Journals reviewed: Detection of intelligent pension and medical care In April 28, 2011, Chinese Bureau of Statistics released the “In 2010 Sixth National Census Data (No. first)”.In the composition of age, the population aged 60 and over is 177648705,accounting for 13.26%,the population aged 65 and over is 118831709,accounting for 8.87%. Compared with the 2000 fifth national population census, the proportion of the population aged 60 and over increased by 2.93 percentage points, the proportion of the population aged 65 and over increased by 1.91 percentage points.[1]Based on the above data, we can see that China has been in the stage of population aging society, the proportion of elderly in the total population is large. Under the background of the country’s population aging, how to make the elderly live healthier lives and how to detect the body and activity for a disease of the elderly, make the life safer, avoid accidents and so on have been a problem concerned by the whole society.Nowadays, a remote monitoring and diagnosis technology based on network and human physiological parameters sensor has become hot spot of research. This technology mainly take advantage of network information technology to conduct remote data monitoring of human physiological characteristics and distinguishing diagnosis and the realization of interaction between patients and medical personnel, medical institution, medical equipment, to achieve real-time online monitoring and make evaluation to the state of the person being monitoring. Once the abnormal situation, there will be a timely alarm or informs of alerting relevant personnel for disposal. At present, the domestic research in this area is divided into three levels: (1) the intelligent research about disease diagnosis and treatment,(2) health monitoring and management based on network.(3) preliminary intelligent medical system.The study on first level is modeling or expert system to some disease diagnosis. The main process is: according to the experience of doctor and pathological knowledge and clinical data, we can make the extracted factors and characteristics closely related to the disease as the input parameters and whether suffering this disease as the output parameters, and then use the clinical data to model training and validation to discriminate whether suffer this disease for a patient with the proposed model or expert system. Some achievement of research in this area has high rate of success to the diagnosis of partial disease, and accumulate substantial knowledge and experience to the subsequent material intelligent medical treatment. For example, Liaoning University professor Wang Yanqiu guides students to discuss the symptom of abdominal pain, by using fuzzy neural network algorithm, to discriminate the kind of diseases. They study the relevant acute appendicitis, gastric cancers, acute intestinal obstruction and other 12 kinds of diseases.[2] The research include fuzzy neural network and related expert knowledge of various diseases corresponding abdominal pain. Some expert knowledge express with fuzzy neural network, and take advantage of clinical data to train, combined with other relevant information, achieve certain results in the auxiliary diagnosis and treatment of abdominal pain. A similar research is: Shen Hong[3] use BP neural networks to identify 3 kinds of ECG-the normal, inferior wall myocardial infarction and acute anterior myocardial infarction. Wang Jiaxiang[4] discusses the application value of ANN in diagnosis of liver cancer, making higher sensitivity and specificity than traditional methods. Zhao Bingrang[5] apply ANN to the diagnosis of coronary heart disease. They practice by 1200 cases and detect 300 cases, then conduct simulation of 167 cases diagnosis. The results show that the accuracy of ANN diagnosis was 91.02%, sensitivity and specificity were 92.79% and 87.05%. Wang Yijie[6] of Nanjing University of Traditional ChineseMedicine conduct the research about mobile online diagnosis of traditional Chinese medicine diseases, and make a certain effect after expert arguments and trials.Research on this aspect mainly focuses on identification and diagnosis of the diseases, its core is the combination of experience of doctor, pathological knowledge and intelligent algorithm. At present, this method has achieved some results. The accuracy of recognition and diagnosis to some diseases is high by using this method and this method also greatly improves the medical efficiency. The achievement of this aspect has great practical significance to monitoring and treating some remote online patients. Difficulties in research in this area are how to improve the diagnosis accuracy of model or expert system. It needs more relevant information and there is challenge to collection of information. In addition, the expression of expert knowledge is one of the key factors, especially in traditional medicine. Because a lot of theory or knowledge are