Speech emotion recognition is one of the most active areas of research in the field of affective computing and social signal processing. However, most research is directed towards a select group of languages such as English, German, and French. This is mainly due to a lack of available datasets in other languages. Such languages are called low-resource languages given that there is a scarcity of publicly available datasets. In the recent past, there has been a concerted effort within the research community to create and introduce datasets for emotion recognition for low-resource languages. To this end, we introduce in this paper the Urdu-Sindhi Speech Emotion Corpus, a novel dataset consisting of 1,435 speech recordings for two widely spoken languages of South Asia, that is Urdu and Sindhi. Furthermore, we also trained machine learning models to establish a baseline for classification performance, with accuracy being measured in terms of unweighted average recall (UAR). We report that the best performing model for Urdu language achieves a UAR = 65.00% on the validation partition and a UAR = 56.96% on the test partition. Meanwhile, the model for Sindhi language achieved UARs of 66.50% and 55.29% on the validation and test partitions, respectively. This classification performance is considerably better than the chance level UAR of 16.67%. The dataset can be accessed via https://zenodo.org/record/3685274
Objective:A study of pericardial effusions in individuals with dyspnea was conducted to evaluate the prevalence and aetiology. Study Design:Prospective/Observational Study Place and Duration: Multicenteric study conducted at DHQ Hospital Bagh AJK/ Federal Govt. Polyclinic Hospital Islamabad and DHQ Teaching Hospital Gujranwala Medical College, Gujranwala. Duration was six months from 1st Oct 2021 to 31st March 2022. Methods:There were 135 patients of both genders had ages 18-75 years were presented in this study. Patients with dyspnea were admitted to emergency department. After obtaining informed written consent, we compiled detailed demographic information on all enrolled patients.Pericardial effusion was detected in all cases using echocardiography.The causes of pericardial effusion have been studied." SPSS 22.0 was used to analyze the data. Results: There were 75 (55.6%) males and 60 (44.4%) females in this study. Mean age of the patients was 58.16±10.79 years and had mean BMI 23.9±10.45 kg/m2. Majority of the patients were illiterate 90 (66.7%) and 45 (33.3%) were literate. We found frequency of pericardial effusions among 26 (19.3%) cases. Majority were males 17 (65.4%) and 9 (34.6%) were females. Most common cause of pericardial effusions were neoplastic diseases 10 (38.5%), idiopathic found in 8 (30.8%) cases, 3 (11.4%) had uremia, bacterial infections in 2 (7.7%) cases, frequency of HIV cases was 2 (7.7%) and 1 (3.8%) had other causes. Among 26 patients of pericardial effusions, small size effusion found in 14 (53.8%) cases, moderate size in 8 (30.8%) cases and large size in 4 (15.4%) cases. Conclusion: According to this study,patients with unexplained dyspnea had an increased risk of developing pericardial effusion,. The most prevalent cause of pericardial effusion was a neoplastic disease. Keywords:Electrocardiogram, Causes, Pericardial Effusion, Frequency, Dyspnea
In a world where potable water is just about to run dry, it is necessary to introduce new technologies and methods of solar-based water purification systems. Developing countries like Pakistan are cladding a shortage of purified water and its storage process. Our proposed design for water gets purified by using multijunction solar cells, cationic polyacrylamide alum, and lime. Multijunction solar cells are utilized to enhance the efficiency of the system. They utilize the complete spectrum of sunlight and absorb the different colors of light by different materials, and each material has its own bandgap energy. The solar cells generate power which is used to boil the contaminated water for 30 minutes up to 120 degrees for the purification purpose and remove bacteria, protozoa, and viruses because all germs become dead when water boils for 30 minutes. Alum is used for the purpose of purification because alum, cationic polyacrylamide, and lime or coagulant are utilized to remove arsenic from water. To remove COVID-19 from water, ozone gas O3 is injected. Charcoal filter paper is utilized to filter the boiling water energy stored in the battery to drive the system for nighttime purposes. The proposed design is economical, environmentally friendly, and works at maximum time. Nowadays, an IOT-based smart water purification system has been installed which works on solar energy.
Atherosclerosis causing occlusion of coronary vessels by building up of plaque leading to narrowing of vessels supplying heart and causing coronary artery disease, which is the leading and common cause of mortality around the globe. Objective: To find the correlation of Red Cell Distribution Width (RDW) and severity of Coronary Artery Disease (CAD) lesions Methods: A number of 280 patients in total, admitted to cardiology department who presented with chest pain and diagnosed as angina, positive treadmill test and who underwent angiography and were found to have CAD, were enrolled in the study over a period of one year. Modified Gensini score (MGS) is used for assessment of severity of CAD. Each patient was assessed in relation to severity of CAD using MGS scoring system. Results: Out of 280 patients, 218 were assigned to Group A and 70 were assigned to Group B. Mean age of presentation were (52.34± 13.90 vs 50.8± 11.63 years). Male subjects were predominant overall with ratio of 2.63:1. RDW was assessed and was seen to be significantly elevated in Group A in comparison to Group B (14.98± 1.59 vs 13.82 ± 0.91p= <0.0001). After assessing MGS in relation to severity of CAD, significant correlation was observed. RDW was found to be increasing as MGS score increased (14.46± 0.65 vs 14.98± 1.00 vs 15.02± 0.88, p= <0.0001) Conclusions: It was concluded that RDW is a parameter which is cost effective, very easy, readily and urgently available for the assessment and stratification of patients presenting with coronary artery disease.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.