Development of an epileptic seizure prediction algorithm using R–R intervals with self-attentive autoencoder

Epilepsy is a neurological disorder that may affect the autonomic nervous system (ANS) from 15 to 20 min before seizure onset, and disturbances of ANS affect R–R intervals (RRI) on an electrocardiogram (ECG). This study aims to develop a machine learning algorithm for predicting focal epileptic seizures by monitoring R–R interval (RRI) data in real time. The developed algorithm adopts a self-attentive autoencoder (SA-AE), which is a neural network for time-series data. The results of applying the developed seizure prediction algorithm to clinical data demonstrated that it functioned well in most patients; however, false positives (FPs) occurred in specific participants. In a future work, we will investigate the causes of FPs and optimize the developing seizure prediction algorithm to further improve performance using newly added clinical data.

     

Rational Filters for Passive Depth from Defocus

A fundamental problem in depth from defocus is the measurement of relative defocus between images. The performance of previously proposed focus operators are inevitably sensitive to the frequency spectra of local scene textures. As a result, focus operators such as the Laplacian of Gaussian result in poor depth estimates. An alternative is to use large filter banks that densely sample the frequency space. Though this approach can result in better depth accuracy, it sacrifices the computational efficiency that depth from defocus offers over stereo and structure from motion. We propose a class of broadband operators that, when used together, provide invariance to scene texture and produce accurate and dense depth maps. Since the operators are broadband, a small number of them are sufficient for depth estimation of scenes with complex textural properties. In addition, a depth confidence measure is derived that can be computed from the outputs of the operators. This confidence measure permits further refinement of computed depth maps. Experiments are conducted on both synthetic and real scenes to evaluate the performance of the proposed operators. The depth detection gain error is less than 1%, irrespective of texture frequency. Depth accuracy is found to be 0.51.2% of the distance of the object from the imaging optics.     

Relationship of occupation to blood pressure among middle-aged Japanese men--the significance of the differences in body mass index and alcohol consumption

To clarify how and why blood pressure differs between occupations, the proportions of hypertensives, and the measures of blood pressure, body mass index (BMI) and alcohol consumption among the individuals not taking antihypertensive drugs were compared between the eight occupational categories using the data from a health check-up for 589 middle-aged Japanese males, mostly randomly selected from five areas in Japan. After adjusting for age, the relationships of occupation to the proportion of hypertensives and the mean systolic and diastolic blood pressure substantially differed among the five areas. However, after further adjustment for residence, these blood pressure levels (the proportion of hypertensives, and the mean systolic and diastolic blood pressure) were found to be higher for the "Personnel in transport and communications", the "Clerical personnel", the "Managerial and civil personnel" and the "Professional and technical personnel", whereas these values were consistently lowest in the "Service personnel". Age and residence-adjusted mean BMI was also higher for the four occupational categories with the increased blood pressure levels. According to a weighted multiple regression analysis across the eight occupations, the age and residence-adjusted mean BMI was a significant predictor of the age and residence-adjusted mean systolic and diastolic blood pressure (p = 0.068 and 0.018, respectively). These results suggest that the occupation-related changes in BMI may largely contribute to the occupation-related changes in blood pressure.     

A 63-year-old man with progressive cauda equina/conus medullaris syndrome

BACKGROUND: This article presents results of the acute treatment phase of a 2-site study comparing cognitive behavioral group therapy (CBGT) and treatment with the monoamine oxidase inhibitor phenelzine sulfate for social phobia. METHODS: One hundred thirty-three patients from 2 sites received 12 weeks of CBGT, phenelzine therapy, pill placebo administration, or educational-supportive group therapy (an attention-placebo treatment of equal credibility to CBGT). The "allegiance effect," ie, the tendency for treatments to seem most efficacious in settings of similar theoretical orientation and less efficacious in theoretically divergent settings, was also examined by comparing responses to the treatment conditions at both sites: 1 known for pharmacological treatment of anxiety disorders and the other for cognitive behavioral treatment. RESULTs: After 12 weeks, phenelzine therapy and CBGT led to superior response rates and greater change on dimensional measures than did either control condition. However, response to phenelzine therapy was more evident after 6 weeks, and phenelzine therapy was also superior to CBGT after 12 weeks on some measures. There were few differences between sites, suggesting that these treatments can be efficacious at facilities with differing theoretical allegiances. CONCLUSIONS: After 12 weeks, both phenelzine therapy and CBGT were associated with marked positive response. Although phenelzine therapy was superior to CBGT on some measures, both were more efficacious than the control conditions. More extended cognitive behavioral treatment and the combination of modalities may enhance treatment effect.     

Extended operation for T4 lung carcinoma

PURPOSE: The study objective was to determine an "optimal" individual pressure support (PS) level for beginning weaning with PS ventilation in patients with chronic obstructive pulmonary disease (COPD). MATERIALS AND METHODS: Eleven COPD patients intubated and ventilated for acute respiratory failure and judged ready for weaning were studied. The technique consisted of lowering the PS level from a point that was characteristic for each patient and measurable under controlled mechanical ventilation, after setting the ventilator as recommended for COPD patients judged ready for weaning, that is, peak inflation pressure (PIP). This determination was based mainly on exploring the diaphragm with an electromyographic technique by defining the optimal PS level as the lowest PS level associated with no EMG evidence of diaphragmatic stress. Diaphragmatic electromyographic activity (diEMG) was recorded by a bipolar esophageal electrode (Disa-Denmark), and the high-frequency electrical component/low-frequency ratio (H/L) was calculated. The reference H/L was determined during a few spontaneous ventilatory cycles. Muscle stress was defined as a greater than 20% reduction in H/L compared with the reference value. RESULTS: Optimal PS levels ranged from 4 to 24 cm H2O with a mean of 14+/-6 cm H2O. Two patients with optimal PS level at 4 cm H2O did not require weaning and were quickly extubated. For the nine other patients, optimal PS levels were found to be 70% of PIP; in none was it necessary during weaning to use PS levels higher than individual optimal PS levels. CONCLUSIONS: Optimal PS level established with diEMG monitoring seems to be a useful index for beginning weaning in the PS ventilation mode in COPD patients. The hypothesis of beginning weaning with a PS level equal to 70% of PIP needs to be tested.     

