American Scientific Research Journal for Engineering, Technology, and Sciences (ASRJETS)

A Comprehensive Review of Deep Learning Architectures for Computer Vision Applications

Arman Sarraf, Mohammad Azhdari, Saman Sarraf — Fri, 26 Feb 2021 11:35:35 +0000

The emergence of machine learning in the artificial intelligence field led the world of technology to make great strides. Today’s advanced systems with the ability of being designed just like human brain functions has given practitioners the ability to train systems so that they could process, analyze, classify, and predict different data classes. Therefore, the machine learning field has become a hot topic for scientists and researchers to introduce the best network with the highest performance for such mentioned purposes. In this article, computer vision science, image classification implementation, and deep neural networks are presented. This article discusses how models have been designed based on the concept of the human brain. The development of a Convolutional Neural Network (CNN) and its various architectures, which have shown great efficiency and evaluation in object detection, face recognition, image classification, and localization, are also introduced. Furthermore, the utilization and application of CNNs, including voice recognition, image processing, video processing, and text recognition, are examined closely. A literature review is conducted to illustrate the significance and the details of Convolutional Neural Networks in various applications.

AuditModel: A Model for Representation of Continuous Audit Processes Based on ISO 19011

Allison Ramon Araújo de Santana, Paulo Caetano da Silva — Fri, 26 Feb 2021 11:50:12 +0000

Objective of the study: The objective of this article is to propose a model of representation of audit processes that allows its automation, this model is based on ISO 19011, a standard recommended by the International Accreditation Forum (IAF). Methodology / approach: A study was carried out on the standardization of continuous audit processes. ISO 19011 was used as a reference to define the elements of the proposed model. After an analysis in the sections of the standard, sections 05 (establishing objectives of the audit program) and section 06 (conducting the audit) were selected to compose this work. Originality / relevance: The article contains quantitative data related to the performance of audits in Brazil and some limitations for carrying out audits. Through the model, the work makes up for the deficiency of the existence of documentation that helps the understanding, by software developers, auditors and companies, of how an audit should be carried out. It is expected to facilitate the development of audit software with the proposed model. Main results: 14 elements are specified, classified in 4 domains, which together make up the model for representing audit processes. A process is mapped and the specified elements are used to show how the audit processes are to be employed. Theoretical / methodological contributions: It seems feasible to use the methodology in different organizations, it is enough to understand the proposed model, internally map the processes to be audited and apply the concepts described in this work as an example.

Utilization of Healthcare Services by the Elderly Patients at Korle-Bu Teaching Hospital, Accra

Fri, 26 Feb 2021 12:00:34 +0000

Objective: The study assessed the association between predisposing, enabling and need factors on utilization of healthcare services by the elderly attending the Korle-Bu Teaching Hospital.

Methods: The study was a descriptive cross-sectional survey using a mixed method approach. Simple random sampling was used to sample three hundred and sixty-one elderly patients from seven (7) Out-Patient Departments in the Korle-Bu Teaching Hospital who responded to a structured questionnaire. Ordinal Logistic Regression was used to determine the association between the predisposing, enabling and need factors of the elderly and variables measuring utilization of healthcare. In the qualitative study, purposive and convenient samplings were used to select 76 elderly persons from the seven Out-Patient Departments of the hospital. Content analysis was used to analyze the voice recorded qualitative interview data and explained using an appropriate theory.

Quantitative findings: The elderly who obtained above secondary school education were 0.49 times less likely to rate accessibility of healthcare on a higher scale compared with the elderly with pre-secondary education (OR=0.49, 95% CL; 0.28-0.85, p=0.11). The elderly who were beneficiaries of NHI were 0.42 times less likely (OR=0.42, 95% CI; 0.18-0.97) to rate accessibility of healthcare services on a higher scale compared with the elderly who were non-beneficiaries (p=0.042).

The elderly with multiple chronic conditions were 1.56 times more likely to rate the cost of healthcare on a higher scale compared with the elderly with one chronic condition (OR=1.56, 95% CI=1.04-2.34, p=0.03).

Qualitative findings: The elderly persons described the waiting time as long and stressful. They developed swollen feet and bodily pains due to the long waiting time. They clarified that the diagnostic investigation, medication and consultation fees were expensive, leading to postponement of their subsequent visits and deterioration of their health.

Conclusion: Cost was a determining factor in utilizing healthcare. The study recommends that policy makers should include elderly persons from age 60 years to 69 years in the National Health Insurance exemption policy to enable the majority of them to utilize healthcare. Additionally, there is the need to review visits to the healthcare units to schedule time appointments to reduce the long and stressful waiting time.

Landscape Transformation: Temporal Evolution of the Erosion Process on a Hillside on the Island of Itamaracá / Brazil

Mon, 01 Mar 2021 06:29:46 +0000

Urban planning is important to guarantee the quality of life for society, as it proposes spatial planning and problem solving, especially those related to land use. Thus, it was proposed to perform an evaluation of actions that promote and/or accelerate the erosive processes on a hillside located in island of Itamaracá/BR. The “interaction networks” and “land use maps” techniques were used in combination, which resulted in a more accurate environmental assessment, as well as the use of models for future estimates. The results pointed to mediumrisk for the environmental indicators of “occupation types” and evidence of collapse”, and high risk for“urban density”and“vegetation”indicators. It has also been predicted that over the years, the urban sprawl in the area will continue to grow until it reaches stability due to the total occupation of useful areas as well as that the growth rate for vegetation will be negative. Thus, there is a need to mitigate environmental damage in the short term, in order to avoid the occurrence of accidents in the hillside area.