not very accurate, the researchers face to a problem how to better express medical theory and knowledge.Research on second level is mainly lead Internet to the inspection management of the medical and health, to achieve remote or online inspection and management, but the diagnosis function is relatively weak or not. The monitoring research of this system more and more depend on the sensors, and the management is more of an alarm and real-time monitoring of human physiological parameters mechanism. Research on this aspect is: Liu Chun [7] of Institutes of Technology of South China researches a kind of intelligent healthy monitoring equipment based on embedded system which can realize intelligent inspection and diagnosis to human physiological parameters, and transmits the data to the remote monitoring center. Real-time monitoring system identifies healthy risk information and gives an alarm signal and analyzes data, to realize intelligent detection and management to monitoring objects which have differential age, gender, physical and diseases varied from person and person. Xue Bingbing [8] of the Southern Medical University designed a kind of miniature multi-parameters health monitoring terminals based on STM32, which can collect some information of ECG, heart rate and posture, and interact with smart devices, give an alarm for abnormal detection index. Yang Peng[9] of Hebei University of Technology designed intelligent furnishing system which can access to real-time elderly physiological information based on ZigBee protocol wireless body area network. This system can realize the remote real-time monitoring to the elderly health status, and give an alarm to abnormal situation, to avoid accidents. Yu Wenbin[10] of Shanghai Jiao Tong University designed body sensor network, positioning system and intelligent alarm system for the cardiovascular disease and Alzheimer’s disease, to monitor the health status of the elderly. Zhao Jinmeng[11] of Institutes of Technology of South China also performed a similar research.Research on this level is combined a variety of network technology with human physiological parameters sensor, transmits some original medical room monitoring data into convenient and worn equipment in home or portable to monitor, and it is convenient and continuous real-time monitoring which can make objects more convenient. Due to the development of network technology, remote transmission and display about medical data and human physiological health data become a reality, which bring a great revolution of medical treatment and health monitoring. At present, many companies develop this research and relevant products, such as smart watches, smart bracelet and so on which include similar functions. The challenges of this level mainly come from the accuracy of sensor, and how to integrate more sensors and ensure its measurement accuracy will be a long faced problem to researchers in this field.Research on third level is a process that combine two researched to continue to explore online diagnosis and treatment based on the above two researches. At present, this filed is still in the relatively early stage. Many famous companies are studying this field, such as Google, Baidu, Apple, Tencent, Intel, IBM and so on. There are many research institutes which carry out the research on this filed. Mature products have not produced, but there have been experimental products and researches which have some basic framework and for some specific diseases. For example, Hu Bisong[12] of Chinese Remote Sensing Research Institute designed a kind of collaborative surveillance and response system based on Internet and mobile network in the C/S framework, established a set of producer which is suitable for the monitoring and early warning, on-site investigation and emergency response. Detection algorithm of this system use space-time scan statistics and the intelligent diseases diagnosis module use Bayesian algorithm. The system adopts intelligent diagnosis to diseases based on Bayesian algorithm based on probability. Bayesian algorithm requires a large amount of clinical data for training and needs a doctor’s medical knowledge. This part is based on the first level research. After the construction about diagnosis module, the application also needs corresponding data acquisition and the quickly network and the results of the second levels to complete. On this basis, we can conduct further diagnosis and treatment of the online site disease, but this step combined online data with existing models whose generalization ability, fault-tolerant ability and accuracy will be faced with new challenges. Similarly, Li Bing[13] of Beijing University of Posts and Telecommunications designed intelligent diagnosis system based on Delphi on the basis of diseases. It mainly depends on the symptom of diseases and signs of diseases and the clinical laboratory information to make intelligent diagnosis of diseases, to provide scientific