Cu-NMR study on high-T c cuprate La1.89Ca1.11Cu2O6+δ (La2126)

Cu-NMR spectra and the nuclear spin-lattice relaxation rate T ₁ ^-1 have been studied intensively on the bilayer type high-T_c cuprate La_1.89Ca_1.11Cu₂O₆₊ (La2126). The resonance line shift showed a monotonic decrease with lowering temperature in the normal state, indicating that this compound belongs to the lightly-doped region. The Curie-Weiss temperature dependence of (T₁T)^–1 in the normal state shows that the pseudo spin-gap does not always exist in the light-doped bilayer systems.     

Relation between axial compressive strength of reinforcing fibres and fibre diameter

Attempts were made to estimate the fibre axial compressive strength of pitch-based graphitized and polyarylate fibres, and the relationship between the compressive strength and fibre diameter was investigated. The estimated compressive strength of fibres decreases with increasing temperature. This decrease in compressive strength may be accounted for by a decrease in the radial compressing force. There is a linear relationship between the estimated compressive strength and radial compressing force in a temperature range from room temperature to 80°C. The real compressive strength of the fibres, determined by extrapolating this straight line until the radial compressing force is zero, increases with decreasing fibre diameter, but remains almost unchanged at a diameter range smaller than 10 m. In order to obtain reinforcing fibres having a higher compressive strength, it will be necessary to prepare fibres having a diameter smaller than 10 m.     

The effect of urinary tract reconstruction on neurologically impaired women previously treated with an indwelling urethral catheter

PURPOSE: We investigated the changes in sexuality and quality of life that evolve after lower urinary tract reconstruction in neurologically impaired women previously treated with an indwelling urethral catheter. MATERIALS AND METHODS: A total of 18 neurologically impaired women treated with an indwelling urethral catheter underwent bladder reconstruction. Pubovaginal sling urethral compression was required to restore perineal dryness in 13 patients and was the only operation required in conjunction with intermittent catheterization in 3. Eight patients underwent ileocystostomy, that is creation of a "bladder chimney," and 4 underwent augmentation cystoplasty with creation of a continent catheterizable stoma. In 3 patients ileocystoplasty alone with intermittent urethral catheterization was performed. All patients were followed 6 to 40 months (mean 18) after reconstructive surgery using a 9-part questionnaire to score numerically the effect of surgical reconstruction on sexuality and quality of life issues. RESULTS: On a scale of 0 (worst) to 5 (best) mean score for self-esteem improved from 1 preoperatively to 4 postoperatively, self-image from 1 to 4, sexual desire from 2 to 4 and ability to cope with disability from 1 to 4, respectively. In 4 of the 15 women who were sexually active preoperatively the frequency of sexual intercourse doubled from a mean of 3 to 6 times per month, respectively, and all 4 women reported improved sexual satisfaction. All 13 patients with pelvic pain and 5 with symptoms of autonomic dysreflexia noticed significant improvement if not complete resolution of the symptoms. CONCLUSIONS: Neurogenic lower urinary tract dysfunction treated with an indwelling urethral catheter is detrimental to sexuality and quality of life in neurologically impaired women. Urinary tract reconstruction restores not only quality of life but also sexuality by improving self-image, self-esteem and the ability to cope. Indwelling catheterization as a method of long-term urinary treatment should be avoided in women.     

Reorganizing knowledge in neural networks: an explanatory mechanismfor neural networks in data classification problems

We propose an explanatory mechanism for multilayered neural networks (NN). In spite of the effective learning capability as a uniform function approximator, the multilayered NN suffers from unreadability, i.e., it is difficult for the user to interpret or understand the "knowledge" that the NN has by looking at the connection weights and thresholds obtained by backpropagation (BP). This unreadability comes from the distributed nature of the knowledge representation in the NN. In this paper, we propose a method that reorganizes the distributed knowledge in the NN to extract approximate classification rules. Our rule extraction method is based on the analysis of the function that the NN has learned, rather than on the direct interpretation of connection weights as correlation information. More specifically, our method divides the input space into "monotonic regions" where a monotonic region is a set of input patterns that belongs to the same class with the same sensitivity pattern. Approximate classification rules are generated by projecting these monotonic regions.     

The evaluation of speckle contrast with variable speckle generator

Abstract— While laser projection has many advantages, there is a problem with speckle patterns generated as a result of interference of the laser beam and results in bad effects to observers. In 2010, a variable speckle generator, which produces an angular shift of incident light to the screen and generates variable speckle patterns, was suggested. In this study, the performance of a variable speckle generator by using a volume phase holographic beam shaper and scanning mirror was investigated in detail by evaluating both the objective and subjective speckle contrast. The morphology of the speckle pattern was also investigated when the variable speckle generator was activated. With a scanning VPH beam shaper, the objective speckle was effectively reduced because each point of the VPH beam shaper generated different speckle patterns and coherency among each pattern disappeared by using the scan process. On the other hand, subjective speckle was also dramatically reduced by changing the incident angle on the screen, which resulted in generating variable subjective speckle. It was also shown that the speckle reduction rate by using a variable speckle generator did not depend on the coherent length of a laser by evaluating the normalized speckle contrast against the angular shift on the screen.