RESUMO
This proposed research explores a novel approach to image classification by deploying a complex-valued neural network (CVNN) on a Field-Programmable Gate Array (FPGA), specifically for classifying 2D images transformed into polar form. The aim of this research is to address the limitations of existing neural network models in terms of energy and resource efficiency, by exploring the potential of FPGA-based hardware acceleration in conjunction with advanced neural network architectures like CVNNs. The methodological innovation of this research lies in the Cartesian to polar transformation of 2D images, effectively reducing the input data volume required for neural network processing. Subsequent efforts focused on constructing a CVNN model optimized for FPGA implementation, emphasizing the enhancement of computational efficiency and overall performance. The experimental findings provide empirical evidence supporting the efficacy of the image classification system developed in this study. One of the developed models, CVNN_128, achieves an accuracy of 88.3% with an inference time of just 1.6 ms and a power consumption of 4.66 mW for the classification of the MNIST test dataset, which consists of 10,000 frames. While there is a slight concession in accuracy compared to recent FPGA implementations that achieve 94.43%, our model significantly excels in classification speed and power efficiency-surpassing existing models by more than a factor of 100. In conclusion, this paper demonstrates the substantial advantages of the FPGA implementation of CVNNs for image classification tasks, particularly in scenarios where speed, resource, and power consumption are critical.
RESUMO
This research investigates the implementation of complex-exponential-based neurons in FPGA, which can pave the way for implementing bio-inspired spiking neural networks to compensate for the existing computational constraints in conventional artificial neural networks. The increasing use of extensive neural networks and the complexity of models in handling big data lead to higher power consumption and delays. Hence, finding solutions to reduce computational complexity is crucial for addressing power consumption challenges. The complex exponential form effectively encodes oscillating features like frequency, amplitude, and phase shift, streamlining the demanding calculations typical of conventional artificial neurons through levering the simple phase addition of complex exponential functions. The article implements such a two-neuron and a multi-neuron neural model using the Xilinx System Generator and Vivado Design Suite, employing 8-bit, 16-bit, and 32-bit fixed-point data format representations. The study evaluates the accuracy of the proposed neuron model across different FPGA implementations while also providing a detailed analysis of operating frequency, power consumption, and resource usage for the hardware implementations. BRAM-based Vivado designs outperformed Simulink regarding speed, power, and resource efficiency. Specifically, the Vivado BRAM-based approach supported up to 128 neurons, showcasing optimal LUT and FF resource utilization. Such outcomes accommodate choosing the optimal design procedure for implementing spiking neural networks on FPGAs.
RESUMO
The current study seeks to explore the vulnerabilities typically encountered by female migrants in the informal sector in Dhaka city. It used a qualitative research approach, purposively selecting four areas from Dhaka city. Twenty-five semi-structured in-depth interviews during eight months of participant observation were conducted to accomplish the study objective. The authors used the capability approach theory to elucidate the phenomenon of vulnerability experienced by female migrants in the informal sector. The thematic data analyses were performed using the Granheim approach and NVivo 12 software. The findings of this study suggest that migrant women who work on the street face a number of significant challenges. These challenges include sexual assault and harassment, social stigma and cultural barriers, financial obstacles, and extortion and bribery. The authors recommend that governments provide access to state credits, social security, health insurance, and other forms of social protection for informal sector workers. The finding revealed that informal workers are often excluded from these essential benefits, making it difficult for such workers to expand their businesses or have a safety net in case of illness, unemployment, or other shocks.
RESUMO
RESUMO Objetivo O objetivo deste trabalho é avaliar o perfil epidemiológico das conjuntivites atendidas no Pronto Socorro do Hospital Banco de Olhos de Porto Alegre (HBO) com destaque à conjuntivite infecciosa e compará-lo aos atendimentos após o início da pandemia pelo Coronavírus, observando como o isolamento social e as questões de higiene amplamente enfatizadas e estimuladas desde o início a pandemia influenciaram o número de conjuntivites bacterianas e virais atendidas neste serviço de referência. Métodos Estudo transversal e retrospectivo através da análise dos prontuários eletrônicos dos pacientes atendidos no serviço de emergência do HBO no período entre março e junho de 2019 e 2020. Resultados Observou-se uma redução significativa no número de atendimento no departamento de emergência após o início da pandemia. De março a junho de 2019, 21.678 atendimentos foram realizados. No mesmo período de 2020, este número foi de 14.194, uma queda de 34,5%. O índice de conjuntivite como principal causa da visita oftalmológica diminuiu significativamente, sendo a conjuntivite infecciosa aquela que teve a maior queda. Em 2019, a mesma foi responsável por 30,2% dos atendimentos e, em 2020, por 15,5%. Não foi observado mudanças em relação ao sexo mais atendido, no entanto, observou-se um aumento significante na idade do paciente. Conclusão O estudo demonstrou uma importante redução no número de atendimentos na emergência em relacionados à conjuntivite infecciosa após o início da pandemia pelo Coronavírus. Acredita-se que este fato esteja diretamente relacionado ao aumento dos cuidados de higiene, isolamento social e a restrições impostas pela pandemia.
ABSTRACT Objective The objective of this paper is to evaluate the profile of the cases of conjuntivitis treated in the emergency department of the Banco de Olhos Hospital, emphasizing the infectious conjunctivitis, and compare before and after the onset of the Coronavirus pandemic and social isolation, both in public and private health care system. Methods A retrospective and transversal study where electronic files of the patients who visited the emergency department between March and June of 2019 and 2020 were reviewed. Results A significant reduction in the number of consultations at the emergency department was observed after the beginning of the pandemic. From March to June 2019, 21.678 visits were made. In the same period of 2020, this number was 14.194, a drop of 34.5%. The rate of visits having conjunctivitis as main cause also dropped significantly. Infectious conjunctivitis was the one who showed the highest decrease. In 2019, it was responsible for 30.2% of the visits and, in 2020, for 15.5%. There were no changes regarding the gender, but a significantly increase in patients' age was observed. Conclusion The study showed a dramatic reduction in the number of visits at the emergency department of ophthalmology regarding infectious conjunctivitis after the beginning of the pandemic, and we believe that the cause is related with an increase of hygiene care, social isolation and restrictions caused by the Coronavirus pandemic.