references rapidly. Pi Jianfu[14] of Hubei University developed intelligent medical system by using cloud computing and other technologies. This system uses B/S architecture and cloud computing technology to efficiently process large amounts of data, to process data with distributed storage computing system based on Hadoop algorithm, to make quickly and easily effects. GU Gang[15] of Guangdong University of Technology guided students to study the domestic medical intelligent terminals about normal parameters acquisition and transmission. This research designed domestic medical intelligent terminals based on IP network, integrated HD video intercom and conventional medical data acquisition including blood pressure, ECG, body temperature and oxygen and other data, realizing the fast and convenient auxiliary medical diagnosis and monitoring. Liu Lin[16] of University of Electronic Science and Technology designed the mobile terminal intelligent system., its core is FPGA, with wireless communication and Socket technology to finish data acquisition and transmission, and show data with multi-thread methods to realize basic work of intelligent medicine.The above studies try to combine differential network information transmission technology, algorithm and the diagnosis of medicine, making differential intelligent medical experiments and achieving certain effects. Behind these system, there are two major technology support: (1)the network information technology for information transmission and monitoring sensor;(2) the diagnosis model or expert system based on medical theory and clinic data. These two techniques are compared, the first part of the technology is relatively mature, its challenge lives the accuracy of sensor and network data transmission has completely achieved the general requirements of differential diseases diagnosis. The second part of the technology faces more problems, one of the key problem is how to obtain or express medical theoretical knowledge in networktechnology and abundant clinical data. The acquisition of expert knowledge is always a difficulty problem in the field of information, especially in medical aspects. If the expression and acquisition of expert can be improved, the development of intelligent medical technology can be greatly promoted. There is a lot of scholars’ research in this field. For example, Sun Boqing[17] of Harbin Institute of Technology studied the expert knowledge acquisition and expression of diagnosis system in the basic of neural network, and achieve good results in the intelligent diagnosis system corresponding to cardiovascular disease. Zhan Guohua[18] of Hangzhou Normal University guided students to investigate medical networking data fusion algorithm. The study mainly aims at the integration of multi-source heterogeneous data of medical networking in order to improve the network transmission efficiency and reduce power consumption, and finally the design of data fusion system has been tested and achieved a certain effect. Zhang Siqi[19] of the University of Macao study the data of heart diseases diagnosis, see some diagnosis rules of practical reference value, achieve high classification accuracy. They analyze some methods of diagnosis and treatment of data preprocessing in other article, laying the foundation of the data mining [20]. Wang Ping of Xihua University guided students to collect relevant signals with heart sound sensor, pulse sensor, breath sound sensor for the cardiovascular diseases, by using multi-source information fusion methods to diagnose the symptom of the cardiovascular diseases. During the multi-source information fusion process, neural network and cluster analysis and support vector machine algorithm has been used and have achieved good results [21]. These researches based on differential algorithms for the data mining of differential diseases and the researches of medical knowledge laid the foundation of intelligent medicine.At present, in the medical and health monitoring of elderly and patients, most of the researches is similar to the above article. They mainly base on medical theoretical knowledge, abundant clinical data and differential data modeling algorithm, differential network information transmission techniques and so on. There are few researches which can include the impact of the data of daily life and the background of society, but these factors also have a important difference to the health monitoring and prediction of diseases in the elderly, and even adjusting the life style and habits, we can prevent or avoid the happen of diseases by using differential policies and differential social support for groups of differential social background.Researches of the daily life and the social background still remain in the stage of God science and psychology research. For example, Liu Fang[22] carry on the question survey to 483 retired elderly of 4 communities in Wuhan City with the geriatric depression scale and