to classify acoustic wave files collected by the South Australian Water Corporation’s (SA Water’s) SWN over the city of Adelaide. The VGGish model (VGG refers to the team who developed the model—Visual Geometry Group) is selected as a suitable transfer learning model to extract features from wave files. The CNN model classifies an acoustic wave file as an anomaly or other background or environmental noise. Identification of a wave file as an anomaly triggers a Siamese CNN model to determine whether it is related to a regular/irregular scheduled event (for example, irrigation system near public parks or water consumption by large buildings). A field investigation is initiated if a wave file is classified as an anomaly and it is not related to a scheduled event. The developed models have been validated using data that is recorded by SWN in Adelaide. This validation data set comprises 1098 wave files, which are recorded by 34 accelerometers and are associated with 32 known leaks. The validation results shown that accuracy of alarms generated by the developed models is 92.44%. The validations confirm the developed models as an effective tool for water pipeline leak and crack detection, which, in turn, enables proactive management of the pipeline assets.

Pipeline condition assessment is essential for targeted and cost-effective maintenance of aging water transmission and distribution systems. This article proposes a technique for fast and non-invasive assessment of the wall condition of cement mortar–lined metallic pipelines using fluid transient pressure waves (water hammer waves). A step transient pressure wave can be generated by shutting off a side-discharge valve in a pressurised pipeline. The wave propagates along the pipe and reflections occur when it encounters sections of pipe with changes in wall thickness. The wave reflections can be measured by pressure transducers as they are indicative of the location and severity of the wall deterioration. A numerical analysis is conducted to obtain the relationship between the degree of change in wall thickness in a cement mortar–lined pipe and the size of the corresponding pressure wave reflection. As a result, look-up charts are generated for any specific cement mortar–lined pipeline to map this relationship. The wall thickness of a deteriorated or distinct section can be determined directly and quickly from the charts using the size of the reflected wave, thus facilitating on-site pipeline condition assessment. The validity of this time-domain pipeline condition assessment technique is verified by numerical simulations and a case study using the field data measured in a mild steel cement mortar–lined water main in South Australia. The condition of the pipe as assessed by the proposed technique is generally consistent with ultrasonic measurements.

Social marketing has a long and robust history in health education and public health. Social marketing strategies are designed to promote desired behaviors in high-priority health-related areas. Most prior initiatives have utilized an “orientation to consumer needs” in program design and delivery. Traditional social marketing campaigns have targeted patients or specific segments of the public, rather than physicians and other healthcare providers, to deliver health-related messages. This commentary explores an emerging opportunity for the social marketing and medical education communities to collaborate and influence social change of medical students, interns, and residents – an “undiscovered” but influential consumer market. The authors offer a primer on the medical education environment as it relates to social marketing strategies for healthcare providers. Key themes and emerging needs in medical education are outlined. In particular, four major areas for collaboration with the social marketing community are highlighted. These include: emphasis on social accountability, use of technology in education and medical practice, alignment with changes in health care delivery, and future directions in the health care workforce. In addition, four practical strategies for meaningful collaborations between medical education and social marketing leadership are presented. The medical education environment is an ideal platform for social marketing techniques to influence the behavior of developing physicians.

OBJECTIVE: To evaluate the accuracy, clinical correlation, ease of use, and patient acceptance of the Coaguchek and the ProTime Microcoagulation System as compared with standard laboratory methods for prothrombin time determination. METHODS: A total of 30 prothrombin times, expressed as international normalized ratios (INRs), were determined by each handheld device for comparison with standard laboratory testing. Accuracy was evaluated by calculating the absolute difference for each pair of INR values. Clinical correlation was defined as an INR obtained by the handheld monitor that would have resulted in the same therapeutic decision as the INR obtained by the standard laboratory method. Subjects were surveyed to determine which method of INR determination they preferred and their reasons for that preference. RESULTS: Accuracy was superior with the Coaguchek monitor. The absolute difference (mean ± SD) in the laboratory and Coaguchek INRs was 0.28 ± 0.23 (p = 0.96). The absolute difference (mean ± SD) in the laboratory and the ProTime Microcoagulation System INRs was 0.56 ± 0.34 (p < 0.001). For clinical correlation, two out of 24 (8.3%) INRs with the Coaguchek were sufficiently different from the laboratory INR to have resulted in a different therapeutic decision, compared with 12 out of 24 (50%) with the ProTime Microcoagulation System (p < 0.005). Of subjects surveyed, 77.8% preferred the finger stick method. CONCLUSIONS: The Coaguchek was superior to the ProTime Microcoagulation System in accuracy, clinical correlation, and ease of use. The study also showed that patients preferred capillary blood sampling by finger puncture over venipuncture for INR monitoring.