Leak detection in real water distribution networks based on acoustic emission and machine learning.

Water scarcity as well as social and economic damages caused by the increasing amounts of non-revenue water in the water distribution networks (WDNs) have been prompting innovative solutions. A great deal of potable water is wasted due to leakage in the WDNs all over the world. Hence, various leak detection approaches have been explored, including the promising application of acoustic devices. Exploiting the benefits of technological advances in acoustic devices, signal processing, and machine learning (ML), this study aimed to develop a sophisticated system for leak detection in WDNs. Different from laboratory-based studies, this study was conducted on real WDNs in Hong Kong and lasted for about two years. Utilizing acoustic emissions acquired using wireless noise loggers, various ML algorithms were explored to develop inspection models for in-service and buried WDNs. ML classification algorithms can identify patterns in the acquired signals for leak and no-leak statuses. Thus, a combination of features describing acoustic signals in time and frequency domains was utilized to facilitate the development of ML models. Separately for metal and non-metal WDNs, ten well-known ML algorithms were used to develop leak detection models. The validation results demonstrate the promising application of noise loggers and ML for leak detection in real WDNs. Support Vector Machine (SVM), Artificial Neural Network (ANN), and Deep Learning (DL) leak detection models demonstrated a largely stable performance and a very good accuracy, particularly for new unlabelled cases.

Prevalence and pattern of intimate partner violence among men and women in Edo State, Southern Nigeria.

BACKGROUND:  Intimate partner violence (IPV) is a growing concern in Nigeria and globally. Although women are at greater risk of IPV, men are also affected, but this is less reported. AIM:  This study sought to determine the prevalence and pattern of IPV among the respondents and to compare the pattern of IPV among the male and female respondents. SETTING:  The study was conducted in six towns (local government headquarters) across the three senatorial districts in Edo State, Southern Nigeria. METHODS:  The study was a descriptive, cross-sectional, community-based study. A multistage sampling technique was used in selecting 1227 respondents from Edo State, Southern Nigeria. A semistructured, interviewer-administered questionnaire and the Extended Hurt, Insult, Threaten, Scream (E-HITS) tool were used to collect data, which were analysed with Epi Info version 7.1.2.0. RESULTS:  The study found an IPV prevalence of 37.7% among the respondents (confidence interval [CI]: 95%, odds ratio [OR]: 0.169-0.294). The mean age was 38 ± 12 and respondents were mostly female (725, 59.1%), married (770, 62.8%) and unemployed (406, S33.1%), with a tertiary level of education (766, 62.4%). Intimate partner violence was significantly higher among women compared with men (95% CI: 4.474, OR: 3.425-5.846). The pattern of IPV showed a lower OR between sexual and physical IPV (95% CI: 0.276, OR: 0.157-0.485). There was a higher likelihood of IPV among married women (95% CI: 1.737, OR: 1.279-2.358). CONCLUSION:  There is a need to improve the socio-economic status of the Nigerian populace, especially women. Healthy, nonviolent and safe relationships should be promoted in communities by signalling what is socially unacceptable and strengthening sanctions against perpetrators.

Improving the leak detection efficiency in water distribution networks using noise loggers.

Leak detection techniques are effective ways of controlling water leakage in real water distribution networks (WDNs). Nevertheless, developing detection techniques for real WDNs has received little attention compared to the detection models developed based on laboratory simulated leaks. On the other hand, ambient noises and irregular water usage are difficult to simulate in a laboratory environment so detection models based on the laboratory simulated leaks are usually of low efficiency in practical applications. To achieve a better understanding of the detection models of real WDNs, machine learning (ML)-based leak detection models were developed in this work. This study employs wireless sensors to record acoustic signals emitted by real WDNs for the development of the leak detection models. The acquired acoustic signals are de-noised using the discrete wavelet transform. Thereafter, seventeen features are extracted from both the raw and de-noised signals using the principle of linear prediction, and the features are subsequently used for the development of the ML-based leak detection models. A thorough comparison is made for the performances of the detection models in terms of metal and non-metal WDNs, different features, and different ML algorithms, namely decision tree (DT), support vector machine (SVM), artificial neural network (ANN), and k-nearest neighbor (K-NN). Generally, the performance of the ML-based detection models developed by using the features extracted from de-noised signals has a better classification accuracy as compared to the performance of the models developed based on the features extracted from raw signals. For the de-noised signals, the accuracy, precision, and recall for the models developed based on the DT, SVM, and ANN algorithms are 100% for metal and non-metal WDNs.

Contributions of family physicians to health care services in Nigeria.

In Nigeria, family physicians are doctors with specialised training to manage a broad range of clinical conditions and pathologies when they first present, considering the psychosocial, economic, cultural and environmental context of the individual and his or her family. In Nigeria, family physicians may be found at district hospitals but are more likely to be located at tertiary health care facilities, where their roles in medical education, research and clinical services cannot be overemphasised. Many patients present to tertiary facilities with primary-care problems, bypassing primary and secondary care. They are often seen initially by family physicians in general outpatient clinics, where 70% of all problems are managed without referral to other specialists. These physicians are also in charge of most of the National Health Insurance Scheme (NHIS) clinics nationwide. They are thus the gatekeepers to the majority of tertiary hospital services.

The role of the family physician in the fight against Coronavirus disease 2019 in Nigeria.

The Coronavirus disease 2019 (COVID-19) pandemic has been ravaging Nigeria and the world with increasing morbidity and mortality. Despite efforts by the Nigerian government implemented through the Nigerian Centre for Disease Control (NCDC) to reduce the scourge of the disease through public enlightenment and regular updates, the number of new cases and mortalities from COVID-19 are still increasing. Family physicians (FPs) who are the first contact of care for most patients accessing private and public health facilities in Nigeria have been working tirelessly to reduce the scourge of the pandemic in Nigeria. They continuously update themselves through regular webinars and online resources and guidelines provided by the Society of Family Physicians of Nigeria (SOFPON). Measures adopted by FPs across the country in the fight against the scourge include triaging patients as they present to the family medicine clinics; health education and enlightenment of the populace; and ensuring social distancing, regular handwashing and compulsory use of face mask by both physicians and patients during clinical consultations. Other measures include incorporating family-focused behavioural interventions in their practice, home-based care to reduce the number of persons visiting the hospital, telemedicine and Hospice and palliative care services to the elderly and terminally ill. In conclusion, FPs in Nigeria are helping to reduce the scourge of COVID-19 through patient education and innovative healthcare delivery that does not put patients at increased risk of the disease whilst promptly recognising potential COVID-19 patients and referring them for early diagnosis and treatment.

A Case Study of Sexual Abuse of a Minor.

Child Sexual Abuse (CSA) is a crime against children. It is largely underreported and commonly goes unpunished in our society as it is commonly perpetrated by close ones including family relations. Victims are left with the adverse sequelae associated with it sometimes for life. This report highlights the management of a case of PID in a child as a result of incest perpetrated by her father. It also brings to fore the problems and challenges of child sexual abuse in Nigeria. The patient was a 17 year old 100 level university student who lost her mother at the age of 14 and was living with her father alone. The father sexually abused her repeatedly for two years. She became pregnant and had the pregnancy illegally terminated at seven weeks gestation via dilatation and curettage. The procedure was complicated by Pelvic Inflammatory Disease (PID) which necessitated her presentation at the clinic where she was treated. The case brings to the fore the problem of child sexual abuse in Nigeria and its attendant sequelae. The health care providers should have a high index of suspicion for CSA when attending to minors and address sexual problems including CSA where present.