Many modern cultural object collections suffer from the problem of being obtained in unethical and illegal circumstances. Additionally, information about collections, including their status, object ...descriptions, and other data need up-to-date information presented to users. We propose a novel blockchain tool called Salsal that enables the vetting of objects, individually or as part of more extensive collections, to meet required ethical and legal guidelines while informing users about relevant information regarding collections. Blockchain provides a better and more rapid way for users to know about collections using a decentralized and immutable ledger technology. Blockchain can be used to incentivize or even pressure collections to vet their objects for ethical and legal guidelines that can benefit the public who use object collections. The prototype software we have made is presented and compared to other blockchains, with code and demonstration provided. We present how our blockchain can enable benefit, providing a useful vetting process for cultural objects, and allowing a user community to contribute to collections in a transparent and secure manner.
Proximity movements between vehicles transporting materials in manufacturing plants, or “interfaces”, result in occupational injuries and fatalities. Risk assessment for interfaces is currently ...limited to techniques such as safety audits, originally designed for static environments. A data-driven alternative for dynamic environments is desirable to quantify interface risks and to enable the development of effective countermeasures. We present a method to estimate the Risk Prioritization Number (RPN) for mobile vehicle interfaces in manufacturing environments, based on the Probability-Severity-Detectability (PSD) formulation. The highlight of the method is the estimation of the probability of occurrence (P) of vehicle interfaces using machine learning and computer vision techniques. A PCA-based sparse feature vector for machine learning characterizes vehicle geometry from a top-down perspective. Supervised classification on sparse feature vectors using Support Vector Machines (SVMs) is employed to detect vehicles. Computer vision techniques are used for position tracking to identify interfaces and to calculate their probability of occurrence (P). This leads to an automated calculation of RPN based on the PSD formulation. Experimental data is collected in the laboratory using a sample work area layout and scale versions of vehicles. Vehicle interfaces and movements were physically simulated to train and test the machine learning model. The performance of the automated system is compared with human annotation to validate the approach.
Resumo: Os movimentos de proximidade entre os veículos que transportam materiais nas fábricas, ou interfaces, resultam em ferimentos e mortes no trabalho. Atualmente, a avaliação de riscos para interfaces está limitada a técnicas como auditorias de segurança, originalmente projetadas para ambientes estáticos. Para ambientes dinâmicos, uma alternativa baseada no uso extensivo de dados é desejável, de maneira a quantificar riscos e possibilitar o desenvolvimento de contramedidas efetivas. Apresentamos um método para estimar o Número de Priorização de Risco (NPR) para interfaces de veículos móveis em ambientes de fabricação, com base na formulação Severidade-Ocorrência-Detecção (SOD). O Método se destaca pela estimativa da probabilidade de Ocorrência (O) de interfaces de veículos utilizando machine learning e técnicas de visão computacional. Um vetor de recursos esparsos baseado em PCA para machine learning para caracterizar a geometria do veículo de uma perspectiva top-down. A classificação supervisionada em vetores de recursos esparsos utilizando SVMs (Support Vector Machines) é empregada para detectar veículos. Técnicas de visão computacional são usadas para rastreamento de posição para identificar interfaces e calcular sua probabilidade de ocorrência (O). Isso leva a um cálculo automatizado de NPR com base na formulação do SOD. Os dados experimentais são coletados em laboratório utilizando um layout de amostra da área de trabalho e versões em escala de veículos. As interfaces e os movimentos do veículo foram fisicamente simulados para treinar e testar o modelo de machine learning. O desempenho do sistema automatizado é comparado com a anotação humana para validar a abordagem.
Display omitted
•Hierarchically model free-text notes to predict mortality.•Performance compared to severity scores and RNN’s utilizing physiological data.•Notes consistently better than both ...baselines and multi-modal model achieves highest metrics.•More unstructured data needs to be used in clinical prediction.