self-designed questionnaire, through the understanding of the situations and factors of depression symptom of the retired elderly. The results of chi square analysis showed that the low average family income, poor self-care ability, suffering various diseases, loneliness, social support and weak interpersonal relationship, the lack of recreational activities of the elderly have a higher incidence of the depression symptoms. Logistic regression analysis showed that social support, interpersonal relationship, the average family income, occupation, self-care ability, loneliness are the potential factors of occurrence of depression in the elderly. Structural equation model showed that social function, physical health, loneliness to the occurrence of elderly depression have statistical signification. The results show that the relationship between the retired elderly depression symptoms and social function, physical health and loneliness is large. We can prevent the occurrence of diseases by improving social function, strengthening physical exercise, participating more activities and communicating with more people. Tang Zhe[23] study the influence ofpopulation life expectancy and active life expectancy on the economic status of the elderly in Beijing. They investigate 3257 cases of over 55 age people in the urban of Beijing City(Xuan WU), suburban(Da Xing), outer suburb(Huai Rou) in 1992, and understand the survival and health status of the follow-up samples in 1994 and 1997. If they can perform activities of daily life(ADL) independently, we identify they are healthy. The index of socioeconomic status(SES) include education, income, occupancy and family owned property, and is divided into high and low level and be distinguished according to the results of investigation. The life expectancy (LE) and active life expectancy(ALE) are been calculated by using IMACH software multi-state life table. The results show that LE and ALE in the elderly is lower in men than women, but the divisor of ALE and lE is higher in men than women. According differential index calculation, high level of SES increase by 20%~52% than low level of SES (extended to 2.10~5,77 years) in men, 4%~25% in women(extended to 0.6~4.3 years), ALE of men increase by 30%~77%(extended to 2.1~4.0 years),5%~73% in women(extended to 0.6~5.6 years). Social economic status can improve the active life expectancy. Li Haichao[24] establish health demand model by using the ordered Probit model, analyzing the healthy demand influence on social economic factors. We can obtain the sample by using stratified sampling method according to gender, area, including 506 males and 470 females, 450 people from urban and 526 people from rural areas. They analyze these data by using the ordered Probit model with STATA software, making the health status as dependent value and age, income, education, marriage and health behavior and so on factors as independent value. The results show that in two models, there were significant differences on the difference of income, education, age (P<0.05). Health demand increases with the levels of income and the degree of education. With increasing age, health demand decrease. The demand of males is larger than females, because men are main incomers of family, who have more disposable income. The number of children in a family as an increasing health demand significant variable may be due to the increasing of the responsibility and health time of parents lead to the increasing demand of health as a result of the increasing number of children. Regular smoking and drinking liquor has a negative impact on the health demand because these two variables increase people’s contempt for health. In contrast, physical exercise makes people pay more attention to health, so this variable has a positive effect on health demand. The country should consider the influence of social economic factors in formulating the healthy policy, make the policy more scientific and reasonable by using relevant model, which support reference to relevant healthy policy. Peng Xia[25] study the healthy adults pulse pressure difference and its influencing factors in Yunnan Province. They choose the samples of 8000 people to collect data by using the method of cluster, stratified, and random sampling. Two people input parallel data by using EpiData3.0 to establish database, and conduct the data processing and statistical analysis by using SPSS17.0. PP>50mmHg was increased. The results show that the rate of the increased pulse pressure influence is 36.2% on healthy adults of Yunan Province. Gender, age, regular physical examination, smoking, drinking, exercise, sleeping, nap habits, and body mass index (BMI) have differences on the adult pulse pressure difference(P<0.05~0.01); Non conditional Logistic regression analysis showed that smoking(OR=1.84,95%CI:0.39~2.17), age> 65 years(OR=1.01,95%CI:0.31~1.86) are risk factors for the increased pulse pressure difference. We can see