Clinical value of contrast-enhanced ultrasound in improving diagnostic accuracy rate of transthoracic biopsy of anteriormedial mediastinal lesions

Objective： To evaluate the clinical value of contrast-enhanced ultrasound（CEUS） in transthoracic biopsy of anterior-medial mediastinal lesions.Methods： A total of 123 patients with anterior or middle mediastinum lesions required ultrasound guided transthoracic biopsy for pathological diagnosis. Among them, 72 patients received CEUS examinations before biopsy. After CEUS, 8 patients were excluded from biopsy and the rest 64 patients underwent biopsy（CEUS group）. During the same period, 51 patients received biopsy without CEUS examination（US group）. The ultrasonography characteristics, the number of biopsy puncture attempts, diagnostic accuracy rate and the incidence of complications were recorded and compared between the two groups.Results： A large portion of necrosis area or superficial large vessels was found in 8 patients, so the biopsy was cancelled. The internal necrosis was demonstrated in 43.8% of the lesions in CEUS group and in 11.8% of US group（P0.001）. For thymic carcinoma, CEUS increased the detection rate of internal necrosis and pericardial effusion than conventional ultrasound（62.5% vs. 18.8%, P=0.012; 56.3% vs. 12.5%, P=0.023）. The average number of punctures in CEUS group and US group was 2.36±0.70 and 2.21±0.51 times, respectively（P0.05）. The diagnostic accuracy rate of biopsy in CEUS group（96.9%, 62/64） was significantly higher than that in US group（84.3%, 43/51）（P=0.022）. In US group, 2 patients suffered from mediastinal bleeding（3.9%）, while no major complications occurred in CEUS group.Conclusions： CEUS examination provided important information before transthoracic mediastinum biopsy and improved diagnostic accuracy rate in biopsy of anterior and middle mediastinum lesions than conventional ultrasound.

SYSTEM RELIABILITY OF ASSURED ACCURACY RATE FOR MULTI-STATE COMPUTER NETWORKS FROM SERVICE LEVEL AGREEMENTS VIEWPOINT

From the viewpoint of service level agreements, the transmission accuracy rate is one of critical performance indicators to assess internet quality for system managers and customers. Under the assumption that each arc＇s capacity is deterministic, the quickest path problem is to find a path sending a specific of data such that the transmission time is minimized. However, in many real-life networks such as computer networks, each arc has stochastic capacity, lead time and accuracy rate. Such a network is named a multi-state computer network. Under both assured accuracy rate and time constraints, we extend the quickest path problem to compute the probability that d units of data can be sent through multiple minimal paths simultaneously. Such a probability named system reliability is a performance indicator to provide to managers for understanding the ability of system and improvement. An efficient algorithm is proposed to evaluate the system reliability in terms of the approach of minimal paths.

Stochastic computer network with multiple terminals under total accuracy rate

From the viewpoint of service level agreements,data transmission accuracy is one of the critical performances for assessing Internet by service providers and enterprise customers.The stochastic computer network(SCN),in which each edge has several capacities and the accuracy rate,has multiple terminals.This paper is aimed mainly to evaluate the system reliability for an SCN,where system reliability is the probability that the demand can be fulfilled under the total accuracy rate.A minimal capacity vector allows the system to transmit demand to each terminal under the total accuracy rate.This study proposes an efficient algorithm to find all minimal capacity vectors by minimal paths.The system reliability can then be computed in terms of all minimal capacity vectors by the recursive sum of disjoint products(RSDP) algorithm.

Track correlation algorithm based on CNN-LSTM for swarm targets

The rapid development of unmanned aerial vehicle(UAV) swarm, a new type of aerial threat target, has brought great pressure to the air defense early warning system. At present, most of the track correlation algorithms only use part of the target location, speed, and other information for correlation.In this paper, the artificial neural network method is used to establish the corresponding intelligent track correlation model and method according to the characteristics of swarm targets.Precisely, a route correlation method based on convolutional neural networks (CNN) and long short-term memory (LSTM)Neural network is designed. In this model, the CNN is used to extract the formation characteristics of UAV swarm and the spatial position characteristics of single UAV track in the formation,while the LSTM is used to extract the time characteristics of UAV swarm. Experimental results show that compared with the traditional algorithms, the algorithm based on CNN-LSTM neural network can make full use of multiple feature information of the target, and has better robustness and accuracy for swarm targets.

A Novel Machine Learning-Based Hand Gesture Recognition Using HCI on IoT Assisted Cloud Platform

Machine learning is a technique for analyzing data that aids the construction of mathematical models.Because of the growth of the Internet of Things(IoT)and wearable sensor devices,gesture interfaces are becoming a more natural and expedient human-machine interaction method.This type of artificial intelligence that requires minimal or no direct human intervention in decision-making is predicated on the ability of intelligent systems to self-train and detect patterns.The rise of touch-free applications and the number of deaf people have increased the significance of hand gesture recognition.Potential applications of hand gesture recognition research span from online gaming to surgical robotics.The location of the hands,the alignment of the fingers,and the hand-to-body posture are the fundamental components of hierarchical emotions in gestures.Linguistic gestures may be difficult to distinguish from nonsensical motions in the field of gesture recognition.Linguistic gestures may be difficult to distinguish from nonsensical motions in the field of gesture recognition.In this scenario,it may be difficult to overcome segmentation uncertainty caused by accidental hand motions or trembling.When a user performs the same dynamic gesture,the hand shapes and speeds of each user,as well as those often generated by the same user,vary.A machine-learning-based Gesture Recognition Framework(ML-GRF)for recognizing the beginning and end of a gesture sequence in a continuous stream of data is suggested to solve the problem of distinguishing between meaningful dynamic gestures and scattered generation.We have recommended using a similarity matching-based gesture classification approach to reduce the overall computing cost associated with identifying actions,and we have shown how an efficient feature extraction method can be used to reduce the thousands of single gesture information to four binary digit gesture codes.The findings from the simulation support the accuracy,precision,gesture recognition,sensitivity,and efficiency rates.The Machine Learning-based Gesture Recognition Framework(ML-GRF)had an accuracy rate of 98.97%,a precision rate of 97.65%,a gesture recognition rate of 98.04%,a sensitivity rate of 96.99%,and an efficiency rate of 95.12%.