Study on emotion recognition and companion Chatbot using deep neural network

Multimedia Tools and Applications - With the development of technology, the importance of the research on speech emotion recognition and semantic analysis has increased. The research is primarily...     

Re-entrant lines with unreliable asynchronous machines and finite buffers: performance approximation and bottleneck identification

In this paper we study a re-entrant line with unreliable asynchronous exponential machines and finite buffers. First, an approximation method is presented to estimate the throughput of the re-entrant line. The idea of the approximation is to transform an M-machine re-entrant line into a 2M-machine serial line. Then, a system approach to identify a c-bottleneck based on blockage and starvation information is proposed, where a c-bottleneck machine is the machine whose improvement in machine capacity leads to the largest improvement in system throughput compared with improving all other machines. It is shown that the approximation method results in acceptable accuracy, and the bottleneck identification method can correctly detect the bottlenecks in most cases.     

盐干海参的2种核酸提取方法比对及其分子鉴定

目的 建立盐干海参的核酸提取及其分子鉴定方法。方法 选取5种盐干海参, 采用直接处理、洗涤处理和浸泡处理3种处理方式, 比较磁珠法和离心柱法两种核酸抽提方式的提取质量, 并采用聚合酶链式反应(polymerase chain reaction, PCR)法对提取的核酸进行分析确认。结果 同一种抽提方式不同海参处理组间核酸质量没有显著差异, 而两种抽提方式间核酸质量差异显著, 其中磁珠法提取的核酸得率高、纯度高, 而离心柱法提取的核酸得率及纯度均偏低。经PCR扩增验证, 磁珠法提取的核酸效果较佳。将扩增产物进行测序及系统进化分析发现5种海参实际种类与标注名称仿刺参存在较大差异。结论 盐干海参处理方式对核酸提取结果影响不大, 磁珠法提取核酸效果较好,单纯依靠COI和16S rRNA基因通用引物并不能对所有的海参种类进行鉴定。     

基于稀疏自编码器和边缘保持的Wishart马尔科夫随机场的极化SAR图像分类

针对极化SAR图像训练样本数目较少问题以及极化SAR图像同质区域较多的特性,提出了一种新的两层分类框架,结合了稀疏自编码器和边缘保持的Wishart马尔科夫随机场对极化SAR图像进行分类.该框架包括个步骤,第一个步骤使用稀疏自编码器来获得一个初始分类;第二个步骤使用边缘保持的Wishart马尔科夫随机场对第一层的分类结果进行修正.在应用Wishart马尔科夫随机场的过程中,由稀疏自编码器分类得到的边缘得以保持,并且提出了新的分类错误纠正策略确保分类的准确性.因此,通过稀疏自编码器得到的精确分类边缘可用于不同的区域并且在应用Wishart马尔科夫的过程中得以保持.和其他分类方法相比,该方法得到较高的分类精度,证明了新方法的有效性.     

Adaptive channel assignment scheme for wireless networks

In this paper, an adaptive channel assignment scheme is proposed to ensure the quality of services for the wireless networks. The proposed scheme divides the channels into two categories, the guard channels and the shared channels. The number of guard channels is estimated by the Markovian model in order to keep the handoff calls higher priority. The remaining channels, called shared channels, can be used by both new calls and handoff calls. The proposed scheme based on incoming rates of handoff and new calls allocates channels for guard and shared channels. In addition, this approach is able to provide quality of service guarantee in terms of handoff dropping rate. From the simulation, the proposed scheme significantly improves the dropping rate and the blocking rate in comparison with the existing methods.     

Non-Contact Physiological Measurement System for Wearing Masks During the Epidemic

Physiological signals indicate a person’s physical and mental state at any given time. Accordingly, many studies extract physiological signals from the human body with non-contact methods, and most of them require facial feature points. However, under COVID-19, wearing a mask has become a must in many places, so how non-contact physiological information measurements can still be performed correctly even when a mask covers the facial information has become a focus of research. In this study, RGB and thermal infrared cameras were used to execute non-contact physiological information measurement systems for heart rate, blood pressure, respiratory rate, and forehead temperature for people wearing masks due to the pandemic. Using the green (G) minus red (R) signal in the RGB image, the region of interest (ROI) is established in the forehead and nose bridge regions. The photoplethysmography (PPG) waveforms of the two regions are obtained after the acquired PPG signal is subjected to the optical flow method, baseline drift calibration, normalization, and bandpass filtering. The relevant parameters in Deep Neural Networks (DNN) for the regression model can correctly predict the heartbeat and blood pressure. In addition, the temperature change in the ROI of the mask after thermal image processing and filtering can be used to correctly determine the number of breaths. Meanwhile, the thermal image can be used to read the temperature average of the ROI of the forehead, and the forehead temperature can be obtained smoothly. The experimental results show that the above-mentioned physiological signals of a subject can be obtained in 6-s images with the error for both heart rate and blood pressure within 2%~3% and the error of forehead temperature within ±0.5°C.     

