Accurate Recommendation Approach of Psychological Consultation Information Based on User Portrait and TAG_SVD_CF

A hybrid recommendation algorithm of psychological counseling information based on user profile and item tag attribute with singular value decomposition(SVD) technology is developed. To solve the problem of data sparsity of the recommendation algorithm, the SVD technology is applied to collaborative filtering algorithm for optimizing the user item rating matrix. The recommendation algorithm includes two parts: generating medical user profile in accurate recommendation of medical information, and realizing the storage, query and update of user profile, where the index system of medical portrait was established from demographic attribute, interest label dimension and business social dimension. The performances of the developed algorithm are investigated by compared with the traditional cosine similarity and Pearson similarity. The results show that the proposed similarity has a lower mean absolute error and significantly improves the accuracy of the system.

Cancer Pattern among Adults in Najran, Saudi Arabia - 2014-2019

Background: Najran is one of the thirteen regions in Saudi Arabia, located in the southwest of the country with a recently established oncology center and cancer registry. This paper describes for the first time the incidence of cancer in this region which has a unique geographic and demographic attribute. Methodology: This is a retrospective descriptive study that included all adult (diagnosis age >14 years) cancer patients captured by Najran regional cancer registry in the period of 2014 to 2019. Available data, including demographics, diagnosis, site of the tumor, and histopathology were analyzed. Pediatric malignancies were excluded. During the studied period, a regional registry was established and linked to the central Saudi Cancer Registry. All confirmed cancer cases in Najran were captured in this registry. Results: The Total number of records was 1600 diagnosed over a 6-year period (range, 200-330 per year). More females were reported (54.6%) than males (45.4%). The median age was 52 years (SD, ±19). The three most common cancers were breast (14.2 %), thyroid (11.8%), and Colorectal (8.4%). Among the females, breast (25.3%) was the most common cancer followed by thyroid (16.7%), and colorectal (7%); while in males, colorectal cancers (10.2%), hepatocellular carcinoma (6.7%), and leukemia (6.6) were the most common. Conclusions: Breast cancer in females and colorectal cancer in males were the most frequent types of solid malignancies in Najran, Saudi Arabia. Our study shows that the pattern of cancers bears some similarities with the national and Gulf data with some differences that warrant further exploration.

SME’s financial literacy: An overview based on demographic aspects

This study attempts to examine the financial literacy level of SME’s owner in East Java based on demographic aspect. The sample was taken from 65 SME’s in East Java which produce prominent local product. The data were collected by using survey method and deep interview. They were analyzed using descriptive explorative and also cross tabulation for examining SME’s financial literacy based on demographic attribute. Research found that that the financial literacy score of SME’s owner in East Java is good enough, where they have average score 55.8 with the same score of median and mode 66.7. Majority weakness of SME’s owner is the literacy on SME understanding of net asset and insurance premium. Otherwise, whole SME’s owner is fully understood that financial knowledge is so useful for the SME. Other finding shows that there is a relationship between financial literacy’s level and SME’s owner on demographic aspect such as gender, education, the business time established. It can be concluded that demographic aspects determine the financial literacy level of SME’s owner

Learned Features are Better for Ethnicity Classification

Ethnicity is a key demographic attribute of human beings and it plays a vital role in automatic facial recognition and have extensive real world applications such as Human Computer Interaction (HCI); demographic based classification; biometric based recognition; security and defense to name a few. In this paper, we present a novel approach for extracting ethnicity from the facial images. The proposed method makes use of a pre trained Convolutional Neural Network (CNN) to extract the features, then Support Vector Machine (SVM) with linear kernel is used as a classifier. This technique uses translational invariant hierarchical features learned by the network, in contrast to previous works, which use hand crafted features such as Local Binary Pattern (LBP); Gabor, etc. Thorough experiments are presented on ten different facial databases, which strongly suggest that our approach is robust to different expressions and illuminations conditions. Here we consider ethnicity classification as a three class problem including Asian, African-American and Caucasian. Average classification accuracy over all databases is 98.28%, 99.66% and 99.05% for Asian, African-American and Caucasian respectively. All the codes are available for reproducing the results on request.