Isolated hepatic tuberculosis mimicking liver tumors in a dialysis patient

Cases of isolated hepatic tuberculosis (TB) are rare. The diagnosis is often delayed or missed because of nonspecific symptoms and laboratory findings. Besides, the disease is extremely rare even in a country where TB is an alarming public health problem. This report demonstrates the difficulty in correctly diagnosing local hepatic TB. We report the case of a 62‐year‐old male patient with end‐stage renal disease treated with hemodialysis, who developed 2 months of abdominal distension and general anorexia, with hyperechoic hepatic lesions on ultrasound. Computed tomography suspected multiple liver tumors. The liver biopsy finally led to the diagnosis of TB of the liver without other involvements. We conclude that isolated hepatic TB is one of the rare forms of extrapulmonary TB in dialysis patients. A greater awareness of this rare clinical entity may prevent needless surgical interventions.     

Wearing prediction of stellite alloys based on opposite degree algorithm

In order to predict the wearing of stellite alloys,the related methods of rare metals data processing were discussed. The method of opposite degree(OD) algorithm was put forward to predict the wearing of stellite alloys.OD algorithm is based on prior numerical data, posterior numerical data and the opposite degree between numerical forecast data. To compare the performance of predicted results based on different algorithms, the back propagation(BP) and radial basis function(RBF) neural network methods were introduced. Predicted results show that the relative error of OD algorithm is smaller than those of BP and RBF neural network methods. OD algorithm is an effective method to predict the wearing of stellite alloys and it can be applied in practice.     

基于注意力机制与文本信息的用户关系抽取

随着社交媒体的发展,用户之间的关系网络对于社交媒体的分析有很大的帮助。因此,该文主要研究用户好友关系检测。以往的关于用户好友关系抽取的研究主要基于社交媒体上的结构化信息,比如其他好友关系,用户的不同属性等。但是,很多时候用户本身并没有大量的好友信息存在,同时也不一定有很多确定的属性。因此,我们希望基于用户发表的文本信息来对用户关系进行预测。不同于以往的潜在好友推荐算法,该文提出了一种基于注意力机制以及长短时记忆网络(long short-term memory,LSTM)的好友关系预测模型,将好友之间的评论分开处理,通过分析用户之间的评论来判断是否具备一定的好友关系。该模型将好友双方信息拼接后的结果作为输入,并将注意力机制应用于LSTM的输出。实验表明,用户之间的评论对于好友关系预测确实有较大的实际意义,该文提出的模型较之于多个基准系统的效果,取得了明显的提升。在不加入任何其它非文本特征的情况下,实验结果的准确率达到了77%。     

针对不同地质目标的叠前时间偏移成像解释评价

随着计算机硬件和地震勘探成像技术的发展，叠前时间偏移正逐步替代常规的NMO加DMO加叠后时间偏移成为地震数据成像处理方法的主流。但对于不同的地质目标，叠前时间偏移的成像效果是否优于常规NMO加DMO加叠后时间偏移的成像效果呢？为此，从地震数据成像处理方法、处理流程和处理参数等方面进行了讨论，并基于某地区三维数据常规处理结果和叠前时间偏移处理结果，针对不同地质目标进行了剖析与评价。认为：叠前时间偏移成像的垂向分辨率较常规处理明显降低，但对于空间波阻抗变化明显的河流和断层，叠前时间偏移成像的空间分辨率要高于常规处理；对于小于1／4波长的叠置薄储层，叠前时间偏移成像的垂向和空间分辨率低于常规处理结果。     

声波测井换能器激发响应实验研究

声波测井换能器的激发响应由换能器振动时所表现出来的动态阻抗和激发电路参数决定。而换能器的动态（阻抗）参数随压电晶体及其装配方式（力学边界条件）改变。为了测量换能器动态参数的影响，采用声波测井仪器常用的压电晶体和升压变压器，通过改变激发脉冲宽度和直流电压进行了实验，结果发现：在换能器两端的瞬态响应中，一共有三个二阶网络响应，分别对应于不同的频率。最低的一个影响声波测井波形的基线、与换能器主频接近的一个决定激发效率以及电路与压电晶体之间的匹配关系，是激发电路设计中比较关键的，其参数可以通过导纳圆测量仪器得到。