ABSTRACT
End stage kidney disease (ESKD) patients are vulnerable to medical and psychosocial difficulties. We aimed to identify specific concerns for ESKD patients during the early months of the COVID-19 pandemic. Surveys were administered to adult ESKD patients receiving dialysis in three units run by a large dialysis organization affiliated with an academic nephrology practice. Multiple choice and open-ended questions were used to assess patients’ perceptions of access to care and essentials of daily living, and effects of changes in dialysis schedules or prescriptions. Screening questions were used to assess patient anxiety and depression. 172 ESKD patients on dialysis were surveyed. Participants on home dialysis modalities [peritoneal dialysis (PD) or home hemodialysis (HHD)] more commonly reported feeling “very connected” to their dialysis care teams compared to patients on in-center hemodialysis (ICHD) (PD: 74.1%;HHD: 66.7%;ICHD: 62.3%). Patients who identified as White more commonly reported feeling “very connected” compared to patients who identified as non-White (White: 74.4%;Black/African American: 60.5%;Hispanic: 69.6%). Patients with histories of anxiety or depression more commonly reported feeling less cared for during the pandemic. 16.9% of participants reported new transportation issues, 6.4% reported difficulty obtaining medications, and 9.3% reported difficulty getting groceries. A minority of patients met screening criteria for depression or anxiety, though patients with self-reported histories of anxiety or depression had higher screening scores. Five themes emerged as influencing patient experiences: 1) the positive influence of relationships with dialysis staff;2) the value of interactions with family or other caretakers;3) difficulties with access to care;4) changes in physical and mental health;and 5) awareness of, and response to, the COVID-19 pandemic. Our study identifies sub-populations of ESKD patients who may be more vulnerable during the COVID-19 pandemic: those with histories of anxiety or depression, non-White patients, and patients on ICHD. Use of home dialysis modalities may be associated with better patient perceptions of care.
ABSTRACT
Internet of Things (IoT) is a technology which is rapidly growing, the future of IoT is limitless as the data streams have quadrupled over the years. Future markets are going to shift from traditional data processing techniques to Big Data Analytics and Cloud computing as businesses worldwide are shifting to cloud based work approaches which was largely boosted by the Covid-19 pandemic. Fishes are well known to be highly sensitive to the environment, hence they require proper care and attention from their owners. Many a times they forget to feed the fish, change the water, check the pH levels etc. these problems look simple but when it comes to tracking hundreds of fishes it can be difficult, these issues can be easily resolved by using IoT. An IoT system that can be highly beneficial for small to large scale aquariums is necessary e.g. Dubai Aquarium (where hundreds of fishes are constantly monitored). The System can be used to create the ideal conditions required for high yield. The aquaculture sector is going to play a crucial role in the future economy as fishes are getting scarce all over the world. Steps must be taken to streamline processes and by which increase efficiency while improving fish health. IoT based Aquariums can save Ocean Wildlife by building reliable systems that are capable of real-time data processing. Massive tanks can be built for endangered species in remote locations further increasing biodiversity and building a balanced ecosystem. Larger fishes can be monitored using technologies such as RFID, transmitters, etc. since it can be difficult to monitor them in large tanks. Data received from sensors can be stored in some cloud platform and analyzed for future predictions and redundant storage, all sorts of smart devices are able to communicate with each other regardless of hardware and operating system used. The IoT based Aquarium Monitoring device is capable of capturing the water levels inside the aquarium and notifies the user by email when its low. It can switch on/off the lights of the aquarium, control the automatic feeder using and record the room temperature and humidity readings with the help of AWS technologies. The fish feeder is controlled by the user using a voice application or web/app interface. Parameters used in this project are Room Temperature, Humidity, Water Level, LED status and Feeder status. Sensor acquisition is performed by ESP-32, it is also used as data processing device as well as local server/controller. User can monitor the conditions of the aquarium locally or remotely from any part of the world as long as he/she has an Internet connection since data is processed through AWS Lambda, stored in DynamoDB and hosted in AWS API. Data is further visualized using AWS IoT Analytics and QuickSight for proper decision making. Every feature in this model works effortlessly and is highly accurate. A wide scale Industrial Application of this Project can be included in Aquaponics fish management, fish farming, Zoo keeping, etc. The data received can be used to take necessary actions and are stored for future studies. They are highly beneficial for farmers raising a certain species of fishes and for maintaining a balanced ecology. © 2022 IEEE.
ABSTRACT
In order to prevent the spread of CORONA virus, everyone must wear a mask during the pandemic. In these tough times of COVID-19 it is necessary to build a model that detects people with and without mask in real-time as it works as a simple precautionary measure to prevent the spread of virus. If deployed correctly, this machine learning technique helps in simplifying the work of frontline warriors and saving their lives. A basic Convolutional Neural Network (CNN) model is built using TensorFlow, Keras, Scikit-learn and OpenCV to make the algorithm as accurate as possible. Javascript API helps in accessing webcam for real-time face mask detection. Since Google Colab runs on web browser it can't access local hardware like a camera without APIs. The proposed work contains three stages: (i) pre-processing, (ii) Training a CNN and (iii) Real-time classification. The first part is the Pre-processing section, which can be divided into "Grayscale Conversion" of RGB image, "image resizing and normalization" to avoid false predictions. Then the proposed CNN, classifies faces with and without masks as the output layer of proposed CNN architecture contains two neurons with Softmax activation to classify the same. Categorical cross-entropy is employed as loss function. The proposed model has Validation accuracy of 96%. If anyone in the video stream is not wearing a protective mask a Red coloured rectangle is drawn around the face with a dialog entitled as NO MASK and a Green coloured rectangle is drawn around the face of a person wearing MASK