Performance approximation of re-entrant lines with unreliable exponential machines and finite buffers

In this paper, we present an approximation method to estimate the production rate of re-entrant lines with unreliable exponential machines having identical processing times, finite buffers, and last buffer first serve scheduling policy. Recursive procedures are developed and structural properties are investigated. The results show that the proposed method provides an acceptable accuracy in production rate approximation for re-entrant lines.     

Major chemotypes and antioxidative activity of the leaf essential oils of Cinnamomum osmophloeum Kaneh. from a clonal orchard

Essential oils of 92 cutting clones from a clonal orchard of Cinnamomum osmophloeum Kaneh. were obtained by hydrodistillation and characterised by gas chromatography–mass spectrometry. Our results showed that the yields of essential oils ranged between 0.09% and 2.65% (vol/fresh wt). The constituents of essential oils varied among samples. The major chemotypes classified in the individual cutting clones were cinnamaldehyde (50 plants, representing 50–95% of the total volatiles), linalool (1 plant, 73.3%), β-cubebene (2 plants, 59.4% and 78.7%), and cinnamyl acetate (1 plant, 61.8%). The antioxidant activities of the four chemotypes were determined using a 1,1-diphenyl-2-picrylhydrazyl (DPPH) assay. The antioxidant activities of the essential oil decreased in the order of cinnamyl acetate > cinnamaldehyde > β-cubebene > linalool. Indigenous cinnamon oil extract showed a good free radical-scavenging capacity at all concentrations studied, except at 2 μg/ml. The scavenging activity increased with increasing concentration of the extract. The capability of the four essential oil chemotypes to reduce the stable radical, DPPH, to DPPH-H was assayed by a decrease in the IC₅₀ values of 10.4 (cinnamyl acetate type) to 29.7 (linalool type) μg/ml. These results suggest that the leaf essential oil of C. osmophloeum possesses chemical compounds with antioxidant activity which can be used as natural preservatives in food and/or by the pharmaceutical industry. Trees in this plantation which can be used for further propagation for the production of chemotypes of interest were identified.     

A power scheme of a wireless sensor network node for debris flow monitoring with move-triggered wake-up

In countries threatened by debris flow disasters, using wireless sensor networks (WSN) for debris flow monitoring and warning has become an important research topic. To detect the initial movement and subsequent moving status of monitored debris or rocks, a two-phase power scheme for a self-developed wireless inertial sensor has been proposed, implemented, and analyzed in this study. During the first phase, the power of the sensor node is disconnected to ensure that the sensor remains stationary. In the second phase, a hybrid scheme with periodic and move-triggered wake-up is actuated if the sensor is moved by debris or hit by rocks. A simple move detection algorithm is used to determine whether the node should enter sleep mode. The power models of the components of the proposed sensor node have also been discussed. Based on those models, the power consumption of the proposed power scheme has been determined and verified according to measurements. Analysis of the proposed hybrid power scheme can be easily generalized for WSN applications with sensor-triggered schemes. The relationship between the moving rate of monitored objects and the wake-up period in the moving detection algorithm was found to be nearly inversely proportional. The results can be employed to estimate and design sensor node power schemes for other similar applications, such as value asset monitoring and tracking.     

Lean Buffering in Serial Production Lines With Nonidentical Exponential Machines

Lean buffering is the smallest buffer capacity, which is necessary and sufficient to ensure the desired production rate of a manufacturing system. Literature offers methods for designing lean buffering in production systems with identical machines. The current paper extends these methods to serial production lines with nonidentical machines, assuming that they obey the exponential reliability model. For two-machine lines, exact formulas for lean buffering are derived, while for longer lines estimates are obtained. These results can be useful for production line designers and production managers to maintain the required production rate with the smallest possible inventories. Note to Practitioners-In production systems with unreliable machines, operation with no-buffers (i.e., JIT) leads to low throughput. Very large buffers lead to high throughput but undesirable quality and economics properties. So, which level of buffering is good? This is the question addressed in this paper. The good level of buffering is addressed in terms of line efficiency, i.e., the fraction of the maximum of the throughput, which is acceptable for the system. For example, assume that the desired line efficiency is 0.9 (i.e., 90% of the maximum throughput is viewed as satisfactory). Under such an assumption, this paper offers methods for calculating the smallest (i.e., lean) level of buffering, which guarantees the desired throughput, provided that uptime and downtime of the machines are distributed exponentially with arbitrary mean time to failure and mean time to repair.