Fast and accurate interpretation of workload classification model.

How can we interpret predictions of a workload classification model? A workload is a sequence of operations executed in DRAM, where each operation contains a command and an address. Classifying a given sequence into a correct workload type is important for verifying the quality of DRAM. Although a previous model achieves a reasonable accuracy on workload classification, it is challenging to interpret the prediction results since it is a black box model. A promising direction is to exploit interpretation models which compute the amount of attribution each feature gives to the prediction. However, none of the existing interpretable models are tailored for workload classification. The main challenges to be addressed are to 1) provide interpretable features for further improving interpretability, 2) measure the similarity of features for constructing the interpretable super features, and 3) provide consistent interpretations over all instances. In this paper, we propose INFO (INterpretable model For wOrkload classification), a model-agnostic interpretable model which analyzes workload classification results. INFO provides interpretable results while producing accurate predictions. We design super features to enhance interpretability by hierarchically clustering original features used for the classifier. To generate the super features, we define and measure the interpretability-friendly similarity, a variant of Jaccard similarity between original features. Then, INFO globally explains the workload classification model by generalizing super features over all instances. Experiments show that INFO provides intuitive interpretations which are faithful to the original non-interpretable model. INFO also shows up to 2.0× faster running time than the competitor while having comparable accuracies for real-world workload datasets.

Incarceration of early gravid uterus with adenomyosis and myoma: report of two patients managed with uterine reduction.

Although gravid uterine incarceration is typically diagnosed during the early second trimester, we encountered two unusual cases in early pregnancy. A 34-year-old multiparous woman with adenomyosis presented at 7 + 2 weeks of gestation with increased urinary frequency and a sensation of incomplete bladder emptying. The uterine incarceration was successfully reduced by manual reduction and pessary insertion, and she delivered a normal infant at term. In the second case, a 31-year-old nulliparous woman with a large myoma complained of dysuria, acute urinary retention, and intense back pain at 6 weeks of gestation. Manual reduction was successful in the knee-chest position. Subsequent pessary insertion failed; however, a slight reduction in pain was achieved. After a week, the fetus spontaneously aborted. In summary, gravid uterine incarceration is a rare but potentially fatal condition for the fetus, and a suspicion of this condition in patients with urinary symptoms, especially urinary retention and pelvic pain, is important in the early gestation period.

Uterine rupture in pregnancies following myomectomy: A multicenter case series.

OBJECTIVE: The purpose of this case series was to retrospectively examine records of cases with uterine rupture in pregnancies following myomectomy and to describe the clinical features and pregnancy outcomes. METHODS: This study was conducted as a multicenter case series. The patient databases at 7 tertiary hospitals were queried. Records of patients with a diagnosis of uterine rupture in the pregnancy following myomectomy between January 2012 and December 2014 were retrospectively collected. The uterine rupture cases enrolled in this study were defined as follows: through-and-through uterine rupture or tear of the uterine muscle and serosa, occurrence from 24+0 to 41+6 weeks' gestation, singleton pregnancy, and previous laparoscopic myomectomy (LSM) or laparotomic myomectomy (LTM) status. RESULTS: Fourteen pregnant women experienced uterine rupture during their pregnancy after LSM or LTM. Preterm delivery of less than 34 weeks' gestation occurred in 5 cases, while intrauterine fetal death occurred in 3, and 3 cases had fetal distress. Of the 14 uterine rupture cases, none occurred during labor. All mothers survived and had no sequelae, unlike the perinatal outcomes, although they were receiving blood transfusion or treatment for uterine artery embolization because of uterine atony or massive hemorrhage. CONCLUSION: In women of childbearing age who are scheduled to undergo LTM or LSM, the potential risk of uterine rupture on subsequent pregnancy should be explained before surgery. Pregnancy in women after myomectomy should be carefully observed, and they should be adequately counseled during this period.

Invisible Brain: Knowledge in Research Works and Neuron Activity.

If the market has an invisible hand, does knowledge creation and representation have an "invisible brain"? While knowledge is viewed as a product of neuron activity in the brain, can we identify knowledge that is outside the brain but reflects the activity of neurons in the brain? This work suggests that the patterns of neuron activity in the brain can be seen in the representation of knowledge-related activity. Here we show that the neuron activity mechanism seems to represent much of the knowledge learned in the past decades based on published articles, in what can be viewed as an "invisible brain" or collective hidden neural networks. Similar results appear when analyzing knowledge activity in patents. Our work also tries to characterize knowledge increase as neuron network activity growth. The results propose that knowledge-related activity can be seen outside of the neuron activity mechanism. Consequently, knowledge might exist as an independent mechanism.