Search

With the explosive grown network traffic, the traditional port- and payload-based methods are insatiable for the requirements of privacy protection as well as the fast real-time classification for the today traffic classification. Here, a network traffic classification model based on both the Self-Organizing Maps (SOM) and the K-means fusion algorithm is proposed. In which, the traffic data is initially clustered by the SOM network to derive the cluster number and each cluster center value. Then those values are taken as the initial parameters to run the K-means algorithm, achieving optimal classification. As results compared with the traditional K-means algorithm, the initially clustering done by using the SOM network not only inherits its advantages of simple method and efficient processing, but also reduces time cost. Moreover, a significant improvement in coossification accuracy is achieved with our proposed algorithm.

The mechanical arm for needle guidance consists of puncture link, RCM angle adjustment, and passive adjustment of mechanism position. The position of the passive mechanism was locked by manual adjustment, which requires certain locking moment, and the precision can reach 1 mm. In the process of angle adjustment of RCM, it was required that each joint should have an adjustment range of (+) 45 degrees and an adjustment accuracy of 0.5 degrees. Puncture requires high initial acceleration to penetrate human skin tissue. In this paper, the control system of the manipulator was studied.

To assist patients with ankle diseases in completing rehabilitation training, a wearable ankle orthosis was presented in this paper. Firstly, the SEA-DTS (the series elastic actuator based on the double-tendon-sheath transmission mechanism and torsion spring), the execution mechanism of the ankle joint and the control system were described. Then, a series of experiments regarding trajectory tracking, moment step response, and position frequency response are carried out to study the mechanical characteristics of the wearable ankle orthosis. Results show that the participation of the SEA-DTS helps the orthosis work smoothly, while causes a maximum deviation of 3.56° in the trajectory tracking, a 10ms-delay and a maximum 16% overshoot in the moment step response performance, the bandwidth of the orthosis is 5.5Hz. Finally, the results obtained from two isokinetic dynamometer experiments prove the effectiveness of the wearable ankle orthosis, which means the proposed orthosis can assist patients with ankle diseases in completing rehabilitation training.

In response to the current demand for the remote monitoring of older people living alone, a non-contact human vital signs monitoring system based on millimeter wave radar has gradually become the object of research. This paper mainly carried out research regarding the detection method to obtain human breathing and heartbeat signals using a frequency modulated continuous wave system. We completed a portable millimeter-wave radar module for wireless communication. The radar module was a small size and had a WIFI communication interface, so we only needed to provide a power cord for the radar module. The breathing and heartbeat signals were detected and separated by FIR digital filter and the wavelet transform method. By building a cloud computing framework, we realized remote and senseless monitoring of the vital signs for older people living alone. Experiments were also carried out to compare the performance difference between the system and the common contact detection system. The experimental results showed that the life parameter detection system based on the millimeter wave sensor has strong real-time performance and accuracy.

This paper develops an intelligent sports rehabilitation glove based on flexible robot technology. Designed for sports rehabilitation gloves through the rational design of flexible pressure sensing systems, micro-precision drives, intelligent control systems, and ergonomic gloves. Through the use of flexible lasso transmission, rehabilitation training is performed on the patient’s hand, and the endurance and endurance of the wearer’s daily life are enhanced. This paper combines the latest flexible sensing technology, intelligent control technology, and micro-precision driving technology with the advanced concepts and methods of sports medicine. Through the combination of medical and industrial research, it has developed low cost, comfortable wearing, convenient and practical, and can meet families, hospitals, and Wearable smart rehabilitation gloves for use in industries such as industry.

In this paper, we study the field of rehabilitation walker technology. The passive energy storage gravity support exoskeleton is suitable for patients with lower limb dysfunction or limited function caused by lower limb joint, muscle tissue damage or bone disease. The equipment studied in this paper can assist patients to carry out normal ground walking and up and down stairs, realize patient self-care, slow down the patient’s physiological pain, and reduce the economic and energy burden of the patient’s family members. As the proportion of the elderly population continues to rise, the physiological decline during the aging process makes the elderly’s limbs less flexible, with limb motor dysfunction and lower limb motor dysfunction. Manual laborers have long been engaged in labor with repetitive and long working hours. It is easy to cause occupational chronic musculoskeletal injuries or other occupational diseases by maintaining the same or improper working posture for a long time.

Special populations, such as empty-nesters, people with a mental health condition, active children, prison inmates, etc., have a considerable number. The WHO noted that there were 47.5 million people with dementia worldwide in 2016. As the number of people with dementia in low- and middle-income countries continue to increase, it is predicted that the total number of people with dementia will reach 75.6 million in 2030 and reach 135.5 million in 2050. The National Health and Family Planning Commission released the “China Family Development Report (2015)”, which is half of the total number of elderly people. The number of severely mentally disabled patients registered in the country reached 4.297 million, and there were 1, 650 national mental health professional institutions and more than 20, 000 psychiatrists. As of 2012, there were 681 prisons in the country, 300, 000 people in prison, and 1.64 million prisoners. More than 80% of the prisons have established video surveillance systems. The Ministry of Public Security’s “Emergency Release Platform for Children’s Missing Information” is about 100 people abducted every year. The number of missing children who are about one-millionth of a year is not found, and the missing rate is about three-tenths of a million. The real-time positioning of the above-mentioned special population has become the key to solving related problems. Relevant nursing homes, community institutions, mental health institutions, and prisons have become the main demand side.

Minimally invasive surgery is performed by using a slender rod-shaped surgical tool to penetrate into the body through a tiny incision on the surface of the human body. Compared with traditional open surgery, minimally invasive surgery can reduce surgical incisions and surgical scars, shorten recovery time, reduce bleeding volume and complications. At present, minimally invasive puncture surgery is basically performed by experienced physicians. The puncture procedure lasts for a long time and the physician’s energy is limited. Therefore, the development of automated minimally invasive puncture robots is of great significance. This paper studies the structure and control of remote motion centers in minimally invasive surgical robotics.