that the rate of the increased pulse pressure difference of healthy adults of Yunan Province. The main influencing factors are some daily habits.From the above researches, the data of people’s daily life and the data of the socialbackground level have a direct influence to people, especially for the health of the elderly. If these factors are also taken into account on the third level of intelligent medicine, we will greatly improve the prevention of disease and keep people’s daily life health, to ensure the physical state of people’s physiological parameters.Reference:[1]: National Bureau of statistics of China, In 2010 Sixth National Census Data (No. first), [N], 2011[2]: Mao Liang, Intelligent medical aided diagnosis system based on fuzzy neural network, Liaoning: Liaoning University of Technology, 2007.[3]: Shen Hong, Zhang Liangzhen, Qin Wei, Shi Liang BP network system for identifying ECG [J]. Shanghai Journal of Biomedical Engineering, 1998, 19 (4): 13-18.[4]: Wang Jiaxiang, Zhang Bo, Yu Jiekai, et al. Application of serum protein fingerprinting coupled with artificial neural network model in diagnosis of hepatocellular carcinoma [J]. Chin Med J,2005 ,118(15): 1278-1286.[5]: Zhao Bingrang, Hu Beilai, Qin Qin, et al. Application of artificial neural network in the diagnosis of coronary heart disease [J]. Tianjin medicine, 2002,30 (9):575-576.[6]: Wang Yijie, Wang Haixiao, Yang Tao. Mobile phone online TCM diagnosis research based on Bayesian algorithm [J].software journal, 2010, 9 (12): 97-99.[7]: Liu Chun, Zhai Jingmei, Xu Xiao, Chen Zhen. Research of .intelligent health monitoring devices based on Embedded Technology [J] 2009, (11): 258-260..[8]: Xue Bingbing, Wu Shuyu, Li Yaping, Geng Qingshan, Zhou Linghong. Application of micro multi-parameter health monitoring terminals based on STM32, The application of Electronic Technology 2014, 40 (2): 12-15.[9]: Yang Peng, Gao Yong, Xu Qinqi, Xuan Bokai. Intelligent furnishing system of monitoring physiological parameters [J]control engineering, 2013, 20 (6): 1102-1105.[10]: Yu Wenbin, Du Rong, Xiao Long, Cheng Bo, Guan Xinping. The systemic design and application of the elderly livable environmental system [J]. Hebei Province Academy of Sciences, 2011, 28 (3): 10-13.[11]: Zhao Jinmeng, Wu Jianbo, Wu Xiaoming. Reserach of medical monitoring technology to intelligent furnishing [J]. Medical Equipment, 2010, 31 (10): 14-16.[12]: Hu Bisong, Gong Jianhua, Cao WuChun, Fang Liqun. Design and Realization of collaborative epidemical surveillance and response system [J].Computer Engineering,2009, 35 (22): 10-12.[13]: Li Bing. Intelligent disease diagnosis system based on Delphi [J]. Computer technology and development, 2010, 20 (4): 250-253.[14]: Pi Jianfu, Huang Chen. Design and research of intelligent medical analysis system based on Hadoop ,Technology of the Internet of things 2014, (9): 25-27.[15]: You Suqin,of domestic intelligent medical terminal to normal physiological parameters acquisition and transmission. [D]Guangzhou: Guangdong University of Technology, 2011[16]: Han Lu, The design and implementation of the intelligent medical system based on portable terminal [D]. Chengdu: University of Electronic Science and technology, 2013[17]: Sun Baiqing, Pan Qishu, Feng Yingjun, Zhang Changsheng, Guan Zhenzhong. Medical diagnosis system of expert knowledge expression and Acquisition method [J]. Journal of Harbin Institute of Technology, 2001, 33 (1): 134-136.[18]: He Yanwen, Research of medical networking data fusion algorithm.[D]. Hangzhou: Hangzhou University, 2012[19]: Zhang Siqi, Zhou Shuwen, Gong Zhiguo, Dong Mingchui. Research on knowledge discovery in medical data [J].Journal of Shenyang University, 2004, 16 (4): 31-34.[20]: Zhang Siqi, Zhou Shuwen, Gong Zhiguo, Dong Mingchui,Data pre-processing of medical diagnosis system. [J] Control engineering. 2005, 12 (1): 33-35.[21]: Zhao Libo, the multi-sensor information fusion of intelligent medical monitoring system [D]. Chengdu: Xihua University, 2010[22]: Liu Fang, Luo Hao, Hu Shuhua, Liang Xun, Gao Shanrong, Wang ZengzhenThe analusis of the influencing factors of the retired elderly depressive symptoms [J]. Chinese social medical journal 2012, 29, (2):121-123.[23]: Tang Zhe, Toshiko Kaneda, Xiang Manjun, Fang Xianghua, Zachary Zimmer The life expectancy and the healthy life expectancy of the elderly of different social economic status in Beijing city [J]. Chinese Journal of clinical rehabilitation, 2004, 8 (30): 6569-6571.[24]: Li Haichao, Li Yingyan, Wang Aiying, Wu Jian, Wang Yi. Health requirement analysis by using the ordered Probit model [J]Clinical Rehabilitative and Tissue Engineering Research of China , 2008, 12 (11): 2157-2160.[25]: Peng Xia, Luo Yangheng, Song Xianyi, Lu Yichun, Dong Yanrong, Duan Zhiquan, Shi Yanan, Zhao Lijuan, Lu Lin The analysis of pulse pressure difference of healthy adults and relevant factors in Yunan Province [D]. Basic and clinical medicine, 2013, 33 (5): 548-551.。