Healthcare data continues to flourish yet a relatively small portion, mostly structured, is being utilized effectively for predicting clinical outcomes. The rich subjective information available in unstructured clinical notes can possibly facilitate higher discrimination but tends to be under-utilized in mortality prediction. This work attempts to assess the gain in performance when multiple notes that have been minimally preprocessed are used as an input for prediction. A hierarchical architecture consisting of both convolutional and recurrent layers is used to concurrently model the different notes compiled in an individual hospital stay. This approach is evaluated on predicting in-hospital mortality on the MIMIC-III dataset. On comparison to approaches utilizing structured data, it achieved higher metrics despite requiring less cleaning and preprocessing. This demonstrates the potential of unstructured data in enhancing mortality prediction and signifies the need to incorporate more raw unstructured data into current clinical prediction methods.
This study was conducted during 2017-19 with the objective to provide data of distribution of blood group of ABO and Rh(D) and gene frequency among the population of three districts; Multan, Lodhran ...and Khanewal (Multan Division), Pakistan. This information will provide basic facts and figures of region to geneticists, practitioners and blood transfusion programmers. From both genders total 440 subjects were selected from schools and colleges students, prisoners and factory workers etc. randomly in different regions of three districts. Blood samples of both genders were tested for blood groups ABO and Rh(D) factor with help of open slide test method. To observe agglutination, a drop of the antisera, anti-A, anti-B and anti-D were mixed with every blood sample and shook gently for 60 seconds. The predominant blood group was O with 36.48%, 42.57% and 42.08% presence in Multan, Lodhran and Khanewal respectively in all the Rh(D) positive subjects. In Rh(D) negative subjects, blood group A was found predominant with 5.40% in Multan district only amongst the three districts. In Multan the percentage of Rh(D) Positive was 90.55% and Rh(D) negative was 9.45%. In Lodhran, the percentage of Rh(D) positive was 93.25% and Rh(D) negative was 6.75%. in Khanewal, the percentage of Rh(D) positive was 91.22% and Rh(D) negative was 8.78%. Among the 3 districts studied, both Rh(D) positive and Rh(D) negative frequency of blood groups was O> A> B> AB> except Multan where blood group "A" was common among Rh(D) negative subjects.
No toilets and tap water were found in the study areas. 55.60% of the respondents used mostly water from the stream while 25.50% used from the wells. 82.20% of the respondents were self-treated in ...most cases of the above mentioned disease while 12.50% received treatment from the health center and 10.2% traditional healers. The major cause of this infection are favourable environmental conditions for the unhygienic living conditions, poor sanitation, overcrowding, vector, lack of prophylactic measures and ineffectiveness of the malaraial control programmes etc. According to DMCP, 1990 - 1991, incidence was found to be 6.72% and 5.93% respectively in N.W.F.P. These figures are also less as compared to the present study. Conclusion The results of this study provide baseline knowledge about the prevalence of malaria in school going children and indicate areas which are focus with respect to the knowledge as well as improving the quality of education about various aspects of malaria such as preventive measures which being empowered to maintain their health by using the techniques which they learned about this disease.
Healthcare data continues to flourish yet a relatively small portion, mostly structured, is being utilized effectively for predicting clinical outcomes. The rich subjective information available in ...unstructured clinical notes can possibly facilitate higher discrimination but tends to be under-utilized in mortality prediction. This work attempts to assess the gain in performance when multiple notes that have been minimally preprocessed are used as an input for prediction. A hierarchical architecture consisting of both convolutional and recurrent layers is used to concurrently model the different notes compiled in an individual hospital stay. This approach is evaluated on predicting in-hospital mortality on the MIMIC-III dataset. On comparison to approaches utilizing structured data, it achieved higher metrics despite requiring less cleaning and preprocessing. This demonstrates the potential of unstructured data in enhancing mortality prediction and signifies the need to incorporate more raw unstructured data into current clinical prediction methods